--- title: Beta url: https://platform.claude.com/docs/en/api/python/beta --- # Beta ## Domain types ### Anthropic Beta - `type AnthropicBeta = Union[str, Literal["message-batches-2024-09-24", "prompt-caching-2024-07-31", "computer-use-2024-10-22", 47 more]]` - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` ### Beta API Error - `class BetaAPIError` - `type: Literal["api_error"]` default: api_error - `message: str` default: Internal server error ### Beta Authentication Error - `class BetaAuthenticationError` - `type: Literal["authentication_error"]` default: authentication_error - `message: str` default: Authentication error ### Beta Billing Error - `class BetaBillingError` - `type: Literal["billing_error"]` default: billing_error - `message: str` default: Billing error ### Beta Currency - `type BetaCurrency = Literal["USD"]` ### Beta Error - `type BetaError = ...` - `class BetaInvalidRequestError` - `type: Literal["invalid_request_error"]` default: invalid_request_error - `message: str` default: Invalid request - `class BetaAuthenticationError` - `type: Literal["authentication_error"]` default: authentication_error - `message: str` default: Authentication error - `class BetaBillingError` - `type: Literal["billing_error"]` default: billing_error - `message: str` default: Billing error - `class BetaPermissionError` - `type: Literal["permission_error"]` default: permission_error - `message: str` default: Permission denied - `class BetaNotFoundError` - `type: Literal["not_found_error"]` default: not_found_error - `message: str` default: Not found - `class BetaRateLimitError` - `type: Literal["rate_limit_error"]` default: rate_limit_error - `message: str` default: Rate limited - `class BetaGatewayTimeoutError` - `type: Literal["timeout_error"]` default: timeout_error - `message: str` default: Request timeout - `class BetaAPIError` - `type: Literal["api_error"]` default: api_error - `message: str` default: Internal server error - `class BetaOverloadedError` - `type: Literal["overloaded_error"]` default: overloaded_error - `message: str` default: Overloaded ### Beta Error Response - `class BetaErrorResponse` - `type: Literal["error"]` default: error - `error: BetaError` - `class BetaInvalidRequestError` - `type: Literal["invalid_request_error"]` default: invalid_request_error - `message: str` default: Invalid request - `class BetaAuthenticationError` - `type: Literal["authentication_error"]` default: authentication_error - `message: str` default: Authentication error - `class BetaBillingError` - `type: Literal["billing_error"]` default: billing_error - `message: str` default: Billing error - `class BetaPermissionError` - `type: Literal["permission_error"]` default: permission_error - `message: str` default: Permission denied - `class BetaNotFoundError` - `type: Literal["not_found_error"]` default: not_found_error - `message: str` default: Not found - `class BetaRateLimitError` - `type: Literal["rate_limit_error"]` default: rate_limit_error - `message: str` default: Rate limited - `class BetaGatewayTimeoutError` - `type: Literal["timeout_error"]` default: timeout_error - `message: str` default: Request timeout - `class BetaAPIError` - `type: Literal["api_error"]` default: api_error - `message: str` default: Internal server error - `class BetaOverloadedError` - `type: Literal["overloaded_error"]` default: overloaded_error - `message: str` default: Overloaded - `request_id: Optional[str]` ### Beta Gateway Timeout Error - `class BetaGatewayTimeoutError` - `type: Literal["timeout_error"]` default: timeout_error - `message: str` default: Request timeout ### Beta Invalid Request Error - `class BetaInvalidRequestError` - `type: Literal["invalid_request_error"]` default: invalid_request_error - `message: str` default: Invalid request ### Beta Monetary Amount - `class BetaMonetaryAmount` A monetary amount in a specific currency. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. ### Beta Not Found Error - `class BetaNotFoundError` - `type: Literal["not_found_error"]` default: not_found_error - `message: str` default: Not found ### Beta Overloaded Error - `class BetaOverloadedError` - `type: Literal["overloaded_error"]` default: overloaded_error - `message: str` default: Overloaded ### Beta Permission Error - `class BetaPermissionError` - `type: Literal["permission_error"]` default: permission_error - `message: str` default: Permission denied ### Beta Rate Limit Error - `class BetaRateLimitError` - `type: Literal["rate_limit_error"]` default: rate_limit_error - `message: str` default: Rate limited ## Beta › Models ### List Models `beta.models.list(**kwargs) -> SyncPage[BetaModelInfo]` **GET** `/v1/models` List available models. The Models API response can be used to determine which models are available for use in the API. More recently released models are listed first. #### Parameters - `after_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately after this object. - `before_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately before this object. - `lifecycle: Optional[List[Literal["active", "deprecated", "retired"]]]` (query parameter) Filter the list to models in any of the given lifecycle stages (`active`, `deprecated`, or `retired`). Up to 3 values. When omitted, the list contains the `active` and `deprecated` models; `retired` models appear only when `retired` is requested explicitly. maxItems: 3 - `"active"` - `"deprecated"` - `"retired"` - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaModelInfo` - `type: Literal["model"]` Object type. For Models, this is always `"model"`. default: model - `id: str` Unique model identifier. - `allowed_fallback_models: Optional[List[str]]` Model IDs this model accepts as `fallbacks[i].model` on the Messages API. An empty list means the `fallbacks` parameter is not supported for this model as primary. - `capabilities: Optional[BetaModelCapabilities]` Object mapping capability names to their support details. Keys are always present for all known capabilities. - `batch: BetaCapabilitySupport` Whether the model supports the Batch API. - `supported: bool` Whether this capability is supported by the model. - `citations: BetaCapabilitySupport` Whether the model supports citation generation. - `code_execution: BetaCapabilitySupport` Whether code that the model runs in the code execution tool can call the request's other tools, as in programmatic tool calling and dynamic filtering for web search and web fetch. Support for the code execution tool itself is in `server_tools.code_execution`. - `compaction: Optional[BetaCompactionCapability]` Server-side compaction support (the top-level `compaction` parameter) and the accepted `compaction.type` values. - `summarize: BetaCapabilitySupport` Whether the summarize compaction type is supported. - `supported: bool` Whether this capability is supported by the model. - `context_management: BetaContextManagementCapability` Context management support and available strategies. - `clear_thinking_20251015: Optional[BetaCapabilitySupport]` Whether the clear_thinking_20251015 strategy is supported. - `clear_tool_uses_20250919: Optional[BetaCapabilitySupport]` Whether the clear_tool_uses_20250919 strategy is supported. - `compact_20260112: Optional[BetaCapabilitySupport]` Whether the compact_20260112 strategy is supported. - `supported: bool` Whether this capability is supported by the model. - `effort: BetaEffortCapability` Effort (reasoning_effort) support and available levels. - `high: BetaCapabilitySupport` Whether the model supports high effort level. - `low: BetaCapabilitySupport` Whether the model supports low effort level. - `max: BetaCapabilitySupport` Whether the model supports max effort level. - `medium: BetaCapabilitySupport` Whether the model supports medium effort level. - `supported: bool` Whether this capability is supported by the model. - `xhigh: Optional[BetaCapabilitySupport]` Whether the model supports xhigh effort level. - `image_input: BetaCapabilitySupport` Whether the model accepts image content blocks. - `pdf_input: BetaCapabilitySupport` Whether the model accepts PDF content blocks. - `server_tools: BetaServerToolsCapability` Whether this model supports the web search and code execution server tools. `supported` is true when the model supports at least one of the tools. A supported tool can still be rejected for your organization, for example when an admin has turned web search off. - `code_execution: BetaCapabilitySupport` Whether the model supports the code execution tool: true when the model supports at least one version of the tool, not necessarily every version. - `supported: bool` Whether this capability is supported by the model. - `web_search: BetaCapabilitySupport` Whether the model supports the web search tool: true when the model supports at least one version of the tool, not necessarily every version. - `structured_outputs: BetaCapabilitySupport` Whether the model supports structured output / JSON mode / strict tool schemas. - `thinking: BetaThinkingCapability` Thinking capability and supported type configurations. - `supported: bool` Whether this capability is supported by the model. - `types: BetaThinkingTypes` Supported thinking type configurations. - `adaptive: BetaCapabilitySupport` Whether the model accepts thinking with type 'adaptive' (the model decides whether and how much to think). - `disabled: BetaCapabilitySupport` Whether the model accepts thinking with type 'disabled' (thinking turned off). False exactly when a request that sends it gets a 400 from this model. True on a model that does not support thinking. - `enabled: BetaCapabilitySupport` Whether the model accepts thinking with type 'enabled' (extended thinking with a caller-set `budget_tokens`). - `created_at: datetime` RFC 3339 datetime string representing the time at which the model was released. May be set to an epoch value if the release date is unknown. format: date-time - `deprecated_at: Optional[datetime]` RFC 3339 datetime string representing the time of the model's most recent deprecation. Populated for `deprecated` and `retired` models; `null` while the model is `active`. format: date-time - `display_name: str` A human-readable name for the model. - `lifecycle: Literal["active", "deprecated", "retired"]` The model's current lifecycle stage. - `active`: The model is available for use, open to new adopters, and not scheduled for retirement. - `deprecated`: The model remains callable for organizations with existing access, but is headed for retirement and closed to new adopters. - `retired`: The model is no longer available for use; inference requests naming it fail. It remains in the catalogue as the historical record of its retirement. default: active - `"active"` - `"deprecated"` - `"retired"` - `line: Optional[BetaModelLine]` The model line this model belongs to, such as `opus` for both Claude Opus 4.5 and Claude Opus 4.6. More lines may be added. `null` when the model belongs to no line; do not infer a line from the `id`. - `"haiku"` - `"sonnet"` - `"opus"` - `"fable"` - `"mythos"` - `max_input_tokens: Optional[int]` Maximum input context window size in tokens for this model. - `max_tokens: Optional[int]` Maximum value for the `max_tokens` parameter when using this model. - `retires_at: Optional[datetime]` RFC 3339 datetime string representing the model's currently scheduled retirement date. The schedule can be revised until retirement occurs; `null` while the model is `active` or while no retirement is scheduled. A past date on a `deprecated` model means retirement is overdue, not that it has occurred: `lifecycle` is the retirement signal. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.models.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "claude-opus-5", "allowed_fallback_models": [ "string" ], "capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": true }, "compaction": { "summarize": { "supported": true }, "supported": true }, "context_management": { "clear_thinking_20251015": { "supported": true }, "clear_tool_uses_20250919": { "supported": true }, "compact_20260112": { "supported": true }, "supported": true }, "effort": { "high": { "supported": true }, "low": { "supported": true }, "max": { "supported": true }, "medium": { "supported": true }, "supported": true, "xhigh": { "supported": true } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "server_tools": { "code_execution": { "supported": true }, "supported": true, "web_search": { "supported": true } }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "adaptive": { "supported": true }, "disabled": { "supported": true }, "enabled": { "supported": true } } } }, "created_at": "2026-07-24T00:00:00Z", "deprecated_at": "2019-12-27T18:11:19.117Z", "display_name": "Claude Opus 5", "lifecycle": "active", "line": "haiku", "max_input_tokens": 0, "max_tokens": 0, "retires_at": "2019-12-27T18:11:19.117Z", "type": "model" } ], "first_id": "first_id", "has_more": true, "last_id": "last_id" } ``` ### Get a Model `beta.models.retrieve(model_id, **kwargs) -> BetaModelInfo` **GET** `/v1/models/{model_id}` Get a specific model. The Models API response can be used to determine information about a specific model or resolve a model alias to a model ID. #### Parameters - `model_id: str` (path parameter) Model identifier or alias. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaModelInfo` - `type: Literal["model"]` Object type. For Models, this is always `"model"`. default: model - `id: str` Unique model identifier. - `allowed_fallback_models: Optional[List[str]]` Model IDs this model accepts as `fallbacks[i].model` on the Messages API. An empty list means the `fallbacks` parameter is not supported for this model as primary. - `capabilities: Optional[BetaModelCapabilities]` Object mapping capability names to their support details. Keys are always present for all known capabilities. - `batch: BetaCapabilitySupport` Whether the model supports the Batch API. - `supported: bool` Whether this capability is supported by the model. - `citations: BetaCapabilitySupport` Whether the model supports citation generation. - `code_execution: BetaCapabilitySupport` Whether code that the model runs in the code execution tool can call the request's other tools, as in programmatic tool calling and dynamic filtering for web search and web fetch. Support for the code execution tool itself is in `server_tools.code_execution`. - `compaction: Optional[BetaCompactionCapability]` Server-side compaction support (the top-level `compaction` parameter) and the accepted `compaction.type` values. - `summarize: BetaCapabilitySupport` Whether the summarize compaction type is supported. - `supported: bool` Whether this capability is supported by the model. - `context_management: BetaContextManagementCapability` Context management support and available strategies. - `clear_thinking_20251015: Optional[BetaCapabilitySupport]` Whether the clear_thinking_20251015 strategy is supported. - `clear_tool_uses_20250919: Optional[BetaCapabilitySupport]` Whether the clear_tool_uses_20250919 strategy is supported. - `compact_20260112: Optional[BetaCapabilitySupport]` Whether the compact_20260112 strategy is supported. - `supported: bool` Whether this capability is supported by the model. - `effort: BetaEffortCapability` Effort (reasoning_effort) support and available levels. - `high: BetaCapabilitySupport` Whether the model supports high effort level. - `low: BetaCapabilitySupport` Whether the model supports low effort level. - `max: BetaCapabilitySupport` Whether the model supports max effort level. - `medium: BetaCapabilitySupport` Whether the model supports medium effort level. - `supported: bool` Whether this capability is supported by the model. - `xhigh: Optional[BetaCapabilitySupport]` Whether the model supports xhigh effort level. - `image_input: BetaCapabilitySupport` Whether the model accepts image content blocks. - `pdf_input: BetaCapabilitySupport` Whether the model accepts PDF content blocks. - `server_tools: BetaServerToolsCapability` Whether this model supports the web search and code execution server tools. `supported` is true when the model supports at least one of the tools. A supported tool can still be rejected for your organization, for example when an admin has turned web search off. - `code_execution: BetaCapabilitySupport` Whether the model supports the code execution tool: true when the model supports at least one version of the tool, not necessarily every version. - `supported: bool` Whether this capability is supported by the model. - `web_search: BetaCapabilitySupport` Whether the model supports the web search tool: true when the model supports at least one version of the tool, not necessarily every version. - `structured_outputs: BetaCapabilitySupport` Whether the model supports structured output / JSON mode / strict tool schemas. - `thinking: BetaThinkingCapability` Thinking capability and supported type configurations. - `supported: bool` Whether this capability is supported by the model. - `types: BetaThinkingTypes` Supported thinking type configurations. - `adaptive: BetaCapabilitySupport` Whether the model accepts thinking with type 'adaptive' (the model decides whether and how much to think). - `disabled: BetaCapabilitySupport` Whether the model accepts thinking with type 'disabled' (thinking turned off). False exactly when a request that sends it gets a 400 from this model. True on a model that does not support thinking. - `enabled: BetaCapabilitySupport` Whether the model accepts thinking with type 'enabled' (extended thinking with a caller-set `budget_tokens`). - `created_at: datetime` RFC 3339 datetime string representing the time at which the model was released. May be set to an epoch value if the release date is unknown. format: date-time - `deprecated_at: Optional[datetime]` RFC 3339 datetime string representing the time of the model's most recent deprecation. Populated for `deprecated` and `retired` models; `null` while the model is `active`. format: date-time - `display_name: str` A human-readable name for the model. - `lifecycle: Literal["active", "deprecated", "retired"]` The model's current lifecycle stage. - `active`: The model is available for use, open to new adopters, and not scheduled for retirement. - `deprecated`: The model remains callable for organizations with existing access, but is headed for retirement and closed to new adopters. - `retired`: The model is no longer available for use; inference requests naming it fail. It remains in the catalogue as the historical record of its retirement. default: active - `"active"` - `"deprecated"` - `"retired"` - `line: Optional[BetaModelLine]` The model line this model belongs to, such as `opus` for both Claude Opus 4.5 and Claude Opus 4.6. More lines may be added. `null` when the model belongs to no line; do not infer a line from the `id`. - `"haiku"` - `"sonnet"` - `"opus"` - `"fable"` - `"mythos"` - `max_input_tokens: Optional[int]` Maximum input context window size in tokens for this model. - `max_tokens: Optional[int]` Maximum value for the `max_tokens` parameter when using this model. - `retires_at: Optional[datetime]` RFC 3339 datetime string representing the model's currently scheduled retirement date. The schedule can be revised until retirement occurs; `null` while the model is `active` or while no retirement is scheduled. A past date on a `deprecated` model means retirement is overdue, not that it has occurred: `lifecycle` is the retirement signal. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_model_info = client.beta.models.retrieve( model_id="model_id", ) print(beta_model_info.id) ``` ##### Response (200) ```json { "id": "claude-opus-5", "allowed_fallback_models": [ "string" ], "capabilities": { "batch": { "supported": true }, "citations": { "supported": true }, "code_execution": { "supported": true }, "compaction": { "summarize": { "supported": true }, "supported": true }, "context_management": { "clear_thinking_20251015": { "supported": true }, "clear_tool_uses_20250919": { "supported": true }, "compact_20260112": { "supported": true }, "supported": true }, "effort": { "high": { "supported": true }, "low": { "supported": true }, "max": { "supported": true }, "medium": { "supported": true }, "supported": true, "xhigh": { "supported": true } }, "image_input": { "supported": true }, "pdf_input": { "supported": true }, "server_tools": { "code_execution": { "supported": true }, "supported": true, "web_search": { "supported": true } }, "structured_outputs": { "supported": true }, "thinking": { "supported": true, "types": { "adaptive": { "supported": true }, "disabled": { "supported": true }, "enabled": { "supported": true } } } }, "created_at": "2026-07-24T00:00:00Z", "deprecated_at": "2019-12-27T18:11:19.117Z", "display_name": "Claude Opus 5", "lifecycle": "active", "line": "haiku", "max_input_tokens": 0, "max_tokens": 0, "retires_at": "2019-12-27T18:11:19.117Z", "type": "model" } ``` ## Beta › Messages ### Create a Message `beta.messages.create(**kwargs) -> BetaMessage` **POST** `/v1/messages` Send a structured list of input messages with text and/or image content, and the model will generate the next message in the conversation. The Messages API can be used for either single queries or stateless multi-turn conversations. Learn more about the Messages API in our [user guide](https://platform.claude.com/docs/en/get-started?sdk_languages=python) #### Parameters - `max_tokens: int` The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. Set to `0` to populate the [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=python#pre-warming-the-cache) without generating a response. Different models have different maximum values for this parameter. See [models](https://platform.claude.com/docs/en/about-claude/models/overview?sdk_languages=python) for details. minimum: 0 - `messages: Iterable[BetaMessageParam]` Input messages. Our models are trained to operate on alternating `user` and `assistant` conversational turns. When creating a new `Message`, you specify the prior conversational turns with the `messages` parameter, and the model then generates the next `Message` in the conversation. Consecutive `user` or `assistant` turns in your request will be combined into a single turn. Each input message must be an object with a `role` and `content`. You can specify a single `user`-role message, or you can include multiple `user` and `assistant` messages. If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response. This is called prefill. On models that don't support prefill, creating a message that ends with a partial `assistant` response returns a 400 error. See [Prefill not supported](https://platform.claude.com/docs/en/api/errors?sdk_languages=python#prefill-not-supported). Example with a single `user` message: ```json [{"role": "user", "content": "Hello, Claude"}] ``` Example with multiple conversational turns: ```json [ {"role": "user", "content": "Hello there."}, {"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"}, {"role": "user", "content": "Can you explain LLMs in plain English?"}, ] ``` Example with a partially-filled response from Claude, for models that support prefill: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("}, ] ``` Each input message `content` may be either a single `string` or an array of content blocks, where each block has a specific `type`. Using a `string` for `content` is shorthand for an array of one content block of type `"text"`. The following input messages are equivalent: ```json {"role": "user", "content": "Hello, Claude"} ``` ```json {"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]} ``` See [input examples](https://platform.claude.com/docs/en/build-with-claude/working-with-messages?sdk_languages=python). Note that if you want to include a [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices?sdk_languages=python#give-claude-a-role), you can use the top-level `system` parameter — there is no `"system"` role for input messages in the Messages API. There is a limit of 100,000 messages in a single request. - `content: Union[str, List[BetaContentBlockParam]]` - `str` - `List[BetaContentBlockParam]` - `class BetaTextBlockParam` - `type: Literal["text"]` - `text: str` minLength: 1 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `type: Literal["ephemeral"]` - `ttl: Optional[Literal["5m", "1h"]]` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=python) for details. - `"5m"` - `"1h"` - `citations: Optional[List[BetaTextCitationParam]]` - `class BetaCitationCharLocationParam` - `type: Literal["char_location"]` - `cited_text: str` - `document_index: int` minimum: 0 - `document_title: Optional[str]` minLength: 1, maxLength: 500 - `end_char_index: int` - `start_char_index: int` minimum: 0 - `class BetaCitationPageLocationParam` - `type: Literal["page_location"]` - `cited_text: str` - `document_index: int` minimum: 0 - `document_title: Optional[str]` minLength: 1, maxLength: 500 - `end_page_number: int` - `start_page_number: int` minimum: 1 - `class BetaCitationContentBlockLocationParam` - `type: Literal["content_block_location"]` - `cited_text: str` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: int` minimum: 0 - `document_title: Optional[str]` minLength: 1, maxLength: 500 - `end_block_index: int` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: int` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `class BetaCitationWebSearchResultLocationParam` - `type: Literal["web_search_result_location"]` - `cited_text: str` - `encrypted_index: str` - `title: Optional[str]` minLength: 1, maxLength: 512 - `url: str` minLength: 1 - `class BetaCitationSearchResultLocationParam` - `type: Literal["search_result_location"]` - `cited_text: str` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: int` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: int` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: str` - `start_block_index: int` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: Optional[str]` - `class BetaImageBlockParam` - `type: Literal["image"]` - `source: Source` - `class BetaBase64ImageSource` - `type: Literal["base64"]` - `data: str` format: byte - `media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `class BetaURLImageSource` - `type: Literal["url"]` - `url: str` - `class BetaFileImageSource` - `type: Literal["file"]` - `file_id: str` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `transformations: Optional[BetaImageTransformationsParam]` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: Optional[Literal["downsize", "error"]]` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `class BetaRequestDocumentBlock` - `type: Literal["document"]` - `source: Source` - `class BetaBase64PDFSource` - `type: Literal["base64"]` - `data: str` format: byte - `media_type: Literal["application/pdf"]` - `class BetaPlainTextSource` - `type: Literal["text"]` - `data: str` - `media_type: Literal["text/plain"]` - `class BetaContentBlockSource` - `type: Literal["content"]` - `content: Union[str, List[BetaContentBlockSourceContent]]` - `str` - `List[BetaContentBlockSourceContent]` - `class BetaTextBlockParam` - `class BetaImageBlockParam` - `class BetaURLPDFSource` - `type: Literal["url"]` - `url: str` - `class BetaFileDocumentSource` - `type: Literal["file"]` - `file_id: str` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` - `enabled: Optional[bool]` - `context: Optional[str]` minLength: 1 - `title: Optional[str]` minLength: 1, maxLength: 500 - `class BetaSearchResultBlockParam` - `type: Literal["search_result"]` - `content: List[BetaTextBlockParam]` - `type: Literal["text"]` - `text: str` minLength: 1 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[List[BetaTextCitationParam]]` - `source: str` - `title: str` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` - `class BetaThinkingBlockParam` - `type: Literal["thinking"]` - `signature: str` The `signature` value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude. Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`. - `thinking: str` The `thinking` text of this block as returned by the API. - `class BetaRedactedThinkingBlockParam` - `type: Literal["redacted_thinking"]` - `data: str` The `data` value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged. - `class BetaToolUseBlockParam` - `type: Literal["tool_use"]` - `id: str` pattern: ^[a-zA-Z0-9_-]+$ - `input: Dict[str, object]` - `name: str` minLength: 1, maxLength: 200 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `type: Literal["direct"]` - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `type: Literal["code_execution_20250825"]` - `tool_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaServerToolCaller20260120` - `type: Literal["code_execution_20260120"]` - `tool_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: Optional[str]` For a toolset member tool_use, the toolset family this member belongs to. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `class BetaToolResultBlockParam` - `type: Literal["tool_result"]` - `tool_use_id: str` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `content: Optional[Union[str, List[Content], null]]` - `str` - `List[Content]` - `class BetaTextBlockParam` - `class BetaImageBlockParam` - `class BetaSearchResultBlockParam` - `class BetaRequestDocumentBlock` - `class BetaToolReferenceBlockParam` Tool reference block that can be included in tool_result content. - `type: Literal["tool_reference"]` - `tool_name: str` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaBrowserStateBlockParam` The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: Literal["browser_state"]` - `tabs: List[BetaBrowserStateTabEntry]` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: str` The caller-assigned identifier for this tab, unique within the inventory. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `title: str` The title of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: str` The URL of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `active: Optional[bool]` Whether this tab is the active tab after this call. Whenever `tabs` is non-empty, exactly one entry is marked `active: true`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `state_changes: Optional[List[BetaBrowserStateChange]]` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. minItems: 1, maxItems: 200 - `class BetaBrowserStateChangeTabOpened` A tab this call's execution opened that remains open at its end — the creation delta of the `tabs` inventory, not an event log. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: Literal["tab_opened"]` - `tab_id: str` The `tab_id` of the opened tab, present in `tabs`. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `class BetaBrowserStateChangeDownloadStarted` A file download that started during this call. - `type: Literal["download_started"]` - `download_id: str` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: str` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `class BetaBrowserStateChangeDownloadCompleted` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: Literal["download_completed"]` - `download_id: str` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: str` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: Optional[str]` Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `size_bytes: Optional[int]` The completed download's size. minimum: 0 - `class BetaBrowserStateChangeDownloadFailed` A file download that failed — or was cancelled — during this call. - `type: Literal["download_failed"]` - `download_id: str` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: str` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: Optional[str]` The failure or cancellation detail, when known. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `is_error: Optional[bool]` - `toolset_name: Optional[str]` For a toolset member tool_result, the toolset family of the paired tool_use. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `class BetaServerToolUseBlockParam` - `type: Literal["server_tool_use"]` - `id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: Dict[str, object]` - `name: Literal["advisor", "web_search", "web_fetch", 5 more]` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaWebSearchToolResultBlockParam` - `type: Literal["web_search_tool_result"]` - `content: BetaWebSearchToolResultBlockParamContent` - `List[BetaWebSearchResultBlockParam]` - `type: Literal["web_search_result"]` - `encrypted_content: str` - `title: str` - `url: str` - `page_age: Optional[str]` - `class BetaWebSearchToolRequestError` - `type: Literal["web_search_tool_result_error"]` - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaWebFetchToolResultBlockParam` - `type: Literal["web_fetch_tool_result"]` - `content: Content` - `class BetaWebFetchToolResultErrorBlockParam` - `type: Literal["web_fetch_tool_result_error"]` - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `class BetaWebFetchBlockParam` - `type: Literal["web_fetch_result"]` - `content: BetaRequestDocumentBlock` - `url: str` Fetched content URL - `retrieved_at: Optional[str]` ISO 8601 timestamp when the content was retrieved - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaAdvisorToolResultBlockParam` - `type: Literal["advisor_tool_result"]` - `content: Content` - `class BetaAdvisorToolResultErrorParam` - `type: Literal["advisor_tool_result_error"]` - `error_code: Literal["max_uses_exceeded", "prompt_too_long", "too_many_requests", 4 more]` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `class BetaAdvisorResultBlockParam` - `type: Literal["advisor_result"]` - `text: str` - `stop_reason: Optional[str]` - `class BetaAdvisorRedactedResultBlockParam` - `type: Literal["advisor_redacted_result"]` - `encrypted_content: str` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: Optional[str]` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaCodeExecutionToolResultBlockParam` - `type: Literal["code_execution_tool_result"]` - `content: BetaCodeExecutionToolResultBlockParamContent` - `class BetaCodeExecutionToolResultErrorParam` - `type: Literal["code_execution_tool_result_error"]` - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `class BetaCodeExecutionResultBlockParam` - `type: Literal["code_execution_result"]` - `content: List[BetaCodeExecutionOutputBlockParam]` - `type: Literal["code_execution_output"]` - `file_id: str` - `return_code: int` - `stderr: str` - `stdout: str` - `class BetaEncryptedCodeExecutionResultBlockParam` Code execution result with encrypted stdout for PFC + web_search results. - `type: Literal["encrypted_code_execution_result"]` - `content: List[BetaCodeExecutionOutputBlockParam]` - `type: Literal["code_execution_output"]` - `file_id: str` - `encrypted_stdout: str` - `return_code: int` - `stderr: str` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaBashCodeExecutionToolResultBlockParam` - `type: Literal["bash_code_execution_tool_result"]` - `content: Content` - `class BetaBashCodeExecutionToolResultErrorParam` - `type: Literal["bash_code_execution_tool_result_error"]` - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", 2 more]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `class BetaBashCodeExecutionResultBlockParam` - `type: Literal["bash_code_execution_result"]` - `content: List[BetaBashCodeExecutionOutputBlockParam]` - `type: Literal["bash_code_execution_output"]` - `file_id: str` - `return_code: int` - `stderr: str` - `stdout: str` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaTextEditorCodeExecutionToolResultBlockParam` - `type: Literal["text_editor_code_execution_tool_result"]` - `content: Content` - `class BetaTextEditorCodeExecutionToolResultErrorParam` - `type: Literal["text_editor_code_execution_tool_result_error"]` - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", 2 more]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: Optional[str]` - `class BetaTextEditorCodeExecutionViewResultBlockParam` - `type: Literal["text_editor_code_execution_view_result"]` - `content: str` - `file_type: Literal["text", "image", "pdf"]` - `"text"` - `"image"` - `"pdf"` - `num_lines: Optional[int]` - `start_line: Optional[int]` - `total_lines: Optional[int]` - `class BetaTextEditorCodeExecutionCreateResultBlockParam` - `type: Literal["text_editor_code_execution_create_result"]` - `is_file_update: bool` - `class BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - `type: Literal["text_editor_code_execution_str_replace_result"]` - `lines: Optional[List[str]]` - `new_lines: Optional[int]` - `new_start: Optional[int]` - `old_lines: Optional[int]` - `old_start: Optional[int]` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaToolSearchToolResultBlockParam` - `type: Literal["tool_search_tool_result"]` - `content: Content` - `class BetaToolSearchToolResultErrorParam` - `type: Literal["tool_search_tool_result_error"]` - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", "execution_time_exceeded"]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: Optional[str]` - `class BetaToolSearchToolSearchResultBlockParam` - `type: Literal["tool_search_tool_search_result"]` - `tool_references: List[BetaToolReferenceBlockParam]` - `type: Literal["tool_reference"]` - `tool_name: str` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaMCPToolUseBlockParam` - `type: Literal["mcp_tool_use"]` - `id: str` pattern: ^[a-zA-Z0-9_-]+$ - `input: Dict[str, object]` - `name: str` - `server_name: str` The name of the MCP server - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaRequestMCPToolResultBlockParam` - `type: Literal["mcp_tool_result"]` - `tool_use_id: str` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `content: Optional[Union[str, List[BetaTextBlockParam], null]]` - `str` - `List[BetaTextBlockParam]` - `type: Literal["text"]` - `text: str` minLength: 1 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[List[BetaTextCitationParam]]` - `is_error: Optional[bool]` - `class BetaContainerUploadBlockParam` A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory. - `type: Literal["container_upload"]` - `file_id: str` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaCompactionBlockParam` A compaction block containing summary of previous context. Users should round-trip these blocks from responses to subsequent requests to maintain context across compaction boundaries. When content is None, the block represents a failed compaction. The server treats these as no-ops. Empty string content is not allowed. - `type: Literal["compaction"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `content: Optional[str]` Summary of previously compacted content, or null if compaction failed - `encrypted_content: Optional[str]` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: Optional[str]` The block's signature as returned, to be sent back verbatim - `tool_changes: Optional[List[ToolChange]]` The tool changes of the compacted range, as the server returned them on this block: the `tool_addition` and `tool_removal` entries that take the request's `tools` to the tool set in effect at the end of the range. Send them back unchanged with the block. - `class BetaRequestToolAdditionBlock` Mid-conversation directive to make a tool available. `tool` is a reference to a tool (or MCP toolset) declared in the request's `tools`. Under the `inline-tools-2026-09-15` beta it may instead be a reference to a tool defined earlier in `messages`, or a `tool_definition` object that carries an inline tool definition in `definition` (the same object a `tools` entry holds). An `mcp_toolset` definition also requires the `mcp-client-2026-09-15` beta. The tool is offered to the model from this point in the conversation onward. - `type: Literal["tool_addition"]` - `tool: Tool` - `class BetaToolChangeToolReference` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `type: Literal["tool_reference"]` - `name: str` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `class BetaToolChangeMCPToolReference` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `type: Literal["mcp_tool_reference"]` - `name: str` - `server_name: str` - `class BetaToolChangeMCPToolsetReference` Reference to every tool in the named MCP server's toolset. - `type: Literal["mcp_toolset_reference"]` - `server_name: str` - `class BetaToolChangeToolDefinitionParam` A tool defined by value: `definition` is a `tools` entry (any kind `tools` accepts, an MCP toolset included). An `mcp_toolset` given here also requires the `mcp-client-2026-09-15` beta. - `type: Literal["tool_definition"]` - `definition: BetaToolUnion` - `class BetaTool` - `type: Optional[Literal["custom"]]` - `input_schema: InputSchema` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: Optional[str]` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: Optional[bool]` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolBash20241022` - `type: Literal["bash_20241022"]` - `name: Literal["bash"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolBash20250124` - `type: Literal["bash_20250124"]` - `name: Literal["bash"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20250522` - `type: Literal["code_execution_20250522"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20250825` - `type: Literal["code_execution_20250825"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20260120` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: Literal["code_execution_20260120"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20260521` Code execution tool with REPL state persistence. - `type: Literal["code_execution_20260521"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaBrowserToolset20260801` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: Literal["browser_toolset_20260801"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[BetaBrowserToolsetConfigs]` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: Optional[BetaBrowserTypeConfig]` `type`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: Optional[BetaBrowserCloseTabConfig]` `close_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: Optional[BetaBrowserDoubleClickConfig]` `double_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: Optional[BetaBrowserFileUploadConfig]` `file_upload`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: Optional[BetaBrowserFindConfig]` `find`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: Optional[BetaBrowserFormInputConfig]` `form_input`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: Optional[BetaBrowserGetPageTextConfig]` `get_page_text`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: Optional[BetaBrowserHoldKeyConfig]` `hold_key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: Optional[BetaBrowserHoverConfig]` `hover`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: Optional[BetaBrowserJavascriptExecConfig]` `javascript_exec`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: Optional[BetaBrowserKeyConfig]` `key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: Optional[BetaBrowserLeftClickConfig]` `left_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: Optional[BetaBrowserLeftClickDragConfig]` `left_click_drag`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: Optional[BetaBrowserLeftMouseDownConfig]` `left_mouse_down`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: Optional[BetaBrowserLeftMouseUpConfig]` `left_mouse_up`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: Optional[BetaBrowserListTabsConfig]` `list_tabs`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: Optional[BetaBrowserMiddleClickConfig]` `middle_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: Optional[BetaBrowserMouseMoveConfig]` `mouse_move`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: Optional[BetaBrowserNavigateConfig]` `navigate`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: Optional[BetaBrowserNewTabConfig]` `new_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: Optional[BetaBrowserReadConsoleConfig]` `read_console`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: Optional[BetaBrowserReadNetworkConfig]` `read_network`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: Optional[BetaBrowserReadPageConfig]` `read_page`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: Optional[BetaBrowserRightClickConfig]` `right_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: Optional[BetaBrowserScreenshotConfig]` `screenshot`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: Optional[BetaBrowserScrollConfig]` `scroll`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: Optional[BetaBrowserScrollToConfig]` `scroll_to`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: Optional[BetaBrowserSwitchTabConfig]` `switch_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: Optional[BetaBrowserTripleClickConfig]` `triple_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: Optional[BetaBrowserWaitConfig]` `wait`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: Optional[BetaBrowserZoomConfig]` `zoom`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `class BetaToolComputerUse20241022` - `type: Literal["computer_20241022"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaMemoryTool20250818` - `type: Literal["memory_20250818"]` - `name: Literal["memory"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolComputerUse20250124` - `type: Literal["computer_20250124"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20241022` - `type: Literal["text_editor_20241022"]` - `name: Literal["str_replace_editor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolComputerUse20251124` - `type: Literal["computer_20251124"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: Optional[bool]` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaComputerToolset20260801` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: Literal["computer_toolset_20260801"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[BetaComputerToolsetConfigs]` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: Optional[BetaComputerTypeConfig]` `type`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: Optional[BetaComputerCursorPositionConfig]` `cursor_position`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: Optional[BetaComputerDoubleClickConfig]` `double_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: Optional[BetaComputerHoldKeyConfig]` `hold_key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: Optional[BetaComputerKeyConfig]` `key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: Optional[BetaComputerLeftClickConfig]` `left_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: Optional[BetaComputerLeftClickDragConfig]` `left_click_drag`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: Optional[BetaComputerLeftMouseDownConfig]` `left_mouse_down`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: Optional[BetaComputerLeftMouseUpConfig]` `left_mouse_up`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: Optional[BetaComputerMiddleClickConfig]` `middle_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: Optional[BetaComputerMouseMoveConfig]` `mouse_move`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: Optional[BetaComputerRightClickConfig]` `right_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: Optional[BetaComputerScreenshotConfig]` `screenshot`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: Optional[BetaComputerScrollConfig]` `scroll`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: Optional[BetaComputerTripleClickConfig]` `triple_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: Optional[BetaComputerWaitConfig]` `wait`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: Optional[BetaComputerZoomConfig]` `zoom`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `class BetaToolTextEditor20250124` - `type: Literal["text_editor_20250124"]` - `name: Literal["str_replace_editor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20250429` - `type: Literal["text_editor_20250429"]` - `name: Literal["str_replace_based_edit_tool"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20250728` - `type: Literal["text_editor_20250728"]` - `name: Literal["str_replace_based_edit_tool"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `max_characters: Optional[int]` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaWebSearchTool20250305` - `type: Literal["web_search_20250305"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `type: Literal["approximate"]` - `city: Optional[str]` The city of the user. minLength: 1, maxLength: 255 - `country: Optional[str]` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: Optional[str]` The region of the user. minLength: 1, maxLength: 255 - `timezone: Optional[str]` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `class BetaWebFetchTool20250910` - `type: Literal["web_fetch_20250910"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: Optional[ClientToolResults]` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: Literal["all"]` - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: Literal["none"]` - `class BetaWebFetchURLSourceOnly` The tool filter variant under which only the named tools' results contribute. - `type: Literal["only"]` - `tools: List[BetaWebFetchURLSourceToolReference]` - `type: Literal["tool_reference"]` - `name: str` - `class BetaWebFetchURLSourceExcept` The tool filter variant under which every result but the named tools' contributes. - `type: Literal["except"]` - `tools: List[BetaWebFetchURLSourceToolReference]` - `type: Literal["tool_reference"]` - `name: str` - `server_tool_results: Optional[ServerToolResults]` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `class BetaWebFetchURLSourceOnly` The tool filter variant under which only the named tools' results contribute. - `class BetaWebFetchURLSourceExcept` The tool filter variant under which every result but the named tools' contributes. - `user_input: Optional[UserInput]` Whether URLs in user messages are fetchable: "all" or "none". - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `class BetaWebSearchTool20260209` - `type: Literal["web_search_20260209"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `class BetaWebFetchTool20260209` - `type: Literal["web_fetch_20260209"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `class BetaWebFetchTool20260309` Web fetch tool with use_cache parameter for bypassing cached content. - `type: Literal["web_fetch_20260309"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `use_cache: Optional[bool]` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `class BetaWebSearchTool20260318` - `type: Literal["web_search_20260318"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: Optional[Literal["full", "excluded"]]` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `class BetaWebFetchTool20260318` - `type: Literal["web_fetch_20260318"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: Optional[Literal["full", "excluded"]]` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `use_cache: Optional[bool]` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `class BetaAdvisorTool20260301` - `type: Literal["advisor_20260301"]` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `name: Literal["advisor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caching: Optional[BetaCacheControlEphemeral]` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: Optional[int]` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolSearchToolBm25_20251119` - `type: Literal["tool_search_tool_bm25_20251119", "tool_search_tool_bm25"]` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: Literal["tool_search_tool_bm25"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolSearchToolRegex20251119` - `type: Literal["tool_search_tool_regex_20251119", "tool_search_tool_regex"]` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: Literal["tool_search_tool_regex"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaMCPToolset` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: Literal["mcp_toolset"]` - `mcp_server_name: str` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[Dict[str, BetaMCPToolConfig]]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: Optional[bool]` - `enabled: Optional[bool]` - `default_config: Optional[BetaMCPToolDefaultConfig]` Default configuration applied to all tools from this server - `defer_loading: Optional[bool]` - `enabled: Optional[bool]` - `tools: Optional[List[BetaMCPToolParam]]` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: Dict[str, object]` The tool's input schema as the MCP server lists it, verbatim. - `name: str` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: Optional[str]` The tool's description as the MCP server lists it. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaRequestToolRemovalBlock` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name: one declared in the request's `tools` or defined earlier in `messages`. It is no longer offered to the model from this point in the conversation onward. - `type: Literal["tool_removal"]` - `tool: Tool` - `class BetaToolChangeToolReference` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `class BetaToolChangeMCPToolReference` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `class BetaToolChangeMCPToolsetReference` Reference to every tool in the named MCP server's toolset. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaRequestToolAdditionBlock` Mid-conversation directive to make a tool available. `tool` is a reference to a tool (or MCP toolset) declared in the request's `tools`. Under the `inline-tools-2026-09-15` beta it may instead be a reference to a tool defined earlier in `messages`, or a `tool_definition` object that carries an inline tool definition in `definition` (the same object a `tools` entry holds). An `mcp_toolset` definition also requires the `mcp-client-2026-09-15` beta. The tool is offered to the model from this point in the conversation onward. - `class BetaRequestToolRemovalBlock` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name: one declared in the request's `tools` or defined earlier in `messages`. It is no longer offered to the model from this point in the conversation onward. - `class BetaMCPToolListingBlockParam` The tool listing an MCP server returned while an earlier response was produced, as that response carried it. Send the assistant message back unchanged, this block included, and the server uses this listing for the matching `mcp_toolset` instead of asking the MCP server again. - `type: Literal["mcp_tool_listing"]` - `mcp_server_name: str` The name of the MCP server this listing came from, as `mcp_servers` declares it. minLength: 1, maxLength: 255 - `tools: List[BetaMCPToolParam]` The server's tools, exactly as the response listed them. - `input_schema: Dict[str, object]` The tool's input schema as the MCP server lists it, verbatim. - `name: str` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: Optional[str]` The tool's description as the MCP server lists it. - `class BetaFallbackBlockParam` A `fallback` block echoed back from a prior response. Accepted in `messages[].content` and not rendered into the prompt; not validated against the request's `fallbacks` chain or top-level `model`. Echo the assistant turn back verbatim, including this block in its original position. The block marks the boundary between content produced before and after a fallback hop, and the server relies on that boundary to validate the turn: when thinking runs flank the boundary, omitting the block merges them into one span the server cannot validate (the request is rejected), and moving it into the middle of a single run is likewise rejected; between non-thinking blocks the block's placement has no validation effect. - `type: Literal["fallback"]` - `from_: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `to: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `trigger: Optional[object]` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed. - `role: Literal["user", "assistant", "system"]` - `"user"` - `"assistant"` - `"system"` - `clear_at: Optional[Literal["next_user_message", "never"]]` How long this system message's text stays in front of the model. `"never"` (the default) renders it on every request that includes it. `"next_user_message"` renders it only for the user turn it follows: once a later `role: "user"` message exists in `messages` the message stays in the array (send it unchanged) but is no longer shown to the model. Only permitted on `role: "system"` messages. - `"next_user_message"` - `"never"` - `output_config: Optional[BetaSystemMessageOutputConfig]` Per-message output configuration on a role:"system" input message. Fields here apply per-turn; `format` remains top-level only. An empty `{}` is accepted on a message that carries content; a message with neither content nor output_config fields is rejected. - `effort: Optional[Literal["low", "medium", "high", 2 more]]` How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `model: ModelParam` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `cache_control: Optional[BetaCacheControlEphemeralParam]` Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. - `compaction: Optional[BetaCompactionConfigParam]` Compaction configuration. When set on `POST /v1/messages`, the request is a compaction request: the conversation in `messages` is summarized and the response holds only the resulting `compaction` block (`stop_reason` `"compaction"`), which later requests send first in `messages` in place of the messages it summarizes. `POST /v1/messages/count_tokens` accepts this parameter and ignores it: the count it returns is for the conversation in `messages` as sent. Cannot be combined with `context_management`. - `type: Literal["summarize"]` - `instructions: Optional[str]` Replaces the server's default summarization prompt for this request. An empty or whitespace-only value counts as absent. maxLength: 16384 - `container: Optional[Container]` Container identifier for reuse across requests. - `class BetaContainerParams` Container parameters with skills to be loaded. - `id: Optional[str]` Container id - `skills: Optional[List[BetaSkillParams]]` List of skills to load in the container maxItems: 20 - `type: Literal["anthropic", "custom"]` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: str` Skill ID minLength: 1, maxLength: 64 - `version: Optional[str]` Skill version or 'latest' for most recent version minLength: 1, maxLength: 64 - `str` - `context_management: Optional[BetaContextManagementConfigParam]` Context management configuration. This allows you to control how Claude manages context across multiple requests, such as whether to clear function results or not. - `edits: Optional[List[Edit]]` List of context management edits to apply - `class BetaClearToolUses20250919Edit` - `type: Literal["clear_tool_uses_20250919"]` - `clear_at_least: Optional[BetaInputTokensClearAtLeast]` Minimum number of tokens that must be cleared when triggered. Context will only be modified if at least this many tokens can be removed. - `type: Literal["input_tokens"]` - `value: int` minimum: 0 - `clear_tool_inputs: Optional[Union[bool, List[str], null]]` Whether to clear all tool inputs (bool) or specific tool inputs to clear (list) - `bool` - `List[str]` - `exclude_tools: Optional[List[str]]` Tool names whose uses are preserved from clearing - `keep: Optional[BetaToolUsesKeep]` Number of tool uses to retain in the conversation - `type: Literal["tool_uses"]` - `value: int` minimum: 0 - `trigger: Optional[Trigger]` Condition that triggers the context management strategy - `class BetaInputTokensTrigger` - `type: Literal["input_tokens"]` - `value: int` minimum: 1 - `class BetaToolUsesTrigger` - `type: Literal["tool_uses"]` - `value: int` minimum: 1 - `class BetaClearThinking20251015Edit` - `type: Literal["clear_thinking_20251015"]` - `keep: Optional[Keep]` Number of most recent assistant turns to keep thinking blocks for. Older turns will have their thinking blocks removed. - `class BetaThinkingTurns` - `type: Literal["thinking_turns"]` - `value: int` minimum: 1 - `class BetaAllThinkingTurns` - `type: Literal["all"]` - `"all"` - `class BetaCompact20260112Edit` Automatically compact older context when reaching the configured trigger threshold. - `type: Literal["compact_20260112"]` - `instructions: Optional[str]` Additional instructions for summarization. - `pause_after_compaction: Optional[bool]` Whether to pause after compaction and return the compaction block to the user. - `trigger: Optional[BetaInputTokensTrigger]` When to trigger compaction. Defaults to 150000 input tokens. - `diagnostics: Optional[BetaDiagnosticsParam]` Request-level diagnostics. Supply `previous_message_id` to have the response include `diagnostics.cache_miss_reason` explaining any prompt-cache divergence from that prior request. - `previous_message_id: Optional[str]` The `id` (`msg_...`) from this client's previous /v1/messages response. The server compares that request's prompt fingerprint against this one and returns `diagnostics.cache_miss_reason` when the prompt-cache prefix could not be reused. Pass `null` on the first turn to opt in without a prior message to compare. maxLength: 256 - `fallback_credit_token: Optional[FallbackCreditToken]` The `fallback_credit_token` from a prior refusal's `stop_details`. When a preceding request was refused and returned a `fallback_credit_token`, pass that code here on the retry to have the retry's cache-creation tokens for the prefix that was warm on the refused model billed at the cache-read rate. Must be redeemed by the same organization and workspace, with the same request body (optionally extended by one appended `assistant` message whose content is the partial text — with any trailing whitespace stripped from the final text block — and paired server-tool blocks streamed before the refusal; the appended-assistant form is not available for requests with `output_format` set or forced `tool_choice`), on an eligible fallback model, on the same platform, and within 5 minutes of the refusal; a mismatch is a 400. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed with the appended-assistant form — if an exact-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry with the appended-assistant form instead. When the appended-assistant form is used on a model that otherwise disallows assistant-turn prefill, this token also authorizes that one prefill. - `str` - `class BetaFallbackCreditTokenParam` Object form of `fallback_credit_token`: the token plus a redemption mode. Requires `anthropic-beta: fallback-credit-2026-07-01`; without that header the field accepts the bare string only. The bare string and the mode-less object are equivalent (both select `strict`), so wrapping an existing token changes nothing by itself. - `token: str` The opaque `fallback_credit_token` from a prior refusal's `stop_details` — the same string the bare-string form carries. minLength: 1, maxLength: 2048 - `mode: Optional[Literal["strict", "best_effort"]]` How a failing token affects the retry. `strict` (the default, and the bare-string behavior): a failing redemption is a 400 and the retry is not served. `best_effort`: the retry is served either way — a token-layer failure no longer rejects the request; the retry proceeds at normal price and the outcome is reported on the response's `usage.fallback_credit`. Two failures stay hard in both modes: a malformed token, and combining `fallback_credit_token` with `fallbacks`. - `"strict"` - `"best_effort"` - `fallbacks: Optional[BetaFallbacksParam]` Opt-in server-side retry on one or more substitute models when the requested model declines for policy reasons. Tried in order: if the first entry also declines, the second is tried, and so on. Some models don't support fallbacks; on those models, a list of fallback models returns a 400 error. See [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback?sdk_languages=python#server-side-fallback). The string "default" requests the requested model's server-defined default fallback configuration. On a model that doesn't support fallbacks, the request runs on the requested model alone, so a declined request stays declined. - `List[BetaFallbackParam]` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `max_tokens: Optional[int]` - `output_config: Optional[BetaOutputConfig]` - `effort: Optional[Literal["low", "medium", "high", 2 more]]` How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `format: Optional[BetaJSONOutputFormat]` A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs?sdk_languages=python) - `type: Literal["json_schema"]` - `schema: Dict[str, object]` The JSON schema of the format - `task_budget: Optional[BetaTokenTaskBudget]` Configuration for token budget tracking across contexts. - `type: Literal["tokens"]` The budget type. Currently only 'tokens' is supported. - `total: int` Total token budget across all contexts in the session. minimum: 1024 - `remaining: Optional[int]` Remaining tokens in the budget. Use this to track usage across contexts when implementing compaction client-side. Defaults to total if not provided. minimum: 0 - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `thinking: Optional[Thinking]` - `class BetaThinkingConfigEnabled` - `type: Literal["enabled"]` - `budget_tokens: int` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=python) for details. minimum: 1024 - `block_binding: Optional[BetaThinkingBlockBinding]` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `prefix_mismatch_behavior: Optional[BetaThinkingPrefixMismatchBehavior]` "error" (default) | "drop_block". What happens when a thinking block in `messages` fails the conversation check (it was created in a different conversation, or the messages before it have changed since). "error" fails the request with a 400 error. "drop_block" removes the failing blocks and the request proceeds; each removal is reported in `input_transformations`. - `"error"` - `"drop_block"` - `display: Optional[Literal["summarized", "omitted", "updates"]]` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=python#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` - `class BetaThinkingConfigDisabled` - `type: Literal["disabled"]` - `class BetaThinkingConfigBetweenTools` - `type: Literal["between_tools"]` - `class BetaThinkingConfigAdaptive` - `type: Literal["adaptive"]` - `block_binding: Optional[BetaThinkingBlockBinding]` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `display: Optional[Literal["summarized", "omitted", "updates"]]` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=python#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` - `"default"` - `inference_geo: Optional[str]` Specifies the geographic region for inference processing. If not specified, the workspace's `default_inference_geo` is used. - `mcp_servers: Optional[Iterable[BetaRequestMCPServerURLDefinitionParam]]` MCP servers to be utilized in this request maxItems: 20 - `type: Literal["url"]` - `name: str` - `url: str` - `authorization_token: Optional[str]` - `tool_configuration: Optional[BetaRequestMCPServerToolConfiguration]` - `allowed_tools: Optional[List[str]]` - `enabled: Optional[bool]` - `metadata: Optional[BetaMetadataParam]` An object describing metadata about the request. - `user_id: Optional[str]` An external identifier for the user who is associated with the request. This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number. maxLength: 512 - `output_config: Optional[BetaOutputConfigParam]` Configuration options for the model's output, such as the output format. - `service_tier: Optional[Literal["auto", "standard_only"]]` Determines whether to use priority capacity (if available) or standard capacity for this request. Anthropic offers different levels of service for your API requests. See [service-tiers](https://platform.claude.com/docs/en/api/service-tiers?sdk_languages=python) for details. - `"auto"` - `"standard_only"` - `speed: Optional[Literal["standard", "fast"]]` The inference speed mode for this request. `"fast"` enables high output-tokens-per-second inference. - `"standard"` - `"fast"` - `stop_sequences: Optional[Sequence[str]]` Custom text sequences that will cause the model to stop generating. Our models will normally stop when they have naturally completed their turn, which will result in a response `stop_reason` of `"end_turn"`. If you want the model to stop generating when it encounters custom strings of text, you can use the `stop_sequences` parameter. If the model encounters one of the custom sequences, the response `stop_reason` value will be `"stop_sequence"` and the response `stop_sequence` value will contain the matched stop sequence. - `stream: Optional[Literal[false]]` Whether to incrementally stream the response using server-sent events. When `true`, SDKs return a raw event stream. In the TypeScript, Python and Ruby SDKs, the recommended way to stream is `messages.stream()`. It sets `stream` for you and accumulates the events into the final message. See [Streaming with SDKs](https://platform.claude.com/docs/en/build-with-claude/streaming?sdk_languages=python#streaming-with-sdks) for an example in each language. - `system: Optional[Union[str, Iterable[BetaTextBlockParam]]]` System prompt. A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices?sdk_languages=python#give-claude-a-role). - `str` - `Iterable[BetaTextBlockParam]` - `type: Literal["text"]` - `text: str` minLength: 1 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[List[BetaTextCitationParam]]` - `thinking: Optional[BetaThinkingConfigParam]` Configuration for Claude's thinking. With `{"type": "adaptive"}`, Claude decides when and how much to think. With `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of at least 1,024. Thinking tokens count toward your `max_tokens` limit. Which `type` values are accepted, and what happens when you omit `thinking`, depend on the model. See [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=python#configuring-thinking) for each model's behavior. - `class BetaThinkingConfigEnabled` - `class BetaThinkingConfigDisabled` - `class BetaThinkingConfigBetweenTools` - `class BetaThinkingConfigAdaptive` - `tool_choice: Optional[BetaToolChoiceParam]` How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all. - `class BetaToolChoiceAuto` The model will automatically decide whether to use tools. - `type: Literal["auto"]` - `disable_parallel_tool_use: Optional[bool]` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. - `class BetaToolChoiceAny` The model will use any available tools. - `type: Literal["any"]` - `disable_parallel_tool_use: Optional[bool]` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - `class BetaToolChoiceTool` The model will use the specified tool with `tool_choice.name`. - `type: Literal["tool"]` - `name: str` The name of the tool to use. - `disable_parallel_tool_use: Optional[bool]` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - `class BetaToolChoiceNone` The model will not be allowed to use tools. - `type: Literal["none"]` - `tools: Optional[Iterable[BetaToolUnionParam]]` Definitions of tools that the model may use. If you include `tools` in your API request, the model may return `tool_use` content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using `tool_result` content blocks. There are two types of tools: **client tools** and **server tools**. The behavior described below applies to client tools. For [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools?sdk_languages=python), see their individual documentation as each has its own behavior (e.g., the [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool?sdk_languages=python)). Each tool definition includes: * `name`: Name of the tool. * `description`: Optional, but strongly-recommended description of the tool. * `input_schema`: [JSON schema](https://json-schema.org/draft/2020-12) for the tool `input` shape that the model will produce in `tool_use` output content blocks. For example, if you defined `tools` as: ```json [ { "name": "get_stock_price", "description": "Get the current stock price for a given ticker symbol.", "input_schema": { "type": "object", "properties": { "ticker": { "type": "string", "description": "The stock ticker symbol, e.g. AAPL for Apple Inc." } }, "required": ["ticker"] } } ] ``` And then asked the model "What's the S&P 500 at today?", the model might produce `tool_use` content blocks in the response like this: ```json [ { "type": "tool_use", "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "name": "get_stock_price", "input": { "ticker": "^GSPC" } } ] ``` You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an input, and return the following back to the model in a subsequent `user` message: ```json [ { "type": "tool_result", "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "content": "259.75 USD" } ] ``` Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output. See our [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview?sdk_languages=python) for more details. - `class BetaTool` - `class BetaToolBash20241022` - `class BetaToolBash20250124` - `class BetaCodeExecutionTool20250522` - `class BetaCodeExecutionTool20250825` - `class BetaCodeExecutionTool20260120` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `class BetaCodeExecutionTool20260521` Code execution tool with REPL state persistence. - `class BetaBrowserToolset20260801` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `class BetaToolComputerUse20241022` - `class BetaMemoryTool20250818` - `class BetaToolComputerUse20250124` - `class BetaToolTextEditor20241022` - `class BetaToolComputerUse20251124` - `class BetaComputerToolset20260801` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `class BetaToolTextEditor20250124` - `class BetaToolTextEditor20250429` - `class BetaToolTextEditor20250728` - `class BetaWebSearchTool20250305` - `class BetaWebFetchTool20250910` - `class BetaWebSearchTool20260209` - `class BetaWebFetchTool20260209` - `class BetaWebFetchTool20260309` Web fetch tool with use_cache parameter for bypassing cached content. - `class BetaWebSearchTool20260318` - `class BetaWebFetchTool20260318` - `class BetaAdvisorTool20260301` - `class BetaToolSearchToolBm25_20251119` - `class BetaToolSearchToolRegex20251119` - `class BetaMCPToolset` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `user_profile_id: Optional[str]` (header parameter) The user profile ID to attribute this request to. Use when acting on behalf of a party other than your organization. Requires the `user-profiles` beta header. - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaMessage` - `type: Literal["message"]` Object type. For Messages, this is always `"message"`. default: message - `id: str` Unique object identifier. The format and length of IDs may change over time. - `container: Optional[BetaContainer]` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `id: str` Identifier for the container used in this request - `expires_at: datetime` The time at which the container will expire. format: date-time - `skills: Optional[List[BetaContainerSkill]]` Skills loaded in the container - `type: Literal["anthropic", "custom"]` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: str` Skill ID minLength: 1, maxLength: 64 - `version: str` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `content: List[BetaContentBlock]` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `class BetaTextBlock` - `type: Literal["text"]` default: text - `citations: Optional[List[BetaTextCitation]]` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `class BetaCitationCharLocation` - `type: Literal["char_location"]` default: char_location - `cited_text: str` - `document_index: int` minimum: 0 - `document_title: Optional[str]` - `end_char_index: int` - `file_id: Optional[str]` - `start_char_index: int` minimum: 0 - `class BetaCitationPageLocation` - `type: Literal["page_location"]` default: page_location - `cited_text: str` - `document_index: int` minimum: 0 - `document_title: Optional[str]` - `end_page_number: int` - `file_id: Optional[str]` - `start_page_number: int` minimum: 1 - `class BetaCitationContentBlockLocation` - `type: Literal["content_block_location"]` default: content_block_location - `cited_text: str` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: int` minimum: 0 - `document_title: Optional[str]` - `end_block_index: int` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: Optional[str]` - `start_block_index: int` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `class BetaCitationsWebSearchResultLocation` - `type: Literal["web_search_result_location"]` default: web_search_result_location - `cited_text: str` - `encrypted_index: str` - `title: Optional[str]` maxLength: 512 - `url: str` - `class BetaCitationSearchResultLocation` - `type: Literal["search_result_location"]` default: search_result_location - `cited_text: str` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: int` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: int` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: str` - `start_block_index: int` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: Optional[str]` - `text: str` - `class BetaThinkingBlock` - `type: Literal["thinking"]` default: thinking - `signature: str` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=python) for details. - `thinking: str` The text of Claude's thinking process for this block. - `class BetaRedactedThinkingBlock` - `type: Literal["redacted_thinking"]` default: redacted_thinking - `data: str` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=python#redacted-thinking-blocks) for details. - `class BetaToolUseBlock` - `type: Literal["tool_use"]` default: tool_use - `id: str` pattern: ^[a-zA-Z0-9_-]+$ - `input: Dict[str, object]` - `name: str` minLength: 1 - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `type: Literal["direct"]` - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `type: Literal["code_execution_20250825"]` - `tool_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaServerToolCaller20260120` - `type: Literal["code_execution_20260120"]` - `tool_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: Optional[str]` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `class BetaServerToolUseBlock` - `type: Literal["server_tool_use"]` default: server_tool_use - `id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: Dict[str, object]` - `name: Literal["advisor", "web_search", "web_fetch", 5 more]` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaWebSearchToolResultBlock` - `type: Literal["web_search_tool_result"]` default: web_search_tool_result - `content: BetaWebSearchToolResultBlockContent` - `class BetaWebSearchToolResultError` - `type: Literal["web_search_tool_result_error"]` default: web_search_tool_result_error - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `List[BetaWebSearchResultBlock]` - `type: Literal["web_search_result"]` default: web_search_result - `encrypted_content: str` - `page_age: Optional[str]` - `title: str` - `url: str` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaWebFetchToolResultBlock` - `type: Literal["web_fetch_tool_result"]` default: web_fetch_tool_result - `content: Content` - `class BetaWebFetchToolResultErrorBlock` - `type: Literal["web_fetch_tool_result_error"]` default: web_fetch_tool_result_error - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `class BetaWebFetchBlock` - `type: Literal["web_fetch_result"]` default: web_fetch_result - `content: BetaDocumentBlock` - `type: Literal["document"]` default: document - `citations: Optional[BetaCitationConfig]` Citation configuration for the document - `enabled: bool` default: false - `source: Source` - `class BetaBase64PDFSource` - `type: Literal["base64"]` - `data: str` format: byte - `media_type: Literal["application/pdf"]` - `class BetaPlainTextSource` - `type: Literal["text"]` - `data: str` - `media_type: Literal["text/plain"]` - `title: Optional[str]` The title of the document - `retrieved_at: Optional[str]` ISO 8601 timestamp when the content was retrieved - `url: str` Fetched content URL - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaAdvisorToolResultBlock` - `type: Literal["advisor_tool_result"]` default: advisor_tool_result - `content: Content` - `class BetaAdvisorToolResultError` - `type: Literal["advisor_tool_result_error"]` default: advisor_tool_result_error - `error_code: Literal["max_uses_exceeded", "prompt_too_long", "too_many_requests", 4 more]` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `class BetaAdvisorResultBlock` - `type: Literal["advisor_result"]` default: advisor_result - `stop_reason: Optional[str]` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: str` - `class BetaAdvisorRedactedResultBlock` - `type: Literal["advisor_redacted_result"]` default: advisor_redacted_result - `encrypted_content: str` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: Optional[str]` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaCodeExecutionToolResultBlock` - `type: Literal["code_execution_tool_result"]` default: code_execution_tool_result - `content: BetaCodeExecutionToolResultBlockContent` - `class BetaCodeExecutionToolResultError` - `type: Literal["code_execution_tool_result_error"]` default: code_execution_tool_result_error - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `class BetaCodeExecutionResultBlock` - `type: Literal["code_execution_result"]` default: code_execution_result - `content: List[BetaCodeExecutionOutputBlock]` - `type: Literal["code_execution_output"]` default: code_execution_output - `file_id: str` - `return_code: int` - `stderr: str` - `stdout: str` - `class BetaEncryptedCodeExecutionResultBlock` Code execution result with encrypted stdout for PFC + web_search results. - `type: Literal["encrypted_code_execution_result"]` default: encrypted_code_execution_result - `content: List[BetaCodeExecutionOutputBlock]` - `type: Literal["code_execution_output"]` default: code_execution_output - `file_id: str` - `encrypted_stdout: str` - `return_code: int` - `stderr: str` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaBashCodeExecutionToolResultBlock` - `type: Literal["bash_code_execution_tool_result"]` default: bash_code_execution_tool_result - `content: Content` - `class BetaBashCodeExecutionToolResultError` - `type: Literal["bash_code_execution_tool_result_error"]` default: bash_code_execution_tool_result_error - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", 2 more]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `class BetaBashCodeExecutionResultBlock` - `type: Literal["bash_code_execution_result"]` default: bash_code_execution_result - `content: List[BetaBashCodeExecutionOutputBlock]` - `type: Literal["bash_code_execution_output"]` default: bash_code_execution_output - `file_id: str` - `return_code: int` - `stderr: str` - `stdout: str` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaTextEditorCodeExecutionToolResultBlock` - `type: Literal["text_editor_code_execution_tool_result"]` default: text_editor_code_execution_tool_result - `content: Content` - `class BetaTextEditorCodeExecutionToolResultError` - `type: Literal["text_editor_code_execution_tool_result_error"]` default: text_editor_code_execution_tool_result_error - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", 2 more]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: Optional[str]` - `class BetaTextEditorCodeExecutionViewResultBlock` - `type: Literal["text_editor_code_execution_view_result"]` default: text_editor_code_execution_view_result - `content: str` - `file_type: Literal["text", "image", "pdf"]` - `"text"` - `"image"` - `"pdf"` - `num_lines: Optional[int]` - `start_line: Optional[int]` - `total_lines: Optional[int]` - `class BetaTextEditorCodeExecutionCreateResultBlock` - `type: Literal["text_editor_code_execution_create_result"]` default: text_editor_code_execution_create_result - `is_file_update: bool` - `class BetaTextEditorCodeExecutionStrReplaceResultBlock` - `type: Literal["text_editor_code_execution_str_replace_result"]` default: text_editor_code_execution_str_replace_result - `lines: Optional[List[str]]` - `new_lines: Optional[int]` - `new_start: Optional[int]` - `old_lines: Optional[int]` - `old_start: Optional[int]` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaToolSearchToolResultBlock` - `type: Literal["tool_search_tool_result"]` default: tool_search_tool_result - `content: Content` - `class BetaToolSearchToolResultError` - `type: Literal["tool_search_tool_result_error"]` default: tool_search_tool_result_error - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", "execution_time_exceeded"]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: Optional[str]` - `class BetaToolSearchToolSearchResultBlock` - `type: Literal["tool_search_tool_search_result"]` default: tool_search_tool_search_result - `tool_references: List[BetaToolReferenceBlock]` - `type: Literal["tool_reference"]` default: tool_reference - `tool_name: str` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaMCPToolUseBlock` - `type: Literal["mcp_tool_use"]` default: mcp_tool_use - `id: str` pattern: ^[a-zA-Z0-9_-]+$ - `input: Dict[str, object]` - `name: str` The name of the MCP tool - `server_name: str` The name of the MCP server - `class BetaMCPToolResultBlock` - `type: Literal["mcp_tool_result"]` default: mcp_tool_result - `content: Union[str, List[BetaTextBlock]]` - `str` - `List[BetaTextBlock]` - `type: Literal["text"]` default: text - `citations: Optional[List[BetaTextCitation]]` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: str` - `is_error: bool` default: false - `tool_use_id: str` pattern: ^[a-zA-Z0-9_-]+$ - `class BetaContainerUploadBlock` Response model for a file uploaded to the container. - `type: Literal["container_upload"]` default: container_upload - `file_id: str` - `class BetaCompactionBlock` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `type: Literal["compaction"]` default: compaction - `content: Optional[str]` Summary of compacted content, or null if compaction failed - `encrypted_content: Optional[str]` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: Optional[str]` Signature over the summary, to be sent back with the block verbatim - `tool_changes: Optional[List[ToolChange]]` The tool changes of the compacted range: the `tool_addition` and `tool_removal` blocks that take the request's `tools` to the tool set in effect at the end of the range, or `[]` when the range changed no tool. Absent when the server did not compute them. Send the block back unchanged. - `class BetaResponseToolAdditionBlock` An entry of a `compaction` block's `tool_changes`: a tool the compacted range made available, as a reference to a `tools` entry or MCP toolset, or as the tool definition in effect at the end of the range, by value. Send it back unchanged. - `type: Literal["tool_addition"]` default: tool_addition - `tool: Tool` The tool made available: a reference to a `tools` entry or MCP toolset, or a `tool_definition` carrying the definition by value. - `class BetaResponseToolChangeToolReference` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: Literal["tool_reference"]` default: tool_reference - `name: str` - `class BetaResponseToolChangeMCPToolReference` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: Literal["mcp_tool_reference"]` default: mcp_tool_reference - `name: str` - `server_name: str` - `class BetaResponseToolChangeMCPToolsetReference` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: Literal["mcp_toolset_reference"]` default: mcp_toolset_reference - `server_name: str` - `class BetaToolChangeToolDefinition` A tool defined by value, as a `compaction` block's `tool_changes` entry reports it: `definition` is the tool's definition as it was sent, in the form of a `tools` entry, without `cache_control`. Send it back unchanged with the block. - `type: Literal["tool_definition"]` default: tool_definition - `definition: BetaResponseToolUnion` - `class BetaResponseTool` A custom tool definition, as sent. - `type: Optional[Literal["custom"]]` - `input_schema: BetaResponseToolInputSchema` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: Optional[str]` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: Optional[bool]` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolBash20241022` - `type: Literal["bash_20241022"]` - `name: Literal["bash"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `type: Literal["ephemeral"]` - `ttl: Optional[Literal["5m", "1h"]]` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=python) for details. - `"5m"` - `"1h"` - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolBash20250124` - `type: Literal["bash_20250124"]` - `name: Literal["bash"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20250522` - `type: Literal["code_execution_20250522"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20250825` - `type: Literal["code_execution_20250825"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20260120` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: Literal["code_execution_20260120"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20260521` Code execution tool with REPL state persistence. - `type: Literal["code_execution_20260521"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaBrowserToolset20260801` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: Literal["browser_toolset_20260801"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[BetaBrowserToolsetConfigs]` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: Optional[BetaBrowserTypeConfig]` `type`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: Optional[BetaBrowserCloseTabConfig]` `close_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: Optional[BetaBrowserDoubleClickConfig]` `double_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: Optional[BetaBrowserFileUploadConfig]` `file_upload`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: Optional[BetaBrowserFindConfig]` `find`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: Optional[BetaBrowserFormInputConfig]` `form_input`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: Optional[BetaBrowserGetPageTextConfig]` `get_page_text`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: Optional[BetaBrowserHoldKeyConfig]` `hold_key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: Optional[BetaBrowserHoverConfig]` `hover`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: Optional[BetaBrowserJavascriptExecConfig]` `javascript_exec`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: Optional[BetaBrowserKeyConfig]` `key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: Optional[BetaBrowserLeftClickConfig]` `left_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: Optional[BetaBrowserLeftClickDragConfig]` `left_click_drag`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: Optional[BetaBrowserLeftMouseDownConfig]` `left_mouse_down`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: Optional[BetaBrowserLeftMouseUpConfig]` `left_mouse_up`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: Optional[BetaBrowserListTabsConfig]` `list_tabs`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: Optional[BetaBrowserMiddleClickConfig]` `middle_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: Optional[BetaBrowserMouseMoveConfig]` `mouse_move`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: Optional[BetaBrowserNavigateConfig]` `navigate`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: Optional[BetaBrowserNewTabConfig]` `new_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: Optional[BetaBrowserReadConsoleConfig]` `read_console`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: Optional[BetaBrowserReadNetworkConfig]` `read_network`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: Optional[BetaBrowserReadPageConfig]` `read_page`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: Optional[BetaBrowserRightClickConfig]` `right_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: Optional[BetaBrowserScreenshotConfig]` `screenshot`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: Optional[BetaBrowserScrollConfig]` `scroll`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: Optional[BetaBrowserScrollToConfig]` `scroll_to`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: Optional[BetaBrowserSwitchTabConfig]` `switch_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: Optional[BetaBrowserTripleClickConfig]` `triple_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: Optional[BetaBrowserWaitConfig]` `wait`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: Optional[BetaBrowserZoomConfig]` `zoom`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `class BetaToolComputerUse20241022` - `type: Literal["computer_20241022"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaMemoryTool20250818` - `type: Literal["memory_20250818"]` - `name: Literal["memory"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolComputerUse20250124` - `type: Literal["computer_20250124"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20241022` - `type: Literal["text_editor_20241022"]` - `name: Literal["str_replace_editor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolComputerUse20251124` - `type: Literal["computer_20251124"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: Optional[bool]` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaComputerToolset20260801` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: Literal["computer_toolset_20260801"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[BetaComputerToolsetConfigs]` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: Optional[BetaComputerTypeConfig]` `type`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: Optional[BetaComputerCursorPositionConfig]` `cursor_position`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: Optional[BetaComputerDoubleClickConfig]` `double_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: Optional[BetaComputerHoldKeyConfig]` `hold_key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: Optional[BetaComputerKeyConfig]` `key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: Optional[BetaComputerLeftClickConfig]` `left_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: Optional[BetaComputerLeftClickDragConfig]` `left_click_drag`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: Optional[BetaComputerLeftMouseDownConfig]` `left_mouse_down`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: Optional[BetaComputerLeftMouseUpConfig]` `left_mouse_up`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: Optional[BetaComputerMiddleClickConfig]` `middle_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: Optional[BetaComputerMouseMoveConfig]` `mouse_move`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: Optional[BetaComputerRightClickConfig]` `right_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: Optional[BetaComputerScreenshotConfig]` `screenshot`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: Optional[BetaComputerScrollConfig]` `scroll`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: Optional[BetaComputerTripleClickConfig]` `triple_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: Optional[BetaComputerWaitConfig]` `wait`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: Optional[BetaComputerZoomConfig]` `zoom`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `class BetaToolTextEditor20250124` - `type: Literal["text_editor_20250124"]` - `name: Literal["str_replace_editor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20250429` - `type: Literal["text_editor_20250429"]` - `name: Literal["str_replace_based_edit_tool"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20250728` - `type: Literal["text_editor_20250728"]` - `name: Literal["str_replace_based_edit_tool"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `max_characters: Optional[int]` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaWebSearchTool20250305` - `type: Literal["web_search_20250305"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `type: Literal["approximate"]` - `city: Optional[str]` The city of the user. minLength: 1, maxLength: 255 - `country: Optional[str]` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: Optional[str]` The region of the user. minLength: 1, maxLength: 255 - `timezone: Optional[str]` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `class BetaWebFetchTool20250910` - `type: Literal["web_fetch_20250910"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: Optional[bool]` - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: Optional[ClientToolResults]` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: Literal["all"]` - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: Literal["none"]` - `class BetaWebFetchURLSourceOnly` The tool filter variant under which only the named tools' results contribute. - `type: Literal["only"]` - `tools: List[BetaWebFetchURLSourceToolReference]` - `type: Literal["tool_reference"]` - `name: str` - `class BetaWebFetchURLSourceExcept` The tool filter variant under which every result but the named tools' contributes. - `type: Literal["except"]` - `tools: List[BetaWebFetchURLSourceToolReference]` - `type: Literal["tool_reference"]` - `name: str` - `server_tool_results: Optional[ServerToolResults]` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `class BetaWebFetchURLSourceOnly` The tool filter variant under which only the named tools' results contribute. - `class BetaWebFetchURLSourceExcept` The tool filter variant under which every result but the named tools' contributes. - `user_input: Optional[UserInput]` Whether URLs in user messages are fetchable: "all" or "none". - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `class BetaWebSearchTool20260209` - `type: Literal["web_search_20260209"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `class BetaWebFetchTool20260209` - `type: Literal["web_fetch_20260209"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `class BetaWebFetchTool20260309` Web fetch tool with use_cache parameter for bypassing cached content. - `type: Literal["web_fetch_20260309"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `use_cache: Optional[bool]` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `class BetaWebSearchTool20260318` - `type: Literal["web_search_20260318"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: Optional[Literal["full", "excluded"]]` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `class BetaWebFetchTool20260318` - `type: Literal["web_fetch_20260318"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: Optional[Literal["full", "excluded"]]` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `use_cache: Optional[bool]` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `class BetaAdvisorTool20260301` - `type: Literal["advisor_20260301"]` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `name: Literal["advisor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caching: Optional[BetaCacheControlEphemeral]` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: Optional[int]` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolSearchToolBm25_20251119` - `type: Literal["tool_search_tool_bm25_20251119", "tool_search_tool_bm25"]` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: Literal["tool_search_tool_bm25"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolSearchToolRegex20251119` - `type: Literal["tool_search_tool_regex_20251119", "tool_search_tool_regex"]` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: Literal["tool_search_tool_regex"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaMCPToolset` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: Literal["mcp_toolset"]` - `mcp_server_name: str` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[Dict[str, BetaMCPToolConfig]]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: Optional[bool]` - `enabled: Optional[bool]` - `default_config: Optional[BetaMCPToolDefaultConfig]` Default configuration applied to all tools from this server - `defer_loading: Optional[bool]` - `enabled: Optional[bool]` - `tools: Optional[List[BetaMCPToolParam]]` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: Dict[str, object]` The tool's input schema as the MCP server lists it, verbatim. - `name: str` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: Optional[str]` The tool's description as the MCP server lists it. - `class BetaResponseToolRemovalBlock` An entry of a `compaction` block's `tool_changes`: a tool of the request's `tools` (or an MCP tool or toolset) that the compacted range withdrew. Send it back unchanged. - `type: Literal["tool_removal"]` default: tool_removal - `tool: Tool` A reference to the withdrawn `tools` entry, MCP tool or MCP toolset. - `class BetaResponseToolChangeToolReference` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `class BetaResponseToolChangeMCPToolReference` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `class BetaResponseToolChangeMCPToolsetReference` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `class BetaFallbackBlock` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `type: Literal["fallback"]` default: fallback - `from_: BetaFallbackInfo` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `to: BetaFallbackInfo` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `trigger: BetaFallbackRefusalTrigger` What caused the `from` model to hand over at this hop. - `type: Literal["refusal"]` default: refusal - `category: Optional[Literal["cyber", "bio", "frontier_llm", 2 more]]` The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=python). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `class BetaMCPToolListingBlock` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `type: Literal["mcp_tool_listing"]` default: mcp_tool_listing - `mcp_server_name: str` - `tools: List[BetaMCPTool]` - `input_schema: Dict[str, object]` - `name: str` - `description: Optional[str]` - `context_management: Optional[BetaContextManagementResponse]` Context management response. Information about context management strategies applied during the request. - `applied_edits: List[AppliedEdit]` List of context management edits that were applied. - `class BetaClearToolUses20250919EditResponse` - `type: Literal["clear_tool_uses_20250919"]` The type of context management edit applied. default: clear_tool_uses_20250919 - `cleared_input_tokens: int` Number of input tokens cleared by this edit. minimum: 0 - `cleared_tool_uses: int` Number of tool uses that were cleared. minimum: 0 - `class BetaClearThinking20251015EditResponse` - `type: Literal["clear_thinking_20251015"]` The type of context management edit applied. default: clear_thinking_20251015 - `cleared_input_tokens: int` Number of input tokens cleared by this edit. minimum: 0 - `cleared_thinking_turns: int` Number of thinking turns that were cleared. minimum: 0 - `diagnostics: Optional[BetaDiagnostics]` Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected. - `cache_miss_reason: Optional[BetaCacheMissReason]` Explains why the prompt cache could not fully reuse the prefix from the request identified by `diagnostics.previous_message_id`. `null` means diagnosis is still pending — the response was serialized before the background comparison completed. - `class BetaCacheMissModelChanged` - `type: Literal["model_changed"]` default: model_changed - `cache_missed_input_tokens: int` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `class BetaCacheMissSystemChanged` - `type: Literal["system_changed"]` default: system_changed - `cache_missed_input_tokens: int` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `class BetaCacheMissToolsChanged` - `type: Literal["tools_changed"]` default: tools_changed - `cache_missed_input_tokens: int` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `class BetaCacheMissMessagesChanged` - `type: Literal["messages_changed"]` default: messages_changed - `cache_missed_input_tokens: int` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `class BetaCacheMissPreviousMessageNotFound` - `type: Literal["previous_message_not_found"]` default: previous_message_not_found - `class BetaCacheMissUnavailable` - `type: Literal["unavailable"]` default: unavailable - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `role: Literal["assistant"]` Conversational role of the generated message. This will always be `"assistant"`. default: assistant - `stop_details: Optional[BetaRefusalStopDetails]` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `type: Literal["refusal"]` default: refusal - `category: Optional[Literal["cyber", "bio", "frontier_llm", 2 more]]` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=python). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: Optional[str]` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: Optional[str]` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: Optional[bool]` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: Optional[str]` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: Optional[BetaStopReason]` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: Optional[str]` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: BetaUsage` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation: Optional[BetaCacheCreation]` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: int` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: int` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: Optional[int]` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: Optional[int]` The number of input tokens read from the cache. minimum: 0 - `fallback_credit: Optional[BetaFallbackCreditUsage]` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `status: Status` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `class BetaFallbackCreditRedeemed` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: Literal["redeemed"]` default: redeemed - `class BetaFallbackCreditNotApplied` No reprice was applied; `reason` says why. - `type: Literal["not_applied"]` default: not_applied - `reason: Literal["body_mismatch", "continuation_excluded", "continuation_only", 9 more]` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: Optional[List[str]]` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: Optional[str]` The geographic region where inference was performed for this request. - `input_tokens: int` The number of input tokens which were used. minimum: 0 - `iterations: Optional[BetaIterationsUsage]` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `class BetaMessageIterationUsage` Token usage for a sampling iteration. - `type: Literal["message"]` Usage for a sampling iteration default: message - `cache_creation: Optional[BetaCacheCreation]` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: int` The number of input tokens used to create the cache entry. default: 0, minimum: 0 - `cache_read_input_tokens: int` The number of input tokens read from the cache. default: 0, minimum: 0 - `input_tokens: int` The number of input tokens which were used. minimum: 0 - `model: Optional[Model]` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: int` The number of output tokens which were used. minimum: 0 - `class BetaCompactionIterationUsage` Token usage for a compaction iteration. - `type: Literal["compaction"]` Usage for a compaction iteration default: compaction - `cache_creation: Optional[BetaCacheCreation]` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: int` The number of input tokens used to create the cache entry. default: 0, minimum: 0 - `cache_read_input_tokens: int` The number of input tokens read from the cache. default: 0, minimum: 0 - `input_tokens: int` The number of input tokens which were used. minimum: 0 - `output_tokens: int` The number of output tokens which were used. minimum: 0 - `class BetaAdvisorMessageIterationUsage` Token usage for an advisor sub-inference iteration. - `type: Literal["advisor_message"]` Usage for an advisor sub-inference iteration default: advisor_message - `cache_creation: Optional[BetaCacheCreation]` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: int` The number of input tokens used to create the cache entry. default: 0, minimum: 0 - `cache_read_input_tokens: int` The number of input tokens read from the cache. default: 0, minimum: 0 - `input_tokens: int` The number of input tokens which were used. minimum: 0 - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: int` The number of output tokens which were used. minimum: 0 - `class BetaFallbackMessageIterationUsage` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: Literal["fallback_message"]` Usage for the fallback-model attempt that served the response default: fallback_message - `cache_creation: Optional[BetaCacheCreation]` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: int` The number of input tokens used to create the cache entry. default: 0, minimum: 0 - `cache_read_input_tokens: int` The number of input tokens read from the cache. default: 0, minimum: 0 - `input_tokens: int` The number of input tokens which were used. minimum: 0 - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: int` The number of output tokens which were used. minimum: 0 - `output_tokens: int` The number of output tokens which were used. minimum: 0 - `output_tokens_details: Optional[BetaOutputTokensDetails]` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `thinking_tokens: int` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. default: 0, minimum: 0 - `server_tool_use: Optional[BetaServerToolUsage]` The number of server tool requests. - `web_fetch_requests: int` The number of web fetch tool requests. default: 0, minimum: 0 - `web_search_requests: int` The number of web search tool requests. default: 0, minimum: 0 - `service_tier: Optional[Literal["standard", "priority", "batch"]]` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: Optional[Literal["standard", "fast"]]` The inference speed mode used for this request. - `"standard"` - `"fast"` - `input_transformations: Optional[List[BetaInputTransformation]]` Changes the API made to the request's input before showing it to the model, and blocks that failed a binding check but were left unchanged: one entry per block, in request order. Two entry types today. `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. `thinking_mismatch_allowed` — a `thinking` or `redacted_thinking` block that failed the conversation check (the conversation before it differs from the one it was created in, or it carries no record of one on a model that requires it) and was shown to the model all the same, because that check is not enforced for this request. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when there is no entry to report; without the beta, blocks are removed or left in place all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`; blocks left in place count as sent. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `class BetaThinkingDroppedInputTransformation` - `type: Literal["thinking_dropped"]` Always `thinking_dropped` for this entry type. default: thinking_dropped - `path: str` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: Literal["model_binding_mismatch", "prefix_binding_mismatch", "organization_binding_mismatch", "end_user_binding_mismatch"]` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `class BetaThinkingMismatchAllowedInputTransformation` - `type: Literal["thinking_mismatch_allowed"]` Always `thinking_mismatch_allowed` for this entry type. default: thinking_mismatch_allowed - `path: str` Where the block is in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: Literal["model_binding_mismatch", "prefix_binding_mismatch", "organization_binding_mismatch", "end_user_binding_mismatch"]` Which binding check the block failed; the block was shown to the model all the same. Always `prefix_binding_mismatch` today — the conversation before the block differs from the conversation it was created in, or the block carries no record of one on a model that requires it. Were the check enforced for this request, the block would have been removed or the request rejected (`thinking.block_binding.prefix_mismatch_behavior`). A removal also takes the rest of that turn's consecutive thinking blocks, whereas here each block is checked on its own, so `thinking_mismatch_allowed` entries are a lower bound on what enforcement would remove. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `type BetaRawMessageStreamEvent = ...` - `class BetaRawMessageStartEvent` - `type: Literal["message_start"]` default: message_start - `message: BetaMessage` - `class BetaRawMessageDeltaEvent` - `type: Literal["message_delta"]` default: message_delta - `context_management: Optional[BetaContextManagementResponse]` Information about context management strategies applied during the request - `delta: Delta` - `container: Optional[BetaContainer]` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `stop_details: Optional[BetaRefusalStopDetails]` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `stop_reason: Optional[BetaStopReason]` - `stop_sequence: Optional[str]` - `usage: BetaMessageDeltaUsage` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation_input_tokens: Optional[int]` The cumulative number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: Optional[int]` The cumulative number of input tokens read from the cache. minimum: 0 - `fallback_credit: Optional[BetaFallbackCreditUsage]` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `input_tokens: Optional[int]` The cumulative number of input tokens which were used. minimum: 0 - `iterations: Optional[BetaIterationsUsage]` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `output_tokens: int` The cumulative number of output tokens which were used. - `output_tokens_details: Optional[BetaOutputTokensDetails]` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `server_tool_use: Optional[BetaServerToolUsage]` The number of server tool requests. - `input_transformations: Optional[List[BetaInputTransformation]]` Changes the API made to the request's input before showing it to the model, and blocks that failed a binding check but were left unchanged: one entry per block, in request order. Two entry types today. `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. `thinking_mismatch_allowed` — a `thinking` or `redacted_thinking` block that failed the conversation check (the conversation before it differs from the one it was created in, or it carries no record of one on a model that requires it) and was shown to the model all the same, because that check is not enforced for this request. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when there is no entry to report; without the beta, blocks are removed or left in place all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`; blocks left in place count as sent. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `class BetaThinkingDroppedInputTransformation` - `class BetaThinkingMismatchAllowedInputTransformation` - `class BetaRawMessageStopEvent` - `type: Literal["message_stop"]` default: message_stop - `class BetaRawContentBlockStartEvent` - `type: Literal["content_block_start"]` default: content_block_start - `content_block: ContentBlock` - `class BetaTextBlock` - `class BetaThinkingBlock` - `class BetaRedactedThinkingBlock` - `class BetaToolUseBlock` - `class BetaServerToolUseBlock` - `class BetaWebSearchToolResultBlock` - `class BetaWebFetchToolResultBlock` - `class BetaAdvisorToolResultBlock` - `class BetaCodeExecutionToolResultBlock` - `class BetaBashCodeExecutionToolResultBlock` - `class BetaTextEditorCodeExecutionToolResultBlock` - `class BetaToolSearchToolResultBlock` - `class BetaMCPToolUseBlock` - `class BetaMCPToolResultBlock` - `class BetaContainerUploadBlock` Response model for a file uploaded to the container. - `class BetaCompactionBlock` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `class BetaFallbackBlock` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `class BetaMCPToolListingBlock` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `index: int` - `class BetaRawContentBlockDeltaEvent` - `type: Literal["content_block_delta"]` default: content_block_delta - `delta: BetaRawContentBlockDelta` - `class BetaTextDelta` - `type: Literal["text_delta"]` default: text_delta - `text: str` - `class BetaInputJSONDelta` - `type: Literal["input_json_delta"]` default: input_json_delta - `partial_json: str` - `class BetaCitationsDelta` - `type: Literal["citations_delta"]` default: citations_delta - `citation: Citation` - `class BetaCitationCharLocation` - `class BetaCitationPageLocation` - `class BetaCitationContentBlockLocation` - `class BetaCitationsWebSearchResultLocation` - `class BetaCitationSearchResultLocation` - `class BetaThinkingDelta` - `type: Literal["thinking_delta"]` default: thinking_delta - `estimated_tokens: Optional[int]` Per-frame increment of a coarse, running estimate of the tokens this thinking block has produced so far. Present whenever the `thinking-token-count-2026-05-13` beta is set; `null` unless `thinking.display` resolves to `"omitted"` and a count is due this frame. Sum the increments across `thinking_delta` frames on this block for a progress indicator. Each increment is a non-negative multiple of a fixed quantum and the cadence is rate-limited, so this is a deliberately lossy display hint, not a billable count; `usage.output_tokens` remains authoritative. - `thinking: str` The incremental `thinking` text for this content block. Concatenate the `thinking` values of successive `thinking_delta` events to assemble the block's full `thinking` value. - `class BetaSignatureDelta` - `type: Literal["signature_delta"]` default: signature_delta - `signature: str` The `signature` for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a `signature_delta` event just before the block's `content_block_stop` event. - `class BetaCompactionContentBlockDelta` - `type: Literal["compaction_delta"]` default: compaction_delta - `content: Optional[str]` - `encrypted_content: Optional[str]` Opaque metadata from prior compaction, to be round-tripped verbatim - `index: int` - `class BetaRawContentBlockStopEvent` - `type: Literal["content_block_stop"]` default: content_block_stop - `index: int` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_message = client.beta.messages.create( max_tokens=1024, messages=[ { "content": "Hello, world", "role": "user", } ], model="claude-opus-5", ) print(beta_message.id) ``` ##### Response (200) ```json { "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF", "container": { "id": "container_011CpZohnwH4vuy7gazohgSP", "expires_at": "2019-12-27T18:11:19.117Z", "skills": [ { "skill_id": "pdf", "type": "anthropic", "version": "latest" } ] }, "content": [ { "citations": [ { "cited_text": "The grass is green. The sky is blue.", "document_index": 0, "document_title": "My Document", "end_char_index": 0, "file_id": "file_011CNha8iCJcU1wXNR6q4V8w", "start_char_index": 0, "type": "char_location" } ], "text": "Hi! My name is Claude.", "type": "text" } ], "context_management": { "applied_edits": [ { "cleared_input_tokens": 0, "cleared_tool_uses": 0, "type": "clear_tool_uses_20250919" } ] }, "diagnostics": { "cache_miss_reason": { "cache_missed_input_tokens": 0, "type": "model_changed" } }, "model": "claude-opus-5", "role": "assistant", "stop_details": { "category": "cyber", "explanation": "This request was declined because it conflicts with Anthropic's Usage Policy.", "fallback_credit_token": "QW50aHJvcGljL0NsYXVkZQ==", "fallback_has_prefill_claim": true, "recommended_model": "claude-opus-4-8", "type": "refusal" }, "stop_reason": "end_turn", "stop_sequence": null, "type": "message", "usage": { "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_creation_input_tokens": 2051, "cache_read_input_tokens": 2051, "fallback_credit": { "status": { "type": "redeemed" } }, "inference_geo": "global", "input_tokens": 2095, "iterations": [ { "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "input_tokens": 0, "model": "claude-haiku-5-5", "output_tokens": 0, "type": "message" } ], "output_tokens": 503, "output_tokens_details": { "thinking_tokens": 0 }, "server_tool_use": { "web_fetch_requests": 2, "web_search_requests": 0 }, "service_tier": "standard", "speed": "standard" }, "input_transformations": [ { "path": "path", "reason": "model_binding_mismatch", "type": "thinking_dropped" } ] } ``` ### Count tokens in a Message `beta.messages.count_tokens(**kwargs) -> BetaMessageTokensCount` **POST** `/v1/messages/count_tokens` Count the number of tokens in a Message. The Token Count API can be used to count the number of tokens in a Message, including tools, images, and documents, without creating it. Learn more about token counting in our [user guide](https://platform.claude.com/docs/en/build-with-claude/token-counting?sdk_languages=python) #### Parameters - `messages: Iterable[BetaMessageParam]` Input messages. Our models are trained to operate on alternating `user` and `assistant` conversational turns. When creating a new `Message`, you specify the prior conversational turns with the `messages` parameter, and the model then generates the next `Message` in the conversation. Consecutive `user` or `assistant` turns in your request will be combined into a single turn. Each input message must be an object with a `role` and `content`. You can specify a single `user`-role message, or you can include multiple `user` and `assistant` messages. If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response. This is called prefill. On models that don't support prefill, creating a message that ends with a partial `assistant` response returns a 400 error. See [Prefill not supported](https://platform.claude.com/docs/en/api/errors?sdk_languages=python#prefill-not-supported). Example with a single `user` message: ```json [{"role": "user", "content": "Hello, Claude"}] ``` Example with multiple conversational turns: ```json [ {"role": "user", "content": "Hello there."}, {"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"}, {"role": "user", "content": "Can you explain LLMs in plain English?"}, ] ``` Example with a partially-filled response from Claude, for models that support prefill: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("}, ] ``` Each input message `content` may be either a single `string` or an array of content blocks, where each block has a specific `type`. Using a `string` for `content` is shorthand for an array of one content block of type `"text"`. The following input messages are equivalent: ```json {"role": "user", "content": "Hello, Claude"} ``` ```json {"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]} ``` See [input examples](https://platform.claude.com/docs/en/build-with-claude/working-with-messages?sdk_languages=python). Note that if you want to include a [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices?sdk_languages=python#give-claude-a-role), you can use the top-level `system` parameter — there is no `"system"` role for input messages in the Messages API. There is a limit of 100,000 messages in a single request. - `content: Union[str, List[BetaContentBlockParam]]` - `str` - `List[BetaContentBlockParam]` - `class BetaTextBlockParam` - `type: Literal["text"]` - `text: str` minLength: 1 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `type: Literal["ephemeral"]` - `ttl: Optional[Literal["5m", "1h"]]` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=python) for details. - `"5m"` - `"1h"` - `citations: Optional[List[BetaTextCitationParam]]` - `class BetaCitationCharLocationParam` - `type: Literal["char_location"]` - `cited_text: str` - `document_index: int` minimum: 0 - `document_title: Optional[str]` minLength: 1, maxLength: 500 - `end_char_index: int` - `start_char_index: int` minimum: 0 - `class BetaCitationPageLocationParam` - `type: Literal["page_location"]` - `cited_text: str` - `document_index: int` minimum: 0 - `document_title: Optional[str]` minLength: 1, maxLength: 500 - `end_page_number: int` - `start_page_number: int` minimum: 1 - `class BetaCitationContentBlockLocationParam` - `type: Literal["content_block_location"]` - `cited_text: str` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: int` minimum: 0 - `document_title: Optional[str]` minLength: 1, maxLength: 500 - `end_block_index: int` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: int` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `class BetaCitationWebSearchResultLocationParam` - `type: Literal["web_search_result_location"]` - `cited_text: str` - `encrypted_index: str` - `title: Optional[str]` minLength: 1, maxLength: 512 - `url: str` minLength: 1 - `class BetaCitationSearchResultLocationParam` - `type: Literal["search_result_location"]` - `cited_text: str` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: int` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: int` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: str` - `start_block_index: int` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: Optional[str]` - `class BetaImageBlockParam` - `type: Literal["image"]` - `source: Source` - `class BetaBase64ImageSource` - `type: Literal["base64"]` - `data: str` format: byte - `media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `class BetaURLImageSource` - `type: Literal["url"]` - `url: str` - `class BetaFileImageSource` - `type: Literal["file"]` - `file_id: str` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `transformations: Optional[BetaImageTransformationsParam]` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: Optional[Literal["downsize", "error"]]` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `class BetaRequestDocumentBlock` - `type: Literal["document"]` - `source: Source` - `class BetaBase64PDFSource` - `type: Literal["base64"]` - `data: str` format: byte - `media_type: Literal["application/pdf"]` - `class BetaPlainTextSource` - `type: Literal["text"]` - `data: str` - `media_type: Literal["text/plain"]` - `class BetaContentBlockSource` - `type: Literal["content"]` - `content: Union[str, List[BetaContentBlockSourceContent]]` - `str` - `List[BetaContentBlockSourceContent]` - `class BetaTextBlockParam` - `class BetaImageBlockParam` - `class BetaURLPDFSource` - `type: Literal["url"]` - `url: str` - `class BetaFileDocumentSource` - `type: Literal["file"]` - `file_id: str` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` - `enabled: Optional[bool]` - `context: Optional[str]` minLength: 1 - `title: Optional[str]` minLength: 1, maxLength: 500 - `class BetaSearchResultBlockParam` - `type: Literal["search_result"]` - `content: List[BetaTextBlockParam]` - `type: Literal["text"]` - `text: str` minLength: 1 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[List[BetaTextCitationParam]]` - `source: str` - `title: str` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` - `class BetaThinkingBlockParam` - `type: Literal["thinking"]` - `signature: str` The `signature` value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude. Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`. - `thinking: str` The `thinking` text of this block as returned by the API. - `class BetaRedactedThinkingBlockParam` - `type: Literal["redacted_thinking"]` - `data: str` The `data` value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged. - `class BetaToolUseBlockParam` - `type: Literal["tool_use"]` - `id: str` pattern: ^[a-zA-Z0-9_-]+$ - `input: Dict[str, object]` - `name: str` minLength: 1, maxLength: 200 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `type: Literal["direct"]` - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `type: Literal["code_execution_20250825"]` - `tool_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaServerToolCaller20260120` - `type: Literal["code_execution_20260120"]` - `tool_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: Optional[str]` For a toolset member tool_use, the toolset family this member belongs to. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `class BetaToolResultBlockParam` - `type: Literal["tool_result"]` - `tool_use_id: str` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `content: Optional[Union[str, List[Content], null]]` - `str` - `List[Content]` - `class BetaTextBlockParam` - `class BetaImageBlockParam` - `class BetaSearchResultBlockParam` - `class BetaRequestDocumentBlock` - `class BetaToolReferenceBlockParam` Tool reference block that can be included in tool_result content. - `type: Literal["tool_reference"]` - `tool_name: str` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaBrowserStateBlockParam` The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: Literal["browser_state"]` - `tabs: List[BetaBrowserStateTabEntry]` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: str` The caller-assigned identifier for this tab, unique within the inventory. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `title: str` The title of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: str` The URL of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `active: Optional[bool]` Whether this tab is the active tab after this call. Whenever `tabs` is non-empty, exactly one entry is marked `active: true`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `state_changes: Optional[List[BetaBrowserStateChange]]` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. minItems: 1, maxItems: 200 - `class BetaBrowserStateChangeTabOpened` A tab this call's execution opened that remains open at its end — the creation delta of the `tabs` inventory, not an event log. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: Literal["tab_opened"]` - `tab_id: str` The `tab_id` of the opened tab, present in `tabs`. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `class BetaBrowserStateChangeDownloadStarted` A file download that started during this call. - `type: Literal["download_started"]` - `download_id: str` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: str` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `class BetaBrowserStateChangeDownloadCompleted` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: Literal["download_completed"]` - `download_id: str` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: str` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: Optional[str]` Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `size_bytes: Optional[int]` The completed download's size. minimum: 0 - `class BetaBrowserStateChangeDownloadFailed` A file download that failed — or was cancelled — during this call. - `type: Literal["download_failed"]` - `download_id: str` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: str` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: Optional[str]` The failure or cancellation detail, when known. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `is_error: Optional[bool]` - `toolset_name: Optional[str]` For a toolset member tool_result, the toolset family of the paired tool_use. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `class BetaServerToolUseBlockParam` - `type: Literal["server_tool_use"]` - `id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: Dict[str, object]` - `name: Literal["advisor", "web_search", "web_fetch", 5 more]` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaWebSearchToolResultBlockParam` - `type: Literal["web_search_tool_result"]` - `content: BetaWebSearchToolResultBlockParamContent` - `List[BetaWebSearchResultBlockParam]` - `type: Literal["web_search_result"]` - `encrypted_content: str` - `title: str` - `url: str` - `page_age: Optional[str]` - `class BetaWebSearchToolRequestError` - `type: Literal["web_search_tool_result_error"]` - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaWebFetchToolResultBlockParam` - `type: Literal["web_fetch_tool_result"]` - `content: Content` - `class BetaWebFetchToolResultErrorBlockParam` - `type: Literal["web_fetch_tool_result_error"]` - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `class BetaWebFetchBlockParam` - `type: Literal["web_fetch_result"]` - `content: BetaRequestDocumentBlock` - `url: str` Fetched content URL - `retrieved_at: Optional[str]` ISO 8601 timestamp when the content was retrieved - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaAdvisorToolResultBlockParam` - `type: Literal["advisor_tool_result"]` - `content: Content` - `class BetaAdvisorToolResultErrorParam` - `type: Literal["advisor_tool_result_error"]` - `error_code: Literal["max_uses_exceeded", "prompt_too_long", "too_many_requests", 4 more]` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `class BetaAdvisorResultBlockParam` - `type: Literal["advisor_result"]` - `text: str` - `stop_reason: Optional[str]` - `class BetaAdvisorRedactedResultBlockParam` - `type: Literal["advisor_redacted_result"]` - `encrypted_content: str` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: Optional[str]` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaCodeExecutionToolResultBlockParam` - `type: Literal["code_execution_tool_result"]` - `content: BetaCodeExecutionToolResultBlockParamContent` - `class BetaCodeExecutionToolResultErrorParam` - `type: Literal["code_execution_tool_result_error"]` - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `class BetaCodeExecutionResultBlockParam` - `type: Literal["code_execution_result"]` - `content: List[BetaCodeExecutionOutputBlockParam]` - `type: Literal["code_execution_output"]` - `file_id: str` - `return_code: int` - `stderr: str` - `stdout: str` - `class BetaEncryptedCodeExecutionResultBlockParam` Code execution result with encrypted stdout for PFC + web_search results. - `type: Literal["encrypted_code_execution_result"]` - `content: List[BetaCodeExecutionOutputBlockParam]` - `type: Literal["code_execution_output"]` - `file_id: str` - `encrypted_stdout: str` - `return_code: int` - `stderr: str` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaBashCodeExecutionToolResultBlockParam` - `type: Literal["bash_code_execution_tool_result"]` - `content: Content` - `class BetaBashCodeExecutionToolResultErrorParam` - `type: Literal["bash_code_execution_tool_result_error"]` - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", 2 more]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `class BetaBashCodeExecutionResultBlockParam` - `type: Literal["bash_code_execution_result"]` - `content: List[BetaBashCodeExecutionOutputBlockParam]` - `type: Literal["bash_code_execution_output"]` - `file_id: str` - `return_code: int` - `stderr: str` - `stdout: str` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaTextEditorCodeExecutionToolResultBlockParam` - `type: Literal["text_editor_code_execution_tool_result"]` - `content: Content` - `class BetaTextEditorCodeExecutionToolResultErrorParam` - `type: Literal["text_editor_code_execution_tool_result_error"]` - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", 2 more]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: Optional[str]` - `class BetaTextEditorCodeExecutionViewResultBlockParam` - `type: Literal["text_editor_code_execution_view_result"]` - `content: str` - `file_type: Literal["text", "image", "pdf"]` - `"text"` - `"image"` - `"pdf"` - `num_lines: Optional[int]` - `start_line: Optional[int]` - `total_lines: Optional[int]` - `class BetaTextEditorCodeExecutionCreateResultBlockParam` - `type: Literal["text_editor_code_execution_create_result"]` - `is_file_update: bool` - `class BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - `type: Literal["text_editor_code_execution_str_replace_result"]` - `lines: Optional[List[str]]` - `new_lines: Optional[int]` - `new_start: Optional[int]` - `old_lines: Optional[int]` - `old_start: Optional[int]` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaToolSearchToolResultBlockParam` - `type: Literal["tool_search_tool_result"]` - `content: Content` - `class BetaToolSearchToolResultErrorParam` - `type: Literal["tool_search_tool_result_error"]` - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", "execution_time_exceeded"]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: Optional[str]` - `class BetaToolSearchToolSearchResultBlockParam` - `type: Literal["tool_search_tool_search_result"]` - `tool_references: List[BetaToolReferenceBlockParam]` - `type: Literal["tool_reference"]` - `tool_name: str` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaMCPToolUseBlockParam` - `type: Literal["mcp_tool_use"]` - `id: str` pattern: ^[a-zA-Z0-9_-]+$ - `input: Dict[str, object]` - `name: str` - `server_name: str` The name of the MCP server - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaRequestMCPToolResultBlockParam` - `type: Literal["mcp_tool_result"]` - `tool_use_id: str` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `content: Optional[Union[str, List[BetaTextBlockParam], null]]` - `str` - `List[BetaTextBlockParam]` - `type: Literal["text"]` - `text: str` minLength: 1 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[List[BetaTextCitationParam]]` - `is_error: Optional[bool]` - `class BetaContainerUploadBlockParam` A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory. - `type: Literal["container_upload"]` - `file_id: str` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaCompactionBlockParam` A compaction block containing summary of previous context. Users should round-trip these blocks from responses to subsequent requests to maintain context across compaction boundaries. When content is None, the block represents a failed compaction. The server treats these as no-ops. Empty string content is not allowed. - `type: Literal["compaction"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `content: Optional[str]` Summary of previously compacted content, or null if compaction failed - `encrypted_content: Optional[str]` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: Optional[str]` The block's signature as returned, to be sent back verbatim - `tool_changes: Optional[List[ToolChange]]` The tool changes of the compacted range, as the server returned them on this block: the `tool_addition` and `tool_removal` entries that take the request's `tools` to the tool set in effect at the end of the range. Send them back unchanged with the block. - `class BetaRequestToolAdditionBlock` Mid-conversation directive to make a tool available. `tool` is a reference to a tool (or MCP toolset) declared in the request's `tools`. Under the `inline-tools-2026-09-15` beta it may instead be a reference to a tool defined earlier in `messages`, or a `tool_definition` object that carries an inline tool definition in `definition` (the same object a `tools` entry holds). An `mcp_toolset` definition also requires the `mcp-client-2026-09-15` beta. The tool is offered to the model from this point in the conversation onward. - `type: Literal["tool_addition"]` - `tool: Tool` - `class BetaToolChangeToolReference` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `type: Literal["tool_reference"]` - `name: str` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `class BetaToolChangeMCPToolReference` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `type: Literal["mcp_tool_reference"]` - `name: str` - `server_name: str` - `class BetaToolChangeMCPToolsetReference` Reference to every tool in the named MCP server's toolset. - `type: Literal["mcp_toolset_reference"]` - `server_name: str` - `class BetaToolChangeToolDefinitionParam` A tool defined by value: `definition` is a `tools` entry (any kind `tools` accepts, an MCP toolset included). An `mcp_toolset` given here also requires the `mcp-client-2026-09-15` beta. - `type: Literal["tool_definition"]` - `definition: BetaToolUnion` - `class BetaTool` - `type: Optional[Literal["custom"]]` - `input_schema: InputSchema` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: Optional[str]` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: Optional[bool]` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolBash20241022` - `type: Literal["bash_20241022"]` - `name: Literal["bash"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolBash20250124` - `type: Literal["bash_20250124"]` - `name: Literal["bash"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20250522` - `type: Literal["code_execution_20250522"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20250825` - `type: Literal["code_execution_20250825"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20260120` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: Literal["code_execution_20260120"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20260521` Code execution tool with REPL state persistence. - `type: Literal["code_execution_20260521"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaBrowserToolset20260801` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: Literal["browser_toolset_20260801"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[BetaBrowserToolsetConfigs]` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: Optional[BetaBrowserTypeConfig]` `type`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: Optional[BetaBrowserCloseTabConfig]` `close_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: Optional[BetaBrowserDoubleClickConfig]` `double_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: Optional[BetaBrowserFileUploadConfig]` `file_upload`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: Optional[BetaBrowserFindConfig]` `find`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: Optional[BetaBrowserFormInputConfig]` `form_input`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: Optional[BetaBrowserGetPageTextConfig]` `get_page_text`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: Optional[BetaBrowserHoldKeyConfig]` `hold_key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: Optional[BetaBrowserHoverConfig]` `hover`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: Optional[BetaBrowserJavascriptExecConfig]` `javascript_exec`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: Optional[BetaBrowserKeyConfig]` `key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: Optional[BetaBrowserLeftClickConfig]` `left_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: Optional[BetaBrowserLeftClickDragConfig]` `left_click_drag`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: Optional[BetaBrowserLeftMouseDownConfig]` `left_mouse_down`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: Optional[BetaBrowserLeftMouseUpConfig]` `left_mouse_up`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: Optional[BetaBrowserListTabsConfig]` `list_tabs`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: Optional[BetaBrowserMiddleClickConfig]` `middle_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: Optional[BetaBrowserMouseMoveConfig]` `mouse_move`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: Optional[BetaBrowserNavigateConfig]` `navigate`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: Optional[BetaBrowserNewTabConfig]` `new_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: Optional[BetaBrowserReadConsoleConfig]` `read_console`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: Optional[BetaBrowserReadNetworkConfig]` `read_network`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: Optional[BetaBrowserReadPageConfig]` `read_page`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: Optional[BetaBrowserRightClickConfig]` `right_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: Optional[BetaBrowserScreenshotConfig]` `screenshot`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: Optional[BetaBrowserScrollConfig]` `scroll`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: Optional[BetaBrowserScrollToConfig]` `scroll_to`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: Optional[BetaBrowserSwitchTabConfig]` `switch_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: Optional[BetaBrowserTripleClickConfig]` `triple_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: Optional[BetaBrowserWaitConfig]` `wait`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: Optional[BetaBrowserZoomConfig]` `zoom`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `class BetaToolComputerUse20241022` - `type: Literal["computer_20241022"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaMemoryTool20250818` - `type: Literal["memory_20250818"]` - `name: Literal["memory"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolComputerUse20250124` - `type: Literal["computer_20250124"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20241022` - `type: Literal["text_editor_20241022"]` - `name: Literal["str_replace_editor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolComputerUse20251124` - `type: Literal["computer_20251124"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: Optional[bool]` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaComputerToolset20260801` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: Literal["computer_toolset_20260801"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[BetaComputerToolsetConfigs]` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: Optional[BetaComputerTypeConfig]` `type`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: Optional[BetaComputerCursorPositionConfig]` `cursor_position`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: Optional[BetaComputerDoubleClickConfig]` `double_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: Optional[BetaComputerHoldKeyConfig]` `hold_key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: Optional[BetaComputerKeyConfig]` `key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: Optional[BetaComputerLeftClickConfig]` `left_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: Optional[BetaComputerLeftClickDragConfig]` `left_click_drag`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: Optional[BetaComputerLeftMouseDownConfig]` `left_mouse_down`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: Optional[BetaComputerLeftMouseUpConfig]` `left_mouse_up`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: Optional[BetaComputerMiddleClickConfig]` `middle_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: Optional[BetaComputerMouseMoveConfig]` `mouse_move`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: Optional[BetaComputerRightClickConfig]` `right_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: Optional[BetaComputerScreenshotConfig]` `screenshot`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: Optional[BetaComputerScrollConfig]` `scroll`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: Optional[BetaComputerTripleClickConfig]` `triple_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: Optional[BetaComputerWaitConfig]` `wait`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: Optional[BetaComputerZoomConfig]` `zoom`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `class BetaToolTextEditor20250124` - `type: Literal["text_editor_20250124"]` - `name: Literal["str_replace_editor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20250429` - `type: Literal["text_editor_20250429"]` - `name: Literal["str_replace_based_edit_tool"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20250728` - `type: Literal["text_editor_20250728"]` - `name: Literal["str_replace_based_edit_tool"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `max_characters: Optional[int]` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaWebSearchTool20250305` - `type: Literal["web_search_20250305"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `type: Literal["approximate"]` - `city: Optional[str]` The city of the user. minLength: 1, maxLength: 255 - `country: Optional[str]` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: Optional[str]` The region of the user. minLength: 1, maxLength: 255 - `timezone: Optional[str]` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `class BetaWebFetchTool20250910` - `type: Literal["web_fetch_20250910"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: Optional[ClientToolResults]` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: Literal["all"]` - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: Literal["none"]` - `class BetaWebFetchURLSourceOnly` The tool filter variant under which only the named tools' results contribute. - `type: Literal["only"]` - `tools: List[BetaWebFetchURLSourceToolReference]` - `type: Literal["tool_reference"]` - `name: str` - `class BetaWebFetchURLSourceExcept` The tool filter variant under which every result but the named tools' contributes. - `type: Literal["except"]` - `tools: List[BetaWebFetchURLSourceToolReference]` - `type: Literal["tool_reference"]` - `name: str` - `server_tool_results: Optional[ServerToolResults]` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `class BetaWebFetchURLSourceOnly` The tool filter variant under which only the named tools' results contribute. - `class BetaWebFetchURLSourceExcept` The tool filter variant under which every result but the named tools' contributes. - `user_input: Optional[UserInput]` Whether URLs in user messages are fetchable: "all" or "none". - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `class BetaWebSearchTool20260209` - `type: Literal["web_search_20260209"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `class BetaWebFetchTool20260209` - `type: Literal["web_fetch_20260209"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `class BetaWebFetchTool20260309` Web fetch tool with use_cache parameter for bypassing cached content. - `type: Literal["web_fetch_20260309"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `use_cache: Optional[bool]` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `class BetaWebSearchTool20260318` - `type: Literal["web_search_20260318"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: Optional[Literal["full", "excluded"]]` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `class BetaWebFetchTool20260318` - `type: Literal["web_fetch_20260318"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: Optional[Literal["full", "excluded"]]` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `use_cache: Optional[bool]` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `class BetaAdvisorTool20260301` - `type: Literal["advisor_20260301"]` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `name: Literal["advisor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caching: Optional[BetaCacheControlEphemeral]` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: Optional[int]` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolSearchToolBm25_20251119` - `type: Literal["tool_search_tool_bm25_20251119", "tool_search_tool_bm25"]` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: Literal["tool_search_tool_bm25"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolSearchToolRegex20251119` - `type: Literal["tool_search_tool_regex_20251119", "tool_search_tool_regex"]` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: Literal["tool_search_tool_regex"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaMCPToolset` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: Literal["mcp_toolset"]` - `mcp_server_name: str` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[Dict[str, BetaMCPToolConfig]]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: Optional[bool]` - `enabled: Optional[bool]` - `default_config: Optional[BetaMCPToolDefaultConfig]` Default configuration applied to all tools from this server - `defer_loading: Optional[bool]` - `enabled: Optional[bool]` - `tools: Optional[List[BetaMCPToolParam]]` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: Dict[str, object]` The tool's input schema as the MCP server lists it, verbatim. - `name: str` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: Optional[str]` The tool's description as the MCP server lists it. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaRequestToolRemovalBlock` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name: one declared in the request's `tools` or defined earlier in `messages`. It is no longer offered to the model from this point in the conversation onward. - `type: Literal["tool_removal"]` - `tool: Tool` - `class BetaToolChangeToolReference` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `class BetaToolChangeMCPToolReference` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `class BetaToolChangeMCPToolsetReference` Reference to every tool in the named MCP server's toolset. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaRequestToolAdditionBlock` Mid-conversation directive to make a tool available. `tool` is a reference to a tool (or MCP toolset) declared in the request's `tools`. Under the `inline-tools-2026-09-15` beta it may instead be a reference to a tool defined earlier in `messages`, or a `tool_definition` object that carries an inline tool definition in `definition` (the same object a `tools` entry holds). An `mcp_toolset` definition also requires the `mcp-client-2026-09-15` beta. The tool is offered to the model from this point in the conversation onward. - `class BetaRequestToolRemovalBlock` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name: one declared in the request's `tools` or defined earlier in `messages`. It is no longer offered to the model from this point in the conversation onward. - `class BetaMCPToolListingBlockParam` The tool listing an MCP server returned while an earlier response was produced, as that response carried it. Send the assistant message back unchanged, this block included, and the server uses this listing for the matching `mcp_toolset` instead of asking the MCP server again. - `type: Literal["mcp_tool_listing"]` - `mcp_server_name: str` The name of the MCP server this listing came from, as `mcp_servers` declares it. minLength: 1, maxLength: 255 - `tools: List[BetaMCPToolParam]` The server's tools, exactly as the response listed them. - `input_schema: Dict[str, object]` The tool's input schema as the MCP server lists it, verbatim. - `name: str` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: Optional[str]` The tool's description as the MCP server lists it. - `class BetaFallbackBlockParam` A `fallback` block echoed back from a prior response. Accepted in `messages[].content` and not rendered into the prompt; not validated against the request's `fallbacks` chain or top-level `model`. Echo the assistant turn back verbatim, including this block in its original position. The block marks the boundary between content produced before and after a fallback hop, and the server relies on that boundary to validate the turn: when thinking runs flank the boundary, omitting the block merges them into one span the server cannot validate (the request is rejected), and moving it into the middle of a single run is likewise rejected; between non-thinking blocks the block's placement has no validation effect. - `type: Literal["fallback"]` - `from_: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `to: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `trigger: Optional[object]` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed. - `role: Literal["user", "assistant", "system"]` - `"user"` - `"assistant"` - `"system"` - `clear_at: Optional[Literal["next_user_message", "never"]]` How long this system message's text stays in front of the model. `"never"` (the default) renders it on every request that includes it. `"next_user_message"` renders it only for the user turn it follows: once a later `role: "user"` message exists in `messages` the message stays in the array (send it unchanged) but is no longer shown to the model. Only permitted on `role: "system"` messages. - `"next_user_message"` - `"never"` - `output_config: Optional[BetaSystemMessageOutputConfig]` Per-message output configuration on a role:"system" input message. Fields here apply per-turn; `format` remains top-level only. An empty `{}` is accepted on a message that carries content; a message with neither content nor output_config fields is rejected. - `effort: Optional[Literal["low", "medium", "high", 2 more]]` How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `model: ModelParam` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `cache_control: Optional[BetaCacheControlEphemeralParam]` Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. - `compaction: Optional[BetaCompactionConfigParam]` Compaction configuration. When set on `POST /v1/messages`, the request is a compaction request: the conversation in `messages` is summarized and the response holds only the resulting `compaction` block (`stop_reason` `"compaction"`), which later requests send first in `messages` in place of the messages it summarizes. `POST /v1/messages/count_tokens` accepts this parameter and ignores it: the count it returns is for the conversation in `messages` as sent. Cannot be combined with `context_management`. - `type: Literal["summarize"]` - `instructions: Optional[str]` Replaces the server's default summarization prompt for this request. An empty or whitespace-only value counts as absent. maxLength: 16384 - `context_management: Optional[BetaContextManagementConfigParam]` Context management configuration. This allows you to control how Claude manages context across multiple requests, such as whether to clear function results or not. - `edits: Optional[List[Edit]]` List of context management edits to apply - `class BetaClearToolUses20250919Edit` - `type: Literal["clear_tool_uses_20250919"]` - `clear_at_least: Optional[BetaInputTokensClearAtLeast]` Minimum number of tokens that must be cleared when triggered. Context will only be modified if at least this many tokens can be removed. - `type: Literal["input_tokens"]` - `value: int` minimum: 0 - `clear_tool_inputs: Optional[Union[bool, List[str], null]]` Whether to clear all tool inputs (bool) or specific tool inputs to clear (list) - `bool` - `List[str]` - `exclude_tools: Optional[List[str]]` Tool names whose uses are preserved from clearing - `keep: Optional[BetaToolUsesKeep]` Number of tool uses to retain in the conversation - `type: Literal["tool_uses"]` - `value: int` minimum: 0 - `trigger: Optional[Trigger]` Condition that triggers the context management strategy - `class BetaInputTokensTrigger` - `type: Literal["input_tokens"]` - `value: int` minimum: 1 - `class BetaToolUsesTrigger` - `type: Literal["tool_uses"]` - `value: int` minimum: 1 - `class BetaClearThinking20251015Edit` - `type: Literal["clear_thinking_20251015"]` - `keep: Optional[Keep]` Number of most recent assistant turns to keep thinking blocks for. Older turns will have their thinking blocks removed. - `class BetaThinkingTurns` - `type: Literal["thinking_turns"]` - `value: int` minimum: 1 - `class BetaAllThinkingTurns` - `type: Literal["all"]` - `"all"` - `class BetaCompact20260112Edit` Automatically compact older context when reaching the configured trigger threshold. - `type: Literal["compact_20260112"]` - `instructions: Optional[str]` Additional instructions for summarization. - `pause_after_compaction: Optional[bool]` Whether to pause after compaction and return the compaction block to the user. - `trigger: Optional[BetaInputTokensTrigger]` When to trigger compaction. Defaults to 150000 input tokens. - `mcp_servers: Optional[Iterable[BetaRequestMCPServerURLDefinitionParam]]` MCP servers to be utilized in this request maxItems: 20 - `type: Literal["url"]` - `name: str` - `url: str` - `authorization_token: Optional[str]` - `tool_configuration: Optional[BetaRequestMCPServerToolConfiguration]` - `allowed_tools: Optional[List[str]]` - `enabled: Optional[bool]` - `output_config: Optional[BetaOutputConfigParam]` Configuration options for the model's output, such as the output format. - `effort: Optional[Literal["low", "medium", "high", 2 more]]` How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `format: Optional[BetaJSONOutputFormat]` A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs?sdk_languages=python) - `type: Literal["json_schema"]` - `schema: Dict[str, object]` The JSON schema of the format - `task_budget: Optional[BetaTokenTaskBudget]` Configuration for token budget tracking across contexts. - `type: Literal["tokens"]` The budget type. Currently only 'tokens' is supported. - `total: int` Total token budget across all contexts in the session. minimum: 1024 - `remaining: Optional[int]` Remaining tokens in the budget. Use this to track usage across contexts when implementing compaction client-side. Defaults to total if not provided. minimum: 0 - `speed: Optional[Literal["standard", "fast"]]` The inference speed mode for this request. `"fast"` enables high output-tokens-per-second inference. - `"standard"` - `"fast"` - `system: Optional[Union[str, Iterable[BetaTextBlockParam]]]` System prompt. A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices?sdk_languages=python#give-claude-a-role). - `str` - `Iterable[BetaTextBlockParam]` - `type: Literal["text"]` - `text: str` minLength: 1 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[List[BetaTextCitationParam]]` - `thinking: Optional[BetaThinkingConfigParam]` Configuration for Claude's thinking. With `{"type": "adaptive"}`, Claude decides when and how much to think. With `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of at least 1,024. Thinking tokens count toward your `max_tokens` limit. Which `type` values are accepted, and what happens when you omit `thinking`, depend on the model. See [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=python#configuring-thinking) for each model's behavior. - `class BetaThinkingConfigEnabled` - `type: Literal["enabled"]` - `budget_tokens: int` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=python) for details. minimum: 1024 - `block_binding: Optional[BetaThinkingBlockBinding]` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `prefix_mismatch_behavior: Optional[BetaThinkingPrefixMismatchBehavior]` "error" (default) | "drop_block". What happens when a thinking block in `messages` fails the conversation check (it was created in a different conversation, or the messages before it have changed since). "error" fails the request with a 400 error. "drop_block" removes the failing blocks and the request proceeds; each removal is reported in `input_transformations`. - `"error"` - `"drop_block"` - `display: Optional[Literal["summarized", "omitted", "updates"]]` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=python#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` - `class BetaThinkingConfigDisabled` - `type: Literal["disabled"]` - `class BetaThinkingConfigBetweenTools` - `type: Literal["between_tools"]` - `class BetaThinkingConfigAdaptive` - `type: Literal["adaptive"]` - `block_binding: Optional[BetaThinkingBlockBinding]` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `display: Optional[Literal["summarized", "omitted", "updates"]]` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=python#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` - `tool_choice: Optional[BetaToolChoiceParam]` How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all. - `class BetaToolChoiceAuto` The model will automatically decide whether to use tools. - `type: Literal["auto"]` - `disable_parallel_tool_use: Optional[bool]` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. - `class BetaToolChoiceAny` The model will use any available tools. - `type: Literal["any"]` - `disable_parallel_tool_use: Optional[bool]` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - `class BetaToolChoiceTool` The model will use the specified tool with `tool_choice.name`. - `type: Literal["tool"]` - `name: str` The name of the tool to use. - `disable_parallel_tool_use: Optional[bool]` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - `class BetaToolChoiceNone` The model will not be allowed to use tools. - `type: Literal["none"]` - `tools: Optional[Iterable[Tool]]` Definitions of tools that the model may use. If you include `tools` in your API request, the model may return `tool_use` content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using `tool_result` content blocks. There are two types of tools: **client tools** and **server tools**. The behavior described below applies to client tools. For [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools?sdk_languages=python), see their individual documentation as each has its own behavior (e.g., the [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool?sdk_languages=python)). Each tool definition includes: * `name`: Name of the tool. * `description`: Optional, but strongly-recommended description of the tool. * `input_schema`: [JSON schema](https://json-schema.org/draft/2020-12) for the tool `input` shape that the model will produce in `tool_use` output content blocks. For example, if you defined `tools` as: ```json [ { "name": "get_stock_price", "description": "Get the current stock price for a given ticker symbol.", "input_schema": { "type": "object", "properties": { "ticker": { "type": "string", "description": "The stock ticker symbol, e.g. AAPL for Apple Inc." } }, "required": ["ticker"] } } ] ``` And then asked the model "What's the S&P 500 at today?", the model might produce `tool_use` content blocks in the response like this: ```json [ { "type": "tool_use", "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "name": "get_stock_price", "input": { "ticker": "^GSPC" } } ] ``` You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an input, and return the following back to the model in a subsequent `user` message: ```json [ { "type": "tool_result", "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "content": "259.75 USD" } ] ``` Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output. See our [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview?sdk_languages=python) for more details. - `class BetaTool` - `class BetaToolBash20241022` - `class BetaToolBash20250124` - `class BetaCodeExecutionTool20250522` - `class BetaCodeExecutionTool20250825` - `class BetaCodeExecutionTool20260120` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `class BetaCodeExecutionTool20260521` Code execution tool with REPL state persistence. - `class BetaBrowserToolset20260801` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `class BetaToolComputerUse20241022` - `class BetaMemoryTool20250818` - `class BetaToolComputerUse20250124` - `class BetaToolTextEditor20241022` - `class BetaToolComputerUse20251124` - `class BetaComputerToolset20260801` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `class BetaToolTextEditor20250124` - `class BetaToolTextEditor20250429` - `class BetaToolTextEditor20250728` - `class BetaWebSearchTool20250305` - `class BetaWebFetchTool20250910` - `class BetaWebSearchTool20260209` - `class BetaWebFetchTool20260209` - `class BetaWebFetchTool20260309` Web fetch tool with use_cache parameter for bypassing cached content. - `class BetaWebSearchTool20260318` - `class BetaWebFetchTool20260318` - `class BetaAdvisorTool20260301` - `class BetaToolSearchToolBm25_20251119` - `class BetaToolSearchToolRegex20251119` - `class BetaMCPToolset` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `user_profile_id: Optional[str]` (header parameter) The user profile ID to attribute this request to. Use when acting on behalf of a party other than your organization. Requires the `user-profiles` beta header. - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaMessageTokensCount` - `context_management: Optional[BetaCountTokensContextManagementResponse]` Information about context management applied to the message. - `original_input_tokens: int` The original token count before context management was applied - `input_tokens: int` The total number of tokens across the provided list of messages, system prompt, and tools. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_message_tokens_count = client.beta.messages.count_tokens( messages=[ { "content": "Hello, world", "role": "user", } ], model="claude-opus-5", ) print(beta_message_tokens_count.context_management) ``` ##### Response (200) ```json { "context_management": { "original_input_tokens": 0 }, "input_tokens": 2095 } ``` ## Beta › Messages › Batches ### Create a Message Batch `beta.messages.batches.create(**kwargs) -> BetaMessageBatch` **POST** `/v1/messages/batches` Send a batch of Message creation requests. The Message Batches API can be used to process multiple Messages API requests at once. Once a Message Batch is created, it begins processing immediately. Batches can take up to 24 hours to complete. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=python) #### Parameters - `requests: Iterable[Request]` List of requests for prompt completion. Each is an individual request to create a Message. minItems: 1, maxItems: 100000 - `custom_id: str` Developer-provided ID created for each request in a Message Batch. Useful for matching results to requests, as results may be given out of request order. Must be unique for each request within the Message Batch. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]{1,64}$ - `params: RequestParams` Messages API creation parameters for the individual request. See the [Messages API reference](https://platform.claude.com/docs/en/api/messages?sdk_languages=python) for full documentation on available parameters. - `max_tokens: int` The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. Set to `0` to populate the [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=python#pre-warming-the-cache) without generating a response. Different models have different maximum values for this parameter. See [models](https://platform.claude.com/docs/en/about-claude/models/overview?sdk_languages=python) for details. minimum: 0 - `messages: Iterable[BetaMessageParam]` Input messages. Our models are trained to operate on alternating `user` and `assistant` conversational turns. When creating a new `Message`, you specify the prior conversational turns with the `messages` parameter, and the model then generates the next `Message` in the conversation. Consecutive `user` or `assistant` turns in your request will be combined into a single turn. Each input message must be an object with a `role` and `content`. You can specify a single `user`-role message, or you can include multiple `user` and `assistant` messages. If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response. This is called prefill. On models that don't support prefill, creating a message that ends with a partial `assistant` response returns a 400 error. See [Prefill not supported](https://platform.claude.com/docs/en/api/errors?sdk_languages=python#prefill-not-supported). Example with a single `user` message: ```json [{"role": "user", "content": "Hello, Claude"}] ``` Example with multiple conversational turns: ```json [ {"role": "user", "content": "Hello there."}, {"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"}, {"role": "user", "content": "Can you explain LLMs in plain English?"}, ] ``` Example with a partially-filled response from Claude, for models that support prefill: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("}, ] ``` Each input message `content` may be either a single `string` or an array of content blocks, where each block has a specific `type`. Using a `string` for `content` is shorthand for an array of one content block of type `"text"`. The following input messages are equivalent: ```json {"role": "user", "content": "Hello, Claude"} ``` ```json {"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]} ``` See [input examples](https://platform.claude.com/docs/en/build-with-claude/working-with-messages?sdk_languages=python). Note that if you want to include a [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices?sdk_languages=python#give-claude-a-role), you can use the top-level `system` parameter — there is no `"system"` role for input messages in the Messages API. There is a limit of 100,000 messages in a single request. - `content: Union[str, List[BetaContentBlockParam]]` - `str` - `List[BetaContentBlockParam]` - `class BetaTextBlockParam` - `type: Literal["text"]` - `text: str` minLength: 1 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `type: Literal["ephemeral"]` - `ttl: Optional[Literal["5m", "1h"]]` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=python) for details. - `"5m"` - `"1h"` - `citations: Optional[List[BetaTextCitationParam]]` - `class BetaCitationCharLocationParam` - `type: Literal["char_location"]` - `cited_text: str` - `document_index: int` minimum: 0 - `document_title: Optional[str]` minLength: 1, maxLength: 500 - `end_char_index: int` - `start_char_index: int` minimum: 0 - `class BetaCitationPageLocationParam` - `type: Literal["page_location"]` - `cited_text: str` - `document_index: int` minimum: 0 - `document_title: Optional[str]` minLength: 1, maxLength: 500 - `end_page_number: int` - `start_page_number: int` minimum: 1 - `class BetaCitationContentBlockLocationParam` - `type: Literal["content_block_location"]` - `cited_text: str` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: int` minimum: 0 - `document_title: Optional[str]` minLength: 1, maxLength: 500 - `end_block_index: int` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: int` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `class BetaCitationWebSearchResultLocationParam` - `type: Literal["web_search_result_location"]` - `cited_text: str` - `encrypted_index: str` - `title: Optional[str]` minLength: 1, maxLength: 512 - `url: str` minLength: 1 - `class BetaCitationSearchResultLocationParam` - `type: Literal["search_result_location"]` - `cited_text: str` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: int` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: int` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: str` - `start_block_index: int` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: Optional[str]` - `class BetaImageBlockParam` - `type: Literal["image"]` - `source: Source` - `class BetaBase64ImageSource` - `type: Literal["base64"]` - `data: str` format: byte - `media_type: Literal["image/jpeg", "image/png", "image/gif", "image/webp"]` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `class BetaURLImageSource` - `type: Literal["url"]` - `url: str` - `class BetaFileImageSource` - `type: Literal["file"]` - `file_id: str` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `transformations: Optional[BetaImageTransformationsParam]` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: Optional[Literal["downsize", "error"]]` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `class BetaRequestDocumentBlock` - `type: Literal["document"]` - `source: Source` - `class BetaBase64PDFSource` - `type: Literal["base64"]` - `data: str` format: byte - `media_type: Literal["application/pdf"]` - `class BetaPlainTextSource` - `type: Literal["text"]` - `data: str` - `media_type: Literal["text/plain"]` - `class BetaContentBlockSource` - `type: Literal["content"]` - `content: Union[str, List[BetaContentBlockSourceContent]]` - `str` - `List[BetaContentBlockSourceContent]` - `class BetaTextBlockParam` - `class BetaImageBlockParam` - `class BetaURLPDFSource` - `type: Literal["url"]` - `url: str` - `class BetaFileDocumentSource` - `type: Literal["file"]` - `file_id: str` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` - `enabled: Optional[bool]` - `context: Optional[str]` minLength: 1 - `title: Optional[str]` minLength: 1, maxLength: 500 - `class BetaSearchResultBlockParam` - `type: Literal["search_result"]` - `content: List[BetaTextBlockParam]` - `type: Literal["text"]` - `text: str` minLength: 1 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[List[BetaTextCitationParam]]` - `source: str` - `title: str` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` - `class BetaThinkingBlockParam` - `type: Literal["thinking"]` - `signature: str` The `signature` value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude. Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`. - `thinking: str` The `thinking` text of this block as returned by the API. - `class BetaRedactedThinkingBlockParam` - `type: Literal["redacted_thinking"]` - `data: str` The `data` value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged. - `class BetaToolUseBlockParam` - `type: Literal["tool_use"]` - `id: str` pattern: ^[a-zA-Z0-9_-]+$ - `input: Dict[str, object]` - `name: str` minLength: 1, maxLength: 200 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `type: Literal["direct"]` - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `type: Literal["code_execution_20250825"]` - `tool_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaServerToolCaller20260120` - `type: Literal["code_execution_20260120"]` - `tool_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: Optional[str]` For a toolset member tool_use, the toolset family this member belongs to. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `class BetaToolResultBlockParam` - `type: Literal["tool_result"]` - `tool_use_id: str` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `content: Optional[Union[str, List[Content], null]]` - `str` - `List[Content]` - `class BetaTextBlockParam` - `class BetaImageBlockParam` - `class BetaSearchResultBlockParam` - `class BetaRequestDocumentBlock` - `class BetaToolReferenceBlockParam` Tool reference block that can be included in tool_result content. - `type: Literal["tool_reference"]` - `tool_name: str` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaBrowserStateBlockParam` The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: Literal["browser_state"]` - `tabs: List[BetaBrowserStateTabEntry]` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: str` The caller-assigned identifier for this tab, unique within the inventory. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `title: str` The title of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: str` The URL of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `active: Optional[bool]` Whether this tab is the active tab after this call. Whenever `tabs` is non-empty, exactly one entry is marked `active: true`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `state_changes: Optional[List[BetaBrowserStateChange]]` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. minItems: 1, maxItems: 200 - `class BetaBrowserStateChangeTabOpened` A tab this call's execution opened that remains open at its end — the creation delta of the `tabs` inventory, not an event log. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: Literal["tab_opened"]` - `tab_id: str` The `tab_id` of the opened tab, present in `tabs`. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `class BetaBrowserStateChangeDownloadStarted` A file download that started during this call. - `type: Literal["download_started"]` - `download_id: str` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: str` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `class BetaBrowserStateChangeDownloadCompleted` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: Literal["download_completed"]` - `download_id: str` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: str` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: Optional[str]` Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `size_bytes: Optional[int]` The completed download's size. minimum: 0 - `class BetaBrowserStateChangeDownloadFailed` A file download that failed — or was cancelled — during this call. - `type: Literal["download_failed"]` - `download_id: str` The caller-assigned identifier for this download, stable across the state changes reporting it. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: str` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: Optional[str]` The failure or cancellation detail, when known. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `is_error: Optional[bool]` - `toolset_name: Optional[str]` For a toolset member tool_result, the toolset family of the paired tool_use. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `class BetaServerToolUseBlockParam` - `type: Literal["server_tool_use"]` - `id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: Dict[str, object]` - `name: Literal["advisor", "web_search", "web_fetch", 5 more]` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaWebSearchToolResultBlockParam` - `type: Literal["web_search_tool_result"]` - `content: BetaWebSearchToolResultBlockParamContent` - `List[BetaWebSearchResultBlockParam]` - `type: Literal["web_search_result"]` - `encrypted_content: str` - `title: str` - `url: str` - `page_age: Optional[str]` - `class BetaWebSearchToolRequestError` - `type: Literal["web_search_tool_result_error"]` - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaWebFetchToolResultBlockParam` - `type: Literal["web_fetch_tool_result"]` - `content: Content` - `class BetaWebFetchToolResultErrorBlockParam` - `type: Literal["web_fetch_tool_result_error"]` - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `class BetaWebFetchBlockParam` - `type: Literal["web_fetch_result"]` - `content: BetaRequestDocumentBlock` - `url: str` Fetched content URL - `retrieved_at: Optional[str]` ISO 8601 timestamp when the content was retrieved - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaAdvisorToolResultBlockParam` - `type: Literal["advisor_tool_result"]` - `content: Content` - `class BetaAdvisorToolResultErrorParam` - `type: Literal["advisor_tool_result_error"]` - `error_code: Literal["max_uses_exceeded", "prompt_too_long", "too_many_requests", 4 more]` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `class BetaAdvisorResultBlockParam` - `type: Literal["advisor_result"]` - `text: str` - `stop_reason: Optional[str]` - `class BetaAdvisorRedactedResultBlockParam` - `type: Literal["advisor_redacted_result"]` - `encrypted_content: str` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: Optional[str]` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaCodeExecutionToolResultBlockParam` - `type: Literal["code_execution_tool_result"]` - `content: BetaCodeExecutionToolResultBlockParamContent` - `class BetaCodeExecutionToolResultErrorParam` - `type: Literal["code_execution_tool_result_error"]` - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `class BetaCodeExecutionResultBlockParam` - `type: Literal["code_execution_result"]` - `content: List[BetaCodeExecutionOutputBlockParam]` - `type: Literal["code_execution_output"]` - `file_id: str` - `return_code: int` - `stderr: str` - `stdout: str` - `class BetaEncryptedCodeExecutionResultBlockParam` Code execution result with encrypted stdout for PFC + web_search results. - `type: Literal["encrypted_code_execution_result"]` - `content: List[BetaCodeExecutionOutputBlockParam]` - `type: Literal["code_execution_output"]` - `file_id: str` - `encrypted_stdout: str` - `return_code: int` - `stderr: str` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaBashCodeExecutionToolResultBlockParam` - `type: Literal["bash_code_execution_tool_result"]` - `content: Content` - `class BetaBashCodeExecutionToolResultErrorParam` - `type: Literal["bash_code_execution_tool_result_error"]` - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", 2 more]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `class BetaBashCodeExecutionResultBlockParam` - `type: Literal["bash_code_execution_result"]` - `content: List[BetaBashCodeExecutionOutputBlockParam]` - `type: Literal["bash_code_execution_output"]` - `file_id: str` - `return_code: int` - `stderr: str` - `stdout: str` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaTextEditorCodeExecutionToolResultBlockParam` - `type: Literal["text_editor_code_execution_tool_result"]` - `content: Content` - `class BetaTextEditorCodeExecutionToolResultErrorParam` - `type: Literal["text_editor_code_execution_tool_result_error"]` - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", 2 more]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: Optional[str]` - `class BetaTextEditorCodeExecutionViewResultBlockParam` - `type: Literal["text_editor_code_execution_view_result"]` - `content: str` - `file_type: Literal["text", "image", "pdf"]` - `"text"` - `"image"` - `"pdf"` - `num_lines: Optional[int]` - `start_line: Optional[int]` - `total_lines: Optional[int]` - `class BetaTextEditorCodeExecutionCreateResultBlockParam` - `type: Literal["text_editor_code_execution_create_result"]` - `is_file_update: bool` - `class BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - `type: Literal["text_editor_code_execution_str_replace_result"]` - `lines: Optional[List[str]]` - `new_lines: Optional[int]` - `new_start: Optional[int]` - `old_lines: Optional[int]` - `old_start: Optional[int]` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaToolSearchToolResultBlockParam` - `type: Literal["tool_search_tool_result"]` - `content: Content` - `class BetaToolSearchToolResultErrorParam` - `type: Literal["tool_search_tool_result_error"]` - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", "execution_time_exceeded"]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: Optional[str]` - `class BetaToolSearchToolSearchResultBlockParam` - `type: Literal["tool_search_tool_search_result"]` - `tool_references: List[BetaToolReferenceBlockParam]` - `type: Literal["tool_reference"]` - `tool_name: str` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaMCPToolUseBlockParam` - `type: Literal["mcp_tool_use"]` - `id: str` pattern: ^[a-zA-Z0-9_-]+$ - `input: Dict[str, object]` - `name: str` - `server_name: str` The name of the MCP server - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaRequestMCPToolResultBlockParam` - `type: Literal["mcp_tool_result"]` - `tool_use_id: str` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `content: Optional[Union[str, List[BetaTextBlockParam], null]]` - `str` - `List[BetaTextBlockParam]` - `type: Literal["text"]` - `text: str` minLength: 1 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[List[BetaTextCitationParam]]` - `is_error: Optional[bool]` - `class BetaContainerUploadBlockParam` A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory. - `type: Literal["container_upload"]` - `file_id: str` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaCompactionBlockParam` A compaction block containing summary of previous context. Users should round-trip these blocks from responses to subsequent requests to maintain context across compaction boundaries. When content is None, the block represents a failed compaction. The server treats these as no-ops. Empty string content is not allowed. - `type: Literal["compaction"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `content: Optional[str]` Summary of previously compacted content, or null if compaction failed - `encrypted_content: Optional[str]` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: Optional[str]` The block's signature as returned, to be sent back verbatim - `tool_changes: Optional[List[ToolChange]]` The tool changes of the compacted range, as the server returned them on this block: the `tool_addition` and `tool_removal` entries that take the request's `tools` to the tool set in effect at the end of the range. Send them back unchanged with the block. - `class BetaRequestToolAdditionBlock` Mid-conversation directive to make a tool available. `tool` is a reference to a tool (or MCP toolset) declared in the request's `tools`. Under the `inline-tools-2026-09-15` beta it may instead be a reference to a tool defined earlier in `messages`, or a `tool_definition` object that carries an inline tool definition in `definition` (the same object a `tools` entry holds). An `mcp_toolset` definition also requires the `mcp-client-2026-09-15` beta. The tool is offered to the model from this point in the conversation onward. - `type: Literal["tool_addition"]` - `tool: Tool` - `class BetaToolChangeToolReference` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `type: Literal["tool_reference"]` - `name: str` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `class BetaToolChangeMCPToolReference` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `type: Literal["mcp_tool_reference"]` - `name: str` - `server_name: str` - `class BetaToolChangeMCPToolsetReference` Reference to every tool in the named MCP server's toolset. - `type: Literal["mcp_toolset_reference"]` - `server_name: str` - `class BetaToolChangeToolDefinitionParam` A tool defined by value: `definition` is a `tools` entry (any kind `tools` accepts, an MCP toolset included). An `mcp_toolset` given here also requires the `mcp-client-2026-09-15` beta. - `type: Literal["tool_definition"]` - `definition: BetaToolUnion` - `class BetaTool` - `type: Optional[Literal["custom"]]` - `input_schema: InputSchema` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: Optional[str]` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: Optional[bool]` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolBash20241022` - `type: Literal["bash_20241022"]` - `name: Literal["bash"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolBash20250124` - `type: Literal["bash_20250124"]` - `name: Literal["bash"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20250522` - `type: Literal["code_execution_20250522"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20250825` - `type: Literal["code_execution_20250825"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20260120` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: Literal["code_execution_20260120"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20260521` Code execution tool with REPL state persistence. - `type: Literal["code_execution_20260521"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaBrowserToolset20260801` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: Literal["browser_toolset_20260801"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[BetaBrowserToolsetConfigs]` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: Optional[BetaBrowserTypeConfig]` `type`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: Optional[BetaBrowserCloseTabConfig]` `close_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: Optional[BetaBrowserDoubleClickConfig]` `double_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: Optional[BetaBrowserFileUploadConfig]` `file_upload`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: Optional[BetaBrowserFindConfig]` `find`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: Optional[BetaBrowserFormInputConfig]` `form_input`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: Optional[BetaBrowserGetPageTextConfig]` `get_page_text`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: Optional[BetaBrowserHoldKeyConfig]` `hold_key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: Optional[BetaBrowserHoverConfig]` `hover`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: Optional[BetaBrowserJavascriptExecConfig]` `javascript_exec`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: Optional[BetaBrowserKeyConfig]` `key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: Optional[BetaBrowserLeftClickConfig]` `left_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: Optional[BetaBrowserLeftClickDragConfig]` `left_click_drag`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: Optional[BetaBrowserLeftMouseDownConfig]` `left_mouse_down`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: Optional[BetaBrowserLeftMouseUpConfig]` `left_mouse_up`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: Optional[BetaBrowserListTabsConfig]` `list_tabs`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: Optional[BetaBrowserMiddleClickConfig]` `middle_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: Optional[BetaBrowserMouseMoveConfig]` `mouse_move`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: Optional[BetaBrowserNavigateConfig]` `navigate`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: Optional[BetaBrowserNewTabConfig]` `new_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: Optional[BetaBrowserReadConsoleConfig]` `read_console`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: Optional[BetaBrowserReadNetworkConfig]` `read_network`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: Optional[BetaBrowserReadPageConfig]` `read_page`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: Optional[BetaBrowserRightClickConfig]` `right_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: Optional[BetaBrowserScreenshotConfig]` `screenshot`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: Optional[BetaBrowserScrollConfig]` `scroll`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: Optional[BetaBrowserScrollToConfig]` `scroll_to`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: Optional[BetaBrowserSwitchTabConfig]` `switch_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: Optional[BetaBrowserTripleClickConfig]` `triple_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: Optional[BetaBrowserWaitConfig]` `wait`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: Optional[BetaBrowserZoomConfig]` `zoom`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `class BetaToolComputerUse20241022` - `type: Literal["computer_20241022"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaMemoryTool20250818` - `type: Literal["memory_20250818"]` - `name: Literal["memory"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolComputerUse20250124` - `type: Literal["computer_20250124"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20241022` - `type: Literal["text_editor_20241022"]` - `name: Literal["str_replace_editor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolComputerUse20251124` - `type: Literal["computer_20251124"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: Optional[bool]` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaComputerToolset20260801` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: Literal["computer_toolset_20260801"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[BetaComputerToolsetConfigs]` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: Optional[BetaComputerTypeConfig]` `type`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: Optional[BetaComputerCursorPositionConfig]` `cursor_position`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: Optional[BetaComputerDoubleClickConfig]` `double_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: Optional[BetaComputerHoldKeyConfig]` `hold_key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: Optional[BetaComputerKeyConfig]` `key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: Optional[BetaComputerLeftClickConfig]` `left_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: Optional[BetaComputerLeftClickDragConfig]` `left_click_drag`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: Optional[BetaComputerLeftMouseDownConfig]` `left_mouse_down`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: Optional[BetaComputerLeftMouseUpConfig]` `left_mouse_up`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: Optional[BetaComputerMiddleClickConfig]` `middle_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: Optional[BetaComputerMouseMoveConfig]` `mouse_move`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: Optional[BetaComputerRightClickConfig]` `right_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: Optional[BetaComputerScreenshotConfig]` `screenshot`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: Optional[BetaComputerScrollConfig]` `scroll`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: Optional[BetaComputerTripleClickConfig]` `triple_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: Optional[BetaComputerWaitConfig]` `wait`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: Optional[BetaComputerZoomConfig]` `zoom`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `class BetaToolTextEditor20250124` - `type: Literal["text_editor_20250124"]` - `name: Literal["str_replace_editor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20250429` - `type: Literal["text_editor_20250429"]` - `name: Literal["str_replace_based_edit_tool"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20250728` - `type: Literal["text_editor_20250728"]` - `name: Literal["str_replace_based_edit_tool"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `max_characters: Optional[int]` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaWebSearchTool20250305` - `type: Literal["web_search_20250305"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `type: Literal["approximate"]` - `city: Optional[str]` The city of the user. minLength: 1, maxLength: 255 - `country: Optional[str]` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: Optional[str]` The region of the user. minLength: 1, maxLength: 255 - `timezone: Optional[str]` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `class BetaWebFetchTool20250910` - `type: Literal["web_fetch_20250910"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: Optional[ClientToolResults]` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: Literal["all"]` - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: Literal["none"]` - `class BetaWebFetchURLSourceOnly` The tool filter variant under which only the named tools' results contribute. - `type: Literal["only"]` - `tools: List[BetaWebFetchURLSourceToolReference]` - `type: Literal["tool_reference"]` - `name: str` - `class BetaWebFetchURLSourceExcept` The tool filter variant under which every result but the named tools' contributes. - `type: Literal["except"]` - `tools: List[BetaWebFetchURLSourceToolReference]` - `type: Literal["tool_reference"]` - `name: str` - `server_tool_results: Optional[ServerToolResults]` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `class BetaWebFetchURLSourceOnly` The tool filter variant under which only the named tools' results contribute. - `class BetaWebFetchURLSourceExcept` The tool filter variant under which every result but the named tools' contributes. - `user_input: Optional[UserInput]` Whether URLs in user messages are fetchable: "all" or "none". - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `class BetaWebSearchTool20260209` - `type: Literal["web_search_20260209"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `class BetaWebFetchTool20260209` - `type: Literal["web_fetch_20260209"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `class BetaWebFetchTool20260309` Web fetch tool with use_cache parameter for bypassing cached content. - `type: Literal["web_fetch_20260309"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `use_cache: Optional[bool]` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `class BetaWebSearchTool20260318` - `type: Literal["web_search_20260318"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: Optional[Literal["full", "excluded"]]` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `class BetaWebFetchTool20260318` - `type: Literal["web_fetch_20260318"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: Optional[Literal["full", "excluded"]]` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `use_cache: Optional[bool]` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `class BetaAdvisorTool20260301` - `type: Literal["advisor_20260301"]` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `name: Literal["advisor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caching: Optional[BetaCacheControlEphemeral]` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: Optional[int]` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolSearchToolBm25_20251119` - `type: Literal["tool_search_tool_bm25_20251119", "tool_search_tool_bm25"]` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: Literal["tool_search_tool_bm25"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolSearchToolRegex20251119` - `type: Literal["tool_search_tool_regex_20251119", "tool_search_tool_regex"]` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: Literal["tool_search_tool_regex"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaMCPToolset` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: Literal["mcp_toolset"]` - `mcp_server_name: str` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[Dict[str, BetaMCPToolConfig]]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: Optional[bool]` - `enabled: Optional[bool]` - `default_config: Optional[BetaMCPToolDefaultConfig]` Default configuration applied to all tools from this server - `defer_loading: Optional[bool]` - `enabled: Optional[bool]` - `tools: Optional[List[BetaMCPToolParam]]` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: Dict[str, object]` The tool's input schema as the MCP server lists it, verbatim. - `name: str` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: Optional[str]` The tool's description as the MCP server lists it. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaRequestToolRemovalBlock` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name: one declared in the request's `tools` or defined earlier in `messages`. It is no longer offered to the model from this point in the conversation onward. - `type: Literal["tool_removal"]` - `tool: Tool` - `class BetaToolChangeToolReference` Reference to a single tool, by the name the model uses to call it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools; use `mcp_tool_reference` or `mcp_toolset_reference` for those. - `class BetaToolChangeMCPToolReference` Reference to a single MCP tool by its server and remote name; the same `server_name`/`name` pair `mcp_tool_use` carries. - `class BetaToolChangeMCPToolsetReference` Reference to every tool in the named MCP server's toolset. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `class BetaRequestToolAdditionBlock` Mid-conversation directive to make a tool available. `tool` is a reference to a tool (or MCP toolset) declared in the request's `tools`. Under the `inline-tools-2026-09-15` beta it may instead be a reference to a tool defined earlier in `messages`, or a `tool_definition` object that carries an inline tool definition in `definition` (the same object a `tools` entry holds). An `mcp_toolset` definition also requires the `mcp-client-2026-09-15` beta. The tool is offered to the model from this point in the conversation onward. - `class BetaRequestToolRemovalBlock` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name: one declared in the request's `tools` or defined earlier in `messages`. It is no longer offered to the model from this point in the conversation onward. - `class BetaMCPToolListingBlockParam` The tool listing an MCP server returned while an earlier response was produced, as that response carried it. Send the assistant message back unchanged, this block included, and the server uses this listing for the matching `mcp_toolset` instead of asking the MCP server again. - `type: Literal["mcp_tool_listing"]` - `mcp_server_name: str` The name of the MCP server this listing came from, as `mcp_servers` declares it. minLength: 1, maxLength: 255 - `tools: List[BetaMCPToolParam]` The server's tools, exactly as the response listed them. - `input_schema: Dict[str, object]` The tool's input schema as the MCP server lists it, verbatim. - `name: str` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: Optional[str]` The tool's description as the MCP server lists it. - `class BetaFallbackBlockParam` A `fallback` block echoed back from a prior response. Accepted in `messages[].content` and not rendered into the prompt; not validated against the request's `fallbacks` chain or top-level `model`. Echo the assistant turn back verbatim, including this block in its original position. The block marks the boundary between content produced before and after a fallback hop, and the server relies on that boundary to validate the turn: when thinking runs flank the boundary, omitting the block merges them into one span the server cannot validate (the request is rejected), and moving it into the middle of a single run is likewise rejected; between non-thinking blocks the block's placement has no validation effect. - `type: Literal["fallback"]` - `from_: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `to: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `trigger: Optional[object]` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed. - `role: Literal["user", "assistant", "system"]` - `"user"` - `"assistant"` - `"system"` - `clear_at: Optional[Literal["next_user_message", "never"]]` How long this system message's text stays in front of the model. `"never"` (the default) renders it on every request that includes it. `"next_user_message"` renders it only for the user turn it follows: once a later `role: "user"` message exists in `messages` the message stays in the array (send it unchanged) but is no longer shown to the model. Only permitted on `role: "system"` messages. - `"next_user_message"` - `"never"` - `output_config: Optional[BetaSystemMessageOutputConfig]` Per-message output configuration on a role:"system" input message. Fields here apply per-turn; `format` remains top-level only. An empty `{}` is accepted on a message that carries content; a message with neither content nor output_config fields is rejected. - `effort: Optional[Literal["low", "medium", "high", 2 more]]` How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `model: ModelParam` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `cache_control: Optional[BetaCacheControlEphemeralParam]` Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. - `compaction: Optional[BetaCompactionConfigParam]` Compaction configuration. When set on `POST /v1/messages`, the request is a compaction request: the conversation in `messages` is summarized and the response holds only the resulting `compaction` block (`stop_reason` `"compaction"`), which later requests send first in `messages` in place of the messages it summarizes. `POST /v1/messages/count_tokens` accepts this parameter and ignores it: the count it returns is for the conversation in `messages` as sent. Cannot be combined with `context_management`. - `type: Literal["summarize"]` - `instructions: Optional[str]` Replaces the server's default summarization prompt for this request. An empty or whitespace-only value counts as absent. maxLength: 16384 - `container: Optional[RequestParamsContainer]` Container identifier for reuse across requests. - `class BetaContainerParams` Container parameters with skills to be loaded. - `id: Optional[str]` Container id - `skills: Optional[List[BetaSkillParams]]` List of skills to load in the container maxItems: 20 - `type: Literal["anthropic", "custom"]` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: str` Skill ID minLength: 1, maxLength: 64 - `version: Optional[str]` Skill version or 'latest' for most recent version minLength: 1, maxLength: 64 - `str` - `context_management: Optional[BetaContextManagementConfigParam]` Context management configuration. This allows you to control how Claude manages context across multiple requests, such as whether to clear function results or not. - `edits: Optional[List[Edit]]` List of context management edits to apply - `class BetaClearToolUses20250919Edit` - `type: Literal["clear_tool_uses_20250919"]` - `clear_at_least: Optional[BetaInputTokensClearAtLeast]` Minimum number of tokens that must be cleared when triggered. Context will only be modified if at least this many tokens can be removed. - `type: Literal["input_tokens"]` - `value: int` minimum: 0 - `clear_tool_inputs: Optional[Union[bool, List[str], null]]` Whether to clear all tool inputs (bool) or specific tool inputs to clear (list) - `bool` - `List[str]` - `exclude_tools: Optional[List[str]]` Tool names whose uses are preserved from clearing - `keep: Optional[BetaToolUsesKeep]` Number of tool uses to retain in the conversation - `type: Literal["tool_uses"]` - `value: int` minimum: 0 - `trigger: Optional[Trigger]` Condition that triggers the context management strategy - `class BetaInputTokensTrigger` - `type: Literal["input_tokens"]` - `value: int` minimum: 1 - `class BetaToolUsesTrigger` - `type: Literal["tool_uses"]` - `value: int` minimum: 1 - `class BetaClearThinking20251015Edit` - `type: Literal["clear_thinking_20251015"]` - `keep: Optional[Keep]` Number of most recent assistant turns to keep thinking blocks for. Older turns will have their thinking blocks removed. - `class BetaThinkingTurns` - `type: Literal["thinking_turns"]` - `value: int` minimum: 1 - `class BetaAllThinkingTurns` - `type: Literal["all"]` - `"all"` - `class BetaCompact20260112Edit` Automatically compact older context when reaching the configured trigger threshold. - `type: Literal["compact_20260112"]` - `instructions: Optional[str]` Additional instructions for summarization. - `pause_after_compaction: Optional[bool]` Whether to pause after compaction and return the compaction block to the user. - `trigger: Optional[BetaInputTokensTrigger]` When to trigger compaction. Defaults to 150000 input tokens. - `diagnostics: Optional[BetaDiagnosticsParam]` Request-level diagnostics. Supply `previous_message_id` to have the response include `diagnostics.cache_miss_reason` explaining any prompt-cache divergence from that prior request. - `previous_message_id: Optional[str]` The `id` (`msg_...`) from this client's previous /v1/messages response. The server compares that request's prompt fingerprint against this one and returns `diagnostics.cache_miss_reason` when the prompt-cache prefix could not be reused. Pass `null` on the first turn to opt in without a prior message to compare. maxLength: 256 - `fallback_credit_token: Optional[RequestParamsFallbackCreditToken]` The `fallback_credit_token` from a prior refusal's `stop_details`. When a preceding request was refused and returned a `fallback_credit_token`, pass that code here on the retry to have the retry's cache-creation tokens for the prefix that was warm on the refused model billed at the cache-read rate. Must be redeemed by the same organization and workspace, with the same request body (optionally extended by one appended `assistant` message whose content is the partial text — with any trailing whitespace stripped from the final text block — and paired server-tool blocks streamed before the refusal; the appended-assistant form is not available for requests with `output_format` set or forced `tool_choice`), on an eligible fallback model, on the same platform, and within 5 minutes of the refusal; a mismatch is a 400. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed with the appended-assistant form — if an exact-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry with the appended-assistant form instead. When the appended-assistant form is used on a model that otherwise disallows assistant-turn prefill, this token also authorizes that one prefill. - `str` - `class BetaFallbackCreditTokenParam` Object form of `fallback_credit_token`: the token plus a redemption mode. Requires `anthropic-beta: fallback-credit-2026-07-01`; without that header the field accepts the bare string only. The bare string and the mode-less object are equivalent (both select `strict`), so wrapping an existing token changes nothing by itself. - `token: str` The opaque `fallback_credit_token` from a prior refusal's `stop_details` — the same string the bare-string form carries. minLength: 1, maxLength: 2048 - `mode: Optional[Literal["strict", "best_effort"]]` How a failing token affects the retry. `strict` (the default, and the bare-string behavior): a failing redemption is a 400 and the retry is not served. `best_effort`: the retry is served either way — a token-layer failure no longer rejects the request; the retry proceeds at normal price and the outcome is reported on the response's `usage.fallback_credit`. Two failures stay hard in both modes: a malformed token, and combining `fallback_credit_token` with `fallbacks`. - `"strict"` - `"best_effort"` - `fallbacks: Optional[BetaFallbacksParam]` Opt-in server-side retry on one or more substitute models when the requested model declines for policy reasons. Tried in order: if the first entry also declines, the second is tried, and so on. Some models don't support fallbacks; on those models, a list of fallback models returns a 400 error. See [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback?sdk_languages=python#server-side-fallback). The string "default" requests the requested model's server-defined default fallback configuration. On a model that doesn't support fallbacks, the request runs on the requested model alone, so a declined request stays declined. - `List[BetaFallbackParam]` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `max_tokens: Optional[int]` - `output_config: Optional[BetaOutputConfig]` - `effort: Optional[Literal["low", "medium", "high", 2 more]]` How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer. Valid values are `low`, `medium`, `high`, `xhigh`, or `max`. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `format: Optional[BetaJSONOutputFormat]` A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs?sdk_languages=python) - `type: Literal["json_schema"]` - `schema: Dict[str, object]` The JSON schema of the format - `task_budget: Optional[BetaTokenTaskBudget]` Configuration for token budget tracking across contexts. - `type: Literal["tokens"]` The budget type. Currently only 'tokens' is supported. - `total: int` Total token budget across all contexts in the session. minimum: 1024 - `remaining: Optional[int]` Remaining tokens in the budget. Use this to track usage across contexts when implementing compaction client-side. Defaults to total if not provided. minimum: 0 - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `thinking: Optional[Thinking]` - `class BetaThinkingConfigEnabled` - `type: Literal["enabled"]` - `budget_tokens: int` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=python) for details. minimum: 1024 - `block_binding: Optional[BetaThinkingBlockBinding]` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `prefix_mismatch_behavior: Optional[BetaThinkingPrefixMismatchBehavior]` "error" (default) | "drop_block". What happens when a thinking block in `messages` fails the conversation check (it was created in a different conversation, or the messages before it have changed since). "error" fails the request with a 400 error. "drop_block" removes the failing blocks and the request proceeds; each removal is reported in `input_transformations`. - `"error"` - `"drop_block"` - `display: Optional[Literal["summarized", "omitted", "updates"]]` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=python#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` - `class BetaThinkingConfigDisabled` - `type: Literal["disabled"]` - `class BetaThinkingConfigBetweenTools` - `type: Literal["between_tools"]` - `class BetaThinkingConfigAdaptive` - `type: Literal["adaptive"]` - `block_binding: Optional[BetaThinkingBlockBinding]` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. `null`, absent or an empty object means every default. - `display: Optional[Literal["summarized", "omitted", "updates"]]` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=python#controlling-thinking-display). - `"summarized"` - `"omitted"` - `"updates"` - `"default"` - `inference_geo: Optional[str]` Specifies the geographic region for inference processing. If not specified, the workspace's `default_inference_geo` is used. - `mcp_servers: Optional[Iterable[BetaRequestMCPServerURLDefinitionParam]]` MCP servers to be utilized in this request maxItems: 20 - `type: Literal["url"]` - `name: str` - `url: str` - `authorization_token: Optional[str]` - `tool_configuration: Optional[BetaRequestMCPServerToolConfiguration]` - `allowed_tools: Optional[List[str]]` - `enabled: Optional[bool]` - `metadata: Optional[BetaMetadataParam]` An object describing metadata about the request. - `user_id: Optional[str]` An external identifier for the user who is associated with the request. This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number. maxLength: 512 - `output_config: Optional[BetaOutputConfigParam]` Configuration options for the model's output, such as the output format. - `service_tier: Optional[Literal["auto", "standard_only"]]` Determines whether to use priority capacity (if available) or standard capacity for this request. Anthropic offers different levels of service for your API requests. See [service-tiers](https://platform.claude.com/docs/en/api/service-tiers?sdk_languages=python) for details. - `"auto"` - `"standard_only"` - `speed: Optional[Literal["standard", "fast"]]` The inference speed mode for this request. `"fast"` enables high output-tokens-per-second inference. - `"standard"` - `"fast"` - `stop_sequences: Optional[Sequence[str]]` Custom text sequences that will cause the model to stop generating. Our models will normally stop when they have naturally completed their turn, which will result in a response `stop_reason` of `"end_turn"`. If you want the model to stop generating when it encounters custom strings of text, you can use the `stop_sequences` parameter. If the model encounters one of the custom sequences, the response `stop_reason` value will be `"stop_sequence"` and the response `stop_sequence` value will contain the matched stop sequence. - `stream: Optional[bool]` Whether to incrementally stream the response using server-sent events. When `true`, SDKs return a raw event stream. In the TypeScript, Python and Ruby SDKs, the recommended way to stream is `messages.stream()`. It sets `stream` for you and accumulates the events into the final message. See [Streaming with SDKs](https://platform.claude.com/docs/en/build-with-claude/streaming?sdk_languages=python#streaming-with-sdks) for an example in each language. - `system: Optional[Union[str, Iterable[BetaTextBlockParam]]]` System prompt. A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices?sdk_languages=python#give-claude-a-role). - `str` - `Iterable[BetaTextBlockParam]` - `type: Literal["text"]` - `text: str` minLength: 1 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[List[BetaTextCitationParam]]` - `thinking: Optional[BetaThinkingConfigParam]` Configuration for Claude's thinking. With `{"type": "adaptive"}`, Claude decides when and how much to think. With `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of at least 1,024. Thinking tokens count toward your `max_tokens` limit. Which `type` values are accepted, and what happens when you omit `thinking`, depend on the model. See [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking?sdk_languages=python#configuring-thinking) for each model's behavior. - `class BetaThinkingConfigEnabled` - `class BetaThinkingConfigDisabled` - `class BetaThinkingConfigBetweenTools` - `class BetaThinkingConfigAdaptive` - `tool_choice: Optional[BetaToolChoiceParam]` How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all. - `class BetaToolChoiceAuto` The model will automatically decide whether to use tools. - `type: Literal["auto"]` - `disable_parallel_tool_use: Optional[bool]` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. - `class BetaToolChoiceAny` The model will use any available tools. - `type: Literal["any"]` - `disable_parallel_tool_use: Optional[bool]` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - `class BetaToolChoiceTool` The model will use the specified tool with `tool_choice.name`. - `type: Literal["tool"]` - `name: str` The name of the tool to use. - `disable_parallel_tool_use: Optional[bool]` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - `class BetaToolChoiceNone` The model will not be allowed to use tools. - `type: Literal["none"]` - `tools: Optional[Iterable[BetaToolUnionParam]]` Definitions of tools that the model may use. If you include `tools` in your API request, the model may return `tool_use` content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using `tool_result` content blocks. There are two types of tools: **client tools** and **server tools**. The behavior described below applies to client tools. For [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools?sdk_languages=python), see their individual documentation as each has its own behavior (e.g., the [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool?sdk_languages=python)). Each tool definition includes: * `name`: Name of the tool. * `description`: Optional, but strongly-recommended description of the tool. * `input_schema`: [JSON schema](https://json-schema.org/draft/2020-12) for the tool `input` shape that the model will produce in `tool_use` output content blocks. For example, if you defined `tools` as: ```json [ { "name": "get_stock_price", "description": "Get the current stock price for a given ticker symbol.", "input_schema": { "type": "object", "properties": { "ticker": { "type": "string", "description": "The stock ticker symbol, e.g. AAPL for Apple Inc." } }, "required": ["ticker"] } } ] ``` And then asked the model "What's the S&P 500 at today?", the model might produce `tool_use` content blocks in the response like this: ```json [ { "type": "tool_use", "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "name": "get_stock_price", "input": { "ticker": "^GSPC" } } ] ``` You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an input, and return the following back to the model in a subsequent `user` message: ```json [ { "type": "tool_result", "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "content": "259.75 USD" } ] ``` Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output. See our [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview?sdk_languages=python) for more details. - `class BetaTool` - `class BetaToolBash20241022` - `class BetaToolBash20250124` - `class BetaCodeExecutionTool20250522` - `class BetaCodeExecutionTool20250825` - `class BetaCodeExecutionTool20260120` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `class BetaCodeExecutionTool20260521` Code execution tool with REPL state persistence. - `class BetaBrowserToolset20260801` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `class BetaToolComputerUse20241022` - `class BetaMemoryTool20250818` - `class BetaToolComputerUse20250124` - `class BetaToolTextEditor20241022` - `class BetaToolComputerUse20251124` - `class BetaComputerToolset20260801` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `class BetaToolTextEditor20250124` - `class BetaToolTextEditor20250429` - `class BetaToolTextEditor20250728` - `class BetaWebSearchTool20250305` - `class BetaWebFetchTool20250910` - `class BetaWebSearchTool20260209` - `class BetaWebFetchTool20260209` - `class BetaWebFetchTool20260309` Web fetch tool with use_cache parameter for bypassing cached content. - `class BetaWebSearchTool20260318` - `class BetaWebFetchTool20260318` - `class BetaAdvisorTool20260301` - `class BetaToolSearchToolBm25_20251119` - `class BetaToolSearchToolRegex20251119` - `class BetaMCPToolset` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `user_profile_id: Optional[str]` (header parameter) The user profile ID to attribute the requests in this batch to. Use when acting on behalf of a party other than your organization. Requires the `user-profiles` beta header. Applies to every request in the batch; an individual request whose `user_profile_id` body field conflicts with this header is errored. - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaMessageBatch` - `type: Literal["message_batch"]` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `id: str` Unique object identifier. The format and length of IDs may change over time. - `archived_at: Optional[datetime]` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `cancel_initiated_at: Optional[datetime]` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `created_at: datetime` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `ended_at: Optional[datetime]` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `expires_at: datetime` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `processing_status: Literal["in_progress", "canceling", "ended"]` Processing status of the Message Batch. - `"in_progress"` - `"canceling"` - `"ended"` - `request_counts: BetaMessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `canceled: int` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `errored: int` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `expired: int` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `processing: int` Number of requests in the Message Batch that are processing. default: 0 - `succeeded: int` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `results_url: Optional[str]` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_message_batch = client.beta.messages.batches.create( requests=[ { "custom_id": "my-custom-id-1", "params": { "max_tokens": 1024, "messages": [ { "content": "Hello, world", "role": "user", } ], "model": "claude-opus-5", }, } ], ) print(beta_message_batch.id) ``` ##### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ``` ### Retrieve a Message Batch `beta.messages.batches.retrieve(message_batch_id, **kwargs) -> BetaMessageBatch` **GET** `/v1/messages/batches/{message_batch_id}` This endpoint is idempotent and can be used to poll for Message Batch completion. To access the results of a Message Batch, make a request to the `results_url` field in the response. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=python) #### Parameters - `message_batch_id: str` (path parameter) ID of the Message Batch. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaMessageBatch` - `type: Literal["message_batch"]` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `id: str` Unique object identifier. The format and length of IDs may change over time. - `archived_at: Optional[datetime]` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `cancel_initiated_at: Optional[datetime]` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `created_at: datetime` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `ended_at: Optional[datetime]` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `expires_at: datetime` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `processing_status: Literal["in_progress", "canceling", "ended"]` Processing status of the Message Batch. - `"in_progress"` - `"canceling"` - `"ended"` - `request_counts: BetaMessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `canceled: int` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `errored: int` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `expired: int` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `processing: int` Number of requests in the Message Batch that are processing. default: 0 - `succeeded: int` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `results_url: Optional[str]` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_message_batch = client.beta.messages.batches.retrieve( message_batch_id="message_batch_id", ) print(beta_message_batch.id) ``` ##### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ``` ### List Message Batches `beta.messages.batches.list(**kwargs) -> SyncPage[BetaMessageBatch]` **GET** `/v1/messages/batches` List all Message Batches within a Workspace. Most recently created batches are returned first. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=python) #### Parameters - `after_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately after this object. - `before_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately before this object. - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaMessageBatch` - `type: Literal["message_batch"]` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `id: str` Unique object identifier. The format and length of IDs may change over time. - `archived_at: Optional[datetime]` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `cancel_initiated_at: Optional[datetime]` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `created_at: datetime` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `ended_at: Optional[datetime]` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `expires_at: datetime` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `processing_status: Literal["in_progress", "canceling", "ended"]` Processing status of the Message Batch. - `"in_progress"` - `"canceling"` - `"ended"` - `request_counts: BetaMessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `canceled: int` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `errored: int` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `expired: int` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `processing: int` Number of requests in the Message Batch that are processing. default: 0 - `succeeded: int` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `results_url: Optional[str]` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.messages.batches.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ], "first_id": "first_id", "has_more": true, "last_id": "last_id" } ``` ### Cancel a Message Batch `beta.messages.batches.cancel(message_batch_id, **kwargs) -> BetaMessageBatch` **POST** `/v1/messages/batches/{message_batch_id}/cancel` Batches may be canceled any time before processing ends. Once cancellation is initiated, the batch enters a `canceling` state, at which time the system may complete any in-progress, non-interruptible requests before finalizing cancellation. The number of canceled requests is specified in `request_counts`. To determine which requests were canceled, check the individual results within the batch. Note that cancellation may not result in any canceled requests if they were non-interruptible. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=python) #### Parameters - `message_batch_id: str` (path parameter) ID of the Message Batch. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaMessageBatch` - `type: Literal["message_batch"]` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `id: str` Unique object identifier. The format and length of IDs may change over time. - `archived_at: Optional[datetime]` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `cancel_initiated_at: Optional[datetime]` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `created_at: datetime` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `ended_at: Optional[datetime]` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `expires_at: datetime` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `processing_status: Literal["in_progress", "canceling", "ended"]` Processing status of the Message Batch. - `"in_progress"` - `"canceling"` - `"ended"` - `request_counts: BetaMessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `canceled: int` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `errored: int` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `expired: int` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `processing: int` Number of requests in the Message Batch that are processing. default: 0 - `succeeded: int` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `results_url: Optional[str]` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_message_batch = client.beta.messages.batches.cancel( message_batch_id="message_batch_id", ) print(beta_message_batch.id) ``` ##### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ``` ### Delete a Message Batch `beta.messages.batches.delete(message_batch_id, **kwargs) -> BetaDeletedMessageBatch` **DELETE** `/v1/messages/batches/{message_batch_id}` Delete a Message Batch. Message Batches can only be deleted once they've finished processing. If you'd like to delete an in-progress batch, you must first cancel it. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=python) #### Parameters - `message_batch_id: str` (path parameter) ID of the Message Batch. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaDeletedMessageBatch` - `type: Literal["message_batch_deleted"]` Deleted object type. For Message Batches, this is always `"message_batch_deleted"`. default: message_batch_deleted - `id: str` ID of the Message Batch. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_deleted_message_batch = client.beta.messages.batches.delete( message_batch_id="message_batch_id", ) print(beta_deleted_message_batch.id) ``` ##### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "type": "message_batch_deleted" } ``` ### Retrieve Message Batch results `beta.messages.batches.results(message_batch_id, **kwargs) -> BetaMessageBatchIndividualResponse` **GET** `/v1/messages/batches/{message_batch_id}/results` Streams the results of a Message Batch as a `.jsonl` file. Each line in the file is a JSON object containing the result of a single request in the Message Batch. Results are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=python) #### Parameters - `message_batch_id: str` (path parameter) ID of the Message Batch. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaMessageBatchIndividualResponse` This is a single line in the response `.jsonl` file and does not represent the response as a whole. - `custom_id: str` Developer-provided ID created for each request in a Message Batch. Useful for matching results to requests, as results may be given out of request order. Must be unique for each request within the Message Batch. - `result: BetaMessageBatchResult` Processing result for this request. Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration. - `class BetaMessageBatchSucceededResult` - `type: Literal["succeeded"]` default: succeeded - `message: BetaMessage` - `type: Literal["message"]` Object type. For Messages, this is always `"message"`. default: message - `id: str` Unique object identifier. The format and length of IDs may change over time. - `container: Optional[BetaContainer]` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `id: str` Identifier for the container used in this request - `expires_at: datetime` The time at which the container will expire. format: date-time - `skills: Optional[List[BetaContainerSkill]]` Skills loaded in the container - `type: Literal["anthropic", "custom"]` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: str` Skill ID minLength: 1, maxLength: 64 - `version: str` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `content: List[BetaContentBlock]` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `class BetaTextBlock` - `type: Literal["text"]` default: text - `citations: Optional[List[BetaTextCitation]]` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `class BetaCitationCharLocation` - `type: Literal["char_location"]` default: char_location - `cited_text: str` - `document_index: int` minimum: 0 - `document_title: Optional[str]` - `end_char_index: int` - `file_id: Optional[str]` - `start_char_index: int` minimum: 0 - `class BetaCitationPageLocation` - `type: Literal["page_location"]` default: page_location - `cited_text: str` - `document_index: int` minimum: 0 - `document_title: Optional[str]` - `end_page_number: int` - `file_id: Optional[str]` - `start_page_number: int` minimum: 1 - `class BetaCitationContentBlockLocation` - `type: Literal["content_block_location"]` default: content_block_location - `cited_text: str` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: int` minimum: 0 - `document_title: Optional[str]` - `end_block_index: int` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: Optional[str]` - `start_block_index: int` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `class BetaCitationsWebSearchResultLocation` - `type: Literal["web_search_result_location"]` default: web_search_result_location - `cited_text: str` - `encrypted_index: str` - `title: Optional[str]` maxLength: 512 - `url: str` - `class BetaCitationSearchResultLocation` - `type: Literal["search_result_location"]` default: search_result_location - `cited_text: str` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: int` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: int` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: str` - `start_block_index: int` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: Optional[str]` - `text: str` - `class BetaThinkingBlock` - `type: Literal["thinking"]` default: thinking - `signature: str` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=python) for details. - `thinking: str` The text of Claude's thinking process for this block. - `class BetaRedactedThinkingBlock` - `type: Literal["redacted_thinking"]` default: redacted_thinking - `data: str` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking?sdk_languages=python#redacted-thinking-blocks) for details. - `class BetaToolUseBlock` - `type: Literal["tool_use"]` default: tool_use - `id: str` pattern: ^[a-zA-Z0-9_-]+$ - `input: Dict[str, object]` - `name: str` minLength: 1 - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `type: Literal["direct"]` - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `type: Literal["code_execution_20250825"]` - `tool_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaServerToolCaller20260120` - `type: Literal["code_execution_20260120"]` - `tool_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: Optional[str]` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `class BetaServerToolUseBlock` - `type: Literal["server_tool_use"]` default: server_tool_use - `id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: Dict[str, object]` - `name: Literal["advisor", "web_search", "web_fetch", 5 more]` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaWebSearchToolResultBlock` - `type: Literal["web_search_tool_result"]` default: web_search_tool_result - `content: BetaWebSearchToolResultBlockContent` - `class BetaWebSearchToolResultError` - `type: Literal["web_search_tool_result_error"]` default: web_search_tool_result_error - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `List[BetaWebSearchResultBlock]` - `type: Literal["web_search_result"]` default: web_search_result - `encrypted_content: str` - `page_age: Optional[str]` - `title: str` - `url: str` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaWebFetchToolResultBlock` - `type: Literal["web_fetch_tool_result"]` default: web_fetch_tool_result - `content: Content` - `class BetaWebFetchToolResultErrorBlock` - `type: Literal["web_fetch_tool_result_error"]` default: web_fetch_tool_result_error - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `class BetaWebFetchBlock` - `type: Literal["web_fetch_result"]` default: web_fetch_result - `content: BetaDocumentBlock` - `type: Literal["document"]` default: document - `citations: Optional[BetaCitationConfig]` Citation configuration for the document - `enabled: bool` default: false - `source: Source` - `class BetaBase64PDFSource` - `type: Literal["base64"]` - `data: str` format: byte - `media_type: Literal["application/pdf"]` - `class BetaPlainTextSource` - `type: Literal["text"]` - `data: str` - `media_type: Literal["text/plain"]` - `title: Optional[str]` The title of the document - `retrieved_at: Optional[str]` ISO 8601 timestamp when the content was retrieved - `url: str` Fetched content URL - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: Optional[Caller]` - `class BetaDirectCaller` Tool invocation directly from the model. - `class BetaServerToolCaller` Tool invocation generated by a server-side tool. - `class BetaServerToolCaller20260120` - `class BetaAdvisorToolResultBlock` - `type: Literal["advisor_tool_result"]` default: advisor_tool_result - `content: Content` - `class BetaAdvisorToolResultError` - `type: Literal["advisor_tool_result_error"]` default: advisor_tool_result_error - `error_code: Literal["max_uses_exceeded", "prompt_too_long", "too_many_requests", 4 more]` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `class BetaAdvisorResultBlock` - `type: Literal["advisor_result"]` default: advisor_result - `stop_reason: Optional[str]` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: str` - `class BetaAdvisorRedactedResultBlock` - `type: Literal["advisor_redacted_result"]` default: advisor_redacted_result - `encrypted_content: str` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: Optional[str]` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaCodeExecutionToolResultBlock` - `type: Literal["code_execution_tool_result"]` default: code_execution_tool_result - `content: BetaCodeExecutionToolResultBlockContent` - `class BetaCodeExecutionToolResultError` - `type: Literal["code_execution_tool_result_error"]` default: code_execution_tool_result_error - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `class BetaCodeExecutionResultBlock` - `type: Literal["code_execution_result"]` default: code_execution_result - `content: List[BetaCodeExecutionOutputBlock]` - `type: Literal["code_execution_output"]` default: code_execution_output - `file_id: str` - `return_code: int` - `stderr: str` - `stdout: str` - `class BetaEncryptedCodeExecutionResultBlock` Code execution result with encrypted stdout for PFC + web_search results. - `type: Literal["encrypted_code_execution_result"]` default: encrypted_code_execution_result - `content: List[BetaCodeExecutionOutputBlock]` - `type: Literal["code_execution_output"]` default: code_execution_output - `file_id: str` - `encrypted_stdout: str` - `return_code: int` - `stderr: str` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaBashCodeExecutionToolResultBlock` - `type: Literal["bash_code_execution_tool_result"]` default: bash_code_execution_tool_result - `content: Content` - `class BetaBashCodeExecutionToolResultError` - `type: Literal["bash_code_execution_tool_result_error"]` default: bash_code_execution_tool_result_error - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", 2 more]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `class BetaBashCodeExecutionResultBlock` - `type: Literal["bash_code_execution_result"]` default: bash_code_execution_result - `content: List[BetaBashCodeExecutionOutputBlock]` - `type: Literal["bash_code_execution_output"]` default: bash_code_execution_output - `file_id: str` - `return_code: int` - `stderr: str` - `stdout: str` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaTextEditorCodeExecutionToolResultBlock` - `type: Literal["text_editor_code_execution_tool_result"]` default: text_editor_code_execution_tool_result - `content: Content` - `class BetaTextEditorCodeExecutionToolResultError` - `type: Literal["text_editor_code_execution_tool_result_error"]` default: text_editor_code_execution_tool_result_error - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", 2 more]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: Optional[str]` - `class BetaTextEditorCodeExecutionViewResultBlock` - `type: Literal["text_editor_code_execution_view_result"]` default: text_editor_code_execution_view_result - `content: str` - `file_type: Literal["text", "image", "pdf"]` - `"text"` - `"image"` - `"pdf"` - `num_lines: Optional[int]` - `start_line: Optional[int]` - `total_lines: Optional[int]` - `class BetaTextEditorCodeExecutionCreateResultBlock` - `type: Literal["text_editor_code_execution_create_result"]` default: text_editor_code_execution_create_result - `is_file_update: bool` - `class BetaTextEditorCodeExecutionStrReplaceResultBlock` - `type: Literal["text_editor_code_execution_str_replace_result"]` default: text_editor_code_execution_str_replace_result - `lines: Optional[List[str]]` - `new_lines: Optional[int]` - `new_start: Optional[int]` - `old_lines: Optional[int]` - `old_start: Optional[int]` - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaToolSearchToolResultBlock` - `type: Literal["tool_search_tool_result"]` default: tool_search_tool_result - `content: Content` - `class BetaToolSearchToolResultError` - `type: Literal["tool_search_tool_result_error"]` default: tool_search_tool_result_error - `error_code: Literal["invalid_tool_input", "unavailable", "too_many_requests", "execution_time_exceeded"]` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: Optional[str]` - `class BetaToolSearchToolSearchResultBlock` - `type: Literal["tool_search_tool_search_result"]` default: tool_search_tool_search_result - `tool_references: List[BetaToolReferenceBlock]` - `type: Literal["tool_reference"]` default: tool_reference - `tool_name: str` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: str` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `class BetaMCPToolUseBlock` - `type: Literal["mcp_tool_use"]` default: mcp_tool_use - `id: str` pattern: ^[a-zA-Z0-9_-]+$ - `input: Dict[str, object]` - `name: str` The name of the MCP tool - `server_name: str` The name of the MCP server - `class BetaMCPToolResultBlock` - `type: Literal["mcp_tool_result"]` default: mcp_tool_result - `content: Union[str, List[BetaTextBlock]]` - `str` - `List[BetaTextBlock]` - `type: Literal["text"]` default: text - `citations: Optional[List[BetaTextCitation]]` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: str` - `is_error: bool` default: false - `tool_use_id: str` pattern: ^[a-zA-Z0-9_-]+$ - `class BetaContainerUploadBlock` Response model for a file uploaded to the container. - `type: Literal["container_upload"]` default: container_upload - `file_id: str` - `class BetaCompactionBlock` A compaction block returned when autocompact is triggered. When content is None, it indicates the compaction failed to produce a valid summary (e.g., malformed output from the model). Clients may round-trip compaction blocks with null content; the server treats them as no-ops. - `type: Literal["compaction"]` default: compaction - `content: Optional[str]` Summary of compacted content, or null if compaction failed - `encrypted_content: Optional[str]` Opaque metadata from prior compaction, to be round-tripped verbatim - `signature: Optional[str]` Signature over the summary, to be sent back with the block verbatim - `tool_changes: Optional[List[ToolChange]]` The tool changes of the compacted range: the `tool_addition` and `tool_removal` blocks that take the request's `tools` to the tool set in effect at the end of the range, or `[]` when the range changed no tool. Absent when the server did not compute them. Send the block back unchanged. - `class BetaResponseToolAdditionBlock` An entry of a `compaction` block's `tool_changes`: a tool the compacted range made available, as a reference to a `tools` entry or MCP toolset, or as the tool definition in effect at the end of the range, by value. Send it back unchanged. - `type: Literal["tool_addition"]` default: tool_addition - `tool: Tool` The tool made available: a reference to a `tools` entry or MCP toolset, or a `tool_definition` carrying the definition by value. - `class BetaResponseToolChangeToolReference` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `type: Literal["tool_reference"]` default: tool_reference - `name: str` - `class BetaResponseToolChangeMCPToolReference` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: Literal["mcp_tool_reference"]` default: mcp_tool_reference - `name: str` - `server_name: str` - `class BetaResponseToolChangeMCPToolsetReference` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `type: Literal["mcp_toolset_reference"]` default: mcp_toolset_reference - `server_name: str` - `class BetaToolChangeToolDefinition` A tool defined by value, as a `compaction` block's `tool_changes` entry reports it: `definition` is the tool's definition as it was sent, in the form of a `tools` entry, without `cache_control`. Send it back unchanged with the block. - `type: Literal["tool_definition"]` default: tool_definition - `definition: BetaResponseToolUnion` - `class BetaResponseTool` A custom tool definition, as sent. - `type: Optional[Literal["custom"]]` - `input_schema: BetaResponseToolInputSchema` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$ - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description: Optional[str]` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: Optional[bool]` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolBash20241022` - `type: Literal["bash_20241022"]` - `name: Literal["bash"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `type: Literal["ephemeral"]` - `ttl: Optional[Literal["5m", "1h"]]` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching?sdk_languages=python) for details. - `"5m"` - `"1h"` - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolBash20250124` - `type: Literal["bash_20250124"]` - `name: Literal["bash"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20250522` - `type: Literal["code_execution_20250522"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20250825` - `type: Literal["code_execution_20250825"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20260120` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: Literal["code_execution_20260120"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaCodeExecutionTool20260521` Code execution tool with REPL state persistence. - `type: Literal["code_execution_20260521"]` - `name: Literal["code_execution"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaBrowserToolset20260801` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: Literal["browser_toolset_20260801"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[BetaBrowserToolsetConfigs]` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: Optional[BetaBrowserTypeConfig]` `type`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: Optional[BetaBrowserCloseTabConfig]` `close_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: Optional[BetaBrowserDoubleClickConfig]` `double_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: Optional[BetaBrowserFileUploadConfig]` `file_upload`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: Optional[BetaBrowserFindConfig]` `find`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: Optional[BetaBrowserFormInputConfig]` `form_input`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: Optional[BetaBrowserGetPageTextConfig]` `get_page_text`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: Optional[BetaBrowserHoldKeyConfig]` `hold_key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: Optional[BetaBrowserHoverConfig]` `hover`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: Optional[BetaBrowserJavascriptExecConfig]` `javascript_exec`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: Optional[BetaBrowserKeyConfig]` `key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: Optional[BetaBrowserLeftClickConfig]` `left_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: Optional[BetaBrowserLeftClickDragConfig]` `left_click_drag`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: Optional[BetaBrowserLeftMouseDownConfig]` `left_mouse_down`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: Optional[BetaBrowserLeftMouseUpConfig]` `left_mouse_up`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: Optional[BetaBrowserListTabsConfig]` `list_tabs`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: Optional[BetaBrowserMiddleClickConfig]` `middle_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: Optional[BetaBrowserMouseMoveConfig]` `mouse_move`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: Optional[BetaBrowserNavigateConfig]` `navigate`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: Optional[BetaBrowserNewTabConfig]` `new_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: Optional[BetaBrowserReadConsoleConfig]` `read_console`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: Optional[BetaBrowserReadNetworkConfig]` `read_network`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: Optional[BetaBrowserReadPageConfig]` `read_page`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: Optional[BetaBrowserRightClickConfig]` `right_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: Optional[BetaBrowserScreenshotConfig]` `screenshot`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: Optional[BetaBrowserScrollConfig]` `scroll`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: Optional[BetaBrowserScrollToConfig]` `scroll_to`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: Optional[BetaBrowserSwitchTabConfig]` `switch_tab`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: Optional[BetaBrowserTripleClickConfig]` `triple_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: Optional[BetaBrowserWaitConfig]` `wait`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: Optional[BetaBrowserZoomConfig]` `zoom`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `class BetaToolComputerUse20241022` - `type: Literal["computer_20241022"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaMemoryTool20250818` - `type: Literal["memory_20250818"]` - `name: Literal["memory"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolComputerUse20250124` - `type: Literal["computer_20250124"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20241022` - `type: Literal["text_editor_20241022"]` - `name: Literal["str_replace_editor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolComputerUse20251124` - `type: Literal["computer_20251124"]` - `display_height_px: int` The height of the display in pixels. minimum: 1 - `display_width_px: int` The width of the display in pixels. minimum: 1 - `name: Literal["computer"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `display_number: Optional[int]` The X11 display number (e.g. 0, 1) for the display. minimum: 0 - `enable_zoom: Optional[bool]` Whether to enable an action to take a zoomed-in screenshot of the screen. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaComputerToolset20260801` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: Literal["computer_toolset_20260801"]` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[BetaComputerToolsetConfigs]` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type: Optional[BetaComputerTypeConfig]` `type`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: Optional[BetaComputerCursorPositionConfig]` `cursor_position`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: Optional[BetaComputerDoubleClickConfig]` `double_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: Optional[BetaComputerHoldKeyConfig]` `hold_key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: Optional[BetaComputerKeyConfig]` `key`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: Optional[BetaComputerLeftClickConfig]` `left_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: Optional[BetaComputerLeftClickDragConfig]` `left_click_drag`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: Optional[BetaComputerLeftMouseDownConfig]` `left_mouse_down`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: Optional[BetaComputerLeftMouseUpConfig]` `left_mouse_up`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: Optional[BetaComputerMiddleClickConfig]` `middle_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: Optional[BetaComputerMouseMoveConfig]` `mouse_move`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: Optional[BetaComputerRightClickConfig]` `right_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: Optional[BetaComputerScreenshotConfig]` `screenshot`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: Optional[BetaComputerScrollConfig]` `scroll`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: Optional[BetaComputerTripleClickConfig]` `triple_click`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: Optional[BetaComputerWaitConfig]` `wait`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: Optional[BetaComputerZoomConfig]` `zoom`'s config overrides. - `defer_loading: Optional[bool]` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: Optional[bool]` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `class BetaToolTextEditor20250124` - `type: Literal["text_editor_20250124"]` - `name: Literal["str_replace_editor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20250429` - `type: Literal["text_editor_20250429"]` - `name: Literal["str_replace_based_edit_tool"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolTextEditor20250728` - `type: Literal["text_editor_20250728"]` - `name: Literal["str_replace_based_edit_tool"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples: Optional[List[Dict[str, object]]]` - `max_characters: Optional[int]` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaWebSearchTool20250305` - `type: Literal["web_search_20250305"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `type: Literal["approximate"]` - `city: Optional[str]` The city of the user. minLength: 1, maxLength: 255 - `country: Optional[str]` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region: Optional[str]` The region of the user. minLength: 1, maxLength: 255 - `timezone: Optional[str]` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `class BetaWebFetchTool20250910` - `type: Literal["web_fetch_20250910"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: Optional[bool]` - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results: Optional[ClientToolResults]` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: Literal["all"]` - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: Literal["none"]` - `class BetaWebFetchURLSourceOnly` The tool filter variant under which only the named tools' results contribute. - `type: Literal["only"]` - `tools: List[BetaWebFetchURLSourceToolReference]` - `type: Literal["tool_reference"]` - `name: str` - `class BetaWebFetchURLSourceExcept` The tool filter variant under which every result but the named tools' contributes. - `type: Literal["except"]` - `tools: List[BetaWebFetchURLSourceToolReference]` - `type: Literal["tool_reference"]` - `name: str` - `server_tool_results: Optional[ServerToolResults]` Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute. - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `class BetaWebFetchURLSourceOnly` The tool filter variant under which only the named tools' results contribute. - `class BetaWebFetchURLSourceExcept` The tool filter variant under which every result but the named tools' contributes. - `user_input: Optional[UserInput]` Whether URLs in user messages are fetchable: "all" or "none". - `class BetaWebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `class BetaWebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `class BetaWebSearchTool20260209` - `type: Literal["web_search_20260209"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `class BetaWebFetchTool20260209` - `type: Literal["web_fetch_20260209"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `class BetaWebFetchTool20260309` Web fetch tool with use_cache parameter for bypassing cached content. - `type: Literal["web_fetch_20260309"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `use_cache: Optional[bool]` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `class BetaWebSearchTool20260318` - `type: Literal["web_search_20260318"]` - `name: Literal["web_search"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: Optional[List[str]]` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: Optional[Literal["full", "excluded"]]` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `user_location: Optional[BetaUserLocation]` Parameters for the user's location. Used to provide more relevant search results. - `class BetaWebFetchTool20260318` - `type: Literal["web_fetch_20260318"]` - `name: Literal["web_fetch"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains: Optional[List[str]]` List of domains to allow fetching from - `blocked_domains: Optional[List[str]]` List of domains to block fetching from - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `citations: Optional[BetaCitationsConfigParam]` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens: Optional[int]` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. minimum: 1 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion: Optional[Literal["full", "excluded"]]` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn. - `"full"` - `"excluded"` - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `url_sources: Optional[BetaWebFetchURLSources]` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `use_cache: Optional[bool]` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `class BetaAdvisorTool20260301` - `type: Literal["advisor_20260301"]` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. New class of intelligence, strongest in coding and cybersecurity - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `name: Literal["advisor"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `caching: Optional[BetaCacheControlEphemeral]` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: Optional[int]` Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. minimum: 1024 - `max_uses: Optional[int]` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolSearchToolBm25_20251119` - `type: Literal["tool_search_tool_bm25_20251119", "tool_search_tool_bm25"]` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: Literal["tool_search_tool_bm25"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaToolSearchToolRegex20251119` - `type: Literal["tool_search_tool_regex_20251119", "tool_search_tool_regex"]` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: Literal["tool_search_tool_regex"]` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: Optional[List[Literal["direct", "code_execution_20250825", "code_execution_20260120", "code_execution_20260521"]]]` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `defer_loading: Optional[bool]` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict: Optional[bool]` When true, guarantees schema validation on tool names and inputs - `class BetaMCPToolset` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: Literal["mcp_toolset"]` - `mcp_server_name: str` Name of the MCP server to configure tools for minLength: 1, maxLength: 255 - `cache_control: Optional[BetaCacheControlEphemeral]` Create a cache control breakpoint at this content block. - `configs: Optional[Dict[str, BetaMCPToolConfig]]` Configuration overrides for specific tools, keyed by tool name - `defer_loading: Optional[bool]` - `enabled: Optional[bool]` - `default_config: Optional[BetaMCPToolDefaultConfig]` Default configuration applied to all tools from this server - `defer_loading: Optional[bool]` - `enabled: Optional[bool]` - `tools: Optional[List[BetaMCPToolParam]]` The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response. - `input_schema: Dict[str, object]` The tool's input schema as the MCP server lists it, verbatim. - `name: str` The tool's name as the MCP server lists it (not prefixed with the server name). minLength: 1 - `description: Optional[str]` The tool's description as the MCP server lists it. - `class BetaResponseToolRemovalBlock` An entry of a `compaction` block's `tool_changes`: a tool of the request's `tools` (or an MCP tool or toolset) that the compacted range withdrew. Send it back unchanged. - `type: Literal["tool_removal"]` default: tool_removal - `tool: Tool` A reference to the withdrawn `tools` entry, MCP tool or MCP toolset. - `class BetaResponseToolChangeToolReference` Reference to a single tool, by the name the model uses to call it, as a `compaction` block's `tool_changes` entry reports it: a tool declared in `tools` or defined by an earlier `tool_addition` block. Send it back unchanged with the block. - `class BetaResponseToolChangeMCPToolReference` Reference to a single MCP tool, by its server and its name on that server, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `class BetaResponseToolChangeMCPToolsetReference` Reference to every tool in the named MCP server's toolset, as a `compaction` block's `tool_changes` entry reports it. Send it back unchanged with the block. - `class BetaFallbackBlock` Marks the point in `content` where one model's output gives way to the next. One block appears per hop where a preceding model actually ran this turn and declined. A turn where no preceding model ran and declined has no such boundary and carries no block — the signal for whether a fallback model served the response is the presence of a `fallback_message` entry in `usage.iterations`, not this block. The block is treated like a server-tool content block for streaming: it arrives via the standard `content_block_start` / `content_block_stop` pair and carries no deltas. - `type: Literal["fallback"]` default: fallback - `from_: BetaFallbackInfo` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `to: BetaFallbackInfo` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `trigger: BetaFallbackRefusalTrigger` What caused the `from` model to hand over at this hop. - `type: Literal["refusal"]` default: refusal - `category: Optional[Literal["cyber", "bio", "frontier_llm", 2 more]]` The policy category that triggered the `from` model's refusal at this hop. `null` when the refusal doesn't map to a named category. Same vocabulary as `stop_details.category`. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=python). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `class BetaMCPToolListingBlock` The tool listing the server fetched from an MCP server while producing this response. Send the assistant message back unchanged, this block included, so later requests use this listing instead of asking the MCP server again. - `type: Literal["mcp_tool_listing"]` default: mcp_tool_listing - `mcp_server_name: str` - `tools: List[BetaMCPTool]` - `input_schema: Dict[str, object]` - `name: str` - `description: Optional[str]` - `context_management: Optional[BetaContextManagementResponse]` Context management response. Information about context management strategies applied during the request. - `applied_edits: List[AppliedEdit]` List of context management edits that were applied. - `class BetaClearToolUses20250919EditResponse` - `type: Literal["clear_tool_uses_20250919"]` The type of context management edit applied. default: clear_tool_uses_20250919 - `cleared_input_tokens: int` Number of input tokens cleared by this edit. minimum: 0 - `cleared_tool_uses: int` Number of tool uses that were cleared. minimum: 0 - `class BetaClearThinking20251015EditResponse` - `type: Literal["clear_thinking_20251015"]` The type of context management edit applied. default: clear_thinking_20251015 - `cleared_input_tokens: int` Number of input tokens cleared by this edit. minimum: 0 - `cleared_thinking_turns: int` Number of thinking turns that were cleared. minimum: 0 - `diagnostics: Optional[BetaDiagnostics]` Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected. - `cache_miss_reason: Optional[BetaCacheMissReason]` Explains why the prompt cache could not fully reuse the prefix from the request identified by `diagnostics.previous_message_id`. `null` means diagnosis is still pending — the response was serialized before the background comparison completed. - `class BetaCacheMissModelChanged` - `type: Literal["model_changed"]` default: model_changed - `cache_missed_input_tokens: int` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `class BetaCacheMissSystemChanged` - `type: Literal["system_changed"]` default: system_changed - `cache_missed_input_tokens: int` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `class BetaCacheMissToolsChanged` - `type: Literal["tools_changed"]` default: tools_changed - `cache_missed_input_tokens: int` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `class BetaCacheMissMessagesChanged` - `type: Literal["messages_changed"]` default: messages_changed - `cache_missed_input_tokens: int` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `class BetaCacheMissPreviousMessageNotFound` - `type: Literal["previous_message_not_found"]` default: previous_message_not_found - `class BetaCacheMissUnavailable` - `type: Literal["unavailable"]` default: unavailable - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `role: Literal["assistant"]` Conversational role of the generated message. This will always be `"assistant"`. default: assistant - `stop_details: Optional[BetaRefusalStopDetails]` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `type: Literal["refusal"]` default: refusal - `category: Optional[Literal["cyber", "bio", "frontier_llm", 2 more]]` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking?sdk_languages=python). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: Optional[str]` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: Optional[str]` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: Optional[bool]` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: Optional[str]` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: Optional[BetaStopReason]` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: Optional[str]` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: BetaUsage` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation: Optional[BetaCacheCreation]` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: int` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: int` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: Optional[int]` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: Optional[int]` The number of input tokens read from the cache. minimum: 0 - `fallback_credit: Optional[BetaFallbackCreditUsage]` Outcome of the `fallback_credit_token` presented on this request. Present on every response to a non-batch request that carried a `fallback_credit_token`, in either redemption mode; absent otherwise (batch items accept and ignore the token and carry no outcome object). - `status: Status` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `class BetaFallbackCreditRedeemed` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: Literal["redeemed"]` default: redeemed - `class BetaFallbackCreditNotApplied` No reprice was applied; `reason` says why. - `type: Literal["not_applied"]` default: not_applied - `reason: Literal["body_mismatch", "continuation_excluded", "continuation_only", 9 more]` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: Optional[List[str]]` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: Optional[str]` The geographic region where inference was performed for this request. - `input_tokens: int` The number of input tokens which were used. minimum: 0 - `iterations: Optional[BetaIterationsUsage]` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `class BetaMessageIterationUsage` Token usage for a sampling iteration. - `type: Literal["message"]` Usage for a sampling iteration default: message - `cache_creation: Optional[BetaCacheCreation]` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: int` The number of input tokens used to create the cache entry. default: 0, minimum: 0 - `cache_read_input_tokens: int` The number of input tokens read from the cache. default: 0, minimum: 0 - `input_tokens: int` The number of input tokens which were used. minimum: 0 - `model: Optional[Model]` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: int` The number of output tokens which were used. minimum: 0 - `class BetaCompactionIterationUsage` Token usage for a compaction iteration. - `type: Literal["compaction"]` Usage for a compaction iteration default: compaction - `cache_creation: Optional[BetaCacheCreation]` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: int` The number of input tokens used to create the cache entry. default: 0, minimum: 0 - `cache_read_input_tokens: int` The number of input tokens read from the cache. default: 0, minimum: 0 - `input_tokens: int` The number of input tokens which were used. minimum: 0 - `output_tokens: int` The number of output tokens which were used. minimum: 0 - `class BetaAdvisorMessageIterationUsage` Token usage for an advisor sub-inference iteration. - `type: Literal["advisor_message"]` Usage for an advisor sub-inference iteration default: advisor_message - `cache_creation: Optional[BetaCacheCreation]` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: int` The number of input tokens used to create the cache entry. default: 0, minimum: 0 - `cache_read_input_tokens: int` The number of input tokens read from the cache. default: 0, minimum: 0 - `input_tokens: int` The number of input tokens which were used. minimum: 0 - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: int` The number of output tokens which were used. minimum: 0 - `class BetaFallbackMessageIterationUsage` Token usage for the fallback-model attempt of a server-side fallback request. The terminal entry of a fallback-served turn: when a fallback hop's output is the returned message, the entry for the iteration that completed it carries this type in place of `message`. A declined hop and the serving hop's earlier tool-loop iterations produce `message` entries. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: Literal["fallback_message"]` Usage for the fallback-model attempt that served the response default: fallback_message - `cache_creation: Optional[BetaCacheCreation]` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: int` The number of input tokens used to create the cache entry. default: 0, minimum: 0 - `cache_read_input_tokens: int` The number of input tokens read from the cache. default: 0, minimum: 0 - `input_tokens: int` The number of input tokens which were used. minimum: 0 - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: int` The number of output tokens which were used. minimum: 0 - `output_tokens: int` The number of output tokens which were used. minimum: 0 - `output_tokens_details: Optional[BetaOutputTokensDetails]` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `thinking_tokens: int` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. default: 0, minimum: 0 - `server_tool_use: Optional[BetaServerToolUsage]` The number of server tool requests. - `web_fetch_requests: int` The number of web fetch tool requests. default: 0, minimum: 0 - `web_search_requests: int` The number of web search tool requests. default: 0, minimum: 0 - `service_tier: Optional[Literal["standard", "priority", "batch"]]` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: Optional[Literal["standard", "fast"]]` The inference speed mode used for this request. - `"standard"` - `"fast"` - `input_transformations: Optional[List[BetaInputTransformation]]` Changes the API made to the request's input before showing it to the model, and blocks that failed a binding check but were left unchanged: one entry per block, in request order. Two entry types today. `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. `thinking_mismatch_allowed` — a `thinking` or `redacted_thinking` block that failed the conversation check (the conversation before it differs from the one it was created in, or it carries no record of one on a model that requires it) and was shown to the model all the same, because that check is not enforced for this request. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when there is no entry to report; without the beta, blocks are removed or left in place all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`; blocks left in place count as sent. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `class BetaThinkingDroppedInputTransformation` - `type: Literal["thinking_dropped"]` Always `thinking_dropped` for this entry type. default: thinking_dropped - `path: str` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: Literal["model_binding_mismatch", "prefix_binding_mismatch", "organization_binding_mismatch", "end_user_binding_mismatch"]` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `class BetaThinkingMismatchAllowedInputTransformation` - `type: Literal["thinking_mismatch_allowed"]` Always `thinking_mismatch_allowed` for this entry type. default: thinking_mismatch_allowed - `path: str` Where the block is in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: Literal["model_binding_mismatch", "prefix_binding_mismatch", "organization_binding_mismatch", "end_user_binding_mismatch"]` Which binding check the block failed; the block was shown to the model all the same. Always `prefix_binding_mismatch` today — the conversation before the block differs from the conversation it was created in, or the block carries no record of one on a model that requires it. Were the check enforced for this request, the block would have been removed or the request rejected (`thinking.block_binding.prefix_mismatch_behavior`). A removal also takes the rest of that turn's consecutive thinking blocks, whereas here each block is checked on its own, so `thinking_mismatch_allowed` entries are a lower bound on what enforcement would remove. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `class BetaMessageBatchErroredResult` - `type: Literal["errored"]` default: errored - `error: BetaErrorResponse` - `type: Literal["error"]` default: error - `error: BetaError` - `class BetaInvalidRequestError` - `type: Literal["invalid_request_error"]` default: invalid_request_error - `message: str` default: Invalid request - `class BetaAuthenticationError` - `type: Literal["authentication_error"]` default: authentication_error - `message: str` default: Authentication error - `class BetaBillingError` - `type: Literal["billing_error"]` default: billing_error - `message: str` default: Billing error - `class BetaPermissionError` - `type: Literal["permission_error"]` default: permission_error - `message: str` default: Permission denied - `class BetaNotFoundError` - `type: Literal["not_found_error"]` default: not_found_error - `message: str` default: Not found - `class BetaRateLimitError` - `type: Literal["rate_limit_error"]` default: rate_limit_error - `message: str` default: Rate limited - `class BetaGatewayTimeoutError` - `type: Literal["timeout_error"]` default: timeout_error - `message: str` default: Request timeout - `class BetaAPIError` - `type: Literal["api_error"]` default: api_error - `message: str` default: Internal server error - `class BetaOverloadedError` - `type: Literal["overloaded_error"]` default: overloaded_error - `message: str` default: Overloaded - `request_id: Optional[str]` - `class BetaMessageBatchCanceledResult` - `type: Literal["canceled"]` default: canceled - `class BetaMessageBatchExpiredResult` - `type: Literal["expired"]` default: expired #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) for batch in client.beta.messages.batches.results( message_batch_id="message_batch_id", ): print(batch) ``` ## Beta › Agents ### Create Agent `beta.agents.create(**kwargs) -> BetaManagedAgentsAgent` **POST** `/v1/agents` Create Agent #### Parameters - `model: Model` Model identifier. Accepts the [model string](https://platform.claude.com/docs/en/about-claude/models/overview?sdk_languages=python#latest-models-comparison), e.g. `claude-opus-5`, or a `model_config` object for additional configuration control - `Union[Literal["claude-haiku-5-5", "claude-sonnet-5-5", "claude-opus-5-5", 14 more], str]` - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `class BetaManagedAgentsModelConfigParams` An object that defines additional configuration control over model use - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. Accepts a bare level string (`"high"`) or `{"type": "high"}`. On create, omitting it resolves the per-model default; on update, omitting it leaves the stored value unchanged. - `"low"` Low effort. Favors latency over reasoning depth. - `"medium"` Medium effort. Balances latency and reasoning depth. - `"high"` High effort. Favors reasoning depth. - `"xhigh"` Extra-high effort. Not all models accept this level. - `"max"` Maximum effort. Favors reasoning depth over latency. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. On update, `model` is whole-object replacement — omitting inference_geo clears it. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. Defaults to `standard`. - `"standard"` - `"fast"` - `name: str` Human-readable name for the agent. minLength: 1, maxLength: 256 - `description: Optional[str]` Description of what the agent does. maxLength: 2048 - `mcp_servers: Optional[Iterable[BetaManagedAgentsURLMCPServerParams]]` MCP servers this agent connects to. Maximum 20. Names must be unique within the array. Every server must be referenced by an `mcp_toolset` in `tools`; unreferenced servers are rejected. See the [MCP connector guide](https://platform.claude.com/docs/en/managed-agents/mcp-connector?sdk_languages=python). - `type: Literal["url"]` - `name: str` Unique name for this server, referenced by mcp_toolset configurations. 1-255 characters. minLength: 1, maxLength: 255 - `url: str` Endpoint URL for the MCP server. maxLength: 2048 - `metadata: Optional[Dict[str, str]]` Arbitrary key-value metadata. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars. - `multiagent: Optional[BetaManagedAgentsMultiagentParams]` Multiagent orchestration configuration. - `class BetaManagedAgentsMultiagentCoordinatorParams` A coordinator topology: the session's primary thread orchestrates work by spawning session threads, each running an agent drawn from the `agents` roster. - `type: Literal["coordinator"]` - `agents: List[BetaManagedAgentsMultiagentRosterEntryParams]` Agents the coordinator may spawn as session threads. 1–20 entries. Each entry is an agent ID string, a versioned `{"type":"agent","id","version"}` reference, or `{"type":"self"}` to allow recursive self-invocation. Entries must reference distinct agents (after resolving `self` and string forms); at most one `self`. Referenced agents must exist, must not be archived, and must not themselves have `multiagent` set (depth limit 1). - `str` - `class BetaManagedAgentsAgentParams` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `type: Literal["agent"]` - `id: str` The `agent` ID. minLength: 1, maxLength: 128 - `version: Optional[int]` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. format: int32 - `class BetaManagedAgentsMultiagentSelfParams` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: Literal["self"]` - `class BetaManagedAgentsAdvisorParams` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. At most one per roster; the entry occupies the roster name `anthropic.advisor`. - `type: Literal["advisor"]` - `model: str` A Claude model id. The model must be permitted as an advisor for this agent's model. minLength: 1, maxLength: 256 - `class BetaManagedAgentsMultiagent20261001Params` Multiagent configuration with three members, each enabled or disabled on its own. On an update, if the agent's stored `multiagent` also has type `multiagent_20261001`, this configuration is merged into the stored one, level by level, instead of replacing it. A key that the update omits keeps its stored value. A key sent as null takes its default, on create as well, so `"workflows": null` enables workflows. An object sent with a `type` other than the stored one replaces the stored object, and the keys that it omits take their defaults. A `predefined_agents` list that is sent replaces the stored list. Every object that is sent needs its `type`, and an enabled `advisor` needs its `model`. Other validation applies to the merged result. - `type: Literal["multiagent_20261001"]` - `advisor: Optional[BetaManagedAgentsMultiagentAdvisorParams]` Whether the session's primary thread can consult an advisor model. Defaults to disabled. - `class BetaManagedAgentsMultiagentAdvisorEnabledParams` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` A Claude model id. The model must be permitted as an advisor for this agent's model. minLength: 1, maxLength: 256 - `class BetaManagedAgentsMultiagentAdvisorDisabledParams` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: Optional[BetaManagedAgentsMultiagentSubagentsParams]` Whether the agent can spawn session threads. Defaults to enabled. - `class BetaManagedAgentsMultiagentSubagentsEnabledParams` The agent can spawn session threads. Each thread runs a predefined agent, which is a saved agent in `predefined_agents`, or an inline agent, which the agent defines when it spawns the thread and which is not saved. If `inline_agents` is disabled, `predefined_agents` must name at least one agent. - `type: Literal["enabled"]` - `inline_agents: Optional[BetaManagedAgentsMultiagentInlineAgentsParams]` Whether the agent can define inline agents when it spawns session threads. Defaults to enabled. - `class BetaManagedAgentsMultiagentInlineAgentsEnabledParams` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabledParams` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: Optional[List[BetaManagedAgentsMultiagentPredefinedAgentParams]]` Predefined agents that this agent can spawn as session threads. At most 20. Defaults to null. Null and an empty list both mean no predefined agents. This list is separate from `workflows.predefined_agents`, and an agent in one list is not added to the other. - `str` - `class BetaManagedAgentsAgentParams` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `class BetaManagedAgentsMultiagentSelfParams` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `class BetaManagedAgentsMultiagentSubagentsDisabledParams` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: Optional[BetaManagedAgentsMultiagentWorkflowsParams]` Whether the agent can start workflow runs. Defaults to enabled. - `class BetaManagedAgentsMultiagentWorkflowsEnabledParams` The agent can start workflow runs. Each run follows a plan, a program that the agent writes. A plan can use predefined agents, which are the saved agents in `predefined_agents`, and inline agents, which it defines itself and which are not saved. If `inline_agents` is disabled, `predefined_agents` must name at least one agent. - `type: Literal["enabled"]` - `inline_agents: Optional[BetaManagedAgentsMultiagentInlineAgentsParams]` Whether a run's plan can define inline agents. Defaults to enabled. - `predefined_agents: Optional[List[BetaManagedAgentsMultiagentPredefinedAgentParams]]` Predefined agents that a run's plan can use. At most 20. Defaults to null. Null and an empty list both mean no predefined agents. This list is separate from `subagents.predefined_agents`, and an agent in one list is not added to the other. - `str` - `class BetaManagedAgentsAgentParams` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `class BetaManagedAgentsMultiagentSelfParams` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `class BetaManagedAgentsMultiagentWorkflowsDisabledParams` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `skills: Optional[Iterable[BetaManagedAgentsSkillParams]]` Skills available to the agent. - `class BetaManagedAgentsAnthropicSkillParams` An Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` Identifier of the Anthropic skill (e.g., "xlsx"). minLength: 1, maxLength: 64 - `version: Optional[str]` Version to pin. Defaults to latest if omitted. minLength: 1, maxLength: 64 - `class BetaManagedAgentsCustomSkillParams` A user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` Tagged ID of the custom skill (e.g., "skill_01XJ5..."). minLength: 1, maxLength: 64 - `version: Optional[str]` Version to pin. Defaults to latest if omitted. minLength: 1, maxLength: 64 - `system: Optional[str]` System prompt for the agent. maxLength: 100000 - `tools: Optional[Iterable[Tool]]` Tool configurations available to the agent. Maximum of 256 tools across all toolsets allowed. - `class BetaManagedAgentsAgentToolset20260401Params` Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent. - `type: Literal["agent_toolset_20260401"]` - `configs: Optional[List[BetaManagedAgentsAgentToolConfigParams]]` Per-tool configuration overrides. - `class BetaManagedAgentsBashToolConfigParams` Configuration override for the bash tool. - `type: Optional[Literal["bash"]]` - `name: Literal["bash"]` Must be "bash". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfigParams` Configuration override for the edit tool. - `type: Optional[Literal["edit"]]` - `name: Literal["edit"]` Must be "edit". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfigParams` Configuration override for the read tool. - `type: Optional[Literal["read"]]` - `name: Literal["read"]` Must be "read". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfigParams` Configuration override for the write tool. - `type: Optional[Literal["write"]]` - `name: Literal["write"]` Must be "write". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfigParams` Configuration override for the glob tool. - `type: Optional[Literal["glob"]]` - `name: Literal["glob"]` Must be "glob". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfigParams` Configuration override for the grep tool. - `type: Optional[Literal["grep"]]` - `name: Literal["grep"]` Must be "grep". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfigParams` Configuration override for the web_fetch tool. - `type: Optional[Literal["web_fetch"]]` - `name: Literal["web_fetch"]` Must be "web_fetch". - `allowed_domains: Optional[List[str]]` Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: Optional[List[str]]` Never fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `max_content_tokens: Optional[int]` Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs. format: int32 - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSourcesParams]` Which sources contribute URLs the tool may fetch. Omit to allow every source. - `client_tool_results: Optional[Union[BetaManagedAgentsWebFetchURLSourceShorthand, BetaManagedAgentsWebFetchURLSourceToolFilter, null]]` Which custom tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be a custom tool in the same tools array. - `Literal["all", "none"]` - `"all"` - `"none"` - `type BetaManagedAgentsWebFetchURLSourceToolFilter = ...` Which tools' results contribute URLs that may be fetched. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[Union[BetaManagedAgentsWebFetchURLSourceShorthand, BetaManagedAgentsWebFetchURLSourceToolFilter, null]]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be "web_search" or "web_fetch". - `user_input: Optional[Union[BetaManagedAgentsWebFetchURLSourceShorthand, BetaManagedAgentsWebFetchURLSourceUserInput, null]]` Whether URLs in the text of user messages may be fetched: "all" (the default) or "none". - `Literal["all", "none"]` - `"all"` - `"none"` - `type BetaManagedAgentsWebFetchURLSourceUserInput = ...` Whether URLs in the text of user messages may be fetched. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `class BetaManagedAgentsWebSearchToolConfigParams` Configuration override for the web_search tool. - `type: Optional[Literal["web_search"]]` - `name: Literal["web_search"]` Must be "web_search". - `allowed_domains: Optional[List[str]]` Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: Optional[List[str]]` Never return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: Optional[BetaManagedAgentsAgentToolsetDefaultConfigParams]` Default configuration applied to all tools in this set. - `enabled: Optional[bool]` Whether tools are enabled and available to Claude by default. Defaults to true if not specified. - `permission_policy: Optional[PermissionPolicy]` Default permission policy for tools. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolsetParams` Configuration for tools from an MCP server defined in `mcp_servers`. - `type: Literal["mcp_toolset"]` - `mcp_server_name: str` Name of the MCP server. Must match a server name from the mcp_servers array. 1-255 characters. minLength: 1, maxLength: 255 - `configs: Optional[List[BetaManagedAgentsMCPToolConfigParams]]` Per-tool configuration overrides. - `name: str` Name of the MCP tool to configure. 1-128 characters. minLength: 1, maxLength: 128 - `enabled: Optional[bool]` Whether this tool is enabled. Overrides the `default_config` setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Overrides the `default_config` setting. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: Optional[BetaManagedAgentsMCPToolsetDefaultConfigParams]` Default configuration for all tools from this server. - `enabled: Optional[bool]` Whether tools are enabled by default. Defaults to true if not specified. - `permission_policy: Optional[PermissionPolicy]` Default permission policy for tools from this server. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsCustomToolParams` A custom tool that is executed by the API client rather than the agent. When the agent calls this tool, an `agent.custom_tool_use` event is emitted and the session goes idle, waiting for the client to provide the result via a `user.custom_tool_result` event. - `type: Literal["custom"]` - `description: str` Description of what the tool does, shown to the agent to help it decide when to use the tool. minLength: 1 - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema defining the expected input parameters for the tool. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` Unique name for the tool. 1-128 characters; letters, digits, underscores, and hyphens. minLength: 1, maxLength: 128 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsAgent` A Managed Agents `agent`. - `type: Literal["agent"]` - `id: str` - `archived_at: Optional[datetime]` When the agent was archived. Null if not archived. format: date-time - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `metadata: Dict[str, str]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsMultiagent]` Multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsMultiagentCoordinator` Resolved coordinator topology with a concrete agent roster. - `type: Literal["coordinator"]` - `agents: List[Agent]` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `class BetaManagedAgentsAgentReference` A resolved agent reference with a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagent20261001` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsAgentReference]` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsAgentReference]` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `version: int` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_agent = client.beta.agents.create( model="claude-opus-5", name="My First Agent", ) print(beta_managed_agents_agent.id) ``` ##### Response (200) ```json { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "advisor": { "type": "disabled" }, "subagents": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" }, "type": "multiagent_20261001", "workflows": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" } }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ``` ### List Agents `beta.agents.list(**kwargs) -> SyncPageCursor[BetaManagedAgentsAgent]` **GET** `/v1/agents` List Agents #### Parameters - `created_at_gte: Optional[Union[str, datetime]]` (query parameter) Return agents created at or after this time (inclusive). format: date-time - `created_at_lte: Optional[Union[str, datetime]]` (query parameter) Return agents created at or before this time (inclusive). format: date-time - `include_archived: Optional[bool]` (query parameter) Include archived agents in results. Defaults to false. - `limit: Optional[int]` (query parameter) Maximum results per page. Default 20, maximum 100. format: int32 - `page: Optional[str]` (query parameter) Opaque pagination cursor from a previous response. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsAgent` A Managed Agents `agent`. - `type: Literal["agent"]` - `id: str` - `archived_at: Optional[datetime]` When the agent was archived. Null if not archived. format: date-time - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `metadata: Dict[str, str]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsMultiagent]` Multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsMultiagentCoordinator` Resolved coordinator topology with a concrete agent roster. - `type: Literal["coordinator"]` - `agents: List[Agent]` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `class BetaManagedAgentsAgentReference` A resolved agent reference with a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagent20261001` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsAgentReference]` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsAgentReference]` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `version: int` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.agents.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "advisor": { "type": "disabled" }, "subagents": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" }, "type": "multiagent_20261001", "workflows": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" } }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ], "next_page": "next_page" } ``` ### Get Agent `beta.agents.retrieve(agent_id, **kwargs) -> BetaManagedAgentsAgent` **GET** `/v1/agents/{agent_id}` Get Agent #### Parameters - `agent_id: str` (path parameter) Unique identifier of the agent to retrieve. - `version: Optional[int]` (query parameter) Agent version. Omit for the most recent version. Must be at least 1 if specified. format: int32 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsAgent` A Managed Agents `agent`. - `type: Literal["agent"]` - `id: str` - `archived_at: Optional[datetime]` When the agent was archived. Null if not archived. format: date-time - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `metadata: Dict[str, str]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsMultiagent]` Multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsMultiagentCoordinator` Resolved coordinator topology with a concrete agent roster. - `type: Literal["coordinator"]` - `agents: List[Agent]` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `class BetaManagedAgentsAgentReference` A resolved agent reference with a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagent20261001` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsAgentReference]` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsAgentReference]` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `version: int` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_agent = client.beta.agents.retrieve( agent_id="agent_011CZkYpogX7uDKUyvBTophP", ) print(beta_managed_agents_agent.id) ``` ##### Response (200) ```json { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "advisor": { "type": "disabled" }, "subagents": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" }, "type": "multiagent_20261001", "workflows": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" } }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ``` ### Update Agent `beta.agents.update(agent_id, **kwargs) -> BetaManagedAgentsAgent` **POST** `/v1/agents/{agent_id}` Update Agent #### Parameters - `agent_id: str` (path parameter) Unique identifier of the agent to update. - `description: Optional[str]` Description. Omit to preserve; send empty string or null to clear. maxLength: 2048 - `mcp_servers: Optional[Iterable[BetaManagedAgentsURLMCPServerParams]]` MCP servers. Full replacement. Omit to preserve; send empty array or `null` to clear. Names must be unique. Maximum 20. Every server must be referenced by an `mcp_toolset` in the agent's resulting `tools`; unreferenced servers are rejected. See the [MCP connector guide](https://platform.claude.com/docs/en/managed-agents/mcp-connector?sdk_languages=python). - `type: Literal["url"]` - `name: str` Unique name for this server, referenced by mcp_toolset configurations. 1-255 characters. minLength: 1, maxLength: 255 - `url: str` Endpoint URL for the MCP server. maxLength: 2048 - `metadata: Optional[Dict[str, Optional[str]]]` Metadata patch. Set a key to a string to upsert it, or to null to delete it. Omit the field to preserve. The stored bag is limited to 16 keys (up to 64 chars each) with values up to 512 chars. - `model: Optional[Model]` Model identifier. Accepts the [model string](https://platform.claude.com/docs/en/about-claude/models/overview?sdk_languages=python#latest-models-comparison), e.g. `claude-opus-5`, or a `model_config` object for additional configuration control. Omit to preserve. Cannot be cleared. - `Union[Literal["claude-haiku-5-5", "claude-sonnet-5-5", "claude-opus-5-5", 14 more], str]` - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `class BetaManagedAgentsModelConfigParams` An object that defines additional configuration control over model use - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. Accepts a bare level string (`"high"`) or `{"type": "high"}`. On create, omitting it resolves the per-model default; on update, omitting it leaves the stored value unchanged. - `"low"` Low effort. Favors latency over reasoning depth. - `"medium"` Medium effort. Balances latency and reasoning depth. - `"high"` High effort. Favors reasoning depth. - `"xhigh"` Extra-high effort. Not all models accept this level. - `"max"` Maximum effort. Favors reasoning depth over latency. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. On update, `model` is whole-object replacement — omitting inference_geo clears it. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. Defaults to `standard`. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsMultiagentParams]` Multiagent orchestration configuration. Full replacement. Omit to preserve; send null to clear. - `class BetaManagedAgentsMultiagentCoordinatorParams` A coordinator topology: the session's primary thread orchestrates work by spawning session threads, each running an agent drawn from the `agents` roster. - `type: Literal["coordinator"]` - `agents: List[BetaManagedAgentsMultiagentRosterEntryParams]` Agents the coordinator may spawn as session threads. 1–20 entries. Each entry is an agent ID string, a versioned `{"type":"agent","id","version"}` reference, or `{"type":"self"}` to allow recursive self-invocation. Entries must reference distinct agents (after resolving `self` and string forms); at most one `self`. Referenced agents must exist, must not be archived, and must not themselves have `multiagent` set (depth limit 1). - `str` - `class BetaManagedAgentsAgentParams` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `type: Literal["agent"]` - `id: str` The `agent` ID. minLength: 1, maxLength: 128 - `version: Optional[int]` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. format: int32 - `class BetaManagedAgentsMultiagentSelfParams` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: Literal["self"]` - `class BetaManagedAgentsAdvisorParams` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. At most one per roster; the entry occupies the roster name `anthropic.advisor`. - `type: Literal["advisor"]` - `model: str` A Claude model id. The model must be permitted as an advisor for this agent's model. minLength: 1, maxLength: 256 - `class BetaManagedAgentsMultiagent20261001Params` Multiagent configuration with three members, each enabled or disabled on its own. On an update, if the agent's stored `multiagent` also has type `multiagent_20261001`, this configuration is merged into the stored one, level by level, instead of replacing it. A key that the update omits keeps its stored value. A key sent as null takes its default, on create as well, so `"workflows": null` enables workflows. An object sent with a `type` other than the stored one replaces the stored object, and the keys that it omits take their defaults. A `predefined_agents` list that is sent replaces the stored list. Every object that is sent needs its `type`, and an enabled `advisor` needs its `model`. Other validation applies to the merged result. - `type: Literal["multiagent_20261001"]` - `advisor: Optional[BetaManagedAgentsMultiagentAdvisorParams]` Whether the session's primary thread can consult an advisor model. Defaults to disabled. - `class BetaManagedAgentsMultiagentAdvisorEnabledParams` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` A Claude model id. The model must be permitted as an advisor for this agent's model. minLength: 1, maxLength: 256 - `class BetaManagedAgentsMultiagentAdvisorDisabledParams` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: Optional[BetaManagedAgentsMultiagentSubagentsParams]` Whether the agent can spawn session threads. Defaults to enabled. - `class BetaManagedAgentsMultiagentSubagentsEnabledParams` The agent can spawn session threads. Each thread runs a predefined agent, which is a saved agent in `predefined_agents`, or an inline agent, which the agent defines when it spawns the thread and which is not saved. If `inline_agents` is disabled, `predefined_agents` must name at least one agent. - `type: Literal["enabled"]` - `inline_agents: Optional[BetaManagedAgentsMultiagentInlineAgentsParams]` Whether the agent can define inline agents when it spawns session threads. Defaults to enabled. - `class BetaManagedAgentsMultiagentInlineAgentsEnabledParams` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabledParams` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: Optional[List[BetaManagedAgentsMultiagentPredefinedAgentParams]]` Predefined agents that this agent can spawn as session threads. At most 20. Defaults to null. Null and an empty list both mean no predefined agents. This list is separate from `workflows.predefined_agents`, and an agent in one list is not added to the other. - `str` - `class BetaManagedAgentsAgentParams` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `class BetaManagedAgentsMultiagentSelfParams` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `class BetaManagedAgentsMultiagentSubagentsDisabledParams` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: Optional[BetaManagedAgentsMultiagentWorkflowsParams]` Whether the agent can start workflow runs. Defaults to enabled. - `class BetaManagedAgentsMultiagentWorkflowsEnabledParams` The agent can start workflow runs. Each run follows a plan, a program that the agent writes. A plan can use predefined agents, which are the saved agents in `predefined_agents`, and inline agents, which it defines itself and which are not saved. If `inline_agents` is disabled, `predefined_agents` must name at least one agent. - `type: Literal["enabled"]` - `inline_agents: Optional[BetaManagedAgentsMultiagentInlineAgentsParams]` Whether a run's plan can define inline agents. Defaults to enabled. - `predefined_agents: Optional[List[BetaManagedAgentsMultiagentPredefinedAgentParams]]` Predefined agents that a run's plan can use. At most 20. Defaults to null. Null and an empty list both mean no predefined agents. This list is separate from `subagents.predefined_agents`, and an agent in one list is not added to the other. - `str` - `class BetaManagedAgentsAgentParams` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `class BetaManagedAgentsMultiagentSelfParams` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `class BetaManagedAgentsMultiagentWorkflowsDisabledParams` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: Optional[str]` Human-readable name. Must be non-empty. Omit to preserve. Cannot be cleared. maxLength: 256 - `skills: Optional[Iterable[BetaManagedAgentsSkillParams]]` Skills. Full replacement. Omit to preserve; send empty array or null to clear. - `class BetaManagedAgentsAnthropicSkillParams` An Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` Identifier of the Anthropic skill (e.g., "xlsx"). minLength: 1, maxLength: 64 - `version: Optional[str]` Version to pin. Defaults to latest if omitted. minLength: 1, maxLength: 64 - `class BetaManagedAgentsCustomSkillParams` A user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` Tagged ID of the custom skill (e.g., "skill_01XJ5..."). minLength: 1, maxLength: 64 - `version: Optional[str]` Version to pin. Defaults to latest if omitted. minLength: 1, maxLength: 64 - `system: Optional[str]` System prompt. Omit to preserve; send empty string or null to clear. maxLength: 100000 - `tools: Optional[Iterable[Tool]]` Tool configurations available to the agent. Full replacement. Omit to preserve; send empty array or null to clear. Maximum of 256 tools across all toolsets allowed. - `class BetaManagedAgentsAgentToolset20260401Params` Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent. - `type: Literal["agent_toolset_20260401"]` - `configs: Optional[List[BetaManagedAgentsAgentToolConfigParams]]` Per-tool configuration overrides. - `class BetaManagedAgentsBashToolConfigParams` Configuration override for the bash tool. - `type: Optional[Literal["bash"]]` - `name: Literal["bash"]` Must be "bash". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfigParams` Configuration override for the edit tool. - `type: Optional[Literal["edit"]]` - `name: Literal["edit"]` Must be "edit". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfigParams` Configuration override for the read tool. - `type: Optional[Literal["read"]]` - `name: Literal["read"]` Must be "read". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfigParams` Configuration override for the write tool. - `type: Optional[Literal["write"]]` - `name: Literal["write"]` Must be "write". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfigParams` Configuration override for the glob tool. - `type: Optional[Literal["glob"]]` - `name: Literal["glob"]` Must be "glob". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfigParams` Configuration override for the grep tool. - `type: Optional[Literal["grep"]]` - `name: Literal["grep"]` Must be "grep". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfigParams` Configuration override for the web_fetch tool. - `type: Optional[Literal["web_fetch"]]` - `name: Literal["web_fetch"]` Must be "web_fetch". - `allowed_domains: Optional[List[str]]` Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: Optional[List[str]]` Never fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `max_content_tokens: Optional[int]` Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs. format: int32 - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSourcesParams]` Which sources contribute URLs the tool may fetch. Omit to allow every source. - `client_tool_results: Optional[Union[BetaManagedAgentsWebFetchURLSourceShorthand, BetaManagedAgentsWebFetchURLSourceToolFilter, null]]` Which custom tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be a custom tool in the same tools array. - `Literal["all", "none"]` - `"all"` - `"none"` - `type BetaManagedAgentsWebFetchURLSourceToolFilter = ...` Which tools' results contribute URLs that may be fetched. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[Union[BetaManagedAgentsWebFetchURLSourceShorthand, BetaManagedAgentsWebFetchURLSourceToolFilter, null]]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be "web_search" or "web_fetch". - `user_input: Optional[Union[BetaManagedAgentsWebFetchURLSourceShorthand, BetaManagedAgentsWebFetchURLSourceUserInput, null]]` Whether URLs in the text of user messages may be fetched: "all" (the default) or "none". - `Literal["all", "none"]` - `"all"` - `"none"` - `type BetaManagedAgentsWebFetchURLSourceUserInput = ...` Whether URLs in the text of user messages may be fetched. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `class BetaManagedAgentsWebSearchToolConfigParams` Configuration override for the web_search tool. - `type: Optional[Literal["web_search"]]` - `name: Literal["web_search"]` Must be "web_search". - `allowed_domains: Optional[List[str]]` Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: Optional[List[str]]` Never return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: Optional[BetaManagedAgentsAgentToolsetDefaultConfigParams]` Default configuration applied to all tools in this set. - `enabled: Optional[bool]` Whether tools are enabled and available to Claude by default. Defaults to true if not specified. - `permission_policy: Optional[PermissionPolicy]` Default permission policy for tools. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolsetParams` Configuration for tools from an MCP server defined in `mcp_servers`. - `type: Literal["mcp_toolset"]` - `mcp_server_name: str` Name of the MCP server. Must match a server name from the mcp_servers array. 1-255 characters. minLength: 1, maxLength: 255 - `configs: Optional[List[BetaManagedAgentsMCPToolConfigParams]]` Per-tool configuration overrides. - `name: str` Name of the MCP tool to configure. 1-128 characters. minLength: 1, maxLength: 128 - `enabled: Optional[bool]` Whether this tool is enabled. Overrides the `default_config` setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Overrides the `default_config` setting. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: Optional[BetaManagedAgentsMCPToolsetDefaultConfigParams]` Default configuration for all tools from this server. - `enabled: Optional[bool]` Whether tools are enabled by default. Defaults to true if not specified. - `permission_policy: Optional[PermissionPolicy]` Default permission policy for tools from this server. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsCustomToolParams` A custom tool that is executed by the API client rather than the agent. When the agent calls this tool, an `agent.custom_tool_use` event is emitted and the session goes idle, waiting for the client to provide the result via a `user.custom_tool_result` event. - `type: Literal["custom"]` - `description: str` Description of what the tool does, shown to the agent to help it decide when to use the tool. minLength: 1 - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema defining the expected input parameters for the tool. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` Unique name for the tool. 1-128 characters; letters, digits, underscores, and hyphens. minLength: 1, maxLength: 128 - `version: Optional[int]` The agent's current version, used to prevent concurrent overwrites. Obtain this value from a create or retrieve response. Must be at least 1 if specified. When supplied, the request fails if it does not match the server's current version; omit to apply the update unconditionally. format: int32 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsAgent` A Managed Agents `agent`. - `type: Literal["agent"]` - `id: str` - `archived_at: Optional[datetime]` When the agent was archived. Null if not archived. format: date-time - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `metadata: Dict[str, str]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsMultiagent]` Multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsMultiagentCoordinator` Resolved coordinator topology with a concrete agent roster. - `type: Literal["coordinator"]` - `agents: List[Agent]` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `class BetaManagedAgentsAgentReference` A resolved agent reference with a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagent20261001` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsAgentReference]` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsAgentReference]` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `version: int` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_agent = client.beta.agents.update( agent_id="agent_011CZkYpogX7uDKUyvBTophP", description="updated", ) print(beta_managed_agents_agent.id) ``` ##### Response (200) ```json { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "advisor": { "type": "disabled" }, "subagents": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" }, "type": "multiagent_20261001", "workflows": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" } }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ``` ### Archive Agent `beta.agents.archive(agent_id, **kwargs) -> BetaManagedAgentsAgent` **POST** `/v1/agents/{agent_id}/archive` Archive Agent #### Parameters - `agent_id: str` (path parameter) Unique identifier of the agent to archive. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsAgent` A Managed Agents `agent`. - `type: Literal["agent"]` - `id: str` - `archived_at: Optional[datetime]` When the agent was archived. Null if not archived. format: date-time - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `metadata: Dict[str, str]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsMultiagent]` Multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsMultiagentCoordinator` Resolved coordinator topology with a concrete agent roster. - `type: Literal["coordinator"]` - `agents: List[Agent]` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `class BetaManagedAgentsAgentReference` A resolved agent reference with a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagent20261001` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsAgentReference]` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsAgentReference]` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `version: int` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_agent = client.beta.agents.archive( agent_id="agent_011CZkYpogX7uDKUyvBTophP", ) print(beta_managed_agents_agent.id) ``` ##### Response (200) ```json { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "advisor": { "type": "disabled" }, "subagents": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" }, "type": "multiagent_20261001", "workflows": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" } }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ``` ## Beta › Agents › Versions ### List Agent Versions `beta.agents.versions.list(agent_id, **kwargs) -> SyncPageCursor[BetaManagedAgentsAgent]` **GET** `/v1/agents/{agent_id}/versions` List Agent Versions #### Parameters - `agent_id: str` (path parameter) Agent ID to list versions for. - `limit: Optional[int]` (query parameter) Maximum results per page. Default 20, maximum 100. format: int32 - `page: Optional[str]` (query parameter) Opaque pagination cursor. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsAgent` A Managed Agents `agent`. - `type: Literal["agent"]` - `id: str` - `archived_at: Optional[datetime]` When the agent was archived. Null if not archived. format: date-time - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `metadata: Dict[str, str]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsMultiagent]` Multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsMultiagentCoordinator` Resolved coordinator topology with a concrete agent roster. - `type: Literal["coordinator"]` - `agents: List[Agent]` Agents the coordinator may spawn as session threads, each resolved to a specific version. - `class BetaManagedAgentsAgentReference` A resolved agent reference with a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagent20261001` Resolved multiagent configuration with three members, each enabled or disabled on its own. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsAgentReference]` Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsAgentReference]` Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `version: int` The agent's current version. Starts at 1 and increments when the agent is modified. format: int32 #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.agents.versions.list( agent_id="agent_011CZkYpogX7uDKUyvBTophP", ) page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "agent_011CZkYpogX7uDKUyvBTophP", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "A general-purpose starter agent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "metadata": { "foo": "bar" }, "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "advisor": { "type": "disabled" }, "subagents": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" }, "type": "multiagent_20261001", "workflows": { "inline_agents": { "type": "enabled" }, "predefined_agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 } ], "type": "enabled" } }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "updated_at": "2026-03-15T10:00:00Z", "version": 1 } ], "next_page": "next_page" } ``` ## Beta › Environments ### Create Environment `beta.environments.create(**kwargs) -> BetaEnvironment` **POST** `/v1/environments` Create a new environment with the specified configuration. #### Parameters - `name: str` Human-readable name for the environment minLength: 1, maxLength: 256 - `config: Optional[Config]` Environment configuration - `class BetaCloudConfigParams` Request params for `cloud` environment configuration. Fields default to null; on update, omitted fields preserve the existing value. - `type: Literal["cloud"]` Environment type - `networking: Optional[Networking]` Network configuration policy. Omit on update to preserve the existing value. - `class BetaUnrestrictedNetwork` Unrestricted network access. - `type: Literal["unrestricted"]` Network policy type - `class BetaLimitedNetworkParams` Limited network request params. Fields default to null; on update, omitted fields preserve the existing value. - `type: Literal["limited"]` Network policy type - `allow_mcp_servers: Optional[bool]` Permits outbound access to MCP server endpoints configured on the agent, beyond those listed in the `allowed_hosts` array. Defaults to `false`. - `allow_package_managers: Optional[bool]` Permits outbound access to public package registries (PyPI, npm, etc.) beyond those listed in the `allowed_hosts` array. Defaults to `false` on creation. Must be `true` when `packages` are specified. - `allowed_hosts: Optional[List[str]]` Specifies domains the container can reach. - `packages: Optional[BetaPackagesParams]` Package manager configuration. Under `limited` networking, requires `networking.allow_package_managers` to be `true`. Omit on update to preserve the existing value. - `type: Optional[Literal["packages"]]` Package configuration type default: packages - `apt: Optional[List[str]]` Ubuntu/Debian packages to install - `cargo: Optional[List[str]]` Rust packages to install - `gem: Optional[List[str]]` Ruby packages to install - `go: Optional[List[str]]` Go packages to install - `npm: Optional[List[str]]` Node.js packages to install - `pip: Optional[List[str]]` Python packages to install - `class BetaSelfHostedConfigParams` Request params for `self_hosted` environment configuration. - `type: Literal["self_hosted"]` Environment type - `description: Optional[str]` Optional description of the environment maxLength: 1024 - `metadata: Optional[Dict[str, str]]` User-provided metadata key-value pairs - `scope: Optional[Literal["organization", "account"]]` The visibility scope for this environment. 'organization' makes the environment visible to all accounts. 'account' restricts visibility to the owning account only. API organizations support only 'organization'; 'account' is rejected. If not specified, defaults based on organization type. - `"organization"` - `"account"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaEnvironment` Unified Environment resource for both cloud and self-hosted environments. - `type: Literal["environment"]` The type of object (always 'environment') default: environment - `id: str` Environment identifier (e.g., 'env_...') - `archived_at: Optional[str]` RFC 3339 timestamp when environment was archived, or null if not archived - `config: Config` Environment configuration (either Anthropic Cloud or self-hosted) - `class BetaCloudConfig` `cloud` environment configuration. - `type: Literal["cloud"]` Environment type - `networking: Networking` Network configuration policy. - `class BetaUnrestrictedNetwork` Unrestricted network access. - `type: Literal["unrestricted"]` Network policy type - `class BetaLimitedNetwork` Limited network access. - `type: Literal["limited"]` Network policy type - `allow_mcp_servers: bool` Permits outbound access to MCP server endpoints configured on the agent, beyond those listed in the `allowed_hosts` array. - `allow_package_managers: bool` Permits outbound access to public package registries (PyPI, npm, etc.) beyond those listed in the `allowed_hosts` array. - `allowed_hosts: List[str]` Specifies domains the container can reach. - `packages: BetaPackages` Package manager configuration. - `type: Optional[Literal["packages"]]` Package configuration type default: packages - `apt: List[str]` Ubuntu/Debian packages to install - `cargo: List[str]` Rust packages to install - `gem: List[str]` Ruby packages to install - `go: List[str]` Go packages to install - `npm: List[str]` Node.js packages to install - `pip: List[str]` Python packages to install - `class BetaSelfHostedConfig` Configuration for self-hosted environments. - `type: Literal["self_hosted"]` Environment type - `created_at: str` RFC 3339 timestamp when environment was created - `description: Optional[str]` User-provided description for the environment; null when unset - `metadata: Dict[str, str]` User-provided metadata key-value pairs - `name: str` Human-readable name for the environment - `updated_at: str` RFC 3339 timestamp when environment was last updated - `scope: Optional[Literal["organization", "account"]]` The visibility scope for this environment. 'organization' means visible to all accounts. 'account' means visible only to the owning account. - `"organization"` - `"account"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_environment = client.beta.environments.create( name="python-data-analysis", ) print(beta_environment.id) ``` ##### Response (200) ```json { "id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "archived_at": null, "config": { "networking": { "allow_mcp_servers": false, "allow_package_managers": true, "allowed_hosts": [ "api.example.com" ], "type": "limited" }, "packages": { "apt": [ "string" ], "cargo": [ "string" ], "gem": [ "string" ], "go": [ "string" ], "npm": [ "string" ], "pip": [ "pandas", "numpy" ], "type": "packages" }, "type": "cloud" }, "created_at": "2026-03-15T10:00:00Z", "description": "Python environment with data-analysis packages.", "metadata": {}, "name": "python-data-analysis", "type": "environment", "updated_at": "2026-03-15T10:00:00Z", "scope": "organization" } ``` ### List Environments `beta.environments.list(**kwargs) -> SyncPageCursor[BetaEnvironment]` **GET** `/v1/environments` List environments with pagination support. #### Parameters - `include_archived: Optional[bool]` (query parameter) Include archived environments in the response default: false - `limit: Optional[int]` (query parameter) Maximum number of environments to return default: 20, minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Opaque cursor from previous response for pagination. Pass the `next_page` value from the previous response. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaEnvironment` Unified Environment resource for both cloud and self-hosted environments. - `type: Literal["environment"]` The type of object (always 'environment') default: environment - `id: str` Environment identifier (e.g., 'env_...') - `archived_at: Optional[str]` RFC 3339 timestamp when environment was archived, or null if not archived - `config: Config` Environment configuration (either Anthropic Cloud or self-hosted) - `class BetaCloudConfig` `cloud` environment configuration. - `type: Literal["cloud"]` Environment type - `networking: Networking` Network configuration policy. - `class BetaUnrestrictedNetwork` Unrestricted network access. - `type: Literal["unrestricted"]` Network policy type - `class BetaLimitedNetwork` Limited network access. - `type: Literal["limited"]` Network policy type - `allow_mcp_servers: bool` Permits outbound access to MCP server endpoints configured on the agent, beyond those listed in the `allowed_hosts` array. - `allow_package_managers: bool` Permits outbound access to public package registries (PyPI, npm, etc.) beyond those listed in the `allowed_hosts` array. - `allowed_hosts: List[str]` Specifies domains the container can reach. - `packages: BetaPackages` Package manager configuration. - `type: Optional[Literal["packages"]]` Package configuration type default: packages - `apt: List[str]` Ubuntu/Debian packages to install - `cargo: List[str]` Rust packages to install - `gem: List[str]` Ruby packages to install - `go: List[str]` Go packages to install - `npm: List[str]` Node.js packages to install - `pip: List[str]` Python packages to install - `class BetaSelfHostedConfig` Configuration for self-hosted environments. - `type: Literal["self_hosted"]` Environment type - `created_at: str` RFC 3339 timestamp when environment was created - `description: Optional[str]` User-provided description for the environment; null when unset - `metadata: Dict[str, str]` User-provided metadata key-value pairs - `name: str` Human-readable name for the environment - `updated_at: str` RFC 3339 timestamp when environment was last updated - `scope: Optional[Literal["organization", "account"]]` The visibility scope for this environment. 'organization' means visible to all accounts. 'account' means visible only to the owning account. - `"organization"` - `"account"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.environments.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "archived_at": null, "config": { "networking": { "allow_mcp_servers": false, "allow_package_managers": true, "allowed_hosts": [ "api.example.com" ], "type": "limited" }, "packages": { "apt": [ "string" ], "cargo": [ "string" ], "gem": [ "string" ], "go": [ "string" ], "npm": [ "string" ], "pip": [ "pandas", "numpy" ], "type": "packages" }, "type": "cloud" }, "created_at": "2026-03-15T10:00:00Z", "description": "Python environment with data-analysis packages.", "metadata": {}, "name": "python-data-analysis", "type": "environment", "updated_at": "2026-03-15T10:00:00Z", "scope": "organization" } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=" } ``` ### Get Environment `beta.environments.retrieve(environment_id, **kwargs) -> BetaEnvironment` **GET** `/v1/environments/{environment_id}` Retrieve a specific environment by ID. #### Parameters - `environment_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaEnvironment` Unified Environment resource for both cloud and self-hosted environments. - `type: Literal["environment"]` The type of object (always 'environment') default: environment - `id: str` Environment identifier (e.g., 'env_...') - `archived_at: Optional[str]` RFC 3339 timestamp when environment was archived, or null if not archived - `config: Config` Environment configuration (either Anthropic Cloud or self-hosted) - `class BetaCloudConfig` `cloud` environment configuration. - `type: Literal["cloud"]` Environment type - `networking: Networking` Network configuration policy. - `class BetaUnrestrictedNetwork` Unrestricted network access. - `type: Literal["unrestricted"]` Network policy type - `class BetaLimitedNetwork` Limited network access. - `type: Literal["limited"]` Network policy type - `allow_mcp_servers: bool` Permits outbound access to MCP server endpoints configured on the agent, beyond those listed in the `allowed_hosts` array. - `allow_package_managers: bool` Permits outbound access to public package registries (PyPI, npm, etc.) beyond those listed in the `allowed_hosts` array. - `allowed_hosts: List[str]` Specifies domains the container can reach. - `packages: BetaPackages` Package manager configuration. - `type: Optional[Literal["packages"]]` Package configuration type default: packages - `apt: List[str]` Ubuntu/Debian packages to install - `cargo: List[str]` Rust packages to install - `gem: List[str]` Ruby packages to install - `go: List[str]` Go packages to install - `npm: List[str]` Node.js packages to install - `pip: List[str]` Python packages to install - `class BetaSelfHostedConfig` Configuration for self-hosted environments. - `type: Literal["self_hosted"]` Environment type - `created_at: str` RFC 3339 timestamp when environment was created - `description: Optional[str]` User-provided description for the environment; null when unset - `metadata: Dict[str, str]` User-provided metadata key-value pairs - `name: str` Human-readable name for the environment - `updated_at: str` RFC 3339 timestamp when environment was last updated - `scope: Optional[Literal["organization", "account"]]` The visibility scope for this environment. 'organization' means visible to all accounts. 'account' means visible only to the owning account. - `"organization"` - `"account"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_environment = client.beta.environments.retrieve( environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", ) print(beta_environment.id) ``` ##### Response (200) ```json { "id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "archived_at": null, "config": { "networking": { "allow_mcp_servers": false, "allow_package_managers": true, "allowed_hosts": [ "api.example.com" ], "type": "limited" }, "packages": { "apt": [ "string" ], "cargo": [ "string" ], "gem": [ "string" ], "go": [ "string" ], "npm": [ "string" ], "pip": [ "pandas", "numpy" ], "type": "packages" }, "type": "cloud" }, "created_at": "2026-03-15T10:00:00Z", "description": "Python environment with data-analysis packages.", "metadata": {}, "name": "python-data-analysis", "type": "environment", "updated_at": "2026-03-15T10:00:00Z", "scope": "organization" } ``` ### Update Environment `beta.environments.update(environment_id, **kwargs) -> BetaEnvironment` **POST** `/v1/environments/{environment_id}` Update an existing environment's configuration. #### Parameters - `environment_id: str` (path parameter) - `config: Optional[Config]` Updated environment configuration - `class BetaCloudConfigParams` Request params for `cloud` environment configuration. Fields default to null; on update, omitted fields preserve the existing value. - `type: Literal["cloud"]` Environment type - `networking: Optional[Networking]` Network configuration policy. Omit on update to preserve the existing value. - `class BetaUnrestrictedNetwork` Unrestricted network access. - `type: Literal["unrestricted"]` Network policy type - `class BetaLimitedNetworkParams` Limited network request params. Fields default to null; on update, omitted fields preserve the existing value. - `type: Literal["limited"]` Network policy type - `allow_mcp_servers: Optional[bool]` Permits outbound access to MCP server endpoints configured on the agent, beyond those listed in the `allowed_hosts` array. Defaults to `false`. - `allow_package_managers: Optional[bool]` Permits outbound access to public package registries (PyPI, npm, etc.) beyond those listed in the `allowed_hosts` array. Defaults to `false` on creation. Must be `true` when `packages` are specified. - `allowed_hosts: Optional[List[str]]` Specifies domains the container can reach. - `packages: Optional[BetaPackagesParams]` Package manager configuration. Under `limited` networking, requires `networking.allow_package_managers` to be `true`. Omit on update to preserve the existing value. - `type: Optional[Literal["packages"]]` Package configuration type default: packages - `apt: Optional[List[str]]` Ubuntu/Debian packages to install - `cargo: Optional[List[str]]` Rust packages to install - `gem: Optional[List[str]]` Ruby packages to install - `go: Optional[List[str]]` Go packages to install - `npm: Optional[List[str]]` Node.js packages to install - `pip: Optional[List[str]]` Python packages to install - `class BetaSelfHostedConfigParams` Request params for `self_hosted` environment configuration. - `type: Literal["self_hosted"]` Environment type - `description: Optional[str]` Updated description of the environment. Omit to preserve; null clears to null; an empty string is stored as an empty string. maxLength: 1024 - `metadata: Optional[Dict[str, Optional[str]]]` User-provided metadata key-value pairs. Set a value to null or empty string to delete the key. - `name: Optional[str]` Updated name for the environment minLength: 1, maxLength: 256 - `scope: Optional[Literal["organization", "account"]]` The visibility scope for this environment. 'organization' makes the environment visible to all accounts. 'account' restricts visibility to the owning account only. - `"organization"` - `"account"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaEnvironment` Unified Environment resource for both cloud and self-hosted environments. - `type: Literal["environment"]` The type of object (always 'environment') default: environment - `id: str` Environment identifier (e.g., 'env_...') - `archived_at: Optional[str]` RFC 3339 timestamp when environment was archived, or null if not archived - `config: Config` Environment configuration (either Anthropic Cloud or self-hosted) - `class BetaCloudConfig` `cloud` environment configuration. - `type: Literal["cloud"]` Environment type - `networking: Networking` Network configuration policy. - `class BetaUnrestrictedNetwork` Unrestricted network access. - `type: Literal["unrestricted"]` Network policy type - `class BetaLimitedNetwork` Limited network access. - `type: Literal["limited"]` Network policy type - `allow_mcp_servers: bool` Permits outbound access to MCP server endpoints configured on the agent, beyond those listed in the `allowed_hosts` array. - `allow_package_managers: bool` Permits outbound access to public package registries (PyPI, npm, etc.) beyond those listed in the `allowed_hosts` array. - `allowed_hosts: List[str]` Specifies domains the container can reach. - `packages: BetaPackages` Package manager configuration. - `type: Optional[Literal["packages"]]` Package configuration type default: packages - `apt: List[str]` Ubuntu/Debian packages to install - `cargo: List[str]` Rust packages to install - `gem: List[str]` Ruby packages to install - `go: List[str]` Go packages to install - `npm: List[str]` Node.js packages to install - `pip: List[str]` Python packages to install - `class BetaSelfHostedConfig` Configuration for self-hosted environments. - `type: Literal["self_hosted"]` Environment type - `created_at: str` RFC 3339 timestamp when environment was created - `description: Optional[str]` User-provided description for the environment; null when unset - `metadata: Dict[str, str]` User-provided metadata key-value pairs - `name: str` Human-readable name for the environment - `updated_at: str` RFC 3339 timestamp when environment was last updated - `scope: Optional[Literal["organization", "account"]]` The visibility scope for this environment. 'organization' means visible to all accounts. 'account' means visible only to the owning account. - `"organization"` - `"account"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_environment = client.beta.environments.update( environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", ) print(beta_environment.id) ``` ##### Response (200) ```json { "id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "archived_at": null, "config": { "networking": { "allow_mcp_servers": false, "allow_package_managers": true, "allowed_hosts": [ "api.example.com" ], "type": "limited" }, "packages": { "apt": [ "string" ], "cargo": [ "string" ], "gem": [ "string" ], "go": [ "string" ], "npm": [ "string" ], "pip": [ "pandas", "numpy" ], "type": "packages" }, "type": "cloud" }, "created_at": "2026-03-15T10:00:00Z", "description": "Python environment with data-analysis packages.", "metadata": {}, "name": "python-data-analysis", "type": "environment", "updated_at": "2026-03-15T10:00:00Z", "scope": "organization" } ``` ### Delete Environment `beta.environments.delete(environment_id, **kwargs) -> BetaEnvironmentDeleteResponse` **DELETE** `/v1/environments/{environment_id}` Delete an environment by ID. Returns a confirmation of the deletion. #### Parameters - `environment_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaEnvironmentDeleteResponse` Response after deleting an environment. - `type: Literal["environment_deleted"]` The type of response default: environment_deleted - `id: str` Environment identifier #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_environment_delete_response = client.beta.environments.delete( environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", ) print(beta_environment_delete_response.id) ``` ##### Response (200) ```json { "id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "type": "environment_deleted" } ``` ### Archive Environment `beta.environments.archive(environment_id, **kwargs) -> BetaEnvironment` **POST** `/v1/environments/{environment_id}/archive` Archive an environment by ID. Archived environments cannot be used to create new sessions. #### Parameters - `environment_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaEnvironment` Unified Environment resource for both cloud and self-hosted environments. - `type: Literal["environment"]` The type of object (always 'environment') default: environment - `id: str` Environment identifier (e.g., 'env_...') - `archived_at: Optional[str]` RFC 3339 timestamp when environment was archived, or null if not archived - `config: Config` Environment configuration (either Anthropic Cloud or self-hosted) - `class BetaCloudConfig` `cloud` environment configuration. - `type: Literal["cloud"]` Environment type - `networking: Networking` Network configuration policy. - `class BetaUnrestrictedNetwork` Unrestricted network access. - `type: Literal["unrestricted"]` Network policy type - `class BetaLimitedNetwork` Limited network access. - `type: Literal["limited"]` Network policy type - `allow_mcp_servers: bool` Permits outbound access to MCP server endpoints configured on the agent, beyond those listed in the `allowed_hosts` array. - `allow_package_managers: bool` Permits outbound access to public package registries (PyPI, npm, etc.) beyond those listed in the `allowed_hosts` array. - `allowed_hosts: List[str]` Specifies domains the container can reach. - `packages: BetaPackages` Package manager configuration. - `type: Optional[Literal["packages"]]` Package configuration type default: packages - `apt: List[str]` Ubuntu/Debian packages to install - `cargo: List[str]` Rust packages to install - `gem: List[str]` Ruby packages to install - `go: List[str]` Go packages to install - `npm: List[str]` Node.js packages to install - `pip: List[str]` Python packages to install - `class BetaSelfHostedConfig` Configuration for self-hosted environments. - `type: Literal["self_hosted"]` Environment type - `created_at: str` RFC 3339 timestamp when environment was created - `description: Optional[str]` User-provided description for the environment; null when unset - `metadata: Dict[str, str]` User-provided metadata key-value pairs - `name: str` Human-readable name for the environment - `updated_at: str` RFC 3339 timestamp when environment was last updated - `scope: Optional[Literal["organization", "account"]]` The visibility scope for this environment. 'organization' means visible to all accounts. 'account' means visible only to the owning account. - `"organization"` - `"account"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_environment = client.beta.environments.archive( environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", ) print(beta_environment.id) ``` ##### Response (200) ```json { "id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "archived_at": null, "config": { "networking": { "allow_mcp_servers": false, "allow_package_managers": true, "allowed_hosts": [ "api.example.com" ], "type": "limited" }, "packages": { "apt": [ "string" ], "cargo": [ "string" ], "gem": [ "string" ], "go": [ "string" ], "npm": [ "string" ], "pip": [ "pandas", "numpy" ], "type": "packages" }, "type": "cloud" }, "created_at": "2026-03-15T10:00:00Z", "description": "Python environment with data-analysis packages.", "metadata": {}, "name": "python-data-analysis", "type": "environment", "updated_at": "2026-03-15T10:00:00Z", "scope": "organization" } ``` ## Beta › Environments › Work ### Get Work Item `beta.environments.work.retrieve(work_id, **kwargs) -> BetaSelfHostedWork` **GET** `/v1/environments/{environment_id}/work/{work_id}` Note: these endpoints are called automatically by the pre-built environment worker provided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Retrieve detailed information about a specific work item. #### Parameters - `environment_id: str` (path parameter) - `work_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaSelfHostedWork` Work resource representing a unit of work in a self-hosted environment. Work items are queued when sessions are created or when long-dormant sessions receive new messages. The environment worker polls for work to execute in a self-hosted sandbox. - `type: Literal["work"]` The type of object (always 'work') default: work - `id: str` Work identifier (e.g., 'work_...') - `acknowledged_at: Optional[str]` RFC 3339 timestamp when the work item was acknowledged and assigned to a self-hosted sandbox - `created_at: str` RFC 3339 timestamp when work was created - `data: BetaSessionWorkData` The actual work to be performed - `type: Literal["session"]` Type of work data - `id: str` Session identifier (e.g., 'session_...') - `environment_id: str` Environment identifier this work belongs to (e.g., `env_...`) - `latest_heartbeat_at: Optional[str]` RFC 3339 timestamp of the most recent heartbeat - `metadata: Dict[str, str]` User-provided metadata key-value pairs associated with this work item - `secret: Optional[str]` Credential payload used by the environment worker to execute this work item. May be populated when polling for work; null on all other retrieval paths. - `started_at: Optional[str]` RFC 3339 timestamp when work execution started - `state: Literal["queued", "starting", "active", 2 more]` Current state of the work item - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: Optional[str]` RFC 3339 timestamp when stop was requested - `stopped_at: Optional[str]` RFC 3339 timestamp when work execution stopped #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_self_hosted_work = client.beta.environments.work.retrieve( work_id="work_id", environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", ) print(beta_self_hosted_work.id) ``` ##### Response (200) ```json { "id": "id", "acknowledged_at": "acknowledged_at", "created_at": "created_at", "data": { "id": "id", "type": "session" }, "environment_id": "environment_id", "latest_heartbeat_at": "latest_heartbeat_at", "metadata": { "foo": "string" }, "secret": "secret", "started_at": "started_at", "state": "queued", "stop_requested_at": "stop_requested_at", "stopped_at": "stopped_at", "type": "work" } ``` ### Poll for Work `beta.environments.work.poll(environment_id, **kwargs) -> BetaSelfHostedWork` **GET** `/v1/environments/{environment_id}/work/poll` Note: these endpoints are called automatically by the pre-built environment worker provided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Long poll for work items in the queue. #### Parameters - `environment_id: str` (path parameter) - `block_ms: Optional[int]` (query parameter) How long to wait for work to arrive before returning. Must be 1-999 in milliseconds. Defaults to non-blocking (returns immediately if no work is available). minimum: 1 - `reclaim_older_than_ms: Optional[int]` (query parameter) Reclaim unacknowledged work items older than this many milliseconds. If omitted, uses the default (5000ms). minimum: 1 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `anthropic_worker_id: Optional[str]` (header parameter) Unique identifier for the specific worker polling, used to track aggregated environment-level work metrics in Console #### Returns - `class BetaSelfHostedWork` Work resource representing a unit of work in a self-hosted environment. Work items are queued when sessions are created or when long-dormant sessions receive new messages. The environment worker polls for work to execute in a self-hosted sandbox. - `type: Literal["work"]` The type of object (always 'work') default: work - `id: str` Work identifier (e.g., 'work_...') - `acknowledged_at: Optional[str]` RFC 3339 timestamp when the work item was acknowledged and assigned to a self-hosted sandbox - `created_at: str` RFC 3339 timestamp when work was created - `data: BetaSessionWorkData` The actual work to be performed - `type: Literal["session"]` Type of work data - `id: str` Session identifier (e.g., 'session_...') - `environment_id: str` Environment identifier this work belongs to (e.g., `env_...`) - `latest_heartbeat_at: Optional[str]` RFC 3339 timestamp of the most recent heartbeat - `metadata: Dict[str, str]` User-provided metadata key-value pairs associated with this work item - `secret: Optional[str]` Credential payload used by the environment worker to execute this work item. May be populated when polling for work; null on all other retrieval paths. - `started_at: Optional[str]` RFC 3339 timestamp when work execution started - `state: Literal["queued", "starting", "active", 2 more]` Current state of the work item - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: Optional[str]` RFC 3339 timestamp when stop was requested - `stopped_at: Optional[str]` RFC 3339 timestamp when work execution stopped #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_self_hosted_work = client.beta.environments.work.poll( environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", ) print(beta_self_hosted_work.id) ``` ##### Response (200) ```json { "id": "id", "acknowledged_at": "acknowledged_at", "created_at": "created_at", "data": { "id": "id", "type": "session" }, "environment_id": "environment_id", "latest_heartbeat_at": "latest_heartbeat_at", "metadata": { "foo": "string" }, "secret": "secret", "started_at": "started_at", "state": "queued", "stop_requested_at": "stop_requested_at", "stopped_at": "stopped_at", "type": "work" } ``` ### Acknowledge Work `beta.environments.work.ack(work_id, **kwargs) -> BetaSelfHostedWork` **POST** `/v1/environments/{environment_id}/work/{work_id}/ack` Note: these endpoints are called automatically by the pre-built environment worker provided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Acknowledge receipt of a work item, transitioning it from 'queued' to 'starting' and removing it from the queue. #### Parameters - `environment_id: str` (path parameter) - `work_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaSelfHostedWork` Work resource representing a unit of work in a self-hosted environment. Work items are queued when sessions are created or when long-dormant sessions receive new messages. The environment worker polls for work to execute in a self-hosted sandbox. - `type: Literal["work"]` The type of object (always 'work') default: work - `id: str` Work identifier (e.g., 'work_...') - `acknowledged_at: Optional[str]` RFC 3339 timestamp when the work item was acknowledged and assigned to a self-hosted sandbox - `created_at: str` RFC 3339 timestamp when work was created - `data: BetaSessionWorkData` The actual work to be performed - `type: Literal["session"]` Type of work data - `id: str` Session identifier (e.g., 'session_...') - `environment_id: str` Environment identifier this work belongs to (e.g., `env_...`) - `latest_heartbeat_at: Optional[str]` RFC 3339 timestamp of the most recent heartbeat - `metadata: Dict[str, str]` User-provided metadata key-value pairs associated with this work item - `secret: Optional[str]` Credential payload used by the environment worker to execute this work item. May be populated when polling for work; null on all other retrieval paths. - `started_at: Optional[str]` RFC 3339 timestamp when work execution started - `state: Literal["queued", "starting", "active", 2 more]` Current state of the work item - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: Optional[str]` RFC 3339 timestamp when stop was requested - `stopped_at: Optional[str]` RFC 3339 timestamp when work execution stopped #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_self_hosted_work = client.beta.environments.work.ack( work_id="work_id", environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", ) print(beta_self_hosted_work.id) ``` ##### Response (200) ```json { "id": "id", "acknowledged_at": "acknowledged_at", "created_at": "created_at", "data": { "id": "id", "type": "session" }, "environment_id": "environment_id", "latest_heartbeat_at": "latest_heartbeat_at", "metadata": { "foo": "string" }, "secret": "secret", "started_at": "started_at", "state": "queued", "stop_requested_at": "stop_requested_at", "stopped_at": "stopped_at", "type": "work" } ``` ### Record Heartbeat `beta.environments.work.heartbeat(work_id, **kwargs) -> BetaSelfHostedWorkHeartbeatResponse` **POST** `/v1/environments/{environment_id}/work/{work_id}/heartbeat` Note: these endpoints are called automatically by the pre-built environment worker provided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Record a heartbeat for a work item to maintain the lease. #### Parameters - `environment_id: str` (path parameter) - `work_id: str` (path parameter) - `desired_ttl_seconds: Optional[int]` (query parameter) Desired TTL in seconds - `expected_last_heartbeat: Optional[str]` (query parameter) Expected last_heartbeat for conditional update (optimistic concurrency). Use literal 'NO_HEARTBEAT' to claim an unclaimed lease (first heartbeat). For subsequent heartbeats, echo the server's previous last_heartbeat value exactly. Returns 412 Precondition Failed if the actual value doesn't match. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaSelfHostedWorkHeartbeatResponse` Response after recording a heartbeat for a work item. - `type: Literal["work_heartbeat"]` The type of response default: work_heartbeat - `last_heartbeat: str` RFC 3339 timestamp of the actual heartbeat from DB - `lease_extended: bool` Whether the heartbeat succeeded in extending the lease - `state: Literal["queued", "starting", "active", 2 more]` Current state of the work item (active/stopping/stopped) - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `ttl_seconds: int` Effective TTL applied to the lease #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_self_hosted_work_heartbeat_response = client.beta.environments.work.heartbeat( work_id="work_id", environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", ) print(beta_self_hosted_work_heartbeat_response.last_heartbeat) ``` ##### Response (200) ```json { "last_heartbeat": "last_heartbeat", "lease_extended": true, "state": "queued", "ttl_seconds": 0, "type": "work_heartbeat" } ``` ### Stop Work `beta.environments.work.stop(work_id, **kwargs) -> BetaSelfHostedWork` **POST** `/v1/environments/{environment_id}/work/{work_id}/stop` Note: these endpoints are called automatically by the pre-built environment worker provided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Stop a work item, initiating graceful or forced shutdown. #### Parameters - `environment_id: str` (path parameter) - `work_id: str` (path parameter) - `force: Optional[bool]` If true, immediately stop work without graceful shutdown default: false - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaSelfHostedWork` Work resource representing a unit of work in a self-hosted environment. Work items are queued when sessions are created or when long-dormant sessions receive new messages. The environment worker polls for work to execute in a self-hosted sandbox. - `type: Literal["work"]` The type of object (always 'work') default: work - `id: str` Work identifier (e.g., 'work_...') - `acknowledged_at: Optional[str]` RFC 3339 timestamp when the work item was acknowledged and assigned to a self-hosted sandbox - `created_at: str` RFC 3339 timestamp when work was created - `data: BetaSessionWorkData` The actual work to be performed - `type: Literal["session"]` Type of work data - `id: str` Session identifier (e.g., 'session_...') - `environment_id: str` Environment identifier this work belongs to (e.g., `env_...`) - `latest_heartbeat_at: Optional[str]` RFC 3339 timestamp of the most recent heartbeat - `metadata: Dict[str, str]` User-provided metadata key-value pairs associated with this work item - `secret: Optional[str]` Credential payload used by the environment worker to execute this work item. May be populated when polling for work; null on all other retrieval paths. - `started_at: Optional[str]` RFC 3339 timestamp when work execution started - `state: Literal["queued", "starting", "active", 2 more]` Current state of the work item - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: Optional[str]` RFC 3339 timestamp when stop was requested - `stopped_at: Optional[str]` RFC 3339 timestamp when work execution stopped #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_self_hosted_work = client.beta.environments.work.stop( work_id="work_id", environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", ) print(beta_self_hosted_work.id) ``` ##### Response (200) ```json { "id": "id", "acknowledged_at": "acknowledged_at", "created_at": "created_at", "data": { "id": "id", "type": "session" }, "environment_id": "environment_id", "latest_heartbeat_at": "latest_heartbeat_at", "metadata": { "foo": "string" }, "secret": "secret", "started_at": "started_at", "state": "queued", "stop_requested_at": "stop_requested_at", "stopped_at": "stopped_at", "type": "work" } ``` ### List Work Items `beta.environments.work.list(environment_id, **kwargs) -> SyncPageCursor[BetaSelfHostedWork]` **GET** `/v1/environments/{environment_id}/work` Note: these endpoints are called automatically by the pre-built environment worker provided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. List work items in an environment. #### Parameters - `environment_id: str` (path parameter) - `limit: Optional[int]` (query parameter) Maximum number of work items to return default: 20, minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Opaque cursor from previous response for pagination - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaSelfHostedWork` Work resource representing a unit of work in a self-hosted environment. Work items are queued when sessions are created or when long-dormant sessions receive new messages. The environment worker polls for work to execute in a self-hosted sandbox. - `type: Literal["work"]` The type of object (always 'work') default: work - `id: str` Work identifier (e.g., 'work_...') - `acknowledged_at: Optional[str]` RFC 3339 timestamp when the work item was acknowledged and assigned to a self-hosted sandbox - `created_at: str` RFC 3339 timestamp when work was created - `data: BetaSessionWorkData` The actual work to be performed - `type: Literal["session"]` Type of work data - `id: str` Session identifier (e.g., 'session_...') - `environment_id: str` Environment identifier this work belongs to (e.g., `env_...`) - `latest_heartbeat_at: Optional[str]` RFC 3339 timestamp of the most recent heartbeat - `metadata: Dict[str, str]` User-provided metadata key-value pairs associated with this work item - `secret: Optional[str]` Credential payload used by the environment worker to execute this work item. May be populated when polling for work; null on all other retrieval paths. - `started_at: Optional[str]` RFC 3339 timestamp when work execution started - `state: Literal["queued", "starting", "active", 2 more]` Current state of the work item - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: Optional[str]` RFC 3339 timestamp when stop was requested - `stopped_at: Optional[str]` RFC 3339 timestamp when work execution stopped #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.environments.work.list( environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", ) page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "id", "acknowledged_at": "acknowledged_at", "created_at": "created_at", "data": { "id": "id", "type": "session" }, "environment_id": "environment_id", "latest_heartbeat_at": "latest_heartbeat_at", "metadata": { "foo": "string" }, "secret": "secret", "started_at": "started_at", "state": "queued", "stop_requested_at": "stop_requested_at", "stopped_at": "stopped_at", "type": "work" } ], "next_page": "next_page" } ``` ### Update Work Item `beta.environments.work.update(work_id, **kwargs) -> BetaSelfHostedWork` **POST** `/v1/environments/{environment_id}/work/{work_id}` Note: these endpoints are called automatically by the pre-built environment worker provided in the SDKs and CLI, for orchestrating sessions with self-hosted sandbox environments. They are included here as a reference; you do not need to invoke them directly. Update work item metadata with merge semantics. #### Parameters - `environment_id: str` (path parameter) - `work_id: str` (path parameter) - `metadata: Dict[str, Optional[str]]` Metadata patch. Set a key to a string to upsert it, or to null to delete it. Omit the field to preserve existing metadata. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaSelfHostedWork` Work resource representing a unit of work in a self-hosted environment. Work items are queued when sessions are created or when long-dormant sessions receive new messages. The environment worker polls for work to execute in a self-hosted sandbox. - `type: Literal["work"]` The type of object (always 'work') default: work - `id: str` Work identifier (e.g., 'work_...') - `acknowledged_at: Optional[str]` RFC 3339 timestamp when the work item was acknowledged and assigned to a self-hosted sandbox - `created_at: str` RFC 3339 timestamp when work was created - `data: BetaSessionWorkData` The actual work to be performed - `type: Literal["session"]` Type of work data - `id: str` Session identifier (e.g., 'session_...') - `environment_id: str` Environment identifier this work belongs to (e.g., `env_...`) - `latest_heartbeat_at: Optional[str]` RFC 3339 timestamp of the most recent heartbeat - `metadata: Dict[str, str]` User-provided metadata key-value pairs associated with this work item - `secret: Optional[str]` Credential payload used by the environment worker to execute this work item. May be populated when polling for work; null on all other retrieval paths. - `started_at: Optional[str]` RFC 3339 timestamp when work execution started - `state: Literal["queued", "starting", "active", 2 more]` Current state of the work item - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: Optional[str]` RFC 3339 timestamp when stop was requested - `stopped_at: Optional[str]` RFC 3339 timestamp when work execution stopped #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_self_hosted_work = client.beta.environments.work.update( work_id="work_id", environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", metadata={"foo": "string"}, ) print(beta_self_hosted_work.id) ``` ##### Response (200) ```json { "id": "id", "acknowledged_at": "acknowledged_at", "created_at": "created_at", "data": { "id": "id", "type": "session" }, "environment_id": "environment_id", "latest_heartbeat_at": "latest_heartbeat_at", "metadata": { "foo": "string" }, "secret": "secret", "started_at": "started_at", "state": "queued", "stop_requested_at": "stop_requested_at", "stopped_at": "stopped_at", "type": "work" } ``` ### Get Queue Statistics `beta.environments.work.stats(environment_id, **kwargs) -> BetaSelfHostedWorkQueueStats` **GET** `/v1/environments/{environment_id}/work/stats` Get statistics about the work queue for an environment. #### Parameters - `environment_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaSelfHostedWorkQueueStats` Statistics about the work queue for an environment. Uses Redis Stream consumer group metrics for O(1) queries. - `type: Literal["work_queue_stats"]` The type of object default: work_queue_stats - `depth: int` Number of work items waiting to be picked up (lag from consumer group) - `oldest_queued_at: Optional[str]` RFC 3339 timestamp of oldest item in the work stream (includes both queued and pending items), null if stream empty - `pending: int` Number of work items being processed (polled but not acknowledged) default: 0 - `workers_polling: Optional[int]` Number of workers that have polled for work in the last 30 seconds. Requires worker_id to be sent with poll requests. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_self_hosted_work_queue_stats = client.beta.environments.work.stats( environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", ) print(beta_self_hosted_work_queue_stats.depth) ``` ##### Response (200) ```json { "depth": 0, "oldest_queued_at": "oldest_queued_at", "pending": 0, "type": "work_queue_stats", "workers_polling": 0 } ``` ## Beta › Sessions ### Create Session `beta.sessions.create(**kwargs) -> BetaManagedAgentsSession` **POST** `/v1/sessions` Create Session #### Parameters - `agent: Agent` Agent identifier. Accepts the `agent` ID string, which pins the latest version for the session, or an `agent` object with both id and version specified. - `str` - `class BetaManagedAgentsAgentParams` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `type: Literal["agent"]` - `id: str` The `agent` ID. minLength: 1, maxLength: 128 - `version: Optional[int]` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. format: int32 - `class BetaManagedAgentsAgentWithOverridesParams` Reference to an `agent` plus optional configuration overrides. Each provided field replaces the agent's value for the caller's use; the agent resource is unchanged. - `type: Literal["agent_with_overrides"]` - `id: str` The `agent` ID. minLength: 1, maxLength: 128 - `mcp_servers: Optional[List[BetaManagedAgentsURLMCPServerParams]]` Replacement MCP server list. Full replacement: the provided array becomes the MCP servers. Send an empty array to clear; omit to preserve the agent's servers. - `type: Literal["url"]` - `name: str` Unique name for this server, referenced by mcp_toolset configurations. 1-255 characters. minLength: 1, maxLength: 255 - `url: str` Endpoint URL for the MCP server. maxLength: 2048 - `model: Optional[Model]` Replacement model. Accepts the model string, e.g. `claude-opus-5`, or a `model_config` object. Omit to use the agent's model. - `Union[Literal["claude-haiku-5-5", "claude-sonnet-5-5", "claude-opus-5-5", 14 more], str]` - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `class BetaManagedAgentsModelConfigParams` An object that defines additional configuration control over model use - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. Accepts a bare level string (`"high"`) or `{"type": "high"}`. On create, omitting it resolves the per-model default; on update, omitting it leaves the stored value unchanged. - `"low"` Low effort. Favors latency over reasoning depth. - `"medium"` Medium effort. Balances latency and reasoning depth. - `"high"` High effort. Favors reasoning depth. - `"xhigh"` Extra-high effort. Not all models accept this level. - `"max"` Maximum effort. Favors reasoning depth over latency. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. On update, `model` is whole-object replacement — omitting inference_geo clears it. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. Defaults to `standard`. - `"standard"` - `"fast"` - `skills: Optional[List[BetaManagedAgentsSkillParams]]` Replacement skill list. Full replacement: the provided array becomes the skills. Send an empty array to clear; omit to preserve the agent's skills. - `class BetaManagedAgentsAnthropicSkillParams` An Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` Identifier of the Anthropic skill (e.g., "xlsx"). minLength: 1, maxLength: 64 - `version: Optional[str]` Version to pin. Defaults to latest if omitted. minLength: 1, maxLength: 64 - `class BetaManagedAgentsCustomSkillParams` A user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` Tagged ID of the custom skill (e.g., "skill_01XJ5..."). minLength: 1, maxLength: 64 - `version: Optional[str]` Version to pin. Defaults to latest if omitted. minLength: 1, maxLength: 64 - `system: Optional[str]` Replacement system prompt. Up to 100,000 characters. Set to null to clear the agent's system prompt; omit to preserve it. maxLength: 100000 - `tools: Optional[List[Tool]]` Replacement tool list. Full replacement: the provided array becomes the tool configuration. Send an empty array to clear; omit to preserve the agent's tools. - `class BetaManagedAgentsAgentToolset20260401Params` Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent. - `type: Literal["agent_toolset_20260401"]` - `configs: Optional[List[BetaManagedAgentsAgentToolConfigParams]]` Per-tool configuration overrides. - `class BetaManagedAgentsBashToolConfigParams` Configuration override for the bash tool. - `type: Optional[Literal["bash"]]` - `name: Literal["bash"]` Must be "bash". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfigParams` Configuration override for the edit tool. - `type: Optional[Literal["edit"]]` - `name: Literal["edit"]` Must be "edit". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfigParams` Configuration override for the read tool. - `type: Optional[Literal["read"]]` - `name: Literal["read"]` Must be "read". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfigParams` Configuration override for the write tool. - `type: Optional[Literal["write"]]` - `name: Literal["write"]` Must be "write". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfigParams` Configuration override for the glob tool. - `type: Optional[Literal["glob"]]` - `name: Literal["glob"]` Must be "glob". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfigParams` Configuration override for the grep tool. - `type: Optional[Literal["grep"]]` - `name: Literal["grep"]` Must be "grep". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfigParams` Configuration override for the web_fetch tool. - `type: Optional[Literal["web_fetch"]]` - `name: Literal["web_fetch"]` Must be "web_fetch". - `allowed_domains: Optional[List[str]]` Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: Optional[List[str]]` Never fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `max_content_tokens: Optional[int]` Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs. format: int32 - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSourcesParams]` Which sources contribute URLs the tool may fetch. Omit to allow every source. - `client_tool_results: Optional[Union[BetaManagedAgentsWebFetchURLSourceShorthand, BetaManagedAgentsWebFetchURLSourceToolFilter, null]]` Which custom tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be a custom tool in the same tools array. - `Literal["all", "none"]` - `"all"` - `"none"` - `type BetaManagedAgentsWebFetchURLSourceToolFilter = ...` Which tools' results contribute URLs that may be fetched. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[Union[BetaManagedAgentsWebFetchURLSourceShorthand, BetaManagedAgentsWebFetchURLSourceToolFilter, null]]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be "web_search" or "web_fetch". - `user_input: Optional[Union[BetaManagedAgentsWebFetchURLSourceShorthand, BetaManagedAgentsWebFetchURLSourceUserInput, null]]` Whether URLs in the text of user messages may be fetched: "all" (the default) or "none". - `Literal["all", "none"]` - `"all"` - `"none"` - `type BetaManagedAgentsWebFetchURLSourceUserInput = ...` Whether URLs in the text of user messages may be fetched. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `class BetaManagedAgentsWebSearchToolConfigParams` Configuration override for the web_search tool. - `type: Optional[Literal["web_search"]]` - `name: Literal["web_search"]` Must be "web_search". - `allowed_domains: Optional[List[str]]` Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: Optional[List[str]]` Never return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: Optional[BetaManagedAgentsAgentToolsetDefaultConfigParams]` Default configuration applied to all tools in this set. - `enabled: Optional[bool]` Whether tools are enabled and available to Claude by default. Defaults to true if not specified. - `permission_policy: Optional[PermissionPolicy]` Default permission policy for tools. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolsetParams` Configuration for tools from an MCP server defined in `mcp_servers`. - `type: Literal["mcp_toolset"]` - `mcp_server_name: str` Name of the MCP server. Must match a server name from the mcp_servers array. 1-255 characters. minLength: 1, maxLength: 255 - `configs: Optional[List[BetaManagedAgentsMCPToolConfigParams]]` Per-tool configuration overrides. - `name: str` Name of the MCP tool to configure. 1-128 characters. minLength: 1, maxLength: 128 - `enabled: Optional[bool]` Whether this tool is enabled. Overrides the `default_config` setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Overrides the `default_config` setting. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: Optional[BetaManagedAgentsMCPToolsetDefaultConfigParams]` Default configuration for all tools from this server. - `enabled: Optional[bool]` Whether tools are enabled by default. Defaults to true if not specified. - `permission_policy: Optional[PermissionPolicy]` Default permission policy for tools from this server. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsCustomToolParams` A custom tool that is executed by the API client rather than the agent. When the agent calls this tool, an `agent.custom_tool_use` event is emitted and the session goes idle, waiting for the client to provide the result via a `user.custom_tool_result` event. - `type: Literal["custom"]` - `description: str` Description of what the tool does, shown to the agent to help it decide when to use the tool. minLength: 1 - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema defining the expected input parameters for the tool. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` Unique name for the tool. 1-128 characters; letters, digits, underscores, and hyphens. minLength: 1, maxLength: 128 - `version: Optional[int]` The specific `agent` version to use. Omit to use the latest version. format: int32 - `environment_id: str` ID of the `environment` defining the container configuration for this session. minLength: 1, maxLength: 128 - `budget: Optional[BetaManagedAgentsBudgetLimitParam]` Enforced spend ceiling for the session. Omit to create an uncapped session. Every model the session can run — the agent's model and each callable agent's model — must have a public list price, or the request is rejected with reason `model_not_budgetable`. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `initial_events: Optional[Iterable[InitialEvent]]` Initial events to send to the `session` at creation, processed in order. Supports `user.message` and `user.define_outcome` events. Maximum 50 events. - `class BetaManagedAgentsUserMessageEventParams` Parameters for sending a user message to the session. - `type: Literal["user.message"]` - `content: Iterable[Content]` Array of content blocks for the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `class BetaManagedAgentsUserDefineOutcomeEventParams` Parameters for defining an outcome the agent should work toward. The agent begins work on receipt. - `type: Literal["user.define_outcome"]` - `description: str` What the agent should produce. This is the task specification. - `rubric: Rubric` How to grade the outcome. Text or file reference. - `class BetaManagedAgentsFileRubricParams` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubricParams` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. Maximum 262144 characters. maxLength: 262144 - `max_iterations: Optional[int]` Eval→revision cycles before giving up. Default 3, max 20. format: int32 - `metadata: Optional[Dict[str, str]]` Arbitrary key-value metadata attached to the session. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars. - `resources: Optional[Iterable[Resource]]` Resources (e.g. repositories, files) to mount into the session's container. - `class BetaManagedAgentsGitHubRepositoryResourceParams` Mount a GitHub repository into the session's container. - `type: Literal["github_repository"]` - `url: str` Github URL of the repository minLength: 1, maxLength: 2048 - `authorization_token: Optional[str]` GitHub authorization token used to clone the repository. Required for private repositories; optional for public ones. minLength: 1, maxLength: 4096 - `checkout: Optional[Checkout]` Branch or commit to check out. Defaults to the repository's default branch. - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/workspace/`. minLength: 1, maxLength: 4096 - `class BetaManagedAgentsFileResourceParams` Mount a file uploaded via the Files API into the session. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1, maxLength: 128 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/mnt/session/uploads/`. minLength: 1, maxLength: 4096 - `class BetaManagedAgentsMemoryStoreResourceParam` Parameters for attaching a memory store to an agent session. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to read_write. read_only mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. maxLength: 4096 - `title: Optional[str]` Human-readable session title. maxLength: 500 - `vault_ids: Optional[Sequence[str]]` Vault IDs for stored credentials the agent can use during the session. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsSession` A Managed Agents `session`. - `type: Literal["session"]` - `id: str` - `agent: BetaManagedAgentsSessionAgent` Resolved `agent` definition for a `session`. Snapshot of the `agent` at `session` creation time. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsSessionMultiagent]` Resolved multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsSessionMultiagentCoordinator` Resolved coordinator topology with full agent definitions for each roster member. - `type: Literal["coordinator"]` - `agents: List[Agent]` Full `agent` definitions the coordinator may spawn as session threads. - `class BetaManagedAgentsSessionThreadAgent` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsSessionMultiagent20261001` Resolved multiagent configuration with three members, as copied to the `session` at creation. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsSessionMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsSessionMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that this agent can spawn as session threads. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsSessionMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsSessionMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that a run's plan can use. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `class BetaManagedAgentsMCPToolset` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `version: int` format: int32 - `archived_at: Optional[datetime]` When the session was archived. Null if not archived. format: date-time - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's enforced spend ceiling, or null when no budget is set. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `environment_id: str` - `metadata: Dict[str, str]` - `outcome_evaluations: List[BetaManagedAgentsOutcomeEvaluationResource]` Per-outcome evaluation state. One entry per `define_outcome` event sent to the session. - `type: Literal["outcome_evaluation"]` - `completed_at: Optional[datetime]` When the outcome reached a terminal result. Null while `pending`/`running`/`evaluating`. format: date-time - `description: str` What the agent should produce. - `explanation: Optional[str]` Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable. - `iteration: int` 0-indexed revision cycle the outcome is currently on. format: int32 - `outcome_id: str` Server-generated outc_ ID for this outcome. - `result: str` Current evaluation state. `pending` before the agent begins work; `running` while producing or revising; `evaluating` while the grader scores; `satisfied`/`max_iterations_reached`/`failed`/`interrupted` are terminal. - `resources: List[BetaManagedAgentsSessionResource]` - `class BetaManagedAgentsGitHubRepositoryResource` - `type: Literal["github_repository"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `url: str` - `checkout: Optional[Checkout]` - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `class BetaManagedAgentsFileResource` - `type: Literal["file"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `file_id: str` - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `class BetaManagedAgentsMemoryStoreResource` A memory store attached to an agent session. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `description: Optional[str]` Description of the memory store, snapshotted at attach time. Rendered into the agent's system prompt. Empty string when the store has no description. - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. maxLength: 4096 - `mount_path: Optional[str]` Filesystem path where the store is mounted in the session container, e.g. /mnt/memory/user-preferences. Derived from the store's name. Output-only. - `name: Optional[str]` Display name of the memory store, snapshotted at attach time. Later edits to the store's name do not propagate to this resource. - `stats: BetaManagedAgentsSessionStats` Timing statistics for the session. - `active_seconds: Optional[float]` Cumulative time in seconds the session spent in `running` status. Excludes idle time. format: double - `duration_seconds: Optional[float]` Elapsed time since session creation in seconds. For terminated sessions, frozen at the final update. format: double - `status: Literal["rescheduling", "running", "idle", "terminated"]` - `"rescheduling"` Transient error occurred, retrying automatically. - `"running"` Agent is actively executing. - `"idle"` Agent is waiting for input, including user messages or tool confirmations. Sessions start in idle. - `"terminated"` Session has ended, either due to an error or completion. - `title: Optional[str]` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `usage: BetaManagedAgentsSessionUsage` Cumulative token usage for the session. - `active_seconds: Optional[float]` Cumulative time in seconds during which the session had at least one thread in running status. Overlapping activity from concurrent threads is counted once, unlike `stats.active_seconds`, which sums each thread's own active time. This is the duration the session's runtime cost is priced on. format: double - `cache_creation: Optional[BetaManagedAgentsCacheCreationUsage]` Tokens used to create prompt cache entries, broken down by cache TTL. - `ephemeral_1h_input_tokens: Optional[int]` Tokens used to create 1-hour ephemeral cache entries. format: int32 - `ephemeral_5m_input_tokens: Optional[int]` Tokens used to create 5-minute ephemeral cache entries. format: int32 - `cache_read_input_tokens: Optional[int]` Total tokens read from prompt cache. format: int32 - `input_tokens: Optional[int]` Total input tokens consumed across all turns. format: int32 - `list_cost: Optional[BetaMonetaryAmount]` Cumulative list cost of the session across all turns, priced at public list rates. Absent until cost tracking is available for the session. - `output_tokens: Optional[int]` Total output tokens generated across all turns. format: int32 - `server_tool_use: Optional[BetaManagedAgentsServerToolUsage]` Cumulative server-executed tool usage across all turns. Absent until server-tool tracking is available for the session. - `web_fetch_requests: Optional[int]` Number of server-executed web fetch requests. format: int32 - `web_search_requests: Optional[int]` Number of server-executed web search requests. format: int32 - `vault_ids: List[str]` Vault IDs attached to the session at creation. Empty when no vaults were supplied. - `deployment_id: Optional[str]` Deployment ID when the session was created from a deployment reference. Null otherwise. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_session = client.beta.sessions.create( agent="agent_011CZkYpogX7uDKUyvBTophP", environment_id="env_011CZkZ9X2dpNyB7HsEFoRfW", initial_events=[ { "type": "user.message", "content": [ { "type": "text", "text": "Where is my order #1234?", } ], } ], ) print(beta_managed_agents_session.id) ``` ##### Response (200) ```json { "id": "sesn_011CZkZAtmR3yMPDzynEDxu7", "agent": { "id": "agent_011CZkYpogX7uDKUyvBTophP", "description": "A general-purpose starter agent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "description": "A focused research subagent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "name": "Researcher", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" } ], "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 } ], "type": "coordinator" }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 }, "archived_at": null, "budget": { "max_list_cost": { "amount": "2500", "currency": "USD" }, "type": "limit" }, "created_at": "2026-03-15T10:00:00Z", "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "metadata": {}, "outcome_evaluations": [ { "completed_at": "2026-03-15T10:02:31Z", "description": "Produce a 2-page summary as summary.md", "explanation": "All five sections present with inline citations.", "iteration": 0, "outcome_id": "outc_011CZkZRSw2kEfs6ncTVmjxP", "result": "satisfied", "type": "outcome_evaluation" } ], "resources": [ { "id": "sesrsc_011CZkZBJq5dWxk9fVLNcPht", "created_at": "2026-03-15T10:00:00Z", "file_id": "file_011CNha8iCJcU1wXNR6q4V8w", "mount_path": "/uploads/receipt.pdf", "type": "file", "updated_at": "2026-03-15T10:00:00Z" }, { "id": "sesrsc_011CZkZCKr6eXym1gWMPdQiu", "created_at": "2026-03-15T10:00:00Z", "mount_path": "/workspace/example-repo", "type": "github_repository", "updated_at": "2026-03-15T10:00:00Z", "url": "https://github.com/example-org/example-repo", "checkout": { "name": "main", "type": "branch" } } ], "stats": { "active_seconds": 0, "duration_seconds": 0 }, "status": "idle", "title": "Order #1234 inquiry", "type": "session", "updated_at": "2026-03-15T10:00:00Z", "usage": { "active_seconds": 0, "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_read_input_tokens": 0, "input_tokens": 0, "list_cost": { "amount": "2500", "currency": "USD" }, "output_tokens": 0, "server_tool_use": { "web_fetch_requests": 0, "web_search_requests": 3 } }, "vault_ids": [ "vlt_011CZkZDLs7fYzm1hXNPeRjv" ], "deployment_id": "deployment_id" } ``` ### List Sessions `beta.sessions.list(**kwargs) -> SyncBidirectionalPageCursor[BetaManagedAgentsSession]` **GET** `/v1/sessions` List Sessions #### Parameters - `agent_id: Optional[str]` (query parameter) Filter sessions created with this agent ID. - `agent_version: Optional[int]` (query parameter) Filter by agent version. Only applies when `agent_id` is also set. format: int32 - `created_at_gt: Optional[Union[str, datetime]]` (query parameter) Return sessions created after this time (exclusive). format: date-time - `created_at_gte: Optional[Union[str, datetime]]` (query parameter) Return sessions created at or after this time (inclusive). format: date-time - `created_at_lt: Optional[Union[str, datetime]]` (query parameter) Return sessions created before this time (exclusive). format: date-time - `created_at_lte: Optional[Union[str, datetime]]` (query parameter) Return sessions created at or before this time (inclusive). format: date-time - `deployment_id: Optional[str]` (query parameter) Filter sessions created by this deployment ID. - `include_archived: Optional[bool]` (query parameter) When true, includes archived sessions. Default: false (exclude archived). - `limit: Optional[int]` (query parameter) Maximum number of results to return. format: int32 - `memory_store_id: Optional[str]` (query parameter) Filter sessions whose resources contain a `memory_store` with this memory store ID. - `order: Optional[Literal["asc", "desc"]]` (query parameter) Sort direction for results, ordered by `created_at`. Defaults to `desc` (newest first). - `"asc"` - `"desc"` - `page: Optional[str]` (query parameter) Opaque pagination cursor from a previous response. - `statuses: Optional[List[Literal["rescheduling", "running", "idle", "terminated"]]]` (query parameter) Filter by session status. Repeat the parameter to match any of multiple statuses. - `"rescheduling"` Transient error occurred, retrying automatically. - `"running"` Agent is actively executing. - `"idle"` Agent is waiting for input, including user messages or tool confirmations. Sessions start in idle. - `"terminated"` Session has ended, either due to an error or completion. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsSession` A Managed Agents `session`. - `type: Literal["session"]` - `id: str` - `agent: BetaManagedAgentsSessionAgent` Resolved `agent` definition for a `session`. Snapshot of the `agent` at `session` creation time. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsSessionMultiagent]` Resolved multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsSessionMultiagentCoordinator` Resolved coordinator topology with full agent definitions for each roster member. - `type: Literal["coordinator"]` - `agents: List[Agent]` Full `agent` definitions the coordinator may spawn as session threads. - `class BetaManagedAgentsSessionThreadAgent` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsSessionMultiagent20261001` Resolved multiagent configuration with three members, as copied to the `session` at creation. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsSessionMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsSessionMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that this agent can spawn as session threads. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsSessionMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsSessionMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that a run's plan can use. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `class BetaManagedAgentsMCPToolset` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `version: int` format: int32 - `archived_at: Optional[datetime]` When the session was archived. Null if not archived. format: date-time - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's enforced spend ceiling, or null when no budget is set. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `environment_id: str` - `metadata: Dict[str, str]` - `outcome_evaluations: List[BetaManagedAgentsOutcomeEvaluationResource]` Per-outcome evaluation state. One entry per `define_outcome` event sent to the session. - `type: Literal["outcome_evaluation"]` - `completed_at: Optional[datetime]` When the outcome reached a terminal result. Null while `pending`/`running`/`evaluating`. format: date-time - `description: str` What the agent should produce. - `explanation: Optional[str]` Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable. - `iteration: int` 0-indexed revision cycle the outcome is currently on. format: int32 - `outcome_id: str` Server-generated outc_ ID for this outcome. - `result: str` Current evaluation state. `pending` before the agent begins work; `running` while producing or revising; `evaluating` while the grader scores; `satisfied`/`max_iterations_reached`/`failed`/`interrupted` are terminal. - `resources: List[BetaManagedAgentsSessionResource]` - `class BetaManagedAgentsGitHubRepositoryResource` - `type: Literal["github_repository"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `url: str` - `checkout: Optional[Checkout]` - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `class BetaManagedAgentsFileResource` - `type: Literal["file"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `file_id: str` - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `class BetaManagedAgentsMemoryStoreResource` A memory store attached to an agent session. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `description: Optional[str]` Description of the memory store, snapshotted at attach time. Rendered into the agent's system prompt. Empty string when the store has no description. - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. maxLength: 4096 - `mount_path: Optional[str]` Filesystem path where the store is mounted in the session container, e.g. /mnt/memory/user-preferences. Derived from the store's name. Output-only. - `name: Optional[str]` Display name of the memory store, snapshotted at attach time. Later edits to the store's name do not propagate to this resource. - `stats: BetaManagedAgentsSessionStats` Timing statistics for the session. - `active_seconds: Optional[float]` Cumulative time in seconds the session spent in `running` status. Excludes idle time. format: double - `duration_seconds: Optional[float]` Elapsed time since session creation in seconds. For terminated sessions, frozen at the final update. format: double - `status: Literal["rescheduling", "running", "idle", "terminated"]` - `"rescheduling"` Transient error occurred, retrying automatically. - `"running"` Agent is actively executing. - `"idle"` Agent is waiting for input, including user messages or tool confirmations. Sessions start in idle. - `"terminated"` Session has ended, either due to an error or completion. - `title: Optional[str]` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `usage: BetaManagedAgentsSessionUsage` Cumulative token usage for the session. - `active_seconds: Optional[float]` Cumulative time in seconds during which the session had at least one thread in running status. Overlapping activity from concurrent threads is counted once, unlike `stats.active_seconds`, which sums each thread's own active time. This is the duration the session's runtime cost is priced on. format: double - `cache_creation: Optional[BetaManagedAgentsCacheCreationUsage]` Tokens used to create prompt cache entries, broken down by cache TTL. - `ephemeral_1h_input_tokens: Optional[int]` Tokens used to create 1-hour ephemeral cache entries. format: int32 - `ephemeral_5m_input_tokens: Optional[int]` Tokens used to create 5-minute ephemeral cache entries. format: int32 - `cache_read_input_tokens: Optional[int]` Total tokens read from prompt cache. format: int32 - `input_tokens: Optional[int]` Total input tokens consumed across all turns. format: int32 - `list_cost: Optional[BetaMonetaryAmount]` Cumulative list cost of the session across all turns, priced at public list rates. Absent until cost tracking is available for the session. - `output_tokens: Optional[int]` Total output tokens generated across all turns. format: int32 - `server_tool_use: Optional[BetaManagedAgentsServerToolUsage]` Cumulative server-executed tool usage across all turns. Absent until server-tool tracking is available for the session. - `web_fetch_requests: Optional[int]` Number of server-executed web fetch requests. format: int32 - `web_search_requests: Optional[int]` Number of server-executed web search requests. format: int32 - `vault_ids: List[str]` Vault IDs attached to the session at creation. Empty when no vaults were supplied. - `deployment_id: Optional[str]` Deployment ID when the session was created from a deployment reference. Null otherwise. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.sessions.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "sesn_011CZkZAtmR3yMPDzynEDxu7", "agent": { "id": "agent_011CZkYpogX7uDKUyvBTophP", "description": "A general-purpose starter agent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "description": "A focused research subagent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "name": "Researcher", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" } ], "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 } ], "type": "coordinator" }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 }, "archived_at": null, "budget": { "max_list_cost": { "amount": "2500", "currency": "USD" }, "type": "limit" }, "created_at": "2026-03-15T10:00:00Z", "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "metadata": {}, "outcome_evaluations": [ { "completed_at": "2026-03-15T10:02:31Z", "description": "Produce a 2-page summary as summary.md", "explanation": "All five sections present with inline citations.", "iteration": 0, "outcome_id": "outc_011CZkZRSw2kEfs6ncTVmjxP", "result": "satisfied", "type": "outcome_evaluation" } ], "resources": [ { "id": "sesrsc_011CZkZBJq5dWxk9fVLNcPht", "created_at": "2026-03-15T10:00:00Z", "file_id": "file_011CNha8iCJcU1wXNR6q4V8w", "mount_path": "/uploads/receipt.pdf", "type": "file", "updated_at": "2026-03-15T10:00:00Z" }, { "id": "sesrsc_011CZkZCKr6eXym1gWMPdQiu", "created_at": "2026-03-15T10:00:00Z", "mount_path": "/workspace/example-repo", "type": "github_repository", "updated_at": "2026-03-15T10:00:00Z", "url": "https://github.com/example-org/example-repo", "checkout": { "name": "main", "type": "branch" } } ], "stats": { "active_seconds": 0, "duration_seconds": 0 }, "status": "idle", "title": "Order #1234 inquiry", "type": "session", "updated_at": "2026-03-15T10:00:00Z", "usage": { "active_seconds": 0, "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_read_input_tokens": 0, "input_tokens": 0, "list_cost": { "amount": "2500", "currency": "USD" }, "output_tokens": 0, "server_tool_use": { "web_fetch_requests": 0, "web_search_requests": 3 } }, "vault_ids": [ "vlt_011CZkZDLs7fYzm1hXNPeRjv" ], "deployment_id": "deployment_id" } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=", "prev_page": "page_MjAyNS0wNS0xM1QwMDowMDowMFo=" } ``` ### Get Session `beta.sessions.retrieve(session_id, **kwargs) -> BetaManagedAgentsSession` **GET** `/v1/sessions/{session_id}` Get Session #### Parameters - `session_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsSession` A Managed Agents `session`. - `type: Literal["session"]` - `id: str` - `agent: BetaManagedAgentsSessionAgent` Resolved `agent` definition for a `session`. Snapshot of the `agent` at `session` creation time. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsSessionMultiagent]` Resolved multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsSessionMultiagentCoordinator` Resolved coordinator topology with full agent definitions for each roster member. - `type: Literal["coordinator"]` - `agents: List[Agent]` Full `agent` definitions the coordinator may spawn as session threads. - `class BetaManagedAgentsSessionThreadAgent` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsSessionMultiagent20261001` Resolved multiagent configuration with three members, as copied to the `session` at creation. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsSessionMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsSessionMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that this agent can spawn as session threads. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsSessionMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsSessionMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that a run's plan can use. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `class BetaManagedAgentsMCPToolset` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `version: int` format: int32 - `archived_at: Optional[datetime]` When the session was archived. Null if not archived. format: date-time - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's enforced spend ceiling, or null when no budget is set. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `environment_id: str` - `metadata: Dict[str, str]` - `outcome_evaluations: List[BetaManagedAgentsOutcomeEvaluationResource]` Per-outcome evaluation state. One entry per `define_outcome` event sent to the session. - `type: Literal["outcome_evaluation"]` - `completed_at: Optional[datetime]` When the outcome reached a terminal result. Null while `pending`/`running`/`evaluating`. format: date-time - `description: str` What the agent should produce. - `explanation: Optional[str]` Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable. - `iteration: int` 0-indexed revision cycle the outcome is currently on. format: int32 - `outcome_id: str` Server-generated outc_ ID for this outcome. - `result: str` Current evaluation state. `pending` before the agent begins work; `running` while producing or revising; `evaluating` while the grader scores; `satisfied`/`max_iterations_reached`/`failed`/`interrupted` are terminal. - `resources: List[BetaManagedAgentsSessionResource]` - `class BetaManagedAgentsGitHubRepositoryResource` - `type: Literal["github_repository"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `url: str` - `checkout: Optional[Checkout]` - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `class BetaManagedAgentsFileResource` - `type: Literal["file"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `file_id: str` - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `class BetaManagedAgentsMemoryStoreResource` A memory store attached to an agent session. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `description: Optional[str]` Description of the memory store, snapshotted at attach time. Rendered into the agent's system prompt. Empty string when the store has no description. - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. maxLength: 4096 - `mount_path: Optional[str]` Filesystem path where the store is mounted in the session container, e.g. /mnt/memory/user-preferences. Derived from the store's name. Output-only. - `name: Optional[str]` Display name of the memory store, snapshotted at attach time. Later edits to the store's name do not propagate to this resource. - `stats: BetaManagedAgentsSessionStats` Timing statistics for the session. - `active_seconds: Optional[float]` Cumulative time in seconds the session spent in `running` status. Excludes idle time. format: double - `duration_seconds: Optional[float]` Elapsed time since session creation in seconds. For terminated sessions, frozen at the final update. format: double - `status: Literal["rescheduling", "running", "idle", "terminated"]` - `"rescheduling"` Transient error occurred, retrying automatically. - `"running"` Agent is actively executing. - `"idle"` Agent is waiting for input, including user messages or tool confirmations. Sessions start in idle. - `"terminated"` Session has ended, either due to an error or completion. - `title: Optional[str]` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `usage: BetaManagedAgentsSessionUsage` Cumulative token usage for the session. - `active_seconds: Optional[float]` Cumulative time in seconds during which the session had at least one thread in running status. Overlapping activity from concurrent threads is counted once, unlike `stats.active_seconds`, which sums each thread's own active time. This is the duration the session's runtime cost is priced on. format: double - `cache_creation: Optional[BetaManagedAgentsCacheCreationUsage]` Tokens used to create prompt cache entries, broken down by cache TTL. - `ephemeral_1h_input_tokens: Optional[int]` Tokens used to create 1-hour ephemeral cache entries. format: int32 - `ephemeral_5m_input_tokens: Optional[int]` Tokens used to create 5-minute ephemeral cache entries. format: int32 - `cache_read_input_tokens: Optional[int]` Total tokens read from prompt cache. format: int32 - `input_tokens: Optional[int]` Total input tokens consumed across all turns. format: int32 - `list_cost: Optional[BetaMonetaryAmount]` Cumulative list cost of the session across all turns, priced at public list rates. Absent until cost tracking is available for the session. - `output_tokens: Optional[int]` Total output tokens generated across all turns. format: int32 - `server_tool_use: Optional[BetaManagedAgentsServerToolUsage]` Cumulative server-executed tool usage across all turns. Absent until server-tool tracking is available for the session. - `web_fetch_requests: Optional[int]` Number of server-executed web fetch requests. format: int32 - `web_search_requests: Optional[int]` Number of server-executed web search requests. format: int32 - `vault_ids: List[str]` Vault IDs attached to the session at creation. Empty when no vaults were supplied. - `deployment_id: Optional[str]` Deployment ID when the session was created from a deployment reference. Null otherwise. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_session = client.beta.sessions.retrieve( session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ) print(beta_managed_agents_session.id) ``` ##### Response (200) ```json { "id": "sesn_011CZkZAtmR3yMPDzynEDxu7", "agent": { "id": "agent_011CZkYpogX7uDKUyvBTophP", "description": "A general-purpose starter agent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "description": "A focused research subagent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "name": "Researcher", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" } ], "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 } ], "type": "coordinator" }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 }, "archived_at": null, "budget": { "max_list_cost": { "amount": "2500", "currency": "USD" }, "type": "limit" }, "created_at": "2026-03-15T10:00:00Z", "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "metadata": {}, "outcome_evaluations": [ { "completed_at": "2026-03-15T10:02:31Z", "description": "Produce a 2-page summary as summary.md", "explanation": "All five sections present with inline citations.", "iteration": 0, "outcome_id": "outc_011CZkZRSw2kEfs6ncTVmjxP", "result": "satisfied", "type": "outcome_evaluation" } ], "resources": [ { "id": "sesrsc_011CZkZBJq5dWxk9fVLNcPht", "created_at": "2026-03-15T10:00:00Z", "file_id": "file_011CNha8iCJcU1wXNR6q4V8w", "mount_path": "/uploads/receipt.pdf", "type": "file", "updated_at": "2026-03-15T10:00:00Z" }, { "id": "sesrsc_011CZkZCKr6eXym1gWMPdQiu", "created_at": "2026-03-15T10:00:00Z", "mount_path": "/workspace/example-repo", "type": "github_repository", "updated_at": "2026-03-15T10:00:00Z", "url": "https://github.com/example-org/example-repo", "checkout": { "name": "main", "type": "branch" } } ], "stats": { "active_seconds": 0, "duration_seconds": 0 }, "status": "idle", "title": "Order #1234 inquiry", "type": "session", "updated_at": "2026-03-15T10:00:00Z", "usage": { "active_seconds": 0, "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_read_input_tokens": 0, "input_tokens": 0, "list_cost": { "amount": "2500", "currency": "USD" }, "output_tokens": 0, "server_tool_use": { "web_fetch_requests": 0, "web_search_requests": 3 } }, "vault_ids": [ "vlt_011CZkZDLs7fYzm1hXNPeRjv" ], "deployment_id": "deployment_id" } ``` ### Update Session `beta.sessions.update(session_id, **kwargs) -> BetaManagedAgentsSession` **POST** `/v1/sessions/{session_id}` Update Session #### Parameters - `session_id: str` (path parameter) - `agent: Optional[BetaManagedAgentsSessionAgentUpdateParam]` Agent configuration update. Only `tools` and `mcp_servers` are updatable mid-session. Only valid for sessions created from an agent or deployment reference. The session must not be running. - `mcp_servers: Optional[List[BetaManagedAgentsURLMCPServerParams]]` Replacement MCP server list. Full replacement: the provided array becomes the new value. Send an empty array to clear; omit to preserve. - `type: Literal["url"]` - `name: str` Unique name for this server, referenced by mcp_toolset configurations. 1-255 characters. minLength: 1, maxLength: 255 - `url: str` Endpoint URL for the MCP server. maxLength: 2048 - `tools: Optional[List[Tool]]` Replacement tool list. Full replacement: the provided array becomes the new value. Send an empty array to clear; omit to preserve. - `class BetaManagedAgentsAgentToolset20260401Params` Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent. - `type: Literal["agent_toolset_20260401"]` - `configs: Optional[List[BetaManagedAgentsAgentToolConfigParams]]` Per-tool configuration overrides. - `class BetaManagedAgentsBashToolConfigParams` Configuration override for the bash tool. - `type: Optional[Literal["bash"]]` - `name: Literal["bash"]` Must be "bash". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfigParams` Configuration override for the edit tool. - `type: Optional[Literal["edit"]]` - `name: Literal["edit"]` Must be "edit". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfigParams` Configuration override for the read tool. - `type: Optional[Literal["read"]]` - `name: Literal["read"]` Must be "read". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfigParams` Configuration override for the write tool. - `type: Optional[Literal["write"]]` - `name: Literal["write"]` Must be "write". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfigParams` Configuration override for the glob tool. - `type: Optional[Literal["glob"]]` - `name: Literal["glob"]` Must be "glob". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfigParams` Configuration override for the grep tool. - `type: Optional[Literal["grep"]]` - `name: Literal["grep"]` Must be "grep". - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfigParams` Configuration override for the web_fetch tool. - `type: Optional[Literal["web_fetch"]]` - `name: Literal["web_fetch"]` Must be "web_fetch". - `allowed_domains: Optional[List[str]]` Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: Optional[List[str]]` Never fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `max_content_tokens: Optional[int]` Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs. format: int32 - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSourcesParams]` Which sources contribute URLs the tool may fetch. Omit to allow every source. - `client_tool_results: Optional[Union[BetaManagedAgentsWebFetchURLSourceShorthand, BetaManagedAgentsWebFetchURLSourceToolFilter, null]]` Which custom tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be a custom tool in the same tools array. - `Literal["all", "none"]` - `"all"` - `"none"` - `type BetaManagedAgentsWebFetchURLSourceToolFilter = ...` Which tools' results contribute URLs that may be fetched. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[Union[BetaManagedAgentsWebFetchURLSourceShorthand, BetaManagedAgentsWebFetchURLSourceToolFilter, null]]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched: "all" (the default), "none", or an only or except list. Each name in a list must be "web_search" or "web_fetch". - `user_input: Optional[Union[BetaManagedAgentsWebFetchURLSourceShorthand, BetaManagedAgentsWebFetchURLSourceUserInput, null]]` Whether URLs in the text of user messages may be fetched: "all" (the default) or "none". - `Literal["all", "none"]` - `"all"` - `"none"` - `type BetaManagedAgentsWebFetchURLSourceUserInput = ...` Whether URLs in the text of user messages may be fetched. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `class BetaManagedAgentsWebSearchToolConfigParams` Configuration override for the web_search tool. - `type: Optional[Literal["web_search"]]` - `name: Literal["web_search"]` Must be "web_search". - `allowed_domains: Optional[List[str]]` Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains. - `blocked_domains: Optional[List[str]]` Never return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains. - `enabled: Optional[bool]` Whether this tool is enabled and available to Claude. Overrides the default_config setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: Optional[BetaManagedAgentsAgentToolsetDefaultConfigParams]` Default configuration applied to all tools in this set. - `enabled: Optional[bool]` Whether tools are enabled and available to Claude by default. Defaults to true if not specified. - `permission_policy: Optional[PermissionPolicy]` Default permission policy for tools. Controls whether tool calls are auto-approved or require confirmation. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolsetParams` Configuration for tools from an MCP server defined in `mcp_servers`. - `type: Literal["mcp_toolset"]` - `mcp_server_name: str` Name of the MCP server. Must match a server name from the mcp_servers array. 1-255 characters. minLength: 1, maxLength: 255 - `configs: Optional[List[BetaManagedAgentsMCPToolConfigParams]]` Per-tool configuration overrides. - `name: str` Name of the MCP tool to configure. 1-128 characters. minLength: 1, maxLength: 128 - `enabled: Optional[bool]` Whether this tool is enabled. Overrides the `default_config` setting. - `permission_policy: Optional[PermissionPolicy]` Permission policy for this tool. Overrides the `default_config` setting. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: Optional[BetaManagedAgentsMCPToolsetDefaultConfigParams]` Default configuration for all tools from this server. - `enabled: Optional[bool]` Whether tools are enabled by default. Defaults to true if not specified. - `permission_policy: Optional[PermissionPolicy]` Default permission policy for tools from this server. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsCustomToolParams` A custom tool that is executed by the API client rather than the agent. When the agent calls this tool, an `agent.custom_tool_use` event is emitted and the session goes idle, waiting for the client to provide the result via a `user.custom_tool_result` event. - `type: Literal["custom"]` - `description: str` Description of what the tool does, shown to the agent to help it decide when to use the tool. minLength: 1 - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema defining the expected input parameters for the tool. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` Unique name for the tool. 1-128 characters; letters, digits, underscores, and hyphens. minLength: 1, maxLength: 128 - `budget: Optional[BetaManagedAgentsBudgetLimitParam]` Enforced spend ceiling for the session. Set an object to replace the budget of a session that was created with one, or `null` to remove it; omit to preserve. A budget cannot be added to a session created without one (rejected with reason `budget_create_only`), and a removed budget cannot be re-added. Allowed in any non-terminated status. Lowering `max_list_cost` to at or below the session's consumed list cost is rejected with reason `budget_not_raised`, and every model the session can run must have a public list price or the request is rejected with reason `model_not_budgetable`. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `metadata: Optional[Dict[str, Optional[str]]]` Metadata patch. Set a key to a string to upsert it, or to null to delete it. Omit the field to preserve. - `title: Optional[str]` Human-readable session title. minLength: 1, maxLength: 500 - `vault_ids: Optional[Sequence[str]]` Vault IDs (`vlt_*`) to attach to the session. Not yet supported; requests setting this field are rejected. Reserved for future use. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsSession` A Managed Agents `session`. - `type: Literal["session"]` - `id: str` - `agent: BetaManagedAgentsSessionAgent` Resolved `agent` definition for a `session`. Snapshot of the `agent` at `session` creation time. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsSessionMultiagent]` Resolved multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsSessionMultiagentCoordinator` Resolved coordinator topology with full agent definitions for each roster member. - `type: Literal["coordinator"]` - `agents: List[Agent]` Full `agent` definitions the coordinator may spawn as session threads. - `class BetaManagedAgentsSessionThreadAgent` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsSessionMultiagent20261001` Resolved multiagent configuration with three members, as copied to the `session` at creation. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsSessionMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsSessionMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that this agent can spawn as session threads. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsSessionMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsSessionMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that a run's plan can use. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `class BetaManagedAgentsMCPToolset` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `version: int` format: int32 - `archived_at: Optional[datetime]` When the session was archived. Null if not archived. format: date-time - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's enforced spend ceiling, or null when no budget is set. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `environment_id: str` - `metadata: Dict[str, str]` - `outcome_evaluations: List[BetaManagedAgentsOutcomeEvaluationResource]` Per-outcome evaluation state. One entry per `define_outcome` event sent to the session. - `type: Literal["outcome_evaluation"]` - `completed_at: Optional[datetime]` When the outcome reached a terminal result. Null while `pending`/`running`/`evaluating`. format: date-time - `description: str` What the agent should produce. - `explanation: Optional[str]` Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable. - `iteration: int` 0-indexed revision cycle the outcome is currently on. format: int32 - `outcome_id: str` Server-generated outc_ ID for this outcome. - `result: str` Current evaluation state. `pending` before the agent begins work; `running` while producing or revising; `evaluating` while the grader scores; `satisfied`/`max_iterations_reached`/`failed`/`interrupted` are terminal. - `resources: List[BetaManagedAgentsSessionResource]` - `class BetaManagedAgentsGitHubRepositoryResource` - `type: Literal["github_repository"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `url: str` - `checkout: Optional[Checkout]` - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `class BetaManagedAgentsFileResource` - `type: Literal["file"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `file_id: str` - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `class BetaManagedAgentsMemoryStoreResource` A memory store attached to an agent session. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `description: Optional[str]` Description of the memory store, snapshotted at attach time. Rendered into the agent's system prompt. Empty string when the store has no description. - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. maxLength: 4096 - `mount_path: Optional[str]` Filesystem path where the store is mounted in the session container, e.g. /mnt/memory/user-preferences. Derived from the store's name. Output-only. - `name: Optional[str]` Display name of the memory store, snapshotted at attach time. Later edits to the store's name do not propagate to this resource. - `stats: BetaManagedAgentsSessionStats` Timing statistics for the session. - `active_seconds: Optional[float]` Cumulative time in seconds the session spent in `running` status. Excludes idle time. format: double - `duration_seconds: Optional[float]` Elapsed time since session creation in seconds. For terminated sessions, frozen at the final update. format: double - `status: Literal["rescheduling", "running", "idle", "terminated"]` - `"rescheduling"` Transient error occurred, retrying automatically. - `"running"` Agent is actively executing. - `"idle"` Agent is waiting for input, including user messages or tool confirmations. Sessions start in idle. - `"terminated"` Session has ended, either due to an error or completion. - `title: Optional[str]` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `usage: BetaManagedAgentsSessionUsage` Cumulative token usage for the session. - `active_seconds: Optional[float]` Cumulative time in seconds during which the session had at least one thread in running status. Overlapping activity from concurrent threads is counted once, unlike `stats.active_seconds`, which sums each thread's own active time. This is the duration the session's runtime cost is priced on. format: double - `cache_creation: Optional[BetaManagedAgentsCacheCreationUsage]` Tokens used to create prompt cache entries, broken down by cache TTL. - `ephemeral_1h_input_tokens: Optional[int]` Tokens used to create 1-hour ephemeral cache entries. format: int32 - `ephemeral_5m_input_tokens: Optional[int]` Tokens used to create 5-minute ephemeral cache entries. format: int32 - `cache_read_input_tokens: Optional[int]` Total tokens read from prompt cache. format: int32 - `input_tokens: Optional[int]` Total input tokens consumed across all turns. format: int32 - `list_cost: Optional[BetaMonetaryAmount]` Cumulative list cost of the session across all turns, priced at public list rates. Absent until cost tracking is available for the session. - `output_tokens: Optional[int]` Total output tokens generated across all turns. format: int32 - `server_tool_use: Optional[BetaManagedAgentsServerToolUsage]` Cumulative server-executed tool usage across all turns. Absent until server-tool tracking is available for the session. - `web_fetch_requests: Optional[int]` Number of server-executed web fetch requests. format: int32 - `web_search_requests: Optional[int]` Number of server-executed web search requests. format: int32 - `vault_ids: List[str]` Vault IDs attached to the session at creation. Empty when no vaults were supplied. - `deployment_id: Optional[str]` Deployment ID when the session was created from a deployment reference. Null otherwise. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_session = client.beta.sessions.update( session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ) print(beta_managed_agents_session.id) ``` ##### Response (200) ```json { "id": "sesn_011CZkZAtmR3yMPDzynEDxu7", "agent": { "id": "agent_011CZkYpogX7uDKUyvBTophP", "description": "A general-purpose starter agent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "description": "A focused research subagent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "name": "Researcher", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" } ], "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 } ], "type": "coordinator" }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 }, "archived_at": null, "budget": { "max_list_cost": { "amount": "2500", "currency": "USD" }, "type": "limit" }, "created_at": "2026-03-15T10:00:00Z", "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "metadata": {}, "outcome_evaluations": [ { "completed_at": "2026-03-15T10:02:31Z", "description": "Produce a 2-page summary as summary.md", "explanation": "All five sections present with inline citations.", "iteration": 0, "outcome_id": "outc_011CZkZRSw2kEfs6ncTVmjxP", "result": "satisfied", "type": "outcome_evaluation" } ], "resources": [ { "id": "sesrsc_011CZkZBJq5dWxk9fVLNcPht", "created_at": "2026-03-15T10:00:00Z", "file_id": "file_011CNha8iCJcU1wXNR6q4V8w", "mount_path": "/uploads/receipt.pdf", "type": "file", "updated_at": "2026-03-15T10:00:00Z" }, { "id": "sesrsc_011CZkZCKr6eXym1gWMPdQiu", "created_at": "2026-03-15T10:00:00Z", "mount_path": "/workspace/example-repo", "type": "github_repository", "updated_at": "2026-03-15T10:00:00Z", "url": "https://github.com/example-org/example-repo", "checkout": { "name": "main", "type": "branch" } } ], "stats": { "active_seconds": 0, "duration_seconds": 0 }, "status": "idle", "title": "Order #1234 inquiry", "type": "session", "updated_at": "2026-03-15T10:00:00Z", "usage": { "active_seconds": 0, "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_read_input_tokens": 0, "input_tokens": 0, "list_cost": { "amount": "2500", "currency": "USD" }, "output_tokens": 0, "server_tool_use": { "web_fetch_requests": 0, "web_search_requests": 3 } }, "vault_ids": [ "vlt_011CZkZDLs7fYzm1hXNPeRjv" ], "deployment_id": "deployment_id" } ``` ### Delete Session `beta.sessions.delete(session_id, **kwargs) -> BetaManagedAgentsDeletedSession` **DELETE** `/v1/sessions/{session_id}` Delete Session #### Parameters - `session_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeletedSession` Confirmation that a `session` has been permanently deleted. - `type: Literal["session_deleted"]` - `id: str` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deleted_session = client.beta.sessions.delete( session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ) print(beta_managed_agents_deleted_session.id) ``` ##### Response (200) ```json { "id": "sesn_011CZkZAtmR3yMPDzynEDxu7", "type": "session_deleted" } ``` ### Archive Session `beta.sessions.archive(session_id, **kwargs) -> BetaManagedAgentsSession` **POST** `/v1/sessions/{session_id}/archive` Archive Session #### Parameters - `session_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsSession` A Managed Agents `session`. - `type: Literal["session"]` - `id: str` - `agent: BetaManagedAgentsSessionAgent` Resolved `agent` definition for a `session`. Snapshot of the `agent` at `session` creation time. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsSessionMultiagent]` Resolved multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsSessionMultiagentCoordinator` Resolved coordinator topology with full agent definitions for each roster member. - `type: Literal["coordinator"]` - `agents: List[Agent]` Full `agent` definitions the coordinator may spawn as session threads. - `class BetaManagedAgentsSessionThreadAgent` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsSessionMultiagent20261001` Resolved multiagent configuration with three members, as copied to the `session` at creation. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsSessionMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsSessionMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that this agent can spawn as session threads. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsSessionMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsSessionMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that a run's plan can use. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `class BetaManagedAgentsMCPToolset` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `version: int` format: int32 - `archived_at: Optional[datetime]` When the session was archived. Null if not archived. format: date-time - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's enforced spend ceiling, or null when no budget is set. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `environment_id: str` - `metadata: Dict[str, str]` - `outcome_evaluations: List[BetaManagedAgentsOutcomeEvaluationResource]` Per-outcome evaluation state. One entry per `define_outcome` event sent to the session. - `type: Literal["outcome_evaluation"]` - `completed_at: Optional[datetime]` When the outcome reached a terminal result. Null while `pending`/`running`/`evaluating`. format: date-time - `description: str` What the agent should produce. - `explanation: Optional[str]` Grader's verdict text from the most recent evaluation. For `satisfied`, explains why criteria are met; for `needs_revision` (intermediate), what's missing; for `failed`, why unrecoverable. - `iteration: int` 0-indexed revision cycle the outcome is currently on. format: int32 - `outcome_id: str` Server-generated outc_ ID for this outcome. - `result: str` Current evaluation state. `pending` before the agent begins work; `running` while producing or revising; `evaluating` while the grader scores; `satisfied`/`max_iterations_reached`/`failed`/`interrupted` are terminal. - `resources: List[BetaManagedAgentsSessionResource]` - `class BetaManagedAgentsGitHubRepositoryResource` - `type: Literal["github_repository"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `url: str` - `checkout: Optional[Checkout]` - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `class BetaManagedAgentsFileResource` - `type: Literal["file"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `file_id: str` - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `class BetaManagedAgentsMemoryStoreResource` A memory store attached to an agent session. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `description: Optional[str]` Description of the memory store, snapshotted at attach time. Rendered into the agent's system prompt. Empty string when the store has no description. - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. maxLength: 4096 - `mount_path: Optional[str]` Filesystem path where the store is mounted in the session container, e.g. /mnt/memory/user-preferences. Derived from the store's name. Output-only. - `name: Optional[str]` Display name of the memory store, snapshotted at attach time. Later edits to the store's name do not propagate to this resource. - `stats: BetaManagedAgentsSessionStats` Timing statistics for the session. - `active_seconds: Optional[float]` Cumulative time in seconds the session spent in `running` status. Excludes idle time. format: double - `duration_seconds: Optional[float]` Elapsed time since session creation in seconds. For terminated sessions, frozen at the final update. format: double - `status: Literal["rescheduling", "running", "idle", "terminated"]` - `"rescheduling"` Transient error occurred, retrying automatically. - `"running"` Agent is actively executing. - `"idle"` Agent is waiting for input, including user messages or tool confirmations. Sessions start in idle. - `"terminated"` Session has ended, either due to an error or completion. - `title: Optional[str]` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `usage: BetaManagedAgentsSessionUsage` Cumulative token usage for the session. - `active_seconds: Optional[float]` Cumulative time in seconds during which the session had at least one thread in running status. Overlapping activity from concurrent threads is counted once, unlike `stats.active_seconds`, which sums each thread's own active time. This is the duration the session's runtime cost is priced on. format: double - `cache_creation: Optional[BetaManagedAgentsCacheCreationUsage]` Tokens used to create prompt cache entries, broken down by cache TTL. - `ephemeral_1h_input_tokens: Optional[int]` Tokens used to create 1-hour ephemeral cache entries. format: int32 - `ephemeral_5m_input_tokens: Optional[int]` Tokens used to create 5-minute ephemeral cache entries. format: int32 - `cache_read_input_tokens: Optional[int]` Total tokens read from prompt cache. format: int32 - `input_tokens: Optional[int]` Total input tokens consumed across all turns. format: int32 - `list_cost: Optional[BetaMonetaryAmount]` Cumulative list cost of the session across all turns, priced at public list rates. Absent until cost tracking is available for the session. - `output_tokens: Optional[int]` Total output tokens generated across all turns. format: int32 - `server_tool_use: Optional[BetaManagedAgentsServerToolUsage]` Cumulative server-executed tool usage across all turns. Absent until server-tool tracking is available for the session. - `web_fetch_requests: Optional[int]` Number of server-executed web fetch requests. format: int32 - `web_search_requests: Optional[int]` Number of server-executed web search requests. format: int32 - `vault_ids: List[str]` Vault IDs attached to the session at creation. Empty when no vaults were supplied. - `deployment_id: Optional[str]` Deployment ID when the session was created from a deployment reference. Null otherwise. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_session = client.beta.sessions.archive( session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ) print(beta_managed_agents_session.id) ``` ##### Response (200) ```json { "id": "sesn_011CZkZAtmR3yMPDzynEDxu7", "agent": { "id": "agent_011CZkYpogX7uDKUyvBTophP", "description": "A general-purpose starter agent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "multiagent": { "agents": [ { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "description": "A focused research subagent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "name": "Researcher", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" } ], "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 } ], "type": "coordinator" }, "name": "My First Agent", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" }, { "skill_id": "skill_011CZkZFNu9hAbo3jZPRgTmx", "type": "custom", "version": "2" } ], "system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 }, "archived_at": null, "budget": { "max_list_cost": { "amount": "2500", "currency": "USD" }, "type": "limit" }, "created_at": "2026-03-15T10:00:00Z", "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "metadata": {}, "outcome_evaluations": [ { "completed_at": "2026-03-15T10:02:31Z", "description": "Produce a 2-page summary as summary.md", "explanation": "All five sections present with inline citations.", "iteration": 0, "outcome_id": "outc_011CZkZRSw2kEfs6ncTVmjxP", "result": "satisfied", "type": "outcome_evaluation" } ], "resources": [ { "id": "sesrsc_011CZkZBJq5dWxk9fVLNcPht", "created_at": "2026-03-15T10:00:00Z", "file_id": "file_011CNha8iCJcU1wXNR6q4V8w", "mount_path": "/uploads/receipt.pdf", "type": "file", "updated_at": "2026-03-15T10:00:00Z" }, { "id": "sesrsc_011CZkZCKr6eXym1gWMPdQiu", "created_at": "2026-03-15T10:00:00Z", "mount_path": "/workspace/example-repo", "type": "github_repository", "updated_at": "2026-03-15T10:00:00Z", "url": "https://github.com/example-org/example-repo", "checkout": { "name": "main", "type": "branch" } } ], "stats": { "active_seconds": 0, "duration_seconds": 0 }, "status": "idle", "title": "Order #1234 inquiry", "type": "session", "updated_at": "2026-03-15T10:00:00Z", "usage": { "active_seconds": 0, "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_read_input_tokens": 0, "input_tokens": 0, "list_cost": { "amount": "2500", "currency": "USD" }, "output_tokens": 0, "server_tool_use": { "web_fetch_requests": 0, "web_search_requests": 3 } }, "vault_ids": [ "vlt_011CZkZDLs7fYzm1hXNPeRjv" ], "deployment_id": "deployment_id" } ``` ## Beta › Sessions › Events ### List Events `beta.sessions.events.list(session_id, **kwargs) -> SyncPageCursor[BetaManagedAgentsSessionEvent]` **GET** `/v1/sessions/{session_id}/events` List Events #### Parameters - `session_id: str` (path parameter) - `created_at_gt: Optional[Union[str, datetime]]` (query parameter) Return events created after this time (exclusive). Compared against the event's `processed_at` value. format: date-time - `created_at_gte: Optional[Union[str, datetime]]` (query parameter) Return events created at or after this time (inclusive). Compared against the event's `processed_at` value. format: date-time - `created_at_lt: Optional[Union[str, datetime]]` (query parameter) Return events created before this time (exclusive). Compared against the event's `processed_at` value. format: date-time - `created_at_lte: Optional[Union[str, datetime]]` (query parameter) Return events created at or before this time (inclusive). Compared against the event's `processed_at` value. format: date-time - `limit: Optional[int]` (query parameter) format: int32 - `order: Optional[Literal["asc", "desc"]]` (query parameter) Sort direction for results, ordered by the event's `processed_at`. Defaults to `asc` (chronological). - `"asc"` - `"desc"` - `page: Optional[str]` (query parameter) Opaque pagination cursor from a previous response's `next_page`. - `types: Optional[List[BetaManagedAgentsSessionEventType]]` (query parameter) Filter by event type. Values match the `type` field on returned events (for example, `user.message` or `agent.tool_use`). Omit to return all event types. - `"user.message"` - `"user.interrupt"` - `"user.tool_confirmation"` - `"user.custom_tool_result"` - `"agent.custom_tool_use"` - `"agent.message"` - `"agent.thinking"` - `"agent.mcp_tool_use"` - `"agent.mcp_tool_result"` - `"agent.tool_use"` - `"agent.tool_result"` - `"agent.thread_message_received"` - `"agent.thread_message_sent"` - `"agent.thread_context_compacted"` - `"session.error"` - `"session.status_rescheduled"` - `"session.status_running"` - `"session.status_idle"` - `"session.status_terminated"` - `"session.thread_created"` - `"span.outcome_evaluation_start"` - `"span.outcome_evaluation_end"` - `"span.model_request_start"` - `"span.model_request_end"` - `"span.outcome_evaluation_ongoing"` - `"user.define_outcome"` - `"session.thread_status_running"` - `"session.thread_status_idle"` - `"session.thread_status_terminated"` - `"user.tool_result"` - `"session.thread_status_rescheduled"` - `"session.updated"` - `"system.message"` - `"session.usage"` - `"workflow_run.created"` - `"workflow_run.status_running"` - `"workflow_run.status_idle"` - `"workflow_run.status_ended"` - `"workflow_run.error"` - `"workflow_run.phase_started"` - `"workflow_run.phase_ended"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `type BetaManagedAgentsSessionEvent = ...` Union type for all event types in a session. - `class BetaManagedAgentsUserMessageEvent` A user message event in the session conversation. - `type: Literal["user.message"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Array of content blocks comprising the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `processed_at: Optional[datetime]` Timestamp when the agent finished processing this message. format: date-time - `class BetaManagedAgentsUserInterruptEvent` An interrupt event that pauses agent execution and returns control to the user. - `type: Literal["user.interrupt"]` - `id: str` Unique identifier for this event. - `processed_at: Optional[datetime]` Timestamp when the interrupt was processed. format: date-time - `session_thread_id: Optional[str]` If absent, interrupts every non-archived thread in a multiagent session (or the primary alone in a single-agent session). If present, interrupts only the named thread. - `class BetaManagedAgentsUserToolConfirmationEvent` A tool confirmation event that approves or denies a pending tool execution. - `type: Literal["user.tool_confirmation"]` - `id: str` Unique identifier for this event. - `result: Literal["allow", "deny"]` The confirmation result: 'allow' or 'deny'. - `"allow"` - `"deny"` - `tool_use_id: str` The id of the `agent.tool_use` or `agent.mcp_tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `deny_message: Optional[str]` Optional message providing context for a 'deny' decision. Only allowed when result is 'deny'. maxLength: 10000 - `processed_at: Optional[datetime]` Timestamp when the confirmation was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this confirmation was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsUserCustomToolResultEvent` Event sent by the client providing the result of a custom tool execution. - `type: Literal["user.custom_tool_result"]` - `id: str` Unique identifier for this event. - `custom_tool_use_id: str` The id of the `agent.custom_tool_use` event this result corresponds to. It is also listed in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `type: Literal["search_result"]` - `citations: BetaManagedAgentsSearchResultCitations` Citation settings for this search result. - `enabled: bool` Whether citations are enabled for this search result. - `content: List[BetaManagedAgentsSearchResultContent]` Array of text content blocks from the search result. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `source: str` The URL source of the search result. minLength: 1 - `title: str` The title of the search result. minLength: 1 - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `processed_at: Optional[datetime]` Timestamp when this result was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this result was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsAgentCustomToolUseEvent` Event emitted when the agent calls a custom tool. The session goes idle until the client sends a `user.custom_tool_result` event with the result. The client can send it as soon as this event arrives, without waiting for `session.status_idle`. - `type: Literal["agent.custom_tool_use"]` - `id: str` Unique identifier for this event. - `input: Dict[str, object]` Input parameters for the tool call. - `name: str` Name of the custom tool being called. - `processed_at: datetime` Timestamp when this tool use was processed. format: date-time - `session_thread_id: Optional[str]` When set, this event was cross-posted from a subagent's thread to surface its custom tool use on the primary thread's stream. Empty on the thread's own events. Informational only: the server routes the matching `user.custom_tool_result` by `custom_tool_use_id`, so clients do not send it back. - `class BetaManagedAgentsAgentMessageEvent` An agent response event in the session conversation. - `type: Literal["agent.message"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Array of text blocks comprising the agent response. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `processed_at: datetime` Timestamp when this response was generated. format: date-time - `class BetaManagedAgentsAgentThinkingEvent` Indicates the agent is making forward progress via extended thinking. A progress signal, not a content carrier. - `type: Literal["agent.thinking"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this thinking was produced. format: date-time - `class BetaManagedAgentsAgentMCPToolUseEvent` Event emitted when the agent invokes a tool provided by an MCP server. - `type: Literal["agent.mcp_tool_use"]` - `id: str` Unique identifier for this event. - `input: Dict[str, object]` Input parameters for the tool call. - `mcp_server_name: str` Name of the MCP server providing the tool. - `name: str` Name of the MCP tool being used. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `evaluated_permission: Optional[BetaManagedAgentsAgentEvaluatedPermission]` The evaluated permission policy for this tool invocation. - `"allow"` - `"ask"` - `"deny"` - `evaluation: Optional[BetaManagedAgentsAgentToolEvaluation]` Which resolved permission_policy produced evaluated_permission: always_allow, always_ask, or auto (with the server's per-invocation judgement). Absent only when the server refused the call before any policy applied (for example, the named tool is not enabled in the session); such a refusal has evaluated_permission deny. An event recorded before this field existed reads as the arm its evaluated_permission implies (always_allow for allow, always_ask for ask). - `class BetaManagedAgentsAgentToolEvaluationAlwaysAllow` The resolved permission_policy was always_allow; accompanies evaluated_permission "allow". - `type: Literal["always_allow"]` - `class BetaManagedAgentsAgentToolEvaluationAlwaysAsk` The resolved permission_policy was always_ask; accompanies evaluated_permission "ask". - `type: Literal["always_ask"]` - `class BetaManagedAgentsAgentToolEvaluationAuto` The resolved permission_policy was auto: the server judged this invocation individually. - `type: Literal["auto"]` - `evaluated_permission: BetaManagedAgentsAgentAutoEvaluatedPermission` The server's judgement for this invocation. - `class BetaManagedAgentsAgentAutoEvaluatedPermissionAllow` The server judged the invocation safe to execute without client approval. - `type: Literal["allow"]` - `class BetaManagedAgentsAgentAutoEvaluatedPermissionAsk` The server reached no judgement; the invocation is held for client approval. - `type: Literal["ask"]` - `reason_code: str` The judgement's grounds in registry-bound terms, for client branching and audit rather than end-user display. Open registry; currently "indeterminate" (no judgement was reached). Clients must tolerate values outside this set. maxLength: 64 - `class BetaManagedAgentsAgentAutoEvaluatedPermissionDeny` The server judged the invocation high-risk; it does not execute and a synthetic error tool result is appended. - `type: Literal["deny"]` - `reason_code: str` The judgement's grounds in registry-bound terms. Open registry; currently "high_risk" (judged high-risk; the call does not run). Clients must tolerate values outside this set. maxLength: 64 - `session_thread_id: Optional[str]` When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Informational only: the server routes the matching `user.tool_confirmation` by `tool_use_id`, so clients do not send it back. - `class BetaManagedAgentsAgentMCPToolResultEvent` Event representing the result of an MCP tool execution. - `type: Literal["agent.mcp_tool_result"]` - `id: str` Unique identifier for this event. - `mcp_tool_use_id: str` The id of the `agent.mcp_tool_use` event this result corresponds to. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `class BetaManagedAgentsAgentToolUseEvent` Event emitted when the agent invokes a built-in agent tool. - `type: Literal["agent.tool_use"]` - `id: str` Unique identifier for this event. - `input: Dict[str, object]` Input parameters for the tool call. - `name: str` Name of the agent tool being used. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `evaluated_permission: Optional[BetaManagedAgentsAgentEvaluatedPermission]` The evaluated permission policy for this tool invocation. - `evaluation: Optional[BetaManagedAgentsAgentToolEvaluation]` Which resolved permission_policy produced evaluated_permission: always_allow, always_ask, or auto (with the server's per-invocation judgement). Absent only when the server refused the call before any policy applied (for example, the named tool is not enabled in the session); such a refusal has evaluated_permission deny. An event recorded before this field existed reads as the arm its evaluated_permission implies (always_allow for allow, always_ask for ask). - `session_thread_id: Optional[str]` When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Informational only: the server routes the matching `user.tool_confirmation` or `user.tool_result` by `tool_use_id`, so clients do not send it back. - `class BetaManagedAgentsAgentToolResultEvent` Event representing the result of an agent tool execution. - `type: Literal["agent.tool_result"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `tool_use_id: str` The id of the `agent.tool_use` event this result corresponds to. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `class BetaManagedAgentsAgentThreadMessageReceivedEvent` Delivery event written to the target thread's input stream when an agent-to-agent message arrives. - `type: Literal["agent.thread_message_received"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Message content blocks. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `from_session_thread_id: str` Public `sthr_` ID of the thread that sent the message. - `processed_at: datetime` Timestamp when the message was received. format: date-time - `from_agent_name: Optional[str]` Name of the callable agent this message came from. Absent when received from the primary agent. - `class BetaManagedAgentsAgentThreadMessageSentEvent` Observability event emitted to the sender's output stream when an agent-to-agent message is sent. - `type: Literal["agent.thread_message_sent"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Message content blocks. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `processed_at: datetime` Timestamp when the message was sent. format: date-time - `to_session_thread_id: str` Public `sthr_` ID of the thread the message was sent to. - `to_agent_name: Optional[str]` Name of the callable agent this message was sent to. Absent when sent to the primary agent. - `class BetaManagedAgentsAgentThreadContextCompactedEvent` Indicates that context compaction (summarization) occurred during the session. - `type: Literal["agent.thread_context_compacted"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when compaction was processed. format: date-time - `class BetaManagedAgentsSessionErrorEvent` An error event indicating a problem occurred during session execution. - `type: Literal["session.error"]` - `id: str` Unique identifier for this event. - `error: Error` - `class BetaManagedAgentsUnknownError` An unknown or unexpected error occurred during session execution. A fallback variant; clients that don't recognize a new error code can match on `retry_status` and `message` alone. - `type: Literal["unknown_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `type: Literal["retrying"]` - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `type: Literal["exhausted"]` - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `type: Literal["terminal"]` - `class BetaManagedAgentsModelOverloadedError` The model is currently overloaded. Emitted after automatic retries are exhausted. - `type: Literal["model_overloaded_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsModelRateLimitedError` The model request was rate-limited. - `type: Literal["model_rate_limited_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsModelRequestFailedError` A model request failed for a reason other than overload or rate-limiting. - `type: Literal["model_request_failed_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsMCPConnectionFailedError` Failed to connect to an MCP server. - `type: Literal["mcp_connection_failed_error"]` - `mcp_server_name: str` Name of the MCP server that failed to connect. - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsMCPAuthenticationFailedError` Authentication to an MCP server failed. - `type: Literal["mcp_authentication_failed_error"]` - `mcp_server_name: str` Name of the MCP server that failed authentication. - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsBillingError` The caller's organization or workspace cannot make model requests — out of credits or spend limit reached. Retrying with the same credentials will not succeed; the caller must resolve the billing state. - `type: Literal["billing_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsCredentialHostUnreachableError` An `environment_variable` credential's `auth.networking.allowed_hosts` includes a host the environment's network policy does not permit. - `type: Literal["credential_host_unreachable_error"]` - `credential_id: str` ID of the affected credential. - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `vault_id: str` ID of the vault containing the affected credential. - `class BetaManagedAgentsRepositoryAuthenticationError` The repository host rejected the credentials, or required credentials and received none. - `type: Literal["repository_authentication_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryForbiddenError` The repository host refused access to the repository. - `type: Literal["repository_forbidden_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryNotFoundError` The repository host reported the repository as not found. - `type: Literal["repository_not_found_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryCheckoutError` The requested branch or commit does not exist in the repository. - `type: Literal["repository_checkout_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryCloneError` The repository could not be cloned. - `type: Literal["repository_clone_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `processed_at: datetime` Timestamp when the error occurred. format: date-time - `class BetaManagedAgentsSessionStatusRescheduledEvent` Indicates the session is recovering from an error state and is rescheduled for execution. - `type: Literal["session.status_rescheduled"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `class BetaManagedAgentsSessionStatusRunningEvent` Indicates the session is actively running and the agent is working. - `type: Literal["session.status_running"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `class BetaManagedAgentsSessionStatusIdleEvent` Indicates the agent has paused and is awaiting user input. - `type: Literal["session.status_idle"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `stop_details: Optional[BetaManagedAgentsSessionRefusalStopDetails]` Structured information about why the session stopped. `null` when there is nothing more to report. - `type: Literal["refusal"]` - `category: Optional[Literal["cyber", "bio", "frontier_llm", 2 more]]` The policy category that triggered the refusal, or `null` when there is no named category. New values can be added over time. - `"cyber"` - `"bio"` - `"frontier_llm"` - `"reasoning_extraction"` - `"general_harms"` - `explanation: Optional[str]` Human-readable explanation of the refusal, or `null` when none is available. The wording can change, so do not parse it. - `stop_reason: StopReason` - `class BetaManagedAgentsSessionEndTurn` The agent completed its turn naturally and is ready for the next user message. - `type: Literal["end_turn"]` - `class BetaManagedAgentsSessionRequiresAction` The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running. - `type: Literal["requires_action"]` - `event_ids: List[str]` The ids of events the agent is blocked on. Resolving fewer than all re-emits `session.status_idle` with the remainder. - `class BetaManagedAgentsSessionRetriesExhausted` The turn ended because repeated errors exhausted the retry budget or an error escalated to `retry_status: 'exhausted'`. - `type: Literal["retries_exhausted"]` - `class BetaManagedAgentsSessionBudgetReached` The agent stopped because the session's tracked list cost reached its budget, or because its usage includes a model with no list price (which the budget cannot measure). Raise the budget to continue — or, if raising is rejected because a model has no list price, remove the budget. - `type: Literal["budget_reached"]` - `class BetaManagedAgentsSessionRefusal` The turn ended because the model's response was refused, for example by a safety classifier. - `type: Literal["refusal"]` - `class BetaManagedAgentsSessionStatusTerminatedEvent` Indicates the session has terminated, either due to an error or completion. - `type: Literal["session.status_terminated"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `class BetaManagedAgentsSessionThreadCreatedEvent` Emitted when a child thread is created. Written to the parent thread's output stream so clients observing the session see child creation. - `type: Literal["session.thread_created"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the callable agent the thread runs. - `processed_at: datetime` Timestamp when the thread was created. format: date-time - `session_thread_id: str` Public `sthr_` ID of the newly created thread. - `workflow_run_id: Optional[str]` Identifier of the workflow run that created the thread, or `null` for any other thread. - `class BetaManagedAgentsSpanOutcomeEvaluationStartEvent` Emitted when an outcome evaluation cycle begins. - `type: Literal["span.outcome_evaluation_start"]` - `id: str` Unique identifier for this event. - `iteration: int` 0-indexed revision cycle. 0 is the first evaluation; 1 is the re-evaluation after the first revision; etc. format: int32 - `outcome_id: str` The `outc_` ID of the outcome being evaluated. - `processed_at: datetime` Timestamp when outcome evaluation started. format: date-time - `class BetaManagedAgentsSpanOutcomeEvaluationEndEvent` Emitted when an outcome evaluation cycle completes. Carries the verdict and aggregate token usage. A verdict of `needs_revision` means another evaluation cycle follows; `satisfied`, `max_iterations_reached`, `failed`, or `interrupted` are terminal — no further evaluation cycles follow. - `type: Literal["span.outcome_evaluation_end"]` - `id: str` Unique identifier for this event. - `explanation: str` Human-readable explanation of the verdict. For `needs_revision`, describes which criteria failed and why. - `iteration: int` 0-indexed revision cycle, matching the corresponding `span.outcome_evaluation_start`. format: int32 - `outcome_evaluation_start_id: str` The id of the corresponding `span.outcome_evaluation_start` event. - `outcome_id: str` The `outc_` ID of the outcome being evaluated. - `processed_at: datetime` Timestamp when outcome evaluation ended. format: date-time - `result: str` Evaluation verdict. 'satisfied': criteria met, session goes idle. 'needs_revision': criteria not met, another revision cycle follows. 'max_iterations_reached': evaluation budget exhausted with criteria still unmet — one final acknowledgment turn follows before the session goes idle, but no further evaluation runs. 'failed': grader determined the rubric does not apply to the deliverables. 'interrupted': user sent an interrupt while evaluation was in progress. - `usage: BetaManagedAgentsSpanModelUsage` Aggregate token usage for this evaluation cycle. Sums across all grader model requests within the cycle. - `cache_creation_input_tokens: int` Tokens used to create prompt cache in this request. format: int32 - `cache_read_input_tokens: int` Tokens read from prompt cache in this request. format: int32 - `input_tokens: int` Input tokens consumed by this request. format: int32 - `output_tokens: int` Output tokens generated by this request. format: int32 - `speed: Optional[Literal["standard", "fast"]]` Inference speed tier this request actually ran at. Mirrors `usage.speed` on /v1/messages. Only present when the fast-mode beta is active. - `"standard"` - `"fast"` - `class BetaManagedAgentsSpanModelRequestStartEvent` Emitted when a model request is initiated by the agent. - `type: Literal["span.model_request_start"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the model request started. format: date-time - `class BetaManagedAgentsSpanModelRequestEndEvent` Emitted when a model request completes. - `type: Literal["span.model_request_end"]` - `id: str` Unique identifier for this event. - `is_error: Optional[bool]` Whether the model request resulted in an error. - `model_request_start_id: str` The id of the corresponding `span.model_request_start` event. - `model_usage: BetaManagedAgentsSpanModelUsage` Token usage for this model request. - `processed_at: datetime` Timestamp when the model request completed. format: date-time - `class BetaManagedAgentsSpanOutcomeEvaluationOngoingEvent` Periodic heartbeat emitted while an outcome evaluation cycle is in progress. Distinguishes 'evaluation is actively running' from 'evaluation is stuck' between the corresponding `span.outcome_evaluation_start` and `span.outcome_evaluation_end` events. - `type: Literal["span.outcome_evaluation_ongoing"]` - `id: str` Unique identifier for this event. - `iteration: int` 0-indexed revision cycle, matching the corresponding `span.outcome_evaluation_start`. format: int32 - `outcome_id: str` The `outc_` ID of the outcome being evaluated. - `processed_at: datetime` Timestamp when this heartbeat was emitted. format: date-time - `class BetaManagedAgentsUserDefineOutcomeEvent` Echo of a `user.define_outcome` input event. Carries the server-generated `outcome_id` that subsequent `span.outcome_evaluation_*` events reference. - `type: Literal["user.define_outcome"]` - `id: str` Unique identifier for this event. - `description: str` What the agent should produce. Copied from the input event. - `max_iterations: Optional[int]` Evaluate-then-revise cycles before giving up. Default 3, max 20. format: int32 - `outcome_id: str` Server-generated `outc_` ID for this outcome. Referenced by `span.outcome_evaluation_*` events and the session's `outcome_evaluations` list. - `processed_at: datetime` Timestamp when the outcome was accepted. format: date-time - `rubric: Rubric` How to grade the outcome. File rubrics are currently resolved to their text content; clients should handle both variants. - `class BetaManagedAgentsFileRubric` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubric` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. - `class BetaManagedAgentsSessionDeletedEvent` Emitted when a session has been deleted. Terminates any active event stream — no further events will be emitted for this session. - `type: Literal["session.deleted"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the session was deleted. format: date-time - `class BetaManagedAgentsSessionThreadStatusRunningEvent` A session thread has begun executing. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_running"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that started running. - `class BetaManagedAgentsSessionThreadStatusIdleEvent` A session thread has yielded and is awaiting input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_idle"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that went idle. - `stop_details: Optional[BetaManagedAgentsSessionRefusalStopDetails]` Structured information about why the thread stopped. `null` when there is nothing more to report. - `stop_reason: StopReason` - `class BetaManagedAgentsSessionEndTurn` The agent completed its turn naturally and is ready for the next user message. - `class BetaManagedAgentsSessionRequiresAction` The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running. - `class BetaManagedAgentsSessionRetriesExhausted` The turn ended because repeated errors exhausted the retry budget or an error escalated to `retry_status: 'exhausted'`. - `class BetaManagedAgentsSessionBudgetReached` The agent stopped because the session's tracked list cost reached its budget, or because its usage includes a model with no list price (which the budget cannot measure). Raise the budget to continue — or, if raising is rejected because a model has no list price, remove the budget. - `class BetaManagedAgentsSessionRefusal` The turn ended because the model's response was refused, for example by a safety classifier. - `class BetaManagedAgentsSessionThreadStatusTerminatedEvent` A session thread has terminated and will accept no further input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_terminated"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that terminated. - `class BetaManagedAgentsUserToolResultEvent` Event sent by the client providing the result of an agent-toolset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `type: Literal["user.tool_result"]` - `id: str` Unique identifier for this event. - `tool_use_id: str` The id of the `agent.tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `processed_at: Optional[datetime]` Timestamp when this result was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this result was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsSessionThreadStatusRescheduledEvent` A session thread hit a transient error and is retrying automatically. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_rescheduled"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that is retrying. - `class BetaManagedAgentsSessionUpdatedEvent` Emitted when an UpdateSession request changed at least one field. Carries only the fields that changed; absent fields were not part of the update. The new configuration applies from the next turn. - `type: Literal["session.updated"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the update was applied. format: date-time - `agent: Optional[BetaManagedAgentsSessionAgent]` The session's effective agent configuration after the update. Present only when the update changed `agent` (tools or mcp_servers); when present it is the full materialised snapshot, not a diff. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsSessionMultiagent]` Resolved multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsSessionMultiagentCoordinator` Resolved coordinator topology with full agent definitions for each roster member. - `type: Literal["coordinator"]` - `agents: List[Agent]` Full `agent` definitions the coordinator may spawn as session threads. - `class BetaManagedAgentsSessionThreadAgent` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsSessionMultiagent20261001` Resolved multiagent configuration with three members, as copied to the `session` at creation. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsSessionMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsSessionMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that this agent can spawn as session threads. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsSessionMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsSessionMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that a run's plan can use. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `class BetaManagedAgentsMCPToolset` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `version: int` format: int32 - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's budget after the update: the new budget when set or replaced, or null when the update removed it. Present only when the update changed the budget. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `metadata: Optional[Dict[str, str]]` The session's full metadata bag after the update. Present when the update set non-empty metadata; absent when metadata was unchanged or cleared to empty. - `title: Optional[str]` The session's new title. Present only when the update changed it. - `class BetaManagedAgentsSystemMessageEvent` A mid-conversation system message event. Carries system-role content that is appended to the session as a `role: "system"` turn. - `type: Literal["system.message"]` - `id: str` Unique identifier for this event. - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `processed_at: Optional[datetime]` Timestamp when this system message was processed. format: date-time - `class BetaManagedAgentsSessionUsageEvent` Periodic snapshot of the session's cumulative usage and tracked list cost. - `type: Literal["session.usage"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the snapshot was taken. format: date-time - `usage: BetaManagedAgentsSessionUsageSnapshot` The session's cumulative usage at the snapshot time. - `active_seconds: Optional[float]` Cumulative time in seconds during which the session had at least one thread in running status. Overlapping activity from concurrent threads is counted once. This is the duration the session's runtime cost is priced on. format: double - `cache_creation: Optional[BetaManagedAgentsCacheCreationUsage]` Tokens used to create prompt cache entries, broken down by cache TTL. - `ephemeral_1h_input_tokens: Optional[int]` Tokens used to create 1-hour ephemeral cache entries. format: int32 - `ephemeral_5m_input_tokens: Optional[int]` Tokens used to create 5-minute ephemeral cache entries. format: int32 - `cache_read_input_tokens: Optional[int]` Total tokens read from prompt cache. format: int32 - `input_tokens: Optional[int]` Total input tokens consumed across all turns. format: int32 - `list_cost: Optional[BetaMonetaryAmount]` Cumulative list cost of the session across all turns, priced at public list rates. - `output_tokens: Optional[int]` Total output tokens generated across all turns. format: int32 - `server_tool_use: Optional[BetaManagedAgentsServerToolUsage]` Cumulative server-executed tool usage across all turns. - `web_fetch_requests: Optional[int]` Number of server-executed web fetch requests. format: int32 - `web_search_requests: Optional[int]` Number of server-executed web search requests. format: int32 - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's configured budget at the snapshot time, or null when the session has no budget. - `class BetaManagedAgentsWorkflowRunCreatedEvent` A workflow run was created. A workflow run is background work that the session's agent starts. Emitted once per run, before the run's other `workflow_run.*` events. - `type: Literal["workflow_run.created"]` - `id: str` Unique identifier for this event. - `description: Optional[str]` Description that the agent gave the run, passed on as written, or `null` if it gave none. - `name: str` Name that the agent gave the run, passed on as written, or a name that the server assigned. - `phases: List[BetaManagedAgentsWorkflowRunPhase]` The phases that the run's plan declares, in the plan's order. Can be empty. - `id: str` Unique identifier for the phase. - `description: Optional[str]` Description that the agent gave the phase, passed on as written, or `null` if it gave none. - `name: str` Name that the agent gave the phase, passed on as written. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunStatusEndedEvent` A workflow run ended. Emitted once per run, as the last of the run's `workflow_run.*` events. - `type: Literal["workflow_run.status_ended"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `result: BetaManagedAgentsWorkflowRunResult` How the run ended. - `class BetaManagedAgentsWorkflowRunResultCompleted` The run's plan, a program that the agent wrote, finished. This does not say whether the work succeeded. - `type: Literal["completed"]` - `class BetaManagedAgentsWorkflowRunResultError` The run failed or reached its time limit. - `type: Literal["error"]` - `error: BetaManagedAgentsWorkflowRunError` Why the run did not finish. - `class BetaManagedAgentsTimeoutWorkflowRunError` The run reached its time limit. - `type: Literal["timeout_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsProgramWorkflowRunError` The plan, a program that the agent wrote, failed, or the server refused it. - `type: Literal["program_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsUnknownWorkflowRunError` A failure that has no type of its own. - `type: Literal["unknown_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsThreadLimitWorkflowRunError` The run exceeded the limit on the number of threads that a run can create. - `type: Literal["thread_limit_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsMaxWorkflowRunsWorkflowRunError` No run was created, because the session was at its limit of open workflow runs, which are runs that have not ended. Only `workflow_run.error` carries this type. - `type: Literal["max_workflow_runs_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsWorkflowRunResultStopped` The agent stopped the run. - `type: Literal["stopped"]` - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunPhaseStartedEvent` A workflow run's plan entered a phase. - `type: Literal["workflow_run.phase_started"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `workflow_run_phase_id: str` Identifier of the phase, as in `phases` on the run's `workflow_run.created` event. - `class BetaManagedAgentsWorkflowRunPhaseEndedEvent` A workflow run's plan left a phase, or the run's end closed it. Emitted once for every `workflow_run.phase_started` event, before the run's `workflow_run.status_ended` event. The event does not say whether the plan finished the phase's work, or why it left. - `type: Literal["workflow_run.phase_ended"]` - `id: str` Unique identifier for this event. - `phase_started_id: str` Identifier of the `workflow_run.phase_started` event that opened the phase. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `workflow_run_phase_id: str` Identifier of the phase, as in `phases` on the run's `workflow_run.created` event. - `class BetaManagedAgentsWorkflowRunStatusRunningEvent` A workflow run is running. Emitted when the run starts to execute, and each time it resumes after being idle. A run that starts idle emits `workflow_run.status_idle` first. - `type: Literal["workflow_run.status_running"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunStatusIdleEvent` A workflow run is idle. Emitted each time the run goes idle, whatever the cause. If the run ends while idle, no `workflow_run.status_running` comes between this event and its `workflow_run.status_ended`. - `type: Literal["workflow_run.status_idle"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunErrorEvent` A workflow run met an error, or an error kept a run from being created. A run that ends with a `result.type` of `error` emits this event before its `workflow_run.status_ended`, with the same `error`. - `type: Literal["workflow_run.error"]` - `id: str` Unique identifier for this event. - `error: BetaManagedAgentsWorkflowRunError` Why the run did not finish, or was not created. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: Optional[str]` Identifier of the run that met the error, or `null` when the error kept a run from being created. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.sessions.events.list( session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ) page = page.data[0] print(page) ``` ##### Response (200) ```json { "data": [ { "id": "sevt_011CZkZGPp1iBcp4kaQSihUm", "content": [ { "text": "Where is my order #1234?", "type": "text" } ], "type": "user.message", "processed_at": "2026-03-15T10:00:00Z" }, { "id": "sevt_011CZkZHPq1jCdq5mbRTjiVn", "content": [ { "text": "Let me look up order #1234 for you.", "type": "text" } ], "processed_at": "2026-03-15T10:00:00Z", "type": "agent.message" } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=" } ``` ### Send Events `beta.sessions.events.send(session_id, **kwargs) -> BetaManagedAgentsSendSessionEvents` **POST** `/v1/sessions/{session_id}/events` Send Events #### Parameters - `session_id: str` (path parameter) - `events: Iterable[BetaManagedAgentsEventParams]` Events to send to the `session`. - `class BetaManagedAgentsUserMessageEventParams` Parameters for sending a user message to the session. - `type: Literal["user.message"]` - `content: Iterable[Content]` Array of content blocks for the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `class BetaManagedAgentsUserInterruptEventParams` Parameters for sending an interrupt to pause the agent. - `type: Literal["user.interrupt"]` - `session_thread_id: Optional[str]` If absent, interrupts every non-archived thread in a multiagent session (or the primary alone in a single-agent session). If present, interrupts only the named thread. - `class BetaManagedAgentsUserToolConfirmationEventParams` Parameters for confirming or denying a tool execution request. - `type: Literal["user.tool_confirmation"]` - `result: Literal["allow", "deny"]` The confirmation result: 'allow' or 'deny'. - `"allow"` - `"deny"` - `tool_use_id: str` The id of the `agent.tool_use` or `agent.mcp_tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. minLength: 1, maxLength: 128 - `deny_message: Optional[str]` Optional message providing context for a 'deny' decision. Only allowed when result is 'deny'. maxLength: 10000 - `class BetaManagedAgentsUserCustomToolResultEventParams` Parameters for providing the result of a custom tool execution. - `type: Literal["user.custom_tool_result"]` - `custom_tool_use_id: str` The id of the `agent.custom_tool_use` event this result corresponds to. It is also listed in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. minLength: 1, maxLength: 128 - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `type: Literal["search_result"]` - `citations: BetaManagedAgentsSearchResultCitations` Citation settings for this search result. - `enabled: bool` Whether citations are enabled for this search result. - `content: List[BetaManagedAgentsSearchResultContent]` Array of text content blocks from the search result. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `source: str` The URL source of the search result. minLength: 1 - `title: str` The title of the search result. minLength: 1 - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `class BetaManagedAgentsUserDefineOutcomeEventParams` Parameters for defining an outcome the agent should work toward. The agent begins work on receipt. - `type: Literal["user.define_outcome"]` - `description: str` What the agent should produce. This is the task specification. - `rubric: Rubric` How to grade the outcome. Text or file reference. - `class BetaManagedAgentsFileRubricParams` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubricParams` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. Maximum 262144 characters. maxLength: 262144 - `max_iterations: Optional[int]` Eval→revision cycles before giving up. Default 3, max 20. format: int32 - `class BetaManagedAgentsUserToolResultEventParams` Parameters for providing the result of an agent-toolset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `type: Literal["user.tool_result"]` - `tool_use_id: str` The id of the `agent.tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. minLength: 1, maxLength: 128 - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `class BetaManagedAgentsSystemMessageEventParams` Privileged context for the accompanying turn and all subsequent turns, appended to the session's system context as a `role: "system"` turn rather than replacing the top-level system prompt. At most one per request: it must be the final event and immediately follow the `user.message`, `user.tool_result`, or `user.custom_tool_result` it accompanies. Only supported on models that accept mid-conversation system messages. - `type: Literal["system.message"]` - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks to append. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsSendSessionEvents` Events that were successfully sent to the session. - `data: Optional[List[Data]]` Sent events - `class BetaManagedAgentsUserMessageEvent` A user message event in the session conversation. - `type: Literal["user.message"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Array of content blocks comprising the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `processed_at: Optional[datetime]` Timestamp when the agent finished processing this message. format: date-time - `class BetaManagedAgentsUserInterruptEvent` An interrupt event that pauses agent execution and returns control to the user. - `type: Literal["user.interrupt"]` - `id: str` Unique identifier for this event. - `processed_at: Optional[datetime]` Timestamp when the interrupt was processed. format: date-time - `session_thread_id: Optional[str]` If absent, interrupts every non-archived thread in a multiagent session (or the primary alone in a single-agent session). If present, interrupts only the named thread. - `class BetaManagedAgentsUserToolConfirmationEvent` A tool confirmation event that approves or denies a pending tool execution. - `type: Literal["user.tool_confirmation"]` - `id: str` Unique identifier for this event. - `result: Literal["allow", "deny"]` The confirmation result: 'allow' or 'deny'. - `"allow"` - `"deny"` - `tool_use_id: str` The id of the `agent.tool_use` or `agent.mcp_tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `deny_message: Optional[str]` Optional message providing context for a 'deny' decision. Only allowed when result is 'deny'. maxLength: 10000 - `processed_at: Optional[datetime]` Timestamp when the confirmation was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this confirmation was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsUserCustomToolResultEvent` Event sent by the client providing the result of a custom tool execution. - `type: Literal["user.custom_tool_result"]` - `id: str` Unique identifier for this event. - `custom_tool_use_id: str` The id of the `agent.custom_tool_use` event this result corresponds to. It is also listed in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `type: Literal["search_result"]` - `citations: BetaManagedAgentsSearchResultCitations` Citation settings for this search result. - `enabled: bool` Whether citations are enabled for this search result. - `content: List[BetaManagedAgentsSearchResultContent]` Array of text content blocks from the search result. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `source: str` The URL source of the search result. minLength: 1 - `title: str` The title of the search result. minLength: 1 - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `processed_at: Optional[datetime]` Timestamp when this result was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this result was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsUserDefineOutcomeEvent` Echo of a `user.define_outcome` input event. Carries the server-generated `outcome_id` that subsequent `span.outcome_evaluation_*` events reference. - `type: Literal["user.define_outcome"]` - `id: str` Unique identifier for this event. - `description: str` What the agent should produce. Copied from the input event. - `max_iterations: Optional[int]` Evaluate-then-revise cycles before giving up. Default 3, max 20. format: int32 - `outcome_id: str` Server-generated `outc_` ID for this outcome. Referenced by `span.outcome_evaluation_*` events and the session's `outcome_evaluations` list. - `processed_at: datetime` Timestamp when the outcome was accepted. format: date-time - `rubric: Rubric` How to grade the outcome. File rubrics are currently resolved to their text content; clients should handle both variants. - `class BetaManagedAgentsFileRubric` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubric` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. - `class BetaManagedAgentsUserToolResultEvent` Event sent by the client providing the result of an agent-toolset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `type: Literal["user.tool_result"]` - `id: str` Unique identifier for this event. - `tool_use_id: str` The id of the `agent.tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `processed_at: Optional[datetime]` Timestamp when this result was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this result was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsSystemMessageEvent` A mid-conversation system message event. Carries system-role content that is appended to the session as a `role: "system"` turn. - `type: Literal["system.message"]` - `id: str` Unique identifier for this event. - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `processed_at: Optional[datetime]` Timestamp when this system message was processed. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_send_session_events = client.beta.sessions.events.send( session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", events=[ { "content": [ { "text": "Where is my order #1234?", "type": "text", } ], "type": "user.message", } ], ) print(beta_managed_agents_send_session_events.data) ``` ##### Response (200) ```json { "data": [ { "id": "sevt_011CZkZGPp1iBcp4kaQSihUm", "content": [ { "text": "Where is my order #1234?", "type": "text" } ], "type": "user.message", "processed_at": "2026-03-15T10:00:00Z" } ] } ``` ### Stream Events `beta.sessions.events.stream(session_id, **kwargs) -> BetaManagedAgentsStreamSessionEvents` **GET** `/v1/sessions/{session_id}/events/stream` Stream Events #### Parameters - `session_id: str` (path parameter) - `event_deltas: Optional[List[BetaManagedAgentsDeltaType]]` (query parameter) When set, this connection also receives streaming deltas (`event_start`, `event_delta`) while an event is being produced, before the event itself arrives. Deltas are best-effort; when the final event is produced it carries the complete content. A model request that ends early (an error or interrupt) produces no final event — its terminal `span.model_request_end` closes the preview. Accepts one or more event types to preview and may be repeated: `agent.message` streams `content_delta` fragments; `agent.thinking` is start-only — a signal that the agent has begun extended thinking, concluded by the `agent.thinking` event itself. Only previews of the requested event types are sent. - `"agent.message"` - `"agent.thinking"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `type BetaManagedAgentsStreamSessionEvents = ...` Server-sent event in the session stream. - `class BetaManagedAgentsUserMessageEvent` A user message event in the session conversation. - `type: Literal["user.message"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Array of content blocks comprising the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `processed_at: Optional[datetime]` Timestamp when the agent finished processing this message. format: date-time - `class BetaManagedAgentsUserInterruptEvent` An interrupt event that pauses agent execution and returns control to the user. - `type: Literal["user.interrupt"]` - `id: str` Unique identifier for this event. - `processed_at: Optional[datetime]` Timestamp when the interrupt was processed. format: date-time - `session_thread_id: Optional[str]` If absent, interrupts every non-archived thread in a multiagent session (or the primary alone in a single-agent session). If present, interrupts only the named thread. - `class BetaManagedAgentsUserToolConfirmationEvent` A tool confirmation event that approves or denies a pending tool execution. - `type: Literal["user.tool_confirmation"]` - `id: str` Unique identifier for this event. - `result: Literal["allow", "deny"]` The confirmation result: 'allow' or 'deny'. - `"allow"` - `"deny"` - `tool_use_id: str` The id of the `agent.tool_use` or `agent.mcp_tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `deny_message: Optional[str]` Optional message providing context for a 'deny' decision. Only allowed when result is 'deny'. maxLength: 10000 - `processed_at: Optional[datetime]` Timestamp when the confirmation was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this confirmation was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsUserCustomToolResultEvent` Event sent by the client providing the result of a custom tool execution. - `type: Literal["user.custom_tool_result"]` - `id: str` Unique identifier for this event. - `custom_tool_use_id: str` The id of the `agent.custom_tool_use` event this result corresponds to. It is also listed in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `type: Literal["search_result"]` - `citations: BetaManagedAgentsSearchResultCitations` Citation settings for this search result. - `enabled: bool` Whether citations are enabled for this search result. - `content: List[BetaManagedAgentsSearchResultContent]` Array of text content blocks from the search result. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `source: str` The URL source of the search result. minLength: 1 - `title: str` The title of the search result. minLength: 1 - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `processed_at: Optional[datetime]` Timestamp when this result was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this result was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsAgentCustomToolUseEvent` Event emitted when the agent calls a custom tool. The session goes idle until the client sends a `user.custom_tool_result` event with the result. The client can send it as soon as this event arrives, without waiting for `session.status_idle`. - `type: Literal["agent.custom_tool_use"]` - `id: str` Unique identifier for this event. - `input: Dict[str, object]` Input parameters for the tool call. - `name: str` Name of the custom tool being called. - `processed_at: datetime` Timestamp when this tool use was processed. format: date-time - `session_thread_id: Optional[str]` When set, this event was cross-posted from a subagent's thread to surface its custom tool use on the primary thread's stream. Empty on the thread's own events. Informational only: the server routes the matching `user.custom_tool_result` by `custom_tool_use_id`, so clients do not send it back. - `class BetaManagedAgentsAgentMessageEvent` An agent response event in the session conversation. - `type: Literal["agent.message"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Array of text blocks comprising the agent response. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `processed_at: datetime` Timestamp when this response was generated. format: date-time - `class BetaManagedAgentsAgentThinkingEvent` Indicates the agent is making forward progress via extended thinking. A progress signal, not a content carrier. - `type: Literal["agent.thinking"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this thinking was produced. format: date-time - `class BetaManagedAgentsAgentMCPToolUseEvent` Event emitted when the agent invokes a tool provided by an MCP server. - `type: Literal["agent.mcp_tool_use"]` - `id: str` Unique identifier for this event. - `input: Dict[str, object]` Input parameters for the tool call. - `mcp_server_name: str` Name of the MCP server providing the tool. - `name: str` Name of the MCP tool being used. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `evaluated_permission: Optional[BetaManagedAgentsAgentEvaluatedPermission]` The evaluated permission policy for this tool invocation. - `"allow"` - `"ask"` - `"deny"` - `evaluation: Optional[BetaManagedAgentsAgentToolEvaluation]` Which resolved permission_policy produced evaluated_permission: always_allow, always_ask, or auto (with the server's per-invocation judgement). Absent only when the server refused the call before any policy applied (for example, the named tool is not enabled in the session); such a refusal has evaluated_permission deny. An event recorded before this field existed reads as the arm its evaluated_permission implies (always_allow for allow, always_ask for ask). - `class BetaManagedAgentsAgentToolEvaluationAlwaysAllow` The resolved permission_policy was always_allow; accompanies evaluated_permission "allow". - `type: Literal["always_allow"]` - `class BetaManagedAgentsAgentToolEvaluationAlwaysAsk` The resolved permission_policy was always_ask; accompanies evaluated_permission "ask". - `type: Literal["always_ask"]` - `class BetaManagedAgentsAgentToolEvaluationAuto` The resolved permission_policy was auto: the server judged this invocation individually. - `type: Literal["auto"]` - `evaluated_permission: BetaManagedAgentsAgentAutoEvaluatedPermission` The server's judgement for this invocation. - `class BetaManagedAgentsAgentAutoEvaluatedPermissionAllow` The server judged the invocation safe to execute without client approval. - `type: Literal["allow"]` - `class BetaManagedAgentsAgentAutoEvaluatedPermissionAsk` The server reached no judgement; the invocation is held for client approval. - `type: Literal["ask"]` - `reason_code: str` The judgement's grounds in registry-bound terms, for client branching and audit rather than end-user display. Open registry; currently "indeterminate" (no judgement was reached). Clients must tolerate values outside this set. maxLength: 64 - `class BetaManagedAgentsAgentAutoEvaluatedPermissionDeny` The server judged the invocation high-risk; it does not execute and a synthetic error tool result is appended. - `type: Literal["deny"]` - `reason_code: str` The judgement's grounds in registry-bound terms. Open registry; currently "high_risk" (judged high-risk; the call does not run). Clients must tolerate values outside this set. maxLength: 64 - `session_thread_id: Optional[str]` When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Informational only: the server routes the matching `user.tool_confirmation` by `tool_use_id`, so clients do not send it back. - `class BetaManagedAgentsAgentMCPToolResultEvent` Event representing the result of an MCP tool execution. - `type: Literal["agent.mcp_tool_result"]` - `id: str` Unique identifier for this event. - `mcp_tool_use_id: str` The id of the `agent.mcp_tool_use` event this result corresponds to. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `class BetaManagedAgentsAgentToolUseEvent` Event emitted when the agent invokes a built-in agent tool. - `type: Literal["agent.tool_use"]` - `id: str` Unique identifier for this event. - `input: Dict[str, object]` Input parameters for the tool call. - `name: str` Name of the agent tool being used. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `evaluated_permission: Optional[BetaManagedAgentsAgentEvaluatedPermission]` The evaluated permission policy for this tool invocation. - `evaluation: Optional[BetaManagedAgentsAgentToolEvaluation]` Which resolved permission_policy produced evaluated_permission: always_allow, always_ask, or auto (with the server's per-invocation judgement). Absent only when the server refused the call before any policy applied (for example, the named tool is not enabled in the session); such a refusal has evaluated_permission deny. An event recorded before this field existed reads as the arm its evaluated_permission implies (always_allow for allow, always_ask for ask). - `session_thread_id: Optional[str]` When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Informational only: the server routes the matching `user.tool_confirmation` or `user.tool_result` by `tool_use_id`, so clients do not send it back. - `class BetaManagedAgentsAgentToolResultEvent` Event representing the result of an agent tool execution. - `type: Literal["agent.tool_result"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `tool_use_id: str` The id of the `agent.tool_use` event this result corresponds to. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `class BetaManagedAgentsAgentThreadMessageReceivedEvent` Delivery event written to the target thread's input stream when an agent-to-agent message arrives. - `type: Literal["agent.thread_message_received"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Message content blocks. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `from_session_thread_id: str` Public `sthr_` ID of the thread that sent the message. - `processed_at: datetime` Timestamp when the message was received. format: date-time - `from_agent_name: Optional[str]` Name of the callable agent this message came from. Absent when received from the primary agent. - `class BetaManagedAgentsAgentThreadMessageSentEvent` Observability event emitted to the sender's output stream when an agent-to-agent message is sent. - `type: Literal["agent.thread_message_sent"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Message content blocks. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `processed_at: datetime` Timestamp when the message was sent. format: date-time - `to_session_thread_id: str` Public `sthr_` ID of the thread the message was sent to. - `to_agent_name: Optional[str]` Name of the callable agent this message was sent to. Absent when sent to the primary agent. - `class BetaManagedAgentsAgentThreadContextCompactedEvent` Indicates that context compaction (summarization) occurred during the session. - `type: Literal["agent.thread_context_compacted"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when compaction was processed. format: date-time - `class BetaManagedAgentsSessionErrorEvent` An error event indicating a problem occurred during session execution. - `type: Literal["session.error"]` - `id: str` Unique identifier for this event. - `error: Error` - `class BetaManagedAgentsUnknownError` An unknown or unexpected error occurred during session execution. A fallback variant; clients that don't recognize a new error code can match on `retry_status` and `message` alone. - `type: Literal["unknown_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `type: Literal["retrying"]` - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `type: Literal["exhausted"]` - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `type: Literal["terminal"]` - `class BetaManagedAgentsModelOverloadedError` The model is currently overloaded. Emitted after automatic retries are exhausted. - `type: Literal["model_overloaded_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsModelRateLimitedError` The model request was rate-limited. - `type: Literal["model_rate_limited_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsModelRequestFailedError` A model request failed for a reason other than overload or rate-limiting. - `type: Literal["model_request_failed_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsMCPConnectionFailedError` Failed to connect to an MCP server. - `type: Literal["mcp_connection_failed_error"]` - `mcp_server_name: str` Name of the MCP server that failed to connect. - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsMCPAuthenticationFailedError` Authentication to an MCP server failed. - `type: Literal["mcp_authentication_failed_error"]` - `mcp_server_name: str` Name of the MCP server that failed authentication. - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsBillingError` The caller's organization or workspace cannot make model requests — out of credits or spend limit reached. Retrying with the same credentials will not succeed; the caller must resolve the billing state. - `type: Literal["billing_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsCredentialHostUnreachableError` An `environment_variable` credential's `auth.networking.allowed_hosts` includes a host the environment's network policy does not permit. - `type: Literal["credential_host_unreachable_error"]` - `credential_id: str` ID of the affected credential. - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `vault_id: str` ID of the vault containing the affected credential. - `class BetaManagedAgentsRepositoryAuthenticationError` The repository host rejected the credentials, or required credentials and received none. - `type: Literal["repository_authentication_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryForbiddenError` The repository host refused access to the repository. - `type: Literal["repository_forbidden_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryNotFoundError` The repository host reported the repository as not found. - `type: Literal["repository_not_found_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryCheckoutError` The requested branch or commit does not exist in the repository. - `type: Literal["repository_checkout_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryCloneError` The repository could not be cloned. - `type: Literal["repository_clone_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `processed_at: datetime` Timestamp when the error occurred. format: date-time - `class BetaManagedAgentsSessionStatusRescheduledEvent` Indicates the session is recovering from an error state and is rescheduled for execution. - `type: Literal["session.status_rescheduled"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `class BetaManagedAgentsSessionStatusRunningEvent` Indicates the session is actively running and the agent is working. - `type: Literal["session.status_running"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `class BetaManagedAgentsSessionStatusIdleEvent` Indicates the agent has paused and is awaiting user input. - `type: Literal["session.status_idle"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `stop_details: Optional[BetaManagedAgentsSessionRefusalStopDetails]` Structured information about why the session stopped. `null` when there is nothing more to report. - `type: Literal["refusal"]` - `category: Optional[Literal["cyber", "bio", "frontier_llm", 2 more]]` The policy category that triggered the refusal, or `null` when there is no named category. New values can be added over time. - `"cyber"` - `"bio"` - `"frontier_llm"` - `"reasoning_extraction"` - `"general_harms"` - `explanation: Optional[str]` Human-readable explanation of the refusal, or `null` when none is available. The wording can change, so do not parse it. - `stop_reason: StopReason` - `class BetaManagedAgentsSessionEndTurn` The agent completed its turn naturally and is ready for the next user message. - `type: Literal["end_turn"]` - `class BetaManagedAgentsSessionRequiresAction` The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running. - `type: Literal["requires_action"]` - `event_ids: List[str]` The ids of events the agent is blocked on. Resolving fewer than all re-emits `session.status_idle` with the remainder. - `class BetaManagedAgentsSessionRetriesExhausted` The turn ended because repeated errors exhausted the retry budget or an error escalated to `retry_status: 'exhausted'`. - `type: Literal["retries_exhausted"]` - `class BetaManagedAgentsSessionBudgetReached` The agent stopped because the session's tracked list cost reached its budget, or because its usage includes a model with no list price (which the budget cannot measure). Raise the budget to continue — or, if raising is rejected because a model has no list price, remove the budget. - `type: Literal["budget_reached"]` - `class BetaManagedAgentsSessionRefusal` The turn ended because the model's response was refused, for example by a safety classifier. - `type: Literal["refusal"]` - `class BetaManagedAgentsSessionStatusTerminatedEvent` Indicates the session has terminated, either due to an error or completion. - `type: Literal["session.status_terminated"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `class BetaManagedAgentsSessionThreadCreatedEvent` Emitted when a child thread is created. Written to the parent thread's output stream so clients observing the session see child creation. - `type: Literal["session.thread_created"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the callable agent the thread runs. - `processed_at: datetime` Timestamp when the thread was created. format: date-time - `session_thread_id: str` Public `sthr_` ID of the newly created thread. - `workflow_run_id: Optional[str]` Identifier of the workflow run that created the thread, or `null` for any other thread. - `class BetaManagedAgentsSpanOutcomeEvaluationStartEvent` Emitted when an outcome evaluation cycle begins. - `type: Literal["span.outcome_evaluation_start"]` - `id: str` Unique identifier for this event. - `iteration: int` 0-indexed revision cycle. 0 is the first evaluation; 1 is the re-evaluation after the first revision; etc. format: int32 - `outcome_id: str` The `outc_` ID of the outcome being evaluated. - `processed_at: datetime` Timestamp when outcome evaluation started. format: date-time - `class BetaManagedAgentsSpanOutcomeEvaluationEndEvent` Emitted when an outcome evaluation cycle completes. Carries the verdict and aggregate token usage. A verdict of `needs_revision` means another evaluation cycle follows; `satisfied`, `max_iterations_reached`, `failed`, or `interrupted` are terminal — no further evaluation cycles follow. - `type: Literal["span.outcome_evaluation_end"]` - `id: str` Unique identifier for this event. - `explanation: str` Human-readable explanation of the verdict. For `needs_revision`, describes which criteria failed and why. - `iteration: int` 0-indexed revision cycle, matching the corresponding `span.outcome_evaluation_start`. format: int32 - `outcome_evaluation_start_id: str` The id of the corresponding `span.outcome_evaluation_start` event. - `outcome_id: str` The `outc_` ID of the outcome being evaluated. - `processed_at: datetime` Timestamp when outcome evaluation ended. format: date-time - `result: str` Evaluation verdict. 'satisfied': criteria met, session goes idle. 'needs_revision': criteria not met, another revision cycle follows. 'max_iterations_reached': evaluation budget exhausted with criteria still unmet — one final acknowledgment turn follows before the session goes idle, but no further evaluation runs. 'failed': grader determined the rubric does not apply to the deliverables. 'interrupted': user sent an interrupt while evaluation was in progress. - `usage: BetaManagedAgentsSpanModelUsage` Aggregate token usage for this evaluation cycle. Sums across all grader model requests within the cycle. - `cache_creation_input_tokens: int` Tokens used to create prompt cache in this request. format: int32 - `cache_read_input_tokens: int` Tokens read from prompt cache in this request. format: int32 - `input_tokens: int` Input tokens consumed by this request. format: int32 - `output_tokens: int` Output tokens generated by this request. format: int32 - `speed: Optional[Literal["standard", "fast"]]` Inference speed tier this request actually ran at. Mirrors `usage.speed` on /v1/messages. Only present when the fast-mode beta is active. - `"standard"` - `"fast"` - `class BetaManagedAgentsSpanModelRequestStartEvent` Emitted when a model request is initiated by the agent. - `type: Literal["span.model_request_start"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the model request started. format: date-time - `class BetaManagedAgentsSpanModelRequestEndEvent` Emitted when a model request completes. - `type: Literal["span.model_request_end"]` - `id: str` Unique identifier for this event. - `is_error: Optional[bool]` Whether the model request resulted in an error. - `model_request_start_id: str` The id of the corresponding `span.model_request_start` event. - `model_usage: BetaManagedAgentsSpanModelUsage` Token usage for this model request. - `processed_at: datetime` Timestamp when the model request completed. format: date-time - `class BetaManagedAgentsSpanOutcomeEvaluationOngoingEvent` Periodic heartbeat emitted while an outcome evaluation cycle is in progress. Distinguishes 'evaluation is actively running' from 'evaluation is stuck' between the corresponding `span.outcome_evaluation_start` and `span.outcome_evaluation_end` events. - `type: Literal["span.outcome_evaluation_ongoing"]` - `id: str` Unique identifier for this event. - `iteration: int` 0-indexed revision cycle, matching the corresponding `span.outcome_evaluation_start`. format: int32 - `outcome_id: str` The `outc_` ID of the outcome being evaluated. - `processed_at: datetime` Timestamp when this heartbeat was emitted. format: date-time - `class BetaManagedAgentsUserDefineOutcomeEvent` Echo of a `user.define_outcome` input event. Carries the server-generated `outcome_id` that subsequent `span.outcome_evaluation_*` events reference. - `type: Literal["user.define_outcome"]` - `id: str` Unique identifier for this event. - `description: str` What the agent should produce. Copied from the input event. - `max_iterations: Optional[int]` Evaluate-then-revise cycles before giving up. Default 3, max 20. format: int32 - `outcome_id: str` Server-generated `outc_` ID for this outcome. Referenced by `span.outcome_evaluation_*` events and the session's `outcome_evaluations` list. - `processed_at: datetime` Timestamp when the outcome was accepted. format: date-time - `rubric: Rubric` How to grade the outcome. File rubrics are currently resolved to their text content; clients should handle both variants. - `class BetaManagedAgentsFileRubric` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubric` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. - `class BetaManagedAgentsSessionDeletedEvent` Emitted when a session has been deleted. Terminates any active event stream — no further events will be emitted for this session. - `type: Literal["session.deleted"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the session was deleted. format: date-time - `class BetaManagedAgentsSessionThreadStatusRunningEvent` A session thread has begun executing. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_running"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that started running. - `class BetaManagedAgentsSessionThreadStatusIdleEvent` A session thread has yielded and is awaiting input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_idle"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that went idle. - `stop_details: Optional[BetaManagedAgentsSessionRefusalStopDetails]` Structured information about why the thread stopped. `null` when there is nothing more to report. - `stop_reason: StopReason` - `class BetaManagedAgentsSessionEndTurn` The agent completed its turn naturally and is ready for the next user message. - `class BetaManagedAgentsSessionRequiresAction` The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running. - `class BetaManagedAgentsSessionRetriesExhausted` The turn ended because repeated errors exhausted the retry budget or an error escalated to `retry_status: 'exhausted'`. - `class BetaManagedAgentsSessionBudgetReached` The agent stopped because the session's tracked list cost reached its budget, or because its usage includes a model with no list price (which the budget cannot measure). Raise the budget to continue — or, if raising is rejected because a model has no list price, remove the budget. - `class BetaManagedAgentsSessionRefusal` The turn ended because the model's response was refused, for example by a safety classifier. - `class BetaManagedAgentsSessionThreadStatusTerminatedEvent` A session thread has terminated and will accept no further input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_terminated"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that terminated. - `class BetaManagedAgentsUserToolResultEvent` Event sent by the client providing the result of an agent-toolset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `type: Literal["user.tool_result"]` - `id: str` Unique identifier for this event. - `tool_use_id: str` The id of the `agent.tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `processed_at: Optional[datetime]` Timestamp when this result was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this result was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsSessionThreadStatusRescheduledEvent` A session thread hit a transient error and is retrying automatically. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_rescheduled"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that is retrying. - `class BetaManagedAgentsSessionUpdatedEvent` Emitted when an UpdateSession request changed at least one field. Carries only the fields that changed; absent fields were not part of the update. The new configuration applies from the next turn. - `type: Literal["session.updated"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the update was applied. format: date-time - `agent: Optional[BetaManagedAgentsSessionAgent]` The session's effective agent configuration after the update. Present only when the update changed `agent` (tools or mcp_servers); when present it is the full materialised snapshot, not a diff. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsSessionMultiagent]` Resolved multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsSessionMultiagentCoordinator` Resolved coordinator topology with full agent definitions for each roster member. - `type: Literal["coordinator"]` - `agents: List[Agent]` Full `agent` definitions the coordinator may spawn as session threads. - `class BetaManagedAgentsSessionThreadAgent` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsSessionMultiagent20261001` Resolved multiagent configuration with three members, as copied to the `session` at creation. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsSessionMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsSessionMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that this agent can spawn as session threads. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsSessionMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsSessionMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that a run's plan can use. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `class BetaManagedAgentsMCPToolset` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `version: int` format: int32 - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's budget after the update: the new budget when set or replaced, or null when the update removed it. Present only when the update changed the budget. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `metadata: Optional[Dict[str, str]]` The session's full metadata bag after the update. Present when the update set non-empty metadata; absent when metadata was unchanged or cleared to empty. - `title: Optional[str]` The session's new title. Present only when the update changed it. - `class BetaManagedAgentsStartEvent` Opens a preview of a buffered event. Carries the previewed event's type and id only. Followed by zero or more event_delta events with the same event id, normally concluded by the buffered event carrying that id. If the producing model request ends without that event (an error or interrupt mid-stream), its terminal span.model_request_end closes the preview. Only sent on stream connections that opt in via event_deltas; never appears in event history. - `type: Literal["event_start"]` - `event: BetaManagedAgentsStartEventPreview` The previewed event's type and id. The event type determines which delta types the preview's event_delta events carry: agent.message events stream content_delta fragments; agent.thinking previews are start-only — no deltas follow, and the buffered agent.thinking with the same id concludes them. - `class BetaManagedAgentsAgentMessagePreview` - `type: Literal["agent.message"]` - `id: str` The id the buffered agent.message will carry if it is emitted. Matches the event_id on this preview's event_delta events. - `class BetaManagedAgentsAgentThinkingPreview` - `type: Literal["agent.thinking"]` - `id: str` The id the buffered agent.thinking will carry if it is emitted. Start-only — no event_delta events follow. - `class BetaManagedAgentsDeltaEvent` An incremental update to an event that is still being streamed. Deltas are best-effort and may stop early; when the buffered event with id == event_id is produced it carries the complete content. A model request that ends early (an error or interrupt) produces no buffered event — its terminal span.model_request_end closes the preview. Only sent on stream connections that opt in via event_deltas; never appears in event history. - `type: Literal["event_delta"]` - `delta: BetaManagedAgentsDeltaContent` One fragment of the previewed event. The delta type is named for the previewed event's field it streams into: agent.message events stream content_delta fragments, each a partial element of the content array. - `type: Literal["content_delta"]` - `content: BetaManagedAgentsTextBlock` A partial element of the content array at index, typed like the element itself — the same shape the buffered agent.message carries in content. - `index: Optional[int]` Which entry in the previewed event's content array this fragment lands in. Insert content as that entry when the index is new; append to the existing entry otherwise. - `event_id: str` The id of the event being previewed. Matches event.id on the corresponding event_start and the buffered event that reconciles the preview. - `class BetaManagedAgentsSystemMessageEvent` A mid-conversation system message event. Carries system-role content that is appended to the session as a `role: "system"` turn. - `type: Literal["system.message"]` - `id: str` Unique identifier for this event. - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `processed_at: Optional[datetime]` Timestamp when this system message was processed. format: date-time - `class BetaManagedAgentsSessionUsageEvent` Periodic snapshot of the session's cumulative usage and tracked list cost. - `type: Literal["session.usage"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the snapshot was taken. format: date-time - `usage: BetaManagedAgentsSessionUsageSnapshot` The session's cumulative usage at the snapshot time. - `active_seconds: Optional[float]` Cumulative time in seconds during which the session had at least one thread in running status. Overlapping activity from concurrent threads is counted once. This is the duration the session's runtime cost is priced on. format: double - `cache_creation: Optional[BetaManagedAgentsCacheCreationUsage]` Tokens used to create prompt cache entries, broken down by cache TTL. - `ephemeral_1h_input_tokens: Optional[int]` Tokens used to create 1-hour ephemeral cache entries. format: int32 - `ephemeral_5m_input_tokens: Optional[int]` Tokens used to create 5-minute ephemeral cache entries. format: int32 - `cache_read_input_tokens: Optional[int]` Total tokens read from prompt cache. format: int32 - `input_tokens: Optional[int]` Total input tokens consumed across all turns. format: int32 - `list_cost: Optional[BetaMonetaryAmount]` Cumulative list cost of the session across all turns, priced at public list rates. - `output_tokens: Optional[int]` Total output tokens generated across all turns. format: int32 - `server_tool_use: Optional[BetaManagedAgentsServerToolUsage]` Cumulative server-executed tool usage across all turns. - `web_fetch_requests: Optional[int]` Number of server-executed web fetch requests. format: int32 - `web_search_requests: Optional[int]` Number of server-executed web search requests. format: int32 - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's configured budget at the snapshot time, or null when the session has no budget. - `class BetaManagedAgentsWorkflowRunCreatedEvent` A workflow run was created. A workflow run is background work that the session's agent starts. Emitted once per run, before the run's other `workflow_run.*` events. - `type: Literal["workflow_run.created"]` - `id: str` Unique identifier for this event. - `description: Optional[str]` Description that the agent gave the run, passed on as written, or `null` if it gave none. - `name: str` Name that the agent gave the run, passed on as written, or a name that the server assigned. - `phases: List[BetaManagedAgentsWorkflowRunPhase]` The phases that the run's plan declares, in the plan's order. Can be empty. - `id: str` Unique identifier for the phase. - `description: Optional[str]` Description that the agent gave the phase, passed on as written, or `null` if it gave none. - `name: str` Name that the agent gave the phase, passed on as written. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunStatusEndedEvent` A workflow run ended. Emitted once per run, as the last of the run's `workflow_run.*` events. - `type: Literal["workflow_run.status_ended"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `result: BetaManagedAgentsWorkflowRunResult` How the run ended. - `class BetaManagedAgentsWorkflowRunResultCompleted` The run's plan, a program that the agent wrote, finished. This does not say whether the work succeeded. - `type: Literal["completed"]` - `class BetaManagedAgentsWorkflowRunResultError` The run failed or reached its time limit. - `type: Literal["error"]` - `error: BetaManagedAgentsWorkflowRunError` Why the run did not finish. - `class BetaManagedAgentsTimeoutWorkflowRunError` The run reached its time limit. - `type: Literal["timeout_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsProgramWorkflowRunError` The plan, a program that the agent wrote, failed, or the server refused it. - `type: Literal["program_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsUnknownWorkflowRunError` A failure that has no type of its own. - `type: Literal["unknown_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsThreadLimitWorkflowRunError` The run exceeded the limit on the number of threads that a run can create. - `type: Literal["thread_limit_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsMaxWorkflowRunsWorkflowRunError` No run was created, because the session was at its limit of open workflow runs, which are runs that have not ended. Only `workflow_run.error` carries this type. - `type: Literal["max_workflow_runs_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsWorkflowRunResultStopped` The agent stopped the run. - `type: Literal["stopped"]` - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunPhaseStartedEvent` A workflow run's plan entered a phase. - `type: Literal["workflow_run.phase_started"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `workflow_run_phase_id: str` Identifier of the phase, as in `phases` on the run's `workflow_run.created` event. - `class BetaManagedAgentsWorkflowRunPhaseEndedEvent` A workflow run's plan left a phase, or the run's end closed it. Emitted once for every `workflow_run.phase_started` event, before the run's `workflow_run.status_ended` event. The event does not say whether the plan finished the phase's work, or why it left. - `type: Literal["workflow_run.phase_ended"]` - `id: str` Unique identifier for this event. - `phase_started_id: str` Identifier of the `workflow_run.phase_started` event that opened the phase. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `workflow_run_phase_id: str` Identifier of the phase, as in `phases` on the run's `workflow_run.created` event. - `class BetaManagedAgentsWorkflowRunStatusRunningEvent` A workflow run is running. Emitted when the run starts to execute, and each time it resumes after being idle. A run that starts idle emits `workflow_run.status_idle` first. - `type: Literal["workflow_run.status_running"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunStatusIdleEvent` A workflow run is idle. Emitted each time the run goes idle, whatever the cause. If the run ends while idle, no `workflow_run.status_running` comes between this event and its `workflow_run.status_ended`. - `type: Literal["workflow_run.status_idle"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunErrorEvent` A workflow run met an error, or an error kept a run from being created. A run that ends with a `result.type` of `error` emits this event before its `workflow_run.status_ended`, with the same `error`. - `type: Literal["workflow_run.error"]` - `id: str` Unique identifier for this event. - `error: BetaManagedAgentsWorkflowRunError` Why the run did not finish, or was not created. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: Optional[str]` Identifier of the run that met the error, or `null` when the error kept a run from being created. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) for event in client.beta.sessions.events.stream( session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ): print(event) ``` ##### Response (200) ```json { "id": "sevt_011CZkZGPp1iBcp4kaQSihUm", "content": [ { "text": "Where is my order #1234?", "type": "text" } ], "type": "user.message", "processed_at": "2026-03-15T10:00:00Z" } ``` ## Beta › Sessions › Resources ### Add Session Resource `beta.sessions.resources.add(session_id, **kwargs) -> BetaManagedAgentsFileResource` **POST** `/v1/sessions/{session_id}/resources` Add Session Resource #### Parameters - `session_id: str` (path parameter) - `file_id: str` ID of a previously uploaded file. minLength: 1, maxLength: 128 - `type: Literal["file"]` - `mount_path: Optional[str]` Mount path in the container. Defaults to `/mnt/session/uploads/`. minLength: 1, maxLength: 4096 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsFileResource` - `type: Literal["file"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `file_id: str` - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_file_resource = client.beta.sessions.resources.add( session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", file_id="file_011CNha8iCJcU1wXNR6q4V8w", type="file", ) print(beta_managed_agents_file_resource.id) ``` ##### Response (200) ```json { "id": "sesrsc_011CZkZBJq5dWxk9fVLNcPht", "created_at": "2026-03-15T10:00:00Z", "file_id": "file_011CNha8iCJcU1wXNR6q4V8w", "mount_path": "/uploads/receipt.pdf", "type": "file", "updated_at": "2026-03-15T10:00:00Z" } ``` ### List Session Resources `beta.sessions.resources.list(session_id, **kwargs) -> SyncPageCursor[BetaManagedAgentsSessionResource]` **GET** `/v1/sessions/{session_id}/resources` List Session Resources #### Parameters - `session_id: str` (path parameter) - `limit: Optional[int]` (query parameter) Maximum number of resources to return per page (max 1000). If omitted, returns all resources. format: int32 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `type BetaManagedAgentsSessionResource = ...` - `class BetaManagedAgentsGitHubRepositoryResource` - `type: Literal["github_repository"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `url: str` - `checkout: Optional[Checkout]` - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `class BetaManagedAgentsFileResource` - `type: Literal["file"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `file_id: str` - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `class BetaManagedAgentsMemoryStoreResource` A memory store attached to an agent session. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `description: Optional[str]` Description of the memory store, snapshotted at attach time. Rendered into the agent's system prompt. Empty string when the store has no description. - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. maxLength: 4096 - `mount_path: Optional[str]` Filesystem path where the store is mounted in the session container, e.g. /mnt/memory/user-preferences. Derived from the store's name. Output-only. - `name: Optional[str]` Display name of the memory store, snapshotted at attach time. Later edits to the store's name do not propagate to this resource. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.sessions.resources.list( session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ) page = page.data[0] print(page) ``` ##### Response (200) ```json { "data": [ { "id": "sesrsc_011CZkZBJq5dWxk9fVLNcPht", "created_at": "2026-03-15T10:00:00Z", "file_id": "file_011CNha8iCJcU1wXNR6q4V8w", "mount_path": "/uploads/receipt.pdf", "type": "file", "updated_at": "2026-03-15T10:00:00Z" }, { "id": "sesrsc_011CZkZCKr6eXym1gWMPdQiu", "created_at": "2026-03-15T10:00:00Z", "mount_path": "/workspace/example-repo", "type": "github_repository", "updated_at": "2026-03-15T10:00:00Z", "url": "https://github.com/example-org/example-repo", "checkout": { "name": "main", "type": "branch" } } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=" } ``` ### Get Session Resource `beta.sessions.resources.retrieve(resource_id, **kwargs) -> ResourceRetrieveResponse` **GET** `/v1/sessions/{session_id}/resources/{resource_id}` Get Session Resource #### Parameters - `session_id: str` (path parameter) - `resource_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `type ResourceRetrieveResponse = ...` The requested session resource. - `class BetaManagedAgentsGitHubRepositoryResource` - `type: Literal["github_repository"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `url: str` - `checkout: Optional[Checkout]` - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `class BetaManagedAgentsFileResource` - `type: Literal["file"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `file_id: str` - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `class BetaManagedAgentsMemoryStoreResource` A memory store attached to an agent session. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `description: Optional[str]` Description of the memory store, snapshotted at attach time. Rendered into the agent's system prompt. Empty string when the store has no description. - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. maxLength: 4096 - `mount_path: Optional[str]` Filesystem path where the store is mounted in the session container, e.g. /mnt/memory/user-preferences. Derived from the store's name. Output-only. - `name: Optional[str]` Display name of the memory store, snapshotted at attach time. Later edits to the store's name do not propagate to this resource. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) resource = client.beta.sessions.resources.retrieve( resource_id="sesrsc_011CZkZBJq5dWxk9fVLNcPht", session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ) print(resource) ``` ##### Response (200) ```json { "id": "sesrsc_011CZkZCKr6eXym1gWMPdQiu", "created_at": "2026-03-15T10:00:00Z", "mount_path": "/workspace/example-repo", "type": "github_repository", "updated_at": "2026-03-15T10:00:00Z", "url": "https://github.com/example-org/example-repo", "checkout": { "name": "main", "type": "branch" } } ``` ### Update Session Resource `beta.sessions.resources.update(resource_id, **kwargs) -> ResourceUpdateResponse` **POST** `/v1/sessions/{session_id}/resources/{resource_id}` Update Session Resource #### Parameters - `session_id: str` (path parameter) - `resource_id: str` (path parameter) - `authorization_token: str` New authorization token for the resource. Currently only `github_repository` resources support token rotation. minLength: 1, maxLength: 4096 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `type ResourceUpdateResponse = ...` The updated session resource. - `class BetaManagedAgentsGitHubRepositoryResource` - `type: Literal["github_repository"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `url: str` - `checkout: Optional[Checkout]` - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `class BetaManagedAgentsFileResource` - `type: Literal["file"]` - `id: str` - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `file_id: str` - `mount_path: str` - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `class BetaManagedAgentsMemoryStoreResource` A memory store attached to an agent session. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `description: Optional[str]` Description of the memory store, snapshotted at attach time. Rendered into the agent's system prompt. Empty string when the store has no description. - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. maxLength: 4096 - `mount_path: Optional[str]` Filesystem path where the store is mounted in the session container, e.g. /mnt/memory/user-preferences. Derived from the store's name. Output-only. - `name: Optional[str]` Display name of the memory store, snapshotted at attach time. Later edits to the store's name do not propagate to this resource. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) resource = client.beta.sessions.resources.update( resource_id="sesrsc_011CZkZBJq5dWxk9fVLNcPht", session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", authorization_token="ghp_exampletoken", ) print(resource) ``` ##### Response (200) ```json { "id": "sesrsc_011CZkZCKr6eXym1gWMPdQiu", "created_at": "2026-03-15T10:00:00Z", "mount_path": "/workspace/example-repo", "type": "github_repository", "updated_at": "2026-03-15T10:00:00Z", "url": "https://github.com/example-org/example-repo", "checkout": { "name": "main", "type": "branch" } } ``` ### Delete Session Resource `beta.sessions.resources.delete(resource_id, **kwargs) -> BetaManagedAgentsDeleteSessionResource` **DELETE** `/v1/sessions/{session_id}/resources/{resource_id}` Delete Session Resource #### Parameters - `session_id: str` (path parameter) - `resource_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeleteSessionResource` Confirmation of resource deletion. - `type: Literal["session_resource_deleted"]` - `id: str` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_delete_session_resource = client.beta.sessions.resources.delete( resource_id="sesrsc_011CZkZBJq5dWxk9fVLNcPht", session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ) print(beta_managed_agents_delete_session_resource.id) ``` ##### Response (200) ```json { "id": "sesrsc_011CZkZBJq5dWxk9fVLNcPht", "type": "session_resource_deleted" } ``` ## Beta › Sessions › Threads ### List Session Threads `beta.sessions.threads.list(session_id, **kwargs) -> SyncPageCursor[BetaManagedAgentsSessionThread]` **GET** `/v1/sessions/{session_id}/threads` List Session Threads #### Parameters - `session_id: str` (path parameter) - `limit: Optional[int]` (query parameter) Maximum results per page. Defaults to 1000. format: int32 - `page: Optional[str]` (query parameter) Opaque pagination cursor from a previous response's `next_page`. Forward-only. - `statuses: Optional[List[BetaManagedAgentsSessionThreadStatus]]` (query parameter) Return only threads that have one of these statuses. Repeat the parameter to give more than one status. Leave it out to return threads of every status. - `"running"` - `"idle"` - `"rescheduling"` - `"terminated"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsSessionThread` An execution thread within a `session`. Each session has one primary thread plus zero or more child threads. - `type: Literal["session_thread"]` - `id: str` Unique identifier for this thread. - `agent: Agent` Resolved agent definition for this thread. Snapshot of the agent at thread creation time. - `class BetaManagedAgentsSessionThreadAgent` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsInlineAgent` An agent that has no Agent resource, and so no `id` or `version`. It is defined inline, in a workflow run's plan or when a session thread is spawned, and is not saved. - `type: Literal["inline"]` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` The name that the agent's definition gave, or one that the server assigned. - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `class BetaManagedAgentsMCPToolset` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `archived_at: Optional[datetime]` When the thread was archived. Null if not archived. format: date-time - `created_at: datetime` When the thread was created. format: date-time - `parent_thread_id: Optional[str]` Parent thread that spawned this thread. Null for the primary thread. - `session_id: str` The session this thread belongs to. - `stats: Optional[BetaManagedAgentsSessionThreadStats]` Timing statistics for this thread. Null until the thread's first status transition. - `active_seconds: Optional[float]` Cumulative time in seconds the thread spent actively running. Excludes idle time. format: double - `duration_seconds: Optional[float]` Elapsed time since thread creation in seconds. For archived threads, frozen at the final update. format: double - `startup_seconds: Optional[float]` Time in seconds for the thread to begin running. Zero for child threads, which start immediately. format: double - `status: BetaManagedAgentsSessionThreadStatus` Current execution status of the thread. - `"running"` - `"idle"` - `"rescheduling"` - `"terminated"` - `updated_at: datetime` When the thread was last updated. format: date-time - `usage: Optional[BetaManagedAgentsSessionThreadUsage]` Cumulative token usage for this thread. Null until the thread's first idle transition. - `active_seconds: Optional[float]` Cumulative time in seconds this thread spent in running status. Equal to `stats.active_seconds`; surfaced here so a thread's usage carries every quantity its cost is priced on. format: double - `cache_creation: Optional[BetaManagedAgentsCacheCreationUsage]` Tokens used to create prompt cache entries, broken down by cache TTL. - `ephemeral_1h_input_tokens: Optional[int]` Tokens used to create 1-hour ephemeral cache entries. format: int32 - `ephemeral_5m_input_tokens: Optional[int]` Tokens used to create 5-minute ephemeral cache entries. format: int32 - `cache_read_input_tokens: Optional[int]` Total tokens read from prompt cache. format: int32 - `input_tokens: Optional[int]` Total input tokens consumed across all turns. format: int32 - `list_cost: Optional[BetaMonetaryAmount]` Cumulative list cost of this thread across all turns, priced at public list rates. Absent until cost tracking is available for the thread. Each figure is rounded to the nearest cent independently and the session's aggregate `usage.list_cost` additionally includes session runtime, so per-thread costs do not sum exactly to the session figure; the session figure is authoritative and is what a budget is enforced against. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `output_tokens: Optional[int]` Total output tokens generated across all turns. format: int32 - `server_tool_use: Optional[BetaManagedAgentsServerToolUsage]` Cumulative server-executed tool usage across all turns of this thread. Absent until server-tool tracking is available for the thread. - `web_fetch_requests: Optional[int]` Number of server-executed web fetch requests. format: int32 - `web_search_requests: Optional[int]` Number of server-executed web search requests. format: int32 - `workflow_run_id: Optional[str]` Identifier of the workflow run that created the thread, or `null` for any other thread. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.sessions.threads.list( session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ) page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "sthr_011CZkZVWa6oJjw1rgXZpnBt", "agent": { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "description": "A focused research subagent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "name": "Researcher", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" } ], "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 }, "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "parent_thread_id": null, "session_id": "sesn_011CZkZAtmR3yMPDzynEDxu7", "stats": { "active_seconds": 0, "duration_seconds": 0, "startup_seconds": 0 }, "status": "idle", "type": "session_thread", "updated_at": "2026-03-15T10:00:00Z", "usage": { "active_seconds": 0, "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_read_input_tokens": 0, "input_tokens": 0, "list_cost": { "amount": "2500", "currency": "USD" }, "output_tokens": 0, "server_tool_use": { "web_fetch_requests": 0, "web_search_requests": 3 } }, "workflow_run_id": null } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=" } ``` ### Get Session Thread `beta.sessions.threads.retrieve(thread_id, **kwargs) -> BetaManagedAgentsSessionThread` **GET** `/v1/sessions/{session_id}/threads/{thread_id}` Get Session Thread #### Parameters - `session_id: str` (path parameter) - `thread_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsSessionThread` An execution thread within a `session`. Each session has one primary thread plus zero or more child threads. - `type: Literal["session_thread"]` - `id: str` Unique identifier for this thread. - `agent: Agent` Resolved agent definition for this thread. Snapshot of the agent at thread creation time. - `class BetaManagedAgentsSessionThreadAgent` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsInlineAgent` An agent that has no Agent resource, and so no `id` or `version`. It is defined inline, in a workflow run's plan or when a session thread is spawned, and is not saved. - `type: Literal["inline"]` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` The name that the agent's definition gave, or one that the server assigned. - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `class BetaManagedAgentsMCPToolset` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `archived_at: Optional[datetime]` When the thread was archived. Null if not archived. format: date-time - `created_at: datetime` When the thread was created. format: date-time - `parent_thread_id: Optional[str]` Parent thread that spawned this thread. Null for the primary thread. - `session_id: str` The session this thread belongs to. - `stats: Optional[BetaManagedAgentsSessionThreadStats]` Timing statistics for this thread. Null until the thread's first status transition. - `active_seconds: Optional[float]` Cumulative time in seconds the thread spent actively running. Excludes idle time. format: double - `duration_seconds: Optional[float]` Elapsed time since thread creation in seconds. For archived threads, frozen at the final update. format: double - `startup_seconds: Optional[float]` Time in seconds for the thread to begin running. Zero for child threads, which start immediately. format: double - `status: BetaManagedAgentsSessionThreadStatus` Current execution status of the thread. - `"running"` - `"idle"` - `"rescheduling"` - `"terminated"` - `updated_at: datetime` When the thread was last updated. format: date-time - `usage: Optional[BetaManagedAgentsSessionThreadUsage]` Cumulative token usage for this thread. Null until the thread's first idle transition. - `active_seconds: Optional[float]` Cumulative time in seconds this thread spent in running status. Equal to `stats.active_seconds`; surfaced here so a thread's usage carries every quantity its cost is priced on. format: double - `cache_creation: Optional[BetaManagedAgentsCacheCreationUsage]` Tokens used to create prompt cache entries, broken down by cache TTL. - `ephemeral_1h_input_tokens: Optional[int]` Tokens used to create 1-hour ephemeral cache entries. format: int32 - `ephemeral_5m_input_tokens: Optional[int]` Tokens used to create 5-minute ephemeral cache entries. format: int32 - `cache_read_input_tokens: Optional[int]` Total tokens read from prompt cache. format: int32 - `input_tokens: Optional[int]` Total input tokens consumed across all turns. format: int32 - `list_cost: Optional[BetaMonetaryAmount]` Cumulative list cost of this thread across all turns, priced at public list rates. Absent until cost tracking is available for the thread. Each figure is rounded to the nearest cent independently and the session's aggregate `usage.list_cost` additionally includes session runtime, so per-thread costs do not sum exactly to the session figure; the session figure is authoritative and is what a budget is enforced against. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `output_tokens: Optional[int]` Total output tokens generated across all turns. format: int32 - `server_tool_use: Optional[BetaManagedAgentsServerToolUsage]` Cumulative server-executed tool usage across all turns of this thread. Absent until server-tool tracking is available for the thread. - `web_fetch_requests: Optional[int]` Number of server-executed web fetch requests. format: int32 - `web_search_requests: Optional[int]` Number of server-executed web search requests. format: int32 - `workflow_run_id: Optional[str]` Identifier of the workflow run that created the thread, or `null` for any other thread. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_session_thread = client.beta.sessions.threads.retrieve( thread_id="sthr_011CZkZVWa6oJjw1rgXZpnBt", session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ) print(beta_managed_agents_session_thread.id) ``` ##### Response (200) ```json { "id": "sthr_011CZkZVWa6oJjw1rgXZpnBt", "agent": { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "description": "A focused research subagent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "name": "Researcher", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" } ], "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 }, "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "parent_thread_id": null, "session_id": "sesn_011CZkZAtmR3yMPDzynEDxu7", "stats": { "active_seconds": 0, "duration_seconds": 0, "startup_seconds": 0 }, "status": "idle", "type": "session_thread", "updated_at": "2026-03-15T10:00:00Z", "usage": { "active_seconds": 0, "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_read_input_tokens": 0, "input_tokens": 0, "list_cost": { "amount": "2500", "currency": "USD" }, "output_tokens": 0, "server_tool_use": { "web_fetch_requests": 0, "web_search_requests": 3 } }, "workflow_run_id": null } ``` ### Archive Session Thread `beta.sessions.threads.archive(thread_id, **kwargs) -> BetaManagedAgentsSessionThread` **POST** `/v1/sessions/{session_id}/threads/{thread_id}/archive` Archive Session Thread #### Parameters - `session_id: str` (path parameter) - `thread_id: str` (path parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsSessionThread` An execution thread within a `session`. Each session has one primary thread plus zero or more child threads. - `type: Literal["session_thread"]` - `id: str` Unique identifier for this thread. - `agent: Agent` Resolved agent definition for this thread. Snapshot of the agent at thread creation time. - `class BetaManagedAgentsSessionThreadAgent` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsInlineAgent` An agent that has no Agent resource, and so no `id` or `version`. It is defined inline, in a workflow run's plan or when a session thread is spawned, and is not saved. - `type: Literal["inline"]` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` The name that the agent's definition gave, or one that the server assigned. - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `class BetaManagedAgentsMCPToolset` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `archived_at: Optional[datetime]` When the thread was archived. Null if not archived. format: date-time - `created_at: datetime` When the thread was created. format: date-time - `parent_thread_id: Optional[str]` Parent thread that spawned this thread. Null for the primary thread. - `session_id: str` The session this thread belongs to. - `stats: Optional[BetaManagedAgentsSessionThreadStats]` Timing statistics for this thread. Null until the thread's first status transition. - `active_seconds: Optional[float]` Cumulative time in seconds the thread spent actively running. Excludes idle time. format: double - `duration_seconds: Optional[float]` Elapsed time since thread creation in seconds. For archived threads, frozen at the final update. format: double - `startup_seconds: Optional[float]` Time in seconds for the thread to begin running. Zero for child threads, which start immediately. format: double - `status: BetaManagedAgentsSessionThreadStatus` Current execution status of the thread. - `"running"` - `"idle"` - `"rescheduling"` - `"terminated"` - `updated_at: datetime` When the thread was last updated. format: date-time - `usage: Optional[BetaManagedAgentsSessionThreadUsage]` Cumulative token usage for this thread. Null until the thread's first idle transition. - `active_seconds: Optional[float]` Cumulative time in seconds this thread spent in running status. Equal to `stats.active_seconds`; surfaced here so a thread's usage carries every quantity its cost is priced on. format: double - `cache_creation: Optional[BetaManagedAgentsCacheCreationUsage]` Tokens used to create prompt cache entries, broken down by cache TTL. - `ephemeral_1h_input_tokens: Optional[int]` Tokens used to create 1-hour ephemeral cache entries. format: int32 - `ephemeral_5m_input_tokens: Optional[int]` Tokens used to create 5-minute ephemeral cache entries. format: int32 - `cache_read_input_tokens: Optional[int]` Total tokens read from prompt cache. format: int32 - `input_tokens: Optional[int]` Total input tokens consumed across all turns. format: int32 - `list_cost: Optional[BetaMonetaryAmount]` Cumulative list cost of this thread across all turns, priced at public list rates. Absent until cost tracking is available for the thread. Each figure is rounded to the nearest cent independently and the session's aggregate `usage.list_cost` additionally includes session runtime, so per-thread costs do not sum exactly to the session figure; the session figure is authoritative and is what a budget is enforced against. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `output_tokens: Optional[int]` Total output tokens generated across all turns. format: int32 - `server_tool_use: Optional[BetaManagedAgentsServerToolUsage]` Cumulative server-executed tool usage across all turns of this thread. Absent until server-tool tracking is available for the thread. - `web_fetch_requests: Optional[int]` Number of server-executed web fetch requests. format: int32 - `web_search_requests: Optional[int]` Number of server-executed web search requests. format: int32 - `workflow_run_id: Optional[str]` Identifier of the workflow run that created the thread, or `null` for any other thread. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_session_thread = client.beta.sessions.threads.archive( thread_id="sthr_011CZkZVWa6oJjw1rgXZpnBt", session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ) print(beta_managed_agents_session_thread.id) ``` ##### Response (200) ```json { "id": "sthr_011CZkZVWa6oJjw1rgXZpnBt", "agent": { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "description": "A focused research subagent.", "mcp_servers": [ { "name": "example-mcp", "type": "url", "url": "https://example-server.modelcontextprotocol.io/sse" } ], "model": { "id": "claude-opus-5", "effort": { "type": "low" }, "inference_geo": "inference_geo", "speed": "standard" }, "name": "Researcher", "skills": [ { "skill_id": "xlsx", "type": "anthropic", "version": "1" } ], "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.", "tools": [ { "configs": [ { "enabled": true, "name": "bash", "permission_policy": { "type": "always_allow" }, "type": "bash" } ], "default_config": { "enabled": true, "permission_policy": { "type": "always_ask" } }, "type": "agent_toolset_20260401" } ], "type": "agent", "version": 1 }, "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "parent_thread_id": null, "session_id": "sesn_011CZkZAtmR3yMPDzynEDxu7", "stats": { "active_seconds": 0, "duration_seconds": 0, "startup_seconds": 0 }, "status": "idle", "type": "session_thread", "updated_at": "2026-03-15T10:00:00Z", "usage": { "active_seconds": 0, "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_read_input_tokens": 0, "input_tokens": 0, "list_cost": { "amount": "2500", "currency": "USD" }, "output_tokens": 0, "server_tool_use": { "web_fetch_requests": 0, "web_search_requests": 3 } }, "workflow_run_id": null } ``` ## Beta › Sessions › Threads › Events ### List Session Thread Events `beta.sessions.threads.events.list(thread_id, **kwargs) -> SyncPageCursor[BetaManagedAgentsSessionEvent]` **GET** `/v1/sessions/{session_id}/threads/{thread_id}/events` List Session Thread Events #### Parameters - `session_id: str` (path parameter) - `thread_id: str` (path parameter) - `limit: Optional[int]` (query parameter) format: int32 - `page: Optional[str]` (query parameter) - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `type BetaManagedAgentsSessionEvent = ...` Union type for all event types in a session. - `class BetaManagedAgentsUserMessageEvent` A user message event in the session conversation. - `type: Literal["user.message"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Array of content blocks comprising the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `processed_at: Optional[datetime]` Timestamp when the agent finished processing this message. format: date-time - `class BetaManagedAgentsUserInterruptEvent` An interrupt event that pauses agent execution and returns control to the user. - `type: Literal["user.interrupt"]` - `id: str` Unique identifier for this event. - `processed_at: Optional[datetime]` Timestamp when the interrupt was processed. format: date-time - `session_thread_id: Optional[str]` If absent, interrupts every non-archived thread in a multiagent session (or the primary alone in a single-agent session). If present, interrupts only the named thread. - `class BetaManagedAgentsUserToolConfirmationEvent` A tool confirmation event that approves or denies a pending tool execution. - `type: Literal["user.tool_confirmation"]` - `id: str` Unique identifier for this event. - `result: Literal["allow", "deny"]` The confirmation result: 'allow' or 'deny'. - `"allow"` - `"deny"` - `tool_use_id: str` The id of the `agent.tool_use` or `agent.mcp_tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `deny_message: Optional[str]` Optional message providing context for a 'deny' decision. Only allowed when result is 'deny'. maxLength: 10000 - `processed_at: Optional[datetime]` Timestamp when the confirmation was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this confirmation was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsUserCustomToolResultEvent` Event sent by the client providing the result of a custom tool execution. - `type: Literal["user.custom_tool_result"]` - `id: str` Unique identifier for this event. - `custom_tool_use_id: str` The id of the `agent.custom_tool_use` event this result corresponds to. It is also listed in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `type: Literal["search_result"]` - `citations: BetaManagedAgentsSearchResultCitations` Citation settings for this search result. - `enabled: bool` Whether citations are enabled for this search result. - `content: List[BetaManagedAgentsSearchResultContent]` Array of text content blocks from the search result. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `source: str` The URL source of the search result. minLength: 1 - `title: str` The title of the search result. minLength: 1 - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `processed_at: Optional[datetime]` Timestamp when this result was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this result was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsAgentCustomToolUseEvent` Event emitted when the agent calls a custom tool. The session goes idle until the client sends a `user.custom_tool_result` event with the result. The client can send it as soon as this event arrives, without waiting for `session.status_idle`. - `type: Literal["agent.custom_tool_use"]` - `id: str` Unique identifier for this event. - `input: Dict[str, object]` Input parameters for the tool call. - `name: str` Name of the custom tool being called. - `processed_at: datetime` Timestamp when this tool use was processed. format: date-time - `session_thread_id: Optional[str]` When set, this event was cross-posted from a subagent's thread to surface its custom tool use on the primary thread's stream. Empty on the thread's own events. Informational only: the server routes the matching `user.custom_tool_result` by `custom_tool_use_id`, so clients do not send it back. - `class BetaManagedAgentsAgentMessageEvent` An agent response event in the session conversation. - `type: Literal["agent.message"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Array of text blocks comprising the agent response. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `processed_at: datetime` Timestamp when this response was generated. format: date-time - `class BetaManagedAgentsAgentThinkingEvent` Indicates the agent is making forward progress via extended thinking. A progress signal, not a content carrier. - `type: Literal["agent.thinking"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this thinking was produced. format: date-time - `class BetaManagedAgentsAgentMCPToolUseEvent` Event emitted when the agent invokes a tool provided by an MCP server. - `type: Literal["agent.mcp_tool_use"]` - `id: str` Unique identifier for this event. - `input: Dict[str, object]` Input parameters for the tool call. - `mcp_server_name: str` Name of the MCP server providing the tool. - `name: str` Name of the MCP tool being used. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `evaluated_permission: Optional[BetaManagedAgentsAgentEvaluatedPermission]` The evaluated permission policy for this tool invocation. - `"allow"` - `"ask"` - `"deny"` - `evaluation: Optional[BetaManagedAgentsAgentToolEvaluation]` Which resolved permission_policy produced evaluated_permission: always_allow, always_ask, or auto (with the server's per-invocation judgement). Absent only when the server refused the call before any policy applied (for example, the named tool is not enabled in the session); such a refusal has evaluated_permission deny. An event recorded before this field existed reads as the arm its evaluated_permission implies (always_allow for allow, always_ask for ask). - `class BetaManagedAgentsAgentToolEvaluationAlwaysAllow` The resolved permission_policy was always_allow; accompanies evaluated_permission "allow". - `type: Literal["always_allow"]` - `class BetaManagedAgentsAgentToolEvaluationAlwaysAsk` The resolved permission_policy was always_ask; accompanies evaluated_permission "ask". - `type: Literal["always_ask"]` - `class BetaManagedAgentsAgentToolEvaluationAuto` The resolved permission_policy was auto: the server judged this invocation individually. - `type: Literal["auto"]` - `evaluated_permission: BetaManagedAgentsAgentAutoEvaluatedPermission` The server's judgement for this invocation. - `class BetaManagedAgentsAgentAutoEvaluatedPermissionAllow` The server judged the invocation safe to execute without client approval. - `type: Literal["allow"]` - `class BetaManagedAgentsAgentAutoEvaluatedPermissionAsk` The server reached no judgement; the invocation is held for client approval. - `type: Literal["ask"]` - `reason_code: str` The judgement's grounds in registry-bound terms, for client branching and audit rather than end-user display. Open registry; currently "indeterminate" (no judgement was reached). Clients must tolerate values outside this set. maxLength: 64 - `class BetaManagedAgentsAgentAutoEvaluatedPermissionDeny` The server judged the invocation high-risk; it does not execute and a synthetic error tool result is appended. - `type: Literal["deny"]` - `reason_code: str` The judgement's grounds in registry-bound terms. Open registry; currently "high_risk" (judged high-risk; the call does not run). Clients must tolerate values outside this set. maxLength: 64 - `session_thread_id: Optional[str]` When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Informational only: the server routes the matching `user.tool_confirmation` by `tool_use_id`, so clients do not send it back. - `class BetaManagedAgentsAgentMCPToolResultEvent` Event representing the result of an MCP tool execution. - `type: Literal["agent.mcp_tool_result"]` - `id: str` Unique identifier for this event. - `mcp_tool_use_id: str` The id of the `agent.mcp_tool_use` event this result corresponds to. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `class BetaManagedAgentsAgentToolUseEvent` Event emitted when the agent invokes a built-in agent tool. - `type: Literal["agent.tool_use"]` - `id: str` Unique identifier for this event. - `input: Dict[str, object]` Input parameters for the tool call. - `name: str` Name of the agent tool being used. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `evaluated_permission: Optional[BetaManagedAgentsAgentEvaluatedPermission]` The evaluated permission policy for this tool invocation. - `evaluation: Optional[BetaManagedAgentsAgentToolEvaluation]` Which resolved permission_policy produced evaluated_permission: always_allow, always_ask, or auto (with the server's per-invocation judgement). Absent only when the server refused the call before any policy applied (for example, the named tool is not enabled in the session); such a refusal has evaluated_permission deny. An event recorded before this field existed reads as the arm its evaluated_permission implies (always_allow for allow, always_ask for ask). - `session_thread_id: Optional[str]` When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Informational only: the server routes the matching `user.tool_confirmation` or `user.tool_result` by `tool_use_id`, so clients do not send it back. - `class BetaManagedAgentsAgentToolResultEvent` Event representing the result of an agent tool execution. - `type: Literal["agent.tool_result"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `tool_use_id: str` The id of the `agent.tool_use` event this result corresponds to. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `class BetaManagedAgentsAgentThreadMessageReceivedEvent` Delivery event written to the target thread's input stream when an agent-to-agent message arrives. - `type: Literal["agent.thread_message_received"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Message content blocks. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `from_session_thread_id: str` Public `sthr_` ID of the thread that sent the message. - `processed_at: datetime` Timestamp when the message was received. format: date-time - `from_agent_name: Optional[str]` Name of the callable agent this message came from. Absent when received from the primary agent. - `class BetaManagedAgentsAgentThreadMessageSentEvent` Observability event emitted to the sender's output stream when an agent-to-agent message is sent. - `type: Literal["agent.thread_message_sent"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Message content blocks. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `processed_at: datetime` Timestamp when the message was sent. format: date-time - `to_session_thread_id: str` Public `sthr_` ID of the thread the message was sent to. - `to_agent_name: Optional[str]` Name of the callable agent this message was sent to. Absent when sent to the primary agent. - `class BetaManagedAgentsAgentThreadContextCompactedEvent` Indicates that context compaction (summarization) occurred during the session. - `type: Literal["agent.thread_context_compacted"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when compaction was processed. format: date-time - `class BetaManagedAgentsSessionErrorEvent` An error event indicating a problem occurred during session execution. - `type: Literal["session.error"]` - `id: str` Unique identifier for this event. - `error: Error` - `class BetaManagedAgentsUnknownError` An unknown or unexpected error occurred during session execution. A fallback variant; clients that don't recognize a new error code can match on `retry_status` and `message` alone. - `type: Literal["unknown_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `type: Literal["retrying"]` - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `type: Literal["exhausted"]` - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `type: Literal["terminal"]` - `class BetaManagedAgentsModelOverloadedError` The model is currently overloaded. Emitted after automatic retries are exhausted. - `type: Literal["model_overloaded_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsModelRateLimitedError` The model request was rate-limited. - `type: Literal["model_rate_limited_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsModelRequestFailedError` A model request failed for a reason other than overload or rate-limiting. - `type: Literal["model_request_failed_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsMCPConnectionFailedError` Failed to connect to an MCP server. - `type: Literal["mcp_connection_failed_error"]` - `mcp_server_name: str` Name of the MCP server that failed to connect. - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsMCPAuthenticationFailedError` Authentication to an MCP server failed. - `type: Literal["mcp_authentication_failed_error"]` - `mcp_server_name: str` Name of the MCP server that failed authentication. - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsBillingError` The caller's organization or workspace cannot make model requests — out of credits or spend limit reached. Retrying with the same credentials will not succeed; the caller must resolve the billing state. - `type: Literal["billing_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsCredentialHostUnreachableError` An `environment_variable` credential's `auth.networking.allowed_hosts` includes a host the environment's network policy does not permit. - `type: Literal["credential_host_unreachable_error"]` - `credential_id: str` ID of the affected credential. - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `vault_id: str` ID of the vault containing the affected credential. - `class BetaManagedAgentsRepositoryAuthenticationError` The repository host rejected the credentials, or required credentials and received none. - `type: Literal["repository_authentication_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryForbiddenError` The repository host refused access to the repository. - `type: Literal["repository_forbidden_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryNotFoundError` The repository host reported the repository as not found. - `type: Literal["repository_not_found_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryCheckoutError` The requested branch or commit does not exist in the repository. - `type: Literal["repository_checkout_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryCloneError` The repository could not be cloned. - `type: Literal["repository_clone_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `processed_at: datetime` Timestamp when the error occurred. format: date-time - `class BetaManagedAgentsSessionStatusRescheduledEvent` Indicates the session is recovering from an error state and is rescheduled for execution. - `type: Literal["session.status_rescheduled"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `class BetaManagedAgentsSessionStatusRunningEvent` Indicates the session is actively running and the agent is working. - `type: Literal["session.status_running"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `class BetaManagedAgentsSessionStatusIdleEvent` Indicates the agent has paused and is awaiting user input. - `type: Literal["session.status_idle"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `stop_details: Optional[BetaManagedAgentsSessionRefusalStopDetails]` Structured information about why the session stopped. `null` when there is nothing more to report. - `type: Literal["refusal"]` - `category: Optional[Literal["cyber", "bio", "frontier_llm", 2 more]]` The policy category that triggered the refusal, or `null` when there is no named category. New values can be added over time. - `"cyber"` - `"bio"` - `"frontier_llm"` - `"reasoning_extraction"` - `"general_harms"` - `explanation: Optional[str]` Human-readable explanation of the refusal, or `null` when none is available. The wording can change, so do not parse it. - `stop_reason: StopReason` - `class BetaManagedAgentsSessionEndTurn` The agent completed its turn naturally and is ready for the next user message. - `type: Literal["end_turn"]` - `class BetaManagedAgentsSessionRequiresAction` The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running. - `type: Literal["requires_action"]` - `event_ids: List[str]` The ids of events the agent is blocked on. Resolving fewer than all re-emits `session.status_idle` with the remainder. - `class BetaManagedAgentsSessionRetriesExhausted` The turn ended because repeated errors exhausted the retry budget or an error escalated to `retry_status: 'exhausted'`. - `type: Literal["retries_exhausted"]` - `class BetaManagedAgentsSessionBudgetReached` The agent stopped because the session's tracked list cost reached its budget, or because its usage includes a model with no list price (which the budget cannot measure). Raise the budget to continue — or, if raising is rejected because a model has no list price, remove the budget. - `type: Literal["budget_reached"]` - `class BetaManagedAgentsSessionRefusal` The turn ended because the model's response was refused, for example by a safety classifier. - `type: Literal["refusal"]` - `class BetaManagedAgentsSessionStatusTerminatedEvent` Indicates the session has terminated, either due to an error or completion. - `type: Literal["session.status_terminated"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `class BetaManagedAgentsSessionThreadCreatedEvent` Emitted when a child thread is created. Written to the parent thread's output stream so clients observing the session see child creation. - `type: Literal["session.thread_created"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the callable agent the thread runs. - `processed_at: datetime` Timestamp when the thread was created. format: date-time - `session_thread_id: str` Public `sthr_` ID of the newly created thread. - `workflow_run_id: Optional[str]` Identifier of the workflow run that created the thread, or `null` for any other thread. - `class BetaManagedAgentsSpanOutcomeEvaluationStartEvent` Emitted when an outcome evaluation cycle begins. - `type: Literal["span.outcome_evaluation_start"]` - `id: str` Unique identifier for this event. - `iteration: int` 0-indexed revision cycle. 0 is the first evaluation; 1 is the re-evaluation after the first revision; etc. format: int32 - `outcome_id: str` The `outc_` ID of the outcome being evaluated. - `processed_at: datetime` Timestamp when outcome evaluation started. format: date-time - `class BetaManagedAgentsSpanOutcomeEvaluationEndEvent` Emitted when an outcome evaluation cycle completes. Carries the verdict and aggregate token usage. A verdict of `needs_revision` means another evaluation cycle follows; `satisfied`, `max_iterations_reached`, `failed`, or `interrupted` are terminal — no further evaluation cycles follow. - `type: Literal["span.outcome_evaluation_end"]` - `id: str` Unique identifier for this event. - `explanation: str` Human-readable explanation of the verdict. For `needs_revision`, describes which criteria failed and why. - `iteration: int` 0-indexed revision cycle, matching the corresponding `span.outcome_evaluation_start`. format: int32 - `outcome_evaluation_start_id: str` The id of the corresponding `span.outcome_evaluation_start` event. - `outcome_id: str` The `outc_` ID of the outcome being evaluated. - `processed_at: datetime` Timestamp when outcome evaluation ended. format: date-time - `result: str` Evaluation verdict. 'satisfied': criteria met, session goes idle. 'needs_revision': criteria not met, another revision cycle follows. 'max_iterations_reached': evaluation budget exhausted with criteria still unmet — one final acknowledgment turn follows before the session goes idle, but no further evaluation runs. 'failed': grader determined the rubric does not apply to the deliverables. 'interrupted': user sent an interrupt while evaluation was in progress. - `usage: BetaManagedAgentsSpanModelUsage` Aggregate token usage for this evaluation cycle. Sums across all grader model requests within the cycle. - `cache_creation_input_tokens: int` Tokens used to create prompt cache in this request. format: int32 - `cache_read_input_tokens: int` Tokens read from prompt cache in this request. format: int32 - `input_tokens: int` Input tokens consumed by this request. format: int32 - `output_tokens: int` Output tokens generated by this request. format: int32 - `speed: Optional[Literal["standard", "fast"]]` Inference speed tier this request actually ran at. Mirrors `usage.speed` on /v1/messages. Only present when the fast-mode beta is active. - `"standard"` - `"fast"` - `class BetaManagedAgentsSpanModelRequestStartEvent` Emitted when a model request is initiated by the agent. - `type: Literal["span.model_request_start"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the model request started. format: date-time - `class BetaManagedAgentsSpanModelRequestEndEvent` Emitted when a model request completes. - `type: Literal["span.model_request_end"]` - `id: str` Unique identifier for this event. - `is_error: Optional[bool]` Whether the model request resulted in an error. - `model_request_start_id: str` The id of the corresponding `span.model_request_start` event. - `model_usage: BetaManagedAgentsSpanModelUsage` Token usage for this model request. - `processed_at: datetime` Timestamp when the model request completed. format: date-time - `class BetaManagedAgentsSpanOutcomeEvaluationOngoingEvent` Periodic heartbeat emitted while an outcome evaluation cycle is in progress. Distinguishes 'evaluation is actively running' from 'evaluation is stuck' between the corresponding `span.outcome_evaluation_start` and `span.outcome_evaluation_end` events. - `type: Literal["span.outcome_evaluation_ongoing"]` - `id: str` Unique identifier for this event. - `iteration: int` 0-indexed revision cycle, matching the corresponding `span.outcome_evaluation_start`. format: int32 - `outcome_id: str` The `outc_` ID of the outcome being evaluated. - `processed_at: datetime` Timestamp when this heartbeat was emitted. format: date-time - `class BetaManagedAgentsUserDefineOutcomeEvent` Echo of a `user.define_outcome` input event. Carries the server-generated `outcome_id` that subsequent `span.outcome_evaluation_*` events reference. - `type: Literal["user.define_outcome"]` - `id: str` Unique identifier for this event. - `description: str` What the agent should produce. Copied from the input event. - `max_iterations: Optional[int]` Evaluate-then-revise cycles before giving up. Default 3, max 20. format: int32 - `outcome_id: str` Server-generated `outc_` ID for this outcome. Referenced by `span.outcome_evaluation_*` events and the session's `outcome_evaluations` list. - `processed_at: datetime` Timestamp when the outcome was accepted. format: date-time - `rubric: Rubric` How to grade the outcome. File rubrics are currently resolved to their text content; clients should handle both variants. - `class BetaManagedAgentsFileRubric` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubric` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. - `class BetaManagedAgentsSessionDeletedEvent` Emitted when a session has been deleted. Terminates any active event stream — no further events will be emitted for this session. - `type: Literal["session.deleted"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the session was deleted. format: date-time - `class BetaManagedAgentsSessionThreadStatusRunningEvent` A session thread has begun executing. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_running"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that started running. - `class BetaManagedAgentsSessionThreadStatusIdleEvent` A session thread has yielded and is awaiting input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_idle"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that went idle. - `stop_details: Optional[BetaManagedAgentsSessionRefusalStopDetails]` Structured information about why the thread stopped. `null` when there is nothing more to report. - `stop_reason: StopReason` - `class BetaManagedAgentsSessionEndTurn` The agent completed its turn naturally and is ready for the next user message. - `class BetaManagedAgentsSessionRequiresAction` The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running. - `class BetaManagedAgentsSessionRetriesExhausted` The turn ended because repeated errors exhausted the retry budget or an error escalated to `retry_status: 'exhausted'`. - `class BetaManagedAgentsSessionBudgetReached` The agent stopped because the session's tracked list cost reached its budget, or because its usage includes a model with no list price (which the budget cannot measure). Raise the budget to continue — or, if raising is rejected because a model has no list price, remove the budget. - `class BetaManagedAgentsSessionRefusal` The turn ended because the model's response was refused, for example by a safety classifier. - `class BetaManagedAgentsSessionThreadStatusTerminatedEvent` A session thread has terminated and will accept no further input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_terminated"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that terminated. - `class BetaManagedAgentsUserToolResultEvent` Event sent by the client providing the result of an agent-toolset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `type: Literal["user.tool_result"]` - `id: str` Unique identifier for this event. - `tool_use_id: str` The id of the `agent.tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `processed_at: Optional[datetime]` Timestamp when this result was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this result was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsSessionThreadStatusRescheduledEvent` A session thread hit a transient error and is retrying automatically. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_rescheduled"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that is retrying. - `class BetaManagedAgentsSessionUpdatedEvent` Emitted when an UpdateSession request changed at least one field. Carries only the fields that changed; absent fields were not part of the update. The new configuration applies from the next turn. - `type: Literal["session.updated"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the update was applied. format: date-time - `agent: Optional[BetaManagedAgentsSessionAgent]` The session's effective agent configuration after the update. Present only when the update changed `agent` (tools or mcp_servers); when present it is the full materialised snapshot, not a diff. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsSessionMultiagent]` Resolved multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsSessionMultiagentCoordinator` Resolved coordinator topology with full agent definitions for each roster member. - `type: Literal["coordinator"]` - `agents: List[Agent]` Full `agent` definitions the coordinator may spawn as session threads. - `class BetaManagedAgentsSessionThreadAgent` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsSessionMultiagent20261001` Resolved multiagent configuration with three members, as copied to the `session` at creation. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsSessionMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsSessionMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that this agent can spawn as session threads. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsSessionMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsSessionMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that a run's plan can use. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `class BetaManagedAgentsMCPToolset` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `version: int` format: int32 - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's budget after the update: the new budget when set or replaced, or null when the update removed it. Present only when the update changed the budget. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `metadata: Optional[Dict[str, str]]` The session's full metadata bag after the update. Present when the update set non-empty metadata; absent when metadata was unchanged or cleared to empty. - `title: Optional[str]` The session's new title. Present only when the update changed it. - `class BetaManagedAgentsSystemMessageEvent` A mid-conversation system message event. Carries system-role content that is appended to the session as a `role: "system"` turn. - `type: Literal["system.message"]` - `id: str` Unique identifier for this event. - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `processed_at: Optional[datetime]` Timestamp when this system message was processed. format: date-time - `class BetaManagedAgentsSessionUsageEvent` Periodic snapshot of the session's cumulative usage and tracked list cost. - `type: Literal["session.usage"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the snapshot was taken. format: date-time - `usage: BetaManagedAgentsSessionUsageSnapshot` The session's cumulative usage at the snapshot time. - `active_seconds: Optional[float]` Cumulative time in seconds during which the session had at least one thread in running status. Overlapping activity from concurrent threads is counted once. This is the duration the session's runtime cost is priced on. format: double - `cache_creation: Optional[BetaManagedAgentsCacheCreationUsage]` Tokens used to create prompt cache entries, broken down by cache TTL. - `ephemeral_1h_input_tokens: Optional[int]` Tokens used to create 1-hour ephemeral cache entries. format: int32 - `ephemeral_5m_input_tokens: Optional[int]` Tokens used to create 5-minute ephemeral cache entries. format: int32 - `cache_read_input_tokens: Optional[int]` Total tokens read from prompt cache. format: int32 - `input_tokens: Optional[int]` Total input tokens consumed across all turns. format: int32 - `list_cost: Optional[BetaMonetaryAmount]` Cumulative list cost of the session across all turns, priced at public list rates. - `output_tokens: Optional[int]` Total output tokens generated across all turns. format: int32 - `server_tool_use: Optional[BetaManagedAgentsServerToolUsage]` Cumulative server-executed tool usage across all turns. - `web_fetch_requests: Optional[int]` Number of server-executed web fetch requests. format: int32 - `web_search_requests: Optional[int]` Number of server-executed web search requests. format: int32 - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's configured budget at the snapshot time, or null when the session has no budget. - `class BetaManagedAgentsWorkflowRunCreatedEvent` A workflow run was created. A workflow run is background work that the session's agent starts. Emitted once per run, before the run's other `workflow_run.*` events. - `type: Literal["workflow_run.created"]` - `id: str` Unique identifier for this event. - `description: Optional[str]` Description that the agent gave the run, passed on as written, or `null` if it gave none. - `name: str` Name that the agent gave the run, passed on as written, or a name that the server assigned. - `phases: List[BetaManagedAgentsWorkflowRunPhase]` The phases that the run's plan declares, in the plan's order. Can be empty. - `id: str` Unique identifier for the phase. - `description: Optional[str]` Description that the agent gave the phase, passed on as written, or `null` if it gave none. - `name: str` Name that the agent gave the phase, passed on as written. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunStatusEndedEvent` A workflow run ended. Emitted once per run, as the last of the run's `workflow_run.*` events. - `type: Literal["workflow_run.status_ended"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `result: BetaManagedAgentsWorkflowRunResult` How the run ended. - `class BetaManagedAgentsWorkflowRunResultCompleted` The run's plan, a program that the agent wrote, finished. This does not say whether the work succeeded. - `type: Literal["completed"]` - `class BetaManagedAgentsWorkflowRunResultError` The run failed or reached its time limit. - `type: Literal["error"]` - `error: BetaManagedAgentsWorkflowRunError` Why the run did not finish. - `class BetaManagedAgentsTimeoutWorkflowRunError` The run reached its time limit. - `type: Literal["timeout_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsProgramWorkflowRunError` The plan, a program that the agent wrote, failed, or the server refused it. - `type: Literal["program_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsUnknownWorkflowRunError` A failure that has no type of its own. - `type: Literal["unknown_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsThreadLimitWorkflowRunError` The run exceeded the limit on the number of threads that a run can create. - `type: Literal["thread_limit_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsMaxWorkflowRunsWorkflowRunError` No run was created, because the session was at its limit of open workflow runs, which are runs that have not ended. Only `workflow_run.error` carries this type. - `type: Literal["max_workflow_runs_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsWorkflowRunResultStopped` The agent stopped the run. - `type: Literal["stopped"]` - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunPhaseStartedEvent` A workflow run's plan entered a phase. - `type: Literal["workflow_run.phase_started"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `workflow_run_phase_id: str` Identifier of the phase, as in `phases` on the run's `workflow_run.created` event. - `class BetaManagedAgentsWorkflowRunPhaseEndedEvent` A workflow run's plan left a phase, or the run's end closed it. Emitted once for every `workflow_run.phase_started` event, before the run's `workflow_run.status_ended` event. The event does not say whether the plan finished the phase's work, or why it left. - `type: Literal["workflow_run.phase_ended"]` - `id: str` Unique identifier for this event. - `phase_started_id: str` Identifier of the `workflow_run.phase_started` event that opened the phase. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `workflow_run_phase_id: str` Identifier of the phase, as in `phases` on the run's `workflow_run.created` event. - `class BetaManagedAgentsWorkflowRunStatusRunningEvent` A workflow run is running. Emitted when the run starts to execute, and each time it resumes after being idle. A run that starts idle emits `workflow_run.status_idle` first. - `type: Literal["workflow_run.status_running"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunStatusIdleEvent` A workflow run is idle. Emitted each time the run goes idle, whatever the cause. If the run ends while idle, no `workflow_run.status_running` comes between this event and its `workflow_run.status_ended`. - `type: Literal["workflow_run.status_idle"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunErrorEvent` A workflow run met an error, or an error kept a run from being created. A run that ends with a `result.type` of `error` emits this event before its `workflow_run.status_ended`, with the same `error`. - `type: Literal["workflow_run.error"]` - `id: str` Unique identifier for this event. - `error: BetaManagedAgentsWorkflowRunError` Why the run did not finish, or was not created. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: Optional[str]` Identifier of the run that met the error, or `null` when the error kept a run from being created. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.sessions.threads.events.list( thread_id="sthr_011CZkZVWa6oJjw1rgXZpnBt", session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ) page = page.data[0] print(page) ``` ##### Response (200) ```json { "data": [ { "id": "sevt_011CZkZGPp1iBcp4kaQSihUm", "content": [ { "text": "Where is my order #1234?", "type": "text" } ], "type": "user.message", "processed_at": "2026-03-15T10:00:00Z" }, { "id": "sevt_011CZkZHPq1jCdq5mbRTjiVn", "content": [ { "text": "Let me look up order #1234 for you.", "type": "text" } ], "processed_at": "2026-03-15T10:00:00Z", "type": "agent.message" } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=" } ``` ### Stream Session Thread Events `beta.sessions.threads.events.stream(thread_id, **kwargs) -> BetaManagedAgentsStreamSessionThreadEvents` **GET** `/v1/sessions/{session_id}/threads/{thread_id}/stream` Stream Session Thread Events #### Parameters - `session_id: str` (path parameter) - `thread_id: str` (path parameter) - `event_deltas: Optional[List[BetaManagedAgentsDeltaType]]` (query parameter) When set, this connection also receives streaming deltas (`event_start`, `event_delta`) while an event is being produced, before the event itself arrives. Deltas are best-effort; when the final event is produced it carries the complete content. A model request that ends early (an error or interrupt) produces no final event — its terminal `span.model_request_end` closes the preview. Accepts one or more event types to preview and may be repeated: `agent.message` streams `content_delta` fragments; `agent.thinking` is start-only — a signal that the agent has begun extended thinking, concluded by the `agent.thinking` event itself. Only previews of the requested event types are sent. - `"agent.message"` - `"agent.thinking"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `type BetaManagedAgentsStreamSessionThreadEvents = ...` Server-sent event in a single thread's stream. - `class BetaManagedAgentsUserMessageEvent` A user message event in the session conversation. - `type: Literal["user.message"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Array of content blocks comprising the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `processed_at: Optional[datetime]` Timestamp when the agent finished processing this message. format: date-time - `class BetaManagedAgentsUserInterruptEvent` An interrupt event that pauses agent execution and returns control to the user. - `type: Literal["user.interrupt"]` - `id: str` Unique identifier for this event. - `processed_at: Optional[datetime]` Timestamp when the interrupt was processed. format: date-time - `session_thread_id: Optional[str]` If absent, interrupts every non-archived thread in a multiagent session (or the primary alone in a single-agent session). If present, interrupts only the named thread. - `class BetaManagedAgentsUserToolConfirmationEvent` A tool confirmation event that approves or denies a pending tool execution. - `type: Literal["user.tool_confirmation"]` - `id: str` Unique identifier for this event. - `result: Literal["allow", "deny"]` The confirmation result: 'allow' or 'deny'. - `"allow"` - `"deny"` - `tool_use_id: str` The id of the `agent.tool_use` or `agent.mcp_tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `deny_message: Optional[str]` Optional message providing context for a 'deny' decision. Only allowed when result is 'deny'. maxLength: 10000 - `processed_at: Optional[datetime]` Timestamp when the confirmation was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this confirmation was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsUserCustomToolResultEvent` Event sent by the client providing the result of a custom tool execution. - `type: Literal["user.custom_tool_result"]` - `id: str` Unique identifier for this event. - `custom_tool_use_id: str` The id of the `agent.custom_tool_use` event this result corresponds to. It is also listed in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `type: Literal["search_result"]` - `citations: BetaManagedAgentsSearchResultCitations` Citation settings for this search result. - `enabled: bool` Whether citations are enabled for this search result. - `content: List[BetaManagedAgentsSearchResultContent]` Array of text content blocks from the search result. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `source: str` The URL source of the search result. minLength: 1 - `title: str` The title of the search result. minLength: 1 - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `processed_at: Optional[datetime]` Timestamp when this result was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this result was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsAgentCustomToolUseEvent` Event emitted when the agent calls a custom tool. The session goes idle until the client sends a `user.custom_tool_result` event with the result. The client can send it as soon as this event arrives, without waiting for `session.status_idle`. - `type: Literal["agent.custom_tool_use"]` - `id: str` Unique identifier for this event. - `input: Dict[str, object]` Input parameters for the tool call. - `name: str` Name of the custom tool being called. - `processed_at: datetime` Timestamp when this tool use was processed. format: date-time - `session_thread_id: Optional[str]` When set, this event was cross-posted from a subagent's thread to surface its custom tool use on the primary thread's stream. Empty on the thread's own events. Informational only: the server routes the matching `user.custom_tool_result` by `custom_tool_use_id`, so clients do not send it back. - `class BetaManagedAgentsAgentMessageEvent` An agent response event in the session conversation. - `type: Literal["agent.message"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Array of text blocks comprising the agent response. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `processed_at: datetime` Timestamp when this response was generated. format: date-time - `class BetaManagedAgentsAgentThinkingEvent` Indicates the agent is making forward progress via extended thinking. A progress signal, not a content carrier. - `type: Literal["agent.thinking"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this thinking was produced. format: date-time - `class BetaManagedAgentsAgentMCPToolUseEvent` Event emitted when the agent invokes a tool provided by an MCP server. - `type: Literal["agent.mcp_tool_use"]` - `id: str` Unique identifier for this event. - `input: Dict[str, object]` Input parameters for the tool call. - `mcp_server_name: str` Name of the MCP server providing the tool. - `name: str` Name of the MCP tool being used. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `evaluated_permission: Optional[BetaManagedAgentsAgentEvaluatedPermission]` The evaluated permission policy for this tool invocation. - `"allow"` - `"ask"` - `"deny"` - `evaluation: Optional[BetaManagedAgentsAgentToolEvaluation]` Which resolved permission_policy produced evaluated_permission: always_allow, always_ask, or auto (with the server's per-invocation judgement). Absent only when the server refused the call before any policy applied (for example, the named tool is not enabled in the session); such a refusal has evaluated_permission deny. An event recorded before this field existed reads as the arm its evaluated_permission implies (always_allow for allow, always_ask for ask). - `class BetaManagedAgentsAgentToolEvaluationAlwaysAllow` The resolved permission_policy was always_allow; accompanies evaluated_permission "allow". - `type: Literal["always_allow"]` - `class BetaManagedAgentsAgentToolEvaluationAlwaysAsk` The resolved permission_policy was always_ask; accompanies evaluated_permission "ask". - `type: Literal["always_ask"]` - `class BetaManagedAgentsAgentToolEvaluationAuto` The resolved permission_policy was auto: the server judged this invocation individually. - `type: Literal["auto"]` - `evaluated_permission: BetaManagedAgentsAgentAutoEvaluatedPermission` The server's judgement for this invocation. - `class BetaManagedAgentsAgentAutoEvaluatedPermissionAllow` The server judged the invocation safe to execute without client approval. - `type: Literal["allow"]` - `class BetaManagedAgentsAgentAutoEvaluatedPermissionAsk` The server reached no judgement; the invocation is held for client approval. - `type: Literal["ask"]` - `reason_code: str` The judgement's grounds in registry-bound terms, for client branching and audit rather than end-user display. Open registry; currently "indeterminate" (no judgement was reached). Clients must tolerate values outside this set. maxLength: 64 - `class BetaManagedAgentsAgentAutoEvaluatedPermissionDeny` The server judged the invocation high-risk; it does not execute and a synthetic error tool result is appended. - `type: Literal["deny"]` - `reason_code: str` The judgement's grounds in registry-bound terms. Open registry; currently "high_risk" (judged high-risk; the call does not run). Clients must tolerate values outside this set. maxLength: 64 - `session_thread_id: Optional[str]` When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Informational only: the server routes the matching `user.tool_confirmation` by `tool_use_id`, so clients do not send it back. - `class BetaManagedAgentsAgentMCPToolResultEvent` Event representing the result of an MCP tool execution. - `type: Literal["agent.mcp_tool_result"]` - `id: str` Unique identifier for this event. - `mcp_tool_use_id: str` The id of the `agent.mcp_tool_use` event this result corresponds to. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `class BetaManagedAgentsAgentToolUseEvent` Event emitted when the agent invokes a built-in agent tool. - `type: Literal["agent.tool_use"]` - `id: str` Unique identifier for this event. - `input: Dict[str, object]` Input parameters for the tool call. - `name: str` Name of the agent tool being used. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `evaluated_permission: Optional[BetaManagedAgentsAgentEvaluatedPermission]` The evaluated permission policy for this tool invocation. - `evaluation: Optional[BetaManagedAgentsAgentToolEvaluation]` Which resolved permission_policy produced evaluated_permission: always_allow, always_ask, or auto (with the server's per-invocation judgement). Absent only when the server refused the call before any policy applied (for example, the named tool is not enabled in the session); such a refusal has evaluated_permission deny. An event recorded before this field existed reads as the arm its evaluated_permission implies (always_allow for allow, always_ask for ask). - `session_thread_id: Optional[str]` When set, this event was cross-posted from a subagent's thread to surface its permission request on the primary thread's stream. Empty on the thread's own events. Informational only: the server routes the matching `user.tool_confirmation` or `user.tool_result` by `tool_use_id`, so clients do not send it back. - `class BetaManagedAgentsAgentToolResultEvent` Event representing the result of an agent tool execution. - `type: Literal["agent.tool_result"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `tool_use_id: str` The id of the `agent.tool_use` event this result corresponds to. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `class BetaManagedAgentsAgentThreadMessageReceivedEvent` Delivery event written to the target thread's input stream when an agent-to-agent message arrives. - `type: Literal["agent.thread_message_received"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Message content blocks. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `from_session_thread_id: str` Public `sthr_` ID of the thread that sent the message. - `processed_at: datetime` Timestamp when the message was received. format: date-time - `from_agent_name: Optional[str]` Name of the callable agent this message came from. Absent when received from the primary agent. - `class BetaManagedAgentsAgentThreadMessageSentEvent` Observability event emitted to the sender's output stream when an agent-to-agent message is sent. - `type: Literal["agent.thread_message_sent"]` - `id: str` Unique identifier for this event. - `content: List[Content]` Message content blocks. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `processed_at: datetime` Timestamp when the message was sent. format: date-time - `to_session_thread_id: str` Public `sthr_` ID of the thread the message was sent to. - `to_agent_name: Optional[str]` Name of the callable agent this message was sent to. Absent when sent to the primary agent. - `class BetaManagedAgentsAgentThreadContextCompactedEvent` Indicates that context compaction (summarization) occurred during the session. - `type: Literal["agent.thread_context_compacted"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when compaction was processed. format: date-time - `class BetaManagedAgentsSessionErrorEvent` An error event indicating a problem occurred during session execution. - `type: Literal["session.error"]` - `id: str` Unique identifier for this event. - `error: Error` - `class BetaManagedAgentsUnknownError` An unknown or unexpected error occurred during session execution. A fallback variant; clients that don't recognize a new error code can match on `retry_status` and `message` alone. - `type: Literal["unknown_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `type: Literal["retrying"]` - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `type: Literal["exhausted"]` - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `type: Literal["terminal"]` - `class BetaManagedAgentsModelOverloadedError` The model is currently overloaded. Emitted after automatic retries are exhausted. - `type: Literal["model_overloaded_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsModelRateLimitedError` The model request was rate-limited. - `type: Literal["model_rate_limited_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsModelRequestFailedError` A model request failed for a reason other than overload or rate-limiting. - `type: Literal["model_request_failed_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsMCPConnectionFailedError` Failed to connect to an MCP server. - `type: Literal["mcp_connection_failed_error"]` - `mcp_server_name: str` Name of the MCP server that failed to connect. - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsMCPAuthenticationFailedError` Authentication to an MCP server failed. - `type: Literal["mcp_authentication_failed_error"]` - `mcp_server_name: str` Name of the MCP server that failed authentication. - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsBillingError` The caller's organization or workspace cannot make model requests — out of credits or spend limit reached. Retrying with the same credentials will not succeed; the caller must resolve the billing state. - `type: Literal["billing_error"]` - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsCredentialHostUnreachableError` An `environment_variable` credential's `auth.networking.allowed_hosts` includes a host the environment's network policy does not permit. - `type: Literal["credential_host_unreachable_error"]` - `credential_id: str` ID of the affected credential. - `message: str` Human-readable error description. - `retry_status: RetryStatus` What the client should do next. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `vault_id: str` ID of the vault containing the affected credential. - `class BetaManagedAgentsRepositoryAuthenticationError` The repository host rejected the credentials, or required credentials and received none. - `type: Literal["repository_authentication_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryForbiddenError` The repository host refused access to the repository. - `type: Literal["repository_forbidden_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryNotFoundError` The repository host reported the repository as not found. - `type: Literal["repository_not_found_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryCheckoutError` The requested branch or commit does not exist in the repository. - `type: Literal["repository_checkout_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `class BetaManagedAgentsRepositoryCloneError` The repository could not be cloned. - `type: Literal["repository_clone_error"]` - `message: str` Human-readable error description. - `repository_url: Optional[str]` URL of the repository that could not be cloned. Null when it could not be identified. - `retry_status: RetryStatus` What the client should do next. Always `retrying`: the session keeps running without the repository. - `class BetaManagedAgentsRetryStatusRetrying` The server is retrying automatically. Client should wait; the same error type may fire again as retrying, then once as exhausted when the retry budget runs out. - `class BetaManagedAgentsRetryStatusExhausted` This turn is dead; queued inputs are flushed and the session returns to idle. Client may send a new prompt. - `class BetaManagedAgentsRetryStatusTerminal` The session encountered a terminal error and will transition to `terminated` state. - `processed_at: datetime` Timestamp when the error occurred. format: date-time - `class BetaManagedAgentsSessionStatusRescheduledEvent` Indicates the session is recovering from an error state and is rescheduled for execution. - `type: Literal["session.status_rescheduled"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `class BetaManagedAgentsSessionStatusRunningEvent` Indicates the session is actively running and the agent is working. - `type: Literal["session.status_running"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `class BetaManagedAgentsSessionStatusIdleEvent` Indicates the agent has paused and is awaiting user input. - `type: Literal["session.status_idle"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `stop_details: Optional[BetaManagedAgentsSessionRefusalStopDetails]` Structured information about why the session stopped. `null` when there is nothing more to report. - `type: Literal["refusal"]` - `category: Optional[Literal["cyber", "bio", "frontier_llm", 2 more]]` The policy category that triggered the refusal, or `null` when there is no named category. New values can be added over time. - `"cyber"` - `"bio"` - `"frontier_llm"` - `"reasoning_extraction"` - `"general_harms"` - `explanation: Optional[str]` Human-readable explanation of the refusal, or `null` when none is available. The wording can change, so do not parse it. - `stop_reason: StopReason` - `class BetaManagedAgentsSessionEndTurn` The agent completed its turn naturally and is ready for the next user message. - `type: Literal["end_turn"]` - `class BetaManagedAgentsSessionRequiresAction` The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running. - `type: Literal["requires_action"]` - `event_ids: List[str]` The ids of events the agent is blocked on. Resolving fewer than all re-emits `session.status_idle` with the remainder. - `class BetaManagedAgentsSessionRetriesExhausted` The turn ended because repeated errors exhausted the retry budget or an error escalated to `retry_status: 'exhausted'`. - `type: Literal["retries_exhausted"]` - `class BetaManagedAgentsSessionBudgetReached` The agent stopped because the session's tracked list cost reached its budget, or because its usage includes a model with no list price (which the budget cannot measure). Raise the budget to continue — or, if raising is rejected because a model has no list price, remove the budget. - `type: Literal["budget_reached"]` - `class BetaManagedAgentsSessionRefusal` The turn ended because the model's response was refused, for example by a safety classifier. - `type: Literal["refusal"]` - `class BetaManagedAgentsSessionStatusTerminatedEvent` Indicates the session has terminated, either due to an error or completion. - `type: Literal["session.status_terminated"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp of status change. format: date-time - `class BetaManagedAgentsSessionThreadCreatedEvent` Emitted when a child thread is created. Written to the parent thread's output stream so clients observing the session see child creation. - `type: Literal["session.thread_created"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the callable agent the thread runs. - `processed_at: datetime` Timestamp when the thread was created. format: date-time - `session_thread_id: str` Public `sthr_` ID of the newly created thread. - `workflow_run_id: Optional[str]` Identifier of the workflow run that created the thread, or `null` for any other thread. - `class BetaManagedAgentsSpanOutcomeEvaluationStartEvent` Emitted when an outcome evaluation cycle begins. - `type: Literal["span.outcome_evaluation_start"]` - `id: str` Unique identifier for this event. - `iteration: int` 0-indexed revision cycle. 0 is the first evaluation; 1 is the re-evaluation after the first revision; etc. format: int32 - `outcome_id: str` The `outc_` ID of the outcome being evaluated. - `processed_at: datetime` Timestamp when outcome evaluation started. format: date-time - `class BetaManagedAgentsSpanOutcomeEvaluationEndEvent` Emitted when an outcome evaluation cycle completes. Carries the verdict and aggregate token usage. A verdict of `needs_revision` means another evaluation cycle follows; `satisfied`, `max_iterations_reached`, `failed`, or `interrupted` are terminal — no further evaluation cycles follow. - `type: Literal["span.outcome_evaluation_end"]` - `id: str` Unique identifier for this event. - `explanation: str` Human-readable explanation of the verdict. For `needs_revision`, describes which criteria failed and why. - `iteration: int` 0-indexed revision cycle, matching the corresponding `span.outcome_evaluation_start`. format: int32 - `outcome_evaluation_start_id: str` The id of the corresponding `span.outcome_evaluation_start` event. - `outcome_id: str` The `outc_` ID of the outcome being evaluated. - `processed_at: datetime` Timestamp when outcome evaluation ended. format: date-time - `result: str` Evaluation verdict. 'satisfied': criteria met, session goes idle. 'needs_revision': criteria not met, another revision cycle follows. 'max_iterations_reached': evaluation budget exhausted with criteria still unmet — one final acknowledgment turn follows before the session goes idle, but no further evaluation runs. 'failed': grader determined the rubric does not apply to the deliverables. 'interrupted': user sent an interrupt while evaluation was in progress. - `usage: BetaManagedAgentsSpanModelUsage` Aggregate token usage for this evaluation cycle. Sums across all grader model requests within the cycle. - `cache_creation_input_tokens: int` Tokens used to create prompt cache in this request. format: int32 - `cache_read_input_tokens: int` Tokens read from prompt cache in this request. format: int32 - `input_tokens: int` Input tokens consumed by this request. format: int32 - `output_tokens: int` Output tokens generated by this request. format: int32 - `speed: Optional[Literal["standard", "fast"]]` Inference speed tier this request actually ran at. Mirrors `usage.speed` on /v1/messages. Only present when the fast-mode beta is active. - `"standard"` - `"fast"` - `class BetaManagedAgentsSpanModelRequestStartEvent` Emitted when a model request is initiated by the agent. - `type: Literal["span.model_request_start"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the model request started. format: date-time - `class BetaManagedAgentsSpanModelRequestEndEvent` Emitted when a model request completes. - `type: Literal["span.model_request_end"]` - `id: str` Unique identifier for this event. - `is_error: Optional[bool]` Whether the model request resulted in an error. - `model_request_start_id: str` The id of the corresponding `span.model_request_start` event. - `model_usage: BetaManagedAgentsSpanModelUsage` Token usage for this model request. - `processed_at: datetime` Timestamp when the model request completed. format: date-time - `class BetaManagedAgentsSpanOutcomeEvaluationOngoingEvent` Periodic heartbeat emitted while an outcome evaluation cycle is in progress. Distinguishes 'evaluation is actively running' from 'evaluation is stuck' between the corresponding `span.outcome_evaluation_start` and `span.outcome_evaluation_end` events. - `type: Literal["span.outcome_evaluation_ongoing"]` - `id: str` Unique identifier for this event. - `iteration: int` 0-indexed revision cycle, matching the corresponding `span.outcome_evaluation_start`. format: int32 - `outcome_id: str` The `outc_` ID of the outcome being evaluated. - `processed_at: datetime` Timestamp when this heartbeat was emitted. format: date-time - `class BetaManagedAgentsUserDefineOutcomeEvent` Echo of a `user.define_outcome` input event. Carries the server-generated `outcome_id` that subsequent `span.outcome_evaluation_*` events reference. - `type: Literal["user.define_outcome"]` - `id: str` Unique identifier for this event. - `description: str` What the agent should produce. Copied from the input event. - `max_iterations: Optional[int]` Evaluate-then-revise cycles before giving up. Default 3, max 20. format: int32 - `outcome_id: str` Server-generated `outc_` ID for this outcome. Referenced by `span.outcome_evaluation_*` events and the session's `outcome_evaluations` list. - `processed_at: datetime` Timestamp when the outcome was accepted. format: date-time - `rubric: Rubric` How to grade the outcome. File rubrics are currently resolved to their text content; clients should handle both variants. - `class BetaManagedAgentsFileRubric` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubric` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. - `class BetaManagedAgentsSessionDeletedEvent` Emitted when a session has been deleted. Terminates any active event stream — no further events will be emitted for this session. - `type: Literal["session.deleted"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the session was deleted. format: date-time - `class BetaManagedAgentsSessionThreadStatusRunningEvent` A session thread has begun executing. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_running"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that started running. - `class BetaManagedAgentsSessionThreadStatusIdleEvent` A session thread has yielded and is awaiting input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_idle"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that went idle. - `stop_details: Optional[BetaManagedAgentsSessionRefusalStopDetails]` Structured information about why the thread stopped. `null` when there is nothing more to report. - `stop_reason: StopReason` - `class BetaManagedAgentsSessionEndTurn` The agent completed its turn naturally and is ready for the next user message. - `class BetaManagedAgentsSessionRequiresAction` The agent is idle waiting on one or more blocking user-input events (tool confirmation, custom tool result, etc.). Resolving all of them transitions the session back to running. - `class BetaManagedAgentsSessionRetriesExhausted` The turn ended because repeated errors exhausted the retry budget or an error escalated to `retry_status: 'exhausted'`. - `class BetaManagedAgentsSessionBudgetReached` The agent stopped because the session's tracked list cost reached its budget, or because its usage includes a model with no list price (which the budget cannot measure). Raise the budget to continue — or, if raising is rejected because a model has no list price, remove the budget. - `class BetaManagedAgentsSessionRefusal` The turn ended because the model's response was refused, for example by a safety classifier. - `class BetaManagedAgentsSessionThreadStatusTerminatedEvent` A session thread has terminated and will accept no further input. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_terminated"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that terminated. - `class BetaManagedAgentsUserToolResultEvent` Event sent by the client providing the result of an agent-toolset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `type: Literal["user.tool_result"]` - `id: str` Unique identifier for this event. - `tool_use_id: str` The id of the `agent.tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/beta/sessions/events/list?sdk_languages=python#beta_managed_agents_session_requires_action.event_ids) `stop_reason.event_ids` field. - `content: Optional[List[Content]]` The result content returned by the tool. - `class BetaManagedAgentsTextBlock` Regular text content. - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `class BetaManagedAgentsSearchResultBlock` A block containing a web search result. - `is_error: Optional[bool]` Whether the tool execution resulted in an error. - `processed_at: Optional[datetime]` Timestamp when this result was processed. format: date-time - `session_thread_id: Optional[str]` Set by the server to the subagent thread this result was routed to. Omitted when it was routed to the primary thread. - `class BetaManagedAgentsSessionThreadStatusRescheduledEvent` A session thread hit a transient error and is retrying automatically. Emitted on the thread's own stream and cross-posted to the primary stream for child threads. - `type: Literal["session.thread_status_rescheduled"]` - `id: str` Unique identifier for this event. - `agent_name: str` Name of the agent the thread runs. - `processed_at: datetime` Timestamp of the status transition. format: date-time - `session_thread_id: str` Public sthr_ ID of the thread that is retrying. - `class BetaManagedAgentsSessionUpdatedEvent` Emitted when an UpdateSession request changed at least one field. Carries only the fields that changed; absent fields were not part of the update. The new configuration applies from the next turn. - `type: Literal["session.updated"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the update was applied. format: date-time - `agent: Optional[BetaManagedAgentsSessionAgent]` The session's effective agent configuration after the update. Present only when the update changed `agent` (tools or mcp_servers); when present it is the full materialised snapshot, not a diff. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `id: BetaManagedAgentsModel` The model that will power your agent. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `"claude-sonnet-5-5"` Efficient model for coding and agents - `"claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-sonnet-5"` Efficient model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` - `"claude-haiku-4-5-20251001"` - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` **Deprecated**: Will reach end-of-life on November 30, 2026. Please migrate to claude-sonnet-5-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information. High-performance model for agents and coding - `str` - `effort: Optional[Effort]` How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied. - `class BetaManagedAgentsEffortLow` Low effort. Favors latency over reasoning depth. - `type: Literal["low"]` - `class BetaManagedAgentsEffortMedium` Medium effort. Balances latency and reasoning depth. - `type: Literal["medium"]` - `class BetaManagedAgentsEffortHigh` High effort. Favors reasoning depth. - `type: Literal["high"]` - `class BetaManagedAgentsEffortXhigh` Extra-high effort. Not all models accept this level. - `type: Literal["xhigh"]` - `class BetaManagedAgentsEffortMax` Maximum effort. Favors reasoning depth over latency. - `type: Literal["max"]` - `inference_geo: Optional[str]` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. - `speed: Optional[Literal["standard", "fast"]]` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time. - `"standard"` - `"fast"` - `multiagent: Optional[BetaManagedAgentsSessionMultiagent]` Resolved multiagent orchestration configuration. Null when the agent is single-threaded. - `class BetaManagedAgentsSessionMultiagentCoordinator` Resolved coordinator topology with full agent definitions for each roster member. - `type: Literal["coordinator"]` - `agents: List[Agent]` Full `agent` definitions the coordinator may spawn as session threads. - `class BetaManagedAgentsSessionThreadAgent` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `type: Literal["url"]` - `name: str` - `url: str` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `type: Literal["anthropic"]` - `skill_id: str` - `version: str` - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `type: Literal["custom"]` - `skill_id: str` - `version: str` - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `type: Literal["agent_toolset_20260401"]` - `configs: List[BetaManagedAgentsAgentToolConfig]` - `class BetaManagedAgentsBashToolConfig` Configuration for the bash tool. - `type: Literal["bash"]` - `enabled: bool` - `name: Literal["bash"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `type: Literal["always_allow"]` - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `type: Literal["always_ask"]` - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `type: Literal["auto"]` - `class BetaManagedAgentsEditToolConfig` Configuration for the edit tool. - `type: Literal["edit"]` - `enabled: bool` - `name: Literal["edit"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsReadToolConfig` Configuration for the read tool. - `type: Literal["read"]` - `enabled: bool` - `name: Literal["read"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWriteToolConfig` Configuration for the write tool. - `type: Literal["write"]` - `enabled: bool` - `name: Literal["write"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGlobToolConfig` Configuration for the glob tool. - `type: Literal["glob"]` - `enabled: bool` - `name: Literal["glob"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsGrepToolConfig` Configuration for the grep tool. - `type: Literal["grep"]` - `enabled: bool` - `name: Literal["grep"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsWebFetchToolConfig` Configuration for the web_fetch tool. - `type: Literal["web_fetch"]` - `enabled: bool` - `name: Literal["web_fetch"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `url_sources: Optional[BetaManagedAgentsWebFetchURLSources]` Which sources contribute URLs the tool may fetch, always in the object form. Null when not set, which allows every source. - `client_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `type: Literal["all"]` - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `type: Literal["none"]` - `class BetaManagedAgentsWebFetchURLSourceOnly` Only the named tools' results contribute URLs that may be fetched. - `type: Literal["only"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `class BetaManagedAgentsWebFetchURLSourceExcept` Every tool's results contribute URLs that may be fetched, except the named tools' results. - `type: Literal["except"]` - `tools: List[BetaManagedAgentsWebFetchURLSourceToolReference]` The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results. - `type: Literal["tool_reference"]` Must be "tool_reference". - `name: str` Name of the tool. Compared exactly, so upper and lower case letters are different. minLength: 1, maxLength: 128 - `server_tool_results: Optional[BetaManagedAgentsWebFetchURLSourceToolFilter]` Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both. - `user_input: Optional[BetaManagedAgentsWebFetchURLSourceUserInput]` Whether URLs in the text of user messages may be fetched. Null when not set, which allows them. - `class BetaManagedAgentsWebFetchURLSourceAll` Every URL from this source may be fetched. This is the default. - `class BetaManagedAgentsWebFetchURLSourceNone` This source contributes no URLs that may be fetched. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `max_content_tokens: Optional[int]` format: int32 - `class BetaManagedAgentsWebSearchToolConfig` Configuration for the web_search tool. - `type: Literal["web_search"]` - `enabled: bool` - `name: Literal["web_search"]` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `allowed_domains: Optional[List[str]]` - `blocked_domains: Optional[List[str]]` - `user_location: Optional[BetaManagedAgentsUserLocation]` Approximate user location for search result localization. - `type: Literal["approximate"]` Location precision. Only "approximate" is supported. - `city: Optional[str]` City name. minLength: 1, maxLength: 255 - `country: Optional[str]` Two-letter ISO 3166-1 country code, uppercase. - `region: Optional[str]` Region or state name. minLength: 1, maxLength: 255 - `timezone: Optional[str]` IANA timezone identifier, e.g. "America/Los_Angeles". minLength: 1, maxLength: 255 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `class BetaManagedAgentsMCPToolset` - `type: Literal["mcp_toolset"]` - `configs: List[BetaManagedAgentsMCPToolConfig]` - `enabled: bool` - `name: str` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server. - `enabled: bool` - `permission_policy: PermissionPolicy` Permission policy for tool execution. - `class BetaManagedAgentsAlwaysAllowPolicy` Tool calls are automatically approved without user confirmation. - `class BetaManagedAgentsAlwaysAskPolicy` Tool calls require user confirmation before execution. - `class BetaManagedAgentsAutoPolicy` The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask. - `mcp_server_name: str` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `type: Literal["custom"]` - `description: str` - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: Literal["object"]` - `properties: Optional[Dict[str, object]]` - `required: Optional[List[str]]` - `name: str` - `version: int` format: int32 - `class BetaManagedAgentsAdvisor` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. - `type: Literal["advisor"]` - `model: str` The advisor model id. - `class BetaManagedAgentsSessionMultiagent20261001` Resolved multiagent configuration with three members, as copied to the `session` at creation. - `type: Literal["multiagent_20261001"]` - `advisor: BetaManagedAgentsMultiagentAdvisor` Whether the session's primary thread can consult an advisor model. - `class BetaManagedAgentsMultiagentAdvisorEnabled` The session's primary thread can consult `model` mid-turn. - `type: Literal["enabled"]` - `model: str` The advisor model id. - `class BetaManagedAgentsMultiagentAdvisorDisabled` The agent has no advisor. - `type: Literal["disabled"]` - `subagents: BetaManagedAgentsSessionMultiagentSubagents` Whether the agent can spawn session threads. - `class BetaManagedAgentsSessionMultiagentSubagentsEnabled` The agent can spawn session threads. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether the agent can define inline agents, which are not saved, when it spawns session threads. - `class BetaManagedAgentsMultiagentInlineAgentsEnabled` The agent can define inline agents. - `type: Literal["enabled"]` - `class BetaManagedAgentsMultiagentInlineAgentsDisabled` The agent cannot define inline agents. - `type: Literal["disabled"]` - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that this agent can spawn as session threads. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentSubagentsDisabled` The agent cannot spawn session threads. - `type: Literal["disabled"]` - `workflows: BetaManagedAgentsSessionMultiagentWorkflows` Whether the agent can start workflow runs. - `class BetaManagedAgentsSessionMultiagentWorkflowsEnabled` The agent can start workflow runs. - `type: Literal["enabled"]` - `inline_agents: BetaManagedAgentsMultiagentInlineAgents` Whether a run's plan can define inline agents, which are not saved. - `predefined_agents: List[BetaManagedAgentsSessionThreadAgent]` Full `agent` definitions of the predefined agents, which are saved agents that a run's plan can use. - `type: Literal["agent"]` - `id: str` - `description: Optional[str]` - `mcp_servers: List[BetaManagedAgentsMCPServerURLDefinition]` - `model: BetaManagedAgentsModelConfig` Model identifier and configuration. - `name: str` - `skills: List[Skill]` - `system: Optional[str]` - `tools: List[Tool]` - `version: int` format: int32 - `class BetaManagedAgentsMultiagentWorkflowsDisabled` The agent cannot start workflow runs. - `type: Literal["disabled"]` - `name: str` - `skills: List[Skill]` - `class BetaManagedAgentsAnthropicSkill` A resolved Anthropic-managed skill. - `class BetaManagedAgentsCustomSkill` A resolved user-created custom skill. - `system: Optional[str]` - `tools: List[Tool]` - `class BetaManagedAgentsAgentToolset20260401` - `class BetaManagedAgentsMCPToolset` - `class BetaManagedAgentsCustomTool` A custom tool as returned in API responses. - `version: int` format: int32 - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's budget after the update: the new budget when set or replaced, or null when the update removed it. Present only when the update changed the budget. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `metadata: Optional[Dict[str, str]]` The session's full metadata bag after the update. Present when the update set non-empty metadata; absent when metadata was unchanged or cleared to empty. - `title: Optional[str]` The session's new title. Present only when the update changed it. - `class BetaManagedAgentsStartEvent` Opens a preview of a buffered event. Carries the previewed event's type and id only. Followed by zero or more event_delta events with the same event id, normally concluded by the buffered event carrying that id. If the producing model request ends without that event (an error or interrupt mid-stream), its terminal span.model_request_end closes the preview. Only sent on stream connections that opt in via event_deltas; never appears in event history. - `type: Literal["event_start"]` - `event: BetaManagedAgentsStartEventPreview` The previewed event's type and id. The event type determines which delta types the preview's event_delta events carry: agent.message events stream content_delta fragments; agent.thinking previews are start-only — no deltas follow, and the buffered agent.thinking with the same id concludes them. - `class BetaManagedAgentsAgentMessagePreview` - `type: Literal["agent.message"]` - `id: str` The id the buffered agent.message will carry if it is emitted. Matches the event_id on this preview's event_delta events. - `class BetaManagedAgentsAgentThinkingPreview` - `type: Literal["agent.thinking"]` - `id: str` The id the buffered agent.thinking will carry if it is emitted. Start-only — no event_delta events follow. - `class BetaManagedAgentsDeltaEvent` An incremental update to an event that is still being streamed. Deltas are best-effort and may stop early; when the buffered event with id == event_id is produced it carries the complete content. A model request that ends early (an error or interrupt) produces no buffered event — its terminal span.model_request_end closes the preview. Only sent on stream connections that opt in via event_deltas; never appears in event history. - `type: Literal["event_delta"]` - `delta: BetaManagedAgentsDeltaContent` One fragment of the previewed event. The delta type is named for the previewed event's field it streams into: agent.message events stream content_delta fragments, each a partial element of the content array. - `type: Literal["content_delta"]` - `content: BetaManagedAgentsTextBlock` A partial element of the content array at index, typed like the element itself — the same shape the buffered agent.message carries in content. - `index: Optional[int]` Which entry in the previewed event's content array this fragment lands in. Insert content as that entry when the index is new; append to the existing entry otherwise. - `event_id: str` The id of the event being previewed. Matches event.id on the corresponding event_start and the buffered event that reconciles the preview. - `class BetaManagedAgentsSystemMessageEvent` A mid-conversation system message event. Carries system-role content that is appended to the session as a `role: "system"` turn. - `type: Literal["system.message"]` - `id: str` Unique identifier for this event. - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `processed_at: Optional[datetime]` Timestamp when this system message was processed. format: date-time - `class BetaManagedAgentsSessionUsageEvent` Periodic snapshot of the session's cumulative usage and tracked list cost. - `type: Literal["session.usage"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when the snapshot was taken. format: date-time - `usage: BetaManagedAgentsSessionUsageSnapshot` The session's cumulative usage at the snapshot time. - `active_seconds: Optional[float]` Cumulative time in seconds during which the session had at least one thread in running status. Overlapping activity from concurrent threads is counted once. This is the duration the session's runtime cost is priced on. format: double - `cache_creation: Optional[BetaManagedAgentsCacheCreationUsage]` Tokens used to create prompt cache entries, broken down by cache TTL. - `ephemeral_1h_input_tokens: Optional[int]` Tokens used to create 1-hour ephemeral cache entries. format: int32 - `ephemeral_5m_input_tokens: Optional[int]` Tokens used to create 5-minute ephemeral cache entries. format: int32 - `cache_read_input_tokens: Optional[int]` Total tokens read from prompt cache. format: int32 - `input_tokens: Optional[int]` Total input tokens consumed across all turns. format: int32 - `list_cost: Optional[BetaMonetaryAmount]` Cumulative list cost of the session across all turns, priced at public list rates. - `output_tokens: Optional[int]` Total output tokens generated across all turns. format: int32 - `server_tool_use: Optional[BetaManagedAgentsServerToolUsage]` Cumulative server-executed tool usage across all turns. - `web_fetch_requests: Optional[int]` Number of server-executed web fetch requests. format: int32 - `web_search_requests: Optional[int]` Number of server-executed web search requests. format: int32 - `budget: Optional[BetaManagedAgentsBudgetLimit]` The session's configured budget at the snapshot time, or null when the session has no budget. - `class BetaManagedAgentsWorkflowRunCreatedEvent` A workflow run was created. A workflow run is background work that the session's agent starts. Emitted once per run, before the run's other `workflow_run.*` events. - `type: Literal["workflow_run.created"]` - `id: str` Unique identifier for this event. - `description: Optional[str]` Description that the agent gave the run, passed on as written, or `null` if it gave none. - `name: str` Name that the agent gave the run, passed on as written, or a name that the server assigned. - `phases: List[BetaManagedAgentsWorkflowRunPhase]` The phases that the run's plan declares, in the plan's order. Can be empty. - `id: str` Unique identifier for the phase. - `description: Optional[str]` Description that the agent gave the phase, passed on as written, or `null` if it gave none. - `name: str` Name that the agent gave the phase, passed on as written. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunStatusEndedEvent` A workflow run ended. Emitted once per run, as the last of the run's `workflow_run.*` events. - `type: Literal["workflow_run.status_ended"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `result: BetaManagedAgentsWorkflowRunResult` How the run ended. - `class BetaManagedAgentsWorkflowRunResultCompleted` The run's plan, a program that the agent wrote, finished. This does not say whether the work succeeded. - `type: Literal["completed"]` - `class BetaManagedAgentsWorkflowRunResultError` The run failed or reached its time limit. - `type: Literal["error"]` - `error: BetaManagedAgentsWorkflowRunError` Why the run did not finish. - `class BetaManagedAgentsTimeoutWorkflowRunError` The run reached its time limit. - `type: Literal["timeout_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsProgramWorkflowRunError` The plan, a program that the agent wrote, failed, or the server refused it. - `type: Literal["program_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsUnknownWorkflowRunError` A failure that has no type of its own. - `type: Literal["unknown_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsThreadLimitWorkflowRunError` The run exceeded the limit on the number of threads that a run can create. - `type: Literal["thread_limit_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsMaxWorkflowRunsWorkflowRunError` No run was created, because the session was at its limit of open workflow runs, which are runs that have not ended. Only `workflow_run.error` carries this type. - `type: Literal["max_workflow_runs_error"]` - `message: str` Short explanation written by the server. It never contains content from the run or its agents. - `class BetaManagedAgentsWorkflowRunResultStopped` The agent stopped the run. - `type: Literal["stopped"]` - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunPhaseStartedEvent` A workflow run's plan entered a phase. - `type: Literal["workflow_run.phase_started"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `workflow_run_phase_id: str` Identifier of the phase, as in `phases` on the run's `workflow_run.created` event. - `class BetaManagedAgentsWorkflowRunPhaseEndedEvent` A workflow run's plan left a phase, or the run's end closed it. Emitted once for every `workflow_run.phase_started` event, before the run's `workflow_run.status_ended` event. The event does not say whether the plan finished the phase's work, or why it left. - `type: Literal["workflow_run.phase_ended"]` - `id: str` Unique identifier for this event. - `phase_started_id: str` Identifier of the `workflow_run.phase_started` event that opened the phase. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `workflow_run_phase_id: str` Identifier of the phase, as in `phases` on the run's `workflow_run.created` event. - `class BetaManagedAgentsWorkflowRunStatusRunningEvent` A workflow run is running. Emitted when the run starts to execute, and each time it resumes after being idle. A run that starts idle emits `workflow_run.status_idle` first. - `type: Literal["workflow_run.status_running"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunStatusIdleEvent` A workflow run is idle. Emitted each time the run goes idle, whatever the cause. If the run ends while idle, no `workflow_run.status_running` comes between this event and its `workflow_run.status_ended`. - `type: Literal["workflow_run.status_idle"]` - `id: str` Unique identifier for this event. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: str` Identifier of the run. The same value is on all of the run's `workflow_run.*` events. - `class BetaManagedAgentsWorkflowRunErrorEvent` A workflow run met an error, or an error kept a run from being created. A run that ends with a `result.type` of `error` emits this event before its `workflow_run.status_ended`, with the same `error`. - `type: Literal["workflow_run.error"]` - `id: str` Unique identifier for this event. - `error: BetaManagedAgentsWorkflowRunError` Why the run did not finish, or was not created. - `processed_at: datetime` Timestamp when this event was processed. format: date-time - `workflow_run_id: Optional[str]` Identifier of the run that met the error, or `null` when the error kept a run from being created. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) for event in client.beta.sessions.threads.events.stream( thread_id="sthr_011CZkZVWa6oJjw1rgXZpnBt", session_id="sesn_011CZkZAtmR3yMPDzynEDxu7", ): print(event) ``` ##### Response (200) ```json { "id": "sevt_011CZkZGPp1iBcp4kaQSihUm", "content": [ { "text": "Where is my order #1234?", "type": "text" } ], "type": "user.message", "processed_at": "2026-03-15T10:00:00Z" } ``` ## Beta › Deployments ### Create Deployment `beta.deployments.create(**kwargs) -> BetaManagedAgentsDeployment` **POST** `/v1/deployments` Create Deployment #### Parameters - `agent: Agent` Agent to deploy. Accepts the `agent` ID string, which pins the latest version, or an `agent` object with both id and version specified. The agent must exist and not be archived. - `str` - `class BetaManagedAgentsAgentParams` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `type: Literal["agent"]` - `id: str` The `agent` ID. minLength: 1, maxLength: 128 - `version: Optional[int]` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. format: int32 - `environment_id: str` ID of the `environment` defining the container configuration for sessions created from this deployment. minLength: 1, maxLength: 128 - `initial_events: Iterable[BetaManagedAgentsDeploymentInitialEventParams]` Events to send to each session immediately after creation. At least 1, maximum 50. - `class BetaManagedAgentsUserMessageEventParams` Parameters for sending a user message to the session. - `type: Literal["user.message"]` - `content: Iterable[Content]` Array of content blocks for the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `class BetaManagedAgentsUserDefineOutcomeEventParams` Parameters for defining an outcome the agent should work toward. The agent begins work on receipt. - `type: Literal["user.define_outcome"]` - `description: str` What the agent should produce. This is the task specification. - `rubric: Rubric` How to grade the outcome. Text or file reference. - `class BetaManagedAgentsFileRubricParams` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubricParams` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. Maximum 262144 characters. maxLength: 262144 - `max_iterations: Optional[int]` Eval→revision cycles before giving up. Default 3, max 20. format: int32 - `class BetaManagedAgentsSystemMessageEventParams` Privileged context for the accompanying turn and all subsequent turns, appended to the session's system context as a `role: "system"` turn rather than replacing the top-level system prompt. At most one per request: it must be the final event and immediately follow the `user.message`, `user.tool_result`, or `user.custom_tool_result` it accompanies. Only supported on models that accept mid-conversation system messages. - `type: Literal["system.message"]` - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks to append. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `name: str` Human-readable name for the deployment. minLength: 1, maxLength: 256 - `budget: Optional[BetaManagedAgentsBudgetLimitParam]` Enforced spend ceiling stamped onto each session created from this deployment, copied at session-creation time. Omit to leave sessions uncapped. The deployment agent's model must have a public list price, or the request is rejected; a multiagent roster is re-validated in full when each fire copies the cap, which fails closed the same way. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `description: Optional[str]` Description of what the deployment does. maxLength: 2048 - `metadata: Optional[Dict[str, str]]` Arbitrary key-value metadata. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars. - `resources: Optional[Iterable[Resource]]` Resources (e.g. repositories, files) to mount into each session's container. Maximum 500. - `class BetaManagedAgentsGitHubRepositoryResourceParams` Mount a GitHub repository into the session's container. - `type: Literal["github_repository"]` - `url: str` Github URL of the repository minLength: 1, maxLength: 2048 - `authorization_token: Optional[str]` GitHub authorization token used to clone the repository. Required for private repositories; optional for public ones. minLength: 1, maxLength: 4096 - `checkout: Optional[Checkout]` Branch or commit to check out. Defaults to the repository's default branch. - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/workspace/`. minLength: 1, maxLength: 4096 - `class BetaManagedAgentsFileResourceParams` Mount a file uploaded via the Files API into the session. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1, maxLength: 128 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/mnt/session/uploads/`. minLength: 1, maxLength: 4096 - `class BetaManagedAgentsMemoryStoreResourceParam` Parameters for attaching a memory store to an agent session. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to read_write. read_only mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. maxLength: 4096 - `schedule: Optional[BetaManagedAgentsScheduleParams]` Optional recurring cron schedule. When present, the deployment fires automatically. Both expression and timezone are required when schedule is set. - `type: Literal["cron"]` - `expression: str` 5-field POSIX cron expression: minute hour day-of-month month day-of-week (e.g., "0 9 * * 1-5" for weekdays at 9am). Day-of-week is 0-7 where 0 and 7 both mean Sunday. Extended cron syntax - seconds or year fields, and the special characters L, W, #, and ? - is not supported, nor are predefined shortcuts (@daily). minLength: 1, maxLength: 256 - `timezone: str` Required. IANA timezone identifier (e.g., "America/Los_Angeles", "UTC"). Validated against the IANA timezone database. minLength: 1 - `vault_ids: Optional[Sequence[str]]` Vault IDs for stored credentials the agent can use during sessions created from this deployment. Maximum 50. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeployment` A deployment is a configured instance of an agent — it binds the agent to everything needed to run it autonomously: an environment, credentials, initial events, and an optional schedule. - `type: Literal["deployment"]` - `id: str` Unique identifier for this deployment. - `agent: BetaManagedAgentsAgentReference` Reference to the agent this deployment runs, resolved to a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `archived_at: Optional[datetime]` Time the deployment was archived. Null if not archived. format: date-time - `created_at: datetime` Time the deployment was created. format: date-time - `description: Optional[str]` Description of what the deployment does. - `environment_id: str` ID of the `environment` where sessions run. - `initial_events: List[BetaManagedAgentsDeploymentInitialEvent]` Events sent to each session immediately after creation. - `class BetaManagedAgentsDeploymentUserMessageEvent` A user message sent to the session. - `type: Literal["user.message"]` - `content: List[Content]` Array of content blocks for the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `class BetaManagedAgentsDeploymentUserDefineOutcomeEvent` An outcome the agent should work toward. The agent begins work on receipt. - `type: Literal["user.define_outcome"]` - `description: str` What the agent should produce. This is the task specification. - `rubric: Rubric` How to grade the outcome. Text or file reference. - `class BetaManagedAgentsFileRubric` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubric` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. - `max_iterations: Optional[int]` Eval→revision cycles before giving up. Default 3, max 20. format: int32 - `class BetaManagedAgentsDeploymentSystemMessageEvent` Privileged context for the accompanying turn and all subsequent turns, appended to the session's system context as a `role: "system"` turn rather than replacing the top-level system prompt. - `type: Literal["system.message"]` - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks to append. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `metadata: Dict[str, str]` Arbitrary key-value metadata. Maximum 16 pairs. - `name: str` Human-readable name. - `paused_reason: Optional[BetaManagedAgentsDeploymentPausedReason]` Why the deployment is `paused`. Non-null exactly when `status` is `paused`; null otherwise. - `class BetaManagedAgentsManualDeploymentPausedReason` The caller invoked the pause endpoint on the deployment. - `type: Literal["manual"]` - `class BetaManagedAgentsErrorDeploymentPausedReason` A scheduled fire recorded a failed run whose error auto-pauses the deployment. - `type: Literal["error"]` - `error: BetaManagedAgentsDeploymentPausedReasonError` The failed run's error. - `class BetaManagedAgentsEnvironmentArchivedDeploymentPausedReasonError` The deployment's environment was archived. - `type: Literal["environment_archived_error"]` - `class BetaManagedAgentsAgentArchivedDeploymentPausedReasonError` The deployment's agent was archived. - `type: Literal["agent_archived_error"]` - `class BetaManagedAgentsEnvironmentNotFoundDeploymentPausedReasonError` The deployment's environment no longer exists. - `type: Literal["environment_not_found_error"]` - `class BetaManagedAgentsVaultNotFoundDeploymentPausedReasonError` A vault referenced by the deployment no longer exists. - `type: Literal["vault_not_found_error"]` - `class BetaManagedAgentsFileNotFoundDeploymentPausedReasonError` A file resource referenced by the deployment no longer exists. - `type: Literal["file_not_found_error"]` - `class BetaManagedAgentsSessionResourceNotFoundDeploymentPausedReasonError` A referenced resource no longer exists and its kind was not reported. - `type: Literal["session_resource_not_found_error"]` - `class BetaManagedAgentsWorkspaceArchivedDeploymentPausedReasonError` The deployment's workspace was archived. - `type: Literal["workspace_archived_error"]` - `class BetaManagedAgentsOrganizationDisabledDeploymentPausedReasonError` The deployment's organization is disabled. - `type: Literal["organization_disabled_error"]` - `class BetaManagedAgentsMemoryStoreArchivedDeploymentPausedReasonError` A memory store referenced by the deployment is archived. - `type: Literal["memory_store_archived_error"]` - `class BetaManagedAgentsSkillNotFoundDeploymentPausedReasonError` A skill referenced by the deployment's agent no longer exists. - `type: Literal["skill_not_found_error"]` - `class BetaManagedAgentsVaultArchivedDeploymentPausedReasonError` A vault referenced by the deployment is archived. - `type: Literal["vault_archived_error"]` - `class BetaManagedAgentsUnknownDeploymentPausedReasonError` An unrecognized error auto-paused the deployment. A fallback variant; matches a run whose `error.type` is `unknown_error`. - `type: Literal["unknown_error"]` - `class BetaManagedAgentsSelfHostedResourcesUnsupportedDeploymentPausedReasonError` The deployment configures resources, but its environment is self-hosted and cannot mount them. - `type: Literal["self_hosted_resources_unsupported_error"]` - `class BetaManagedAgentsMCPEgressBlockedDeploymentPausedReasonError` An MCP server host used by the deployment's agent is blocked by the environment's network policy. - `type: Literal["mcp_egress_blocked_error"]` - `resources: List[BetaManagedAgentsSessionResourceConfig]` Resources attached to sessions created from this deployment. Echoes the input minus write-only credentials. - `class BetaManagedAgentsGitHubRepositoryResourceConfig` A GitHub repository mounted into each session's container. The authorization token is write-only and never returned. - `type: Literal["github_repository"]` - `url: str` Github URL of the repository - `checkout: Optional[Checkout]` Branch or commit to check out. Defaults to the repository's default branch. - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/workspace/`. - `class BetaManagedAgentsFileResourceConfig` A file mounted into each session's container. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. - `mount_path: Optional[str]` Mount path in the container. Defaults to `/mnt/session/uploads/`. - `class BetaManagedAgentsMemoryStoreResourceConfig` A memory store attached to each session created from this deployment. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. - `schedule: Optional[BetaManagedAgentsSchedule]` Recurring cron schedule. Presence enables scheduled execution; null means manual-only. Includes computed timestamps (next fire times, last run) on the cron variant. - `type: Literal["cron"]` - `expression: str` 5-field POSIX cron expression: minute hour day-of-month month day-of-week (e.g., "0 9 * * 1-5" for weekdays at 9am). Day-of-week is 0-7 where 0 and 7 both mean Sunday. Extended cron syntax - seconds or year fields, and the special characters L, W, #, and ? - is not supported, nor are predefined shortcuts (@daily). minLength: 1, maxLength: 256 - `timezone: str` IANA timezone identifier (e.g., "America/Los_Angeles", "UTC"). minLength: 1 - `last_run_at: Optional[datetime]` Time the most recent scheduled run actually started. Null until one completes; preserved after the deployment is archived. Manual runs do not update this. format: date-time - `upcoming_runs_at: Optional[List[datetime]]` Up to 5 timestamps of upcoming cron occurrences. Non-empty for active and paused deployments (reflects what the schedule would do if unpaused); empty once the deployment is archived (`archived_at` set). Each fire is offset by a small per-schedule jitter, so a run will actually start at or shortly after its listed time. - `status: BetaManagedAgentsDeploymentStatus` Computed status of the deployment: `active` or `paused`. Archived deployments report `active` with `archived_at` set. - `"active"` The deployment is active and can run sessions. Archived deployments also report this status; check `archived_at` to distinguish them. - `"paused"` The deployment is paused. Autonomous triggers are suppressed; manual runs are still permitted. - `updated_at: datetime` Time the deployment was last updated. format: date-time - `vault_ids: List[str]` Vault IDs supplying stored credentials for sessions created from this deployment. - `budget: Optional[BetaManagedAgentsBudgetLimit]` Spend ceiling stamped onto each session created from this deployment. Absent when no budget is set. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deployment = client.beta.deployments.create( agent="string", environment_id="x", initial_events=[ { "content": [ { "text": "Where is my order #1234?", "type": "text", } ], "type": "user.message", } ], name="x", ) print(beta_managed_agents_deployment.id) ``` ##### Response (200) ```json { "id": "depl_011CZkZcDH3vPqd7xnEfwTai", "agent": { "id": "agent_011CZkYpogX7uDKUyvBTophP", "type": "agent", "version": 1 }, "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "Compiles yesterday's orders into a report every weekday morning.", "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "initial_events": [ { "content": [ { "text": "Compile yesterday's orders into report.md.", "type": "text" } ], "type": "user.message" } ], "metadata": {}, "name": "Daily order report", "paused_reason": { "type": "manual" }, "resources": [ { "type": "github_repository", "url": "url", "checkout": { "name": "main", "type": "branch" }, "mount_path": "mount_path" } ], "schedule": { "expression": "0 9 * * 1-5", "timezone": "America/Los_Angeles", "type": "cron", "last_run_at": "2026-03-16T16:00:09Z", "upcoming_runs_at": [ "2026-03-17T16:00:00Z", "2026-03-18T16:00:00Z" ] }, "status": "active", "type": "deployment", "updated_at": "2026-03-15T10:00:00Z", "vault_ids": [ "vlt_011CZkZDLs7fYzm1hXNPeRjv" ], "budget": { "max_list_cost": { "amount": "2500", "currency": "USD" }, "type": "limit" } } ``` ### List Deployments `beta.deployments.list(**kwargs) -> SyncPageCursor[BetaManagedAgentsDeployment]` **GET** `/v1/deployments` List Deployments #### Parameters - `agent_id: Optional[str]` (query parameter) Filter by agent ID. - `created_at_gte: Optional[Union[str, datetime]]` (query parameter) Return deployments created at or after this time (inclusive). format: date-time - `created_at_lte: Optional[Union[str, datetime]]` (query parameter) Return deployments created at or before this time (inclusive). format: date-time - `include_archived: Optional[bool]` (query parameter) When true, includes archived deployments. Default: false (exclude archived). - `limit: Optional[int]` (query parameter) Maximum results per page. Default 20, maximum 100. format: int32 - `page: Optional[str]` (query parameter) Opaque pagination cursor. - `status: Optional[BetaManagedAgentsDeploymentStatus]` (query parameter) Filter by status: `active` or `paused`. Omit for both. To include archived deployments, use `include_archived` instead; the two cannot be combined. - `"active"` The deployment is active and can run sessions. Archived deployments also report this status; check `archived_at` to distinguish them. - `"paused"` The deployment is paused. Autonomous triggers are suppressed; manual runs are still permitted. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeployment` A deployment is a configured instance of an agent — it binds the agent to everything needed to run it autonomously: an environment, credentials, initial events, and an optional schedule. - `type: Literal["deployment"]` - `id: str` Unique identifier for this deployment. - `agent: BetaManagedAgentsAgentReference` Reference to the agent this deployment runs, resolved to a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `archived_at: Optional[datetime]` Time the deployment was archived. Null if not archived. format: date-time - `created_at: datetime` Time the deployment was created. format: date-time - `description: Optional[str]` Description of what the deployment does. - `environment_id: str` ID of the `environment` where sessions run. - `initial_events: List[BetaManagedAgentsDeploymentInitialEvent]` Events sent to each session immediately after creation. - `class BetaManagedAgentsDeploymentUserMessageEvent` A user message sent to the session. - `type: Literal["user.message"]` - `content: List[Content]` Array of content blocks for the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `class BetaManagedAgentsDeploymentUserDefineOutcomeEvent` An outcome the agent should work toward. The agent begins work on receipt. - `type: Literal["user.define_outcome"]` - `description: str` What the agent should produce. This is the task specification. - `rubric: Rubric` How to grade the outcome. Text or file reference. - `class BetaManagedAgentsFileRubric` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubric` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. - `max_iterations: Optional[int]` Eval→revision cycles before giving up. Default 3, max 20. format: int32 - `class BetaManagedAgentsDeploymentSystemMessageEvent` Privileged context for the accompanying turn and all subsequent turns, appended to the session's system context as a `role: "system"` turn rather than replacing the top-level system prompt. - `type: Literal["system.message"]` - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks to append. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `metadata: Dict[str, str]` Arbitrary key-value metadata. Maximum 16 pairs. - `name: str` Human-readable name. - `paused_reason: Optional[BetaManagedAgentsDeploymentPausedReason]` Why the deployment is `paused`. Non-null exactly when `status` is `paused`; null otherwise. - `class BetaManagedAgentsManualDeploymentPausedReason` The caller invoked the pause endpoint on the deployment. - `type: Literal["manual"]` - `class BetaManagedAgentsErrorDeploymentPausedReason` A scheduled fire recorded a failed run whose error auto-pauses the deployment. - `type: Literal["error"]` - `error: BetaManagedAgentsDeploymentPausedReasonError` The failed run's error. - `class BetaManagedAgentsEnvironmentArchivedDeploymentPausedReasonError` The deployment's environment was archived. - `type: Literal["environment_archived_error"]` - `class BetaManagedAgentsAgentArchivedDeploymentPausedReasonError` The deployment's agent was archived. - `type: Literal["agent_archived_error"]` - `class BetaManagedAgentsEnvironmentNotFoundDeploymentPausedReasonError` The deployment's environment no longer exists. - `type: Literal["environment_not_found_error"]` - `class BetaManagedAgentsVaultNotFoundDeploymentPausedReasonError` A vault referenced by the deployment no longer exists. - `type: Literal["vault_not_found_error"]` - `class BetaManagedAgentsFileNotFoundDeploymentPausedReasonError` A file resource referenced by the deployment no longer exists. - `type: Literal["file_not_found_error"]` - `class BetaManagedAgentsSessionResourceNotFoundDeploymentPausedReasonError` A referenced resource no longer exists and its kind was not reported. - `type: Literal["session_resource_not_found_error"]` - `class BetaManagedAgentsWorkspaceArchivedDeploymentPausedReasonError` The deployment's workspace was archived. - `type: Literal["workspace_archived_error"]` - `class BetaManagedAgentsOrganizationDisabledDeploymentPausedReasonError` The deployment's organization is disabled. - `type: Literal["organization_disabled_error"]` - `class BetaManagedAgentsMemoryStoreArchivedDeploymentPausedReasonError` A memory store referenced by the deployment is archived. - `type: Literal["memory_store_archived_error"]` - `class BetaManagedAgentsSkillNotFoundDeploymentPausedReasonError` A skill referenced by the deployment's agent no longer exists. - `type: Literal["skill_not_found_error"]` - `class BetaManagedAgentsVaultArchivedDeploymentPausedReasonError` A vault referenced by the deployment is archived. - `type: Literal["vault_archived_error"]` - `class BetaManagedAgentsUnknownDeploymentPausedReasonError` An unrecognized error auto-paused the deployment. A fallback variant; matches a run whose `error.type` is `unknown_error`. - `type: Literal["unknown_error"]` - `class BetaManagedAgentsSelfHostedResourcesUnsupportedDeploymentPausedReasonError` The deployment configures resources, but its environment is self-hosted and cannot mount them. - `type: Literal["self_hosted_resources_unsupported_error"]` - `class BetaManagedAgentsMCPEgressBlockedDeploymentPausedReasonError` An MCP server host used by the deployment's agent is blocked by the environment's network policy. - `type: Literal["mcp_egress_blocked_error"]` - `resources: List[BetaManagedAgentsSessionResourceConfig]` Resources attached to sessions created from this deployment. Echoes the input minus write-only credentials. - `class BetaManagedAgentsGitHubRepositoryResourceConfig` A GitHub repository mounted into each session's container. The authorization token is write-only and never returned. - `type: Literal["github_repository"]` - `url: str` Github URL of the repository - `checkout: Optional[Checkout]` Branch or commit to check out. Defaults to the repository's default branch. - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/workspace/`. - `class BetaManagedAgentsFileResourceConfig` A file mounted into each session's container. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. - `mount_path: Optional[str]` Mount path in the container. Defaults to `/mnt/session/uploads/`. - `class BetaManagedAgentsMemoryStoreResourceConfig` A memory store attached to each session created from this deployment. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. - `schedule: Optional[BetaManagedAgentsSchedule]` Recurring cron schedule. Presence enables scheduled execution; null means manual-only. Includes computed timestamps (next fire times, last run) on the cron variant. - `type: Literal["cron"]` - `expression: str` 5-field POSIX cron expression: minute hour day-of-month month day-of-week (e.g., "0 9 * * 1-5" for weekdays at 9am). Day-of-week is 0-7 where 0 and 7 both mean Sunday. Extended cron syntax - seconds or year fields, and the special characters L, W, #, and ? - is not supported, nor are predefined shortcuts (@daily). minLength: 1, maxLength: 256 - `timezone: str` IANA timezone identifier (e.g., "America/Los_Angeles", "UTC"). minLength: 1 - `last_run_at: Optional[datetime]` Time the most recent scheduled run actually started. Null until one completes; preserved after the deployment is archived. Manual runs do not update this. format: date-time - `upcoming_runs_at: Optional[List[datetime]]` Up to 5 timestamps of upcoming cron occurrences. Non-empty for active and paused deployments (reflects what the schedule would do if unpaused); empty once the deployment is archived (`archived_at` set). Each fire is offset by a small per-schedule jitter, so a run will actually start at or shortly after its listed time. - `status: BetaManagedAgentsDeploymentStatus` Computed status of the deployment: `active` or `paused`. Archived deployments report `active` with `archived_at` set. - `"active"` The deployment is active and can run sessions. Archived deployments also report this status; check `archived_at` to distinguish them. - `"paused"` The deployment is paused. Autonomous triggers are suppressed; manual runs are still permitted. - `updated_at: datetime` Time the deployment was last updated. format: date-time - `vault_ids: List[str]` Vault IDs supplying stored credentials for sessions created from this deployment. - `budget: Optional[BetaManagedAgentsBudgetLimit]` Spend ceiling stamped onto each session created from this deployment. Absent when no budget is set. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.deployments.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "depl_011CZkZcDH3vPqd7xnEfwTai", "agent": { "id": "agent_011CZkYpogX7uDKUyvBTophP", "type": "agent", "version": 1 }, "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "Compiles yesterday's orders into a report every weekday morning.", "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "initial_events": [ { "content": [ { "text": "Compile yesterday's orders into report.md.", "type": "text" } ], "type": "user.message" } ], "metadata": {}, "name": "Daily order report", "paused_reason": { "type": "manual" }, "resources": [ { "type": "github_repository", "url": "url", "checkout": { "name": "main", "type": "branch" }, "mount_path": "mount_path" } ], "schedule": { "expression": "0 9 * * 1-5", "timezone": "America/Los_Angeles", "type": "cron", "last_run_at": "2026-03-16T16:00:09Z", "upcoming_runs_at": [ "2026-03-17T16:00:00Z", "2026-03-18T16:00:00Z" ] }, "status": "active", "type": "deployment", "updated_at": "2026-03-15T10:00:00Z", "vault_ids": [ "vlt_011CZkZDLs7fYzm1hXNPeRjv" ], "budget": { "max_list_cost": { "amount": "2500", "currency": "USD" }, "type": "limit" } } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=" } ``` ### Get Deployment `beta.deployments.retrieve(deployment_id, **kwargs) -> BetaManagedAgentsDeployment` **GET** `/v1/deployments/{deployment_id}` Get Deployment #### Parameters - `deployment_id: str` (path parameter) Unique identifier of the deployment. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeployment` A deployment is a configured instance of an agent — it binds the agent to everything needed to run it autonomously: an environment, credentials, initial events, and an optional schedule. - `type: Literal["deployment"]` - `id: str` Unique identifier for this deployment. - `agent: BetaManagedAgentsAgentReference` Reference to the agent this deployment runs, resolved to a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `archived_at: Optional[datetime]` Time the deployment was archived. Null if not archived. format: date-time - `created_at: datetime` Time the deployment was created. format: date-time - `description: Optional[str]` Description of what the deployment does. - `environment_id: str` ID of the `environment` where sessions run. - `initial_events: List[BetaManagedAgentsDeploymentInitialEvent]` Events sent to each session immediately after creation. - `class BetaManagedAgentsDeploymentUserMessageEvent` A user message sent to the session. - `type: Literal["user.message"]` - `content: List[Content]` Array of content blocks for the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `class BetaManagedAgentsDeploymentUserDefineOutcomeEvent` An outcome the agent should work toward. The agent begins work on receipt. - `type: Literal["user.define_outcome"]` - `description: str` What the agent should produce. This is the task specification. - `rubric: Rubric` How to grade the outcome. Text or file reference. - `class BetaManagedAgentsFileRubric` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubric` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. - `max_iterations: Optional[int]` Eval→revision cycles before giving up. Default 3, max 20. format: int32 - `class BetaManagedAgentsDeploymentSystemMessageEvent` Privileged context for the accompanying turn and all subsequent turns, appended to the session's system context as a `role: "system"` turn rather than replacing the top-level system prompt. - `type: Literal["system.message"]` - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks to append. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `metadata: Dict[str, str]` Arbitrary key-value metadata. Maximum 16 pairs. - `name: str` Human-readable name. - `paused_reason: Optional[BetaManagedAgentsDeploymentPausedReason]` Why the deployment is `paused`. Non-null exactly when `status` is `paused`; null otherwise. - `class BetaManagedAgentsManualDeploymentPausedReason` The caller invoked the pause endpoint on the deployment. - `type: Literal["manual"]` - `class BetaManagedAgentsErrorDeploymentPausedReason` A scheduled fire recorded a failed run whose error auto-pauses the deployment. - `type: Literal["error"]` - `error: BetaManagedAgentsDeploymentPausedReasonError` The failed run's error. - `class BetaManagedAgentsEnvironmentArchivedDeploymentPausedReasonError` The deployment's environment was archived. - `type: Literal["environment_archived_error"]` - `class BetaManagedAgentsAgentArchivedDeploymentPausedReasonError` The deployment's agent was archived. - `type: Literal["agent_archived_error"]` - `class BetaManagedAgentsEnvironmentNotFoundDeploymentPausedReasonError` The deployment's environment no longer exists. - `type: Literal["environment_not_found_error"]` - `class BetaManagedAgentsVaultNotFoundDeploymentPausedReasonError` A vault referenced by the deployment no longer exists. - `type: Literal["vault_not_found_error"]` - `class BetaManagedAgentsFileNotFoundDeploymentPausedReasonError` A file resource referenced by the deployment no longer exists. - `type: Literal["file_not_found_error"]` - `class BetaManagedAgentsSessionResourceNotFoundDeploymentPausedReasonError` A referenced resource no longer exists and its kind was not reported. - `type: Literal["session_resource_not_found_error"]` - `class BetaManagedAgentsWorkspaceArchivedDeploymentPausedReasonError` The deployment's workspace was archived. - `type: Literal["workspace_archived_error"]` - `class BetaManagedAgentsOrganizationDisabledDeploymentPausedReasonError` The deployment's organization is disabled. - `type: Literal["organization_disabled_error"]` - `class BetaManagedAgentsMemoryStoreArchivedDeploymentPausedReasonError` A memory store referenced by the deployment is archived. - `type: Literal["memory_store_archived_error"]` - `class BetaManagedAgentsSkillNotFoundDeploymentPausedReasonError` A skill referenced by the deployment's agent no longer exists. - `type: Literal["skill_not_found_error"]` - `class BetaManagedAgentsVaultArchivedDeploymentPausedReasonError` A vault referenced by the deployment is archived. - `type: Literal["vault_archived_error"]` - `class BetaManagedAgentsUnknownDeploymentPausedReasonError` An unrecognized error auto-paused the deployment. A fallback variant; matches a run whose `error.type` is `unknown_error`. - `type: Literal["unknown_error"]` - `class BetaManagedAgentsSelfHostedResourcesUnsupportedDeploymentPausedReasonError` The deployment configures resources, but its environment is self-hosted and cannot mount them. - `type: Literal["self_hosted_resources_unsupported_error"]` - `class BetaManagedAgentsMCPEgressBlockedDeploymentPausedReasonError` An MCP server host used by the deployment's agent is blocked by the environment's network policy. - `type: Literal["mcp_egress_blocked_error"]` - `resources: List[BetaManagedAgentsSessionResourceConfig]` Resources attached to sessions created from this deployment. Echoes the input minus write-only credentials. - `class BetaManagedAgentsGitHubRepositoryResourceConfig` A GitHub repository mounted into each session's container. The authorization token is write-only and never returned. - `type: Literal["github_repository"]` - `url: str` Github URL of the repository - `checkout: Optional[Checkout]` Branch or commit to check out. Defaults to the repository's default branch. - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/workspace/`. - `class BetaManagedAgentsFileResourceConfig` A file mounted into each session's container. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. - `mount_path: Optional[str]` Mount path in the container. Defaults to `/mnt/session/uploads/`. - `class BetaManagedAgentsMemoryStoreResourceConfig` A memory store attached to each session created from this deployment. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. - `schedule: Optional[BetaManagedAgentsSchedule]` Recurring cron schedule. Presence enables scheduled execution; null means manual-only. Includes computed timestamps (next fire times, last run) on the cron variant. - `type: Literal["cron"]` - `expression: str` 5-field POSIX cron expression: minute hour day-of-month month day-of-week (e.g., "0 9 * * 1-5" for weekdays at 9am). Day-of-week is 0-7 where 0 and 7 both mean Sunday. Extended cron syntax - seconds or year fields, and the special characters L, W, #, and ? - is not supported, nor are predefined shortcuts (@daily). minLength: 1, maxLength: 256 - `timezone: str` IANA timezone identifier (e.g., "America/Los_Angeles", "UTC"). minLength: 1 - `last_run_at: Optional[datetime]` Time the most recent scheduled run actually started. Null until one completes; preserved after the deployment is archived. Manual runs do not update this. format: date-time - `upcoming_runs_at: Optional[List[datetime]]` Up to 5 timestamps of upcoming cron occurrences. Non-empty for active and paused deployments (reflects what the schedule would do if unpaused); empty once the deployment is archived (`archived_at` set). Each fire is offset by a small per-schedule jitter, so a run will actually start at or shortly after its listed time. - `status: BetaManagedAgentsDeploymentStatus` Computed status of the deployment: `active` or `paused`. Archived deployments report `active` with `archived_at` set. - `"active"` The deployment is active and can run sessions. Archived deployments also report this status; check `archived_at` to distinguish them. - `"paused"` The deployment is paused. Autonomous triggers are suppressed; manual runs are still permitted. - `updated_at: datetime` Time the deployment was last updated. format: date-time - `vault_ids: List[str]` Vault IDs supplying stored credentials for sessions created from this deployment. - `budget: Optional[BetaManagedAgentsBudgetLimit]` Spend ceiling stamped onto each session created from this deployment. Absent when no budget is set. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deployment = client.beta.deployments.retrieve( deployment_id="depl_011CZkZcDH3vPqd7xnEfwTai", ) print(beta_managed_agents_deployment.id) ``` ##### Response (200) ```json { "id": "depl_011CZkZcDH3vPqd7xnEfwTai", "agent": { "id": "agent_011CZkYpogX7uDKUyvBTophP", "type": "agent", "version": 1 }, "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "Compiles yesterday's orders into a report every weekday morning.", "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "initial_events": [ { "content": [ { "text": "Compile yesterday's orders into report.md.", "type": "text" } ], "type": "user.message" } ], "metadata": {}, "name": "Daily order report", "paused_reason": { "type": "manual" }, "resources": [ { "type": "github_repository", "url": "url", "checkout": { "name": "main", "type": "branch" }, "mount_path": "mount_path" } ], "schedule": { "expression": "0 9 * * 1-5", "timezone": "America/Los_Angeles", "type": "cron", "last_run_at": "2026-03-16T16:00:09Z", "upcoming_runs_at": [ "2026-03-17T16:00:00Z", "2026-03-18T16:00:00Z" ] }, "status": "active", "type": "deployment", "updated_at": "2026-03-15T10:00:00Z", "vault_ids": [ "vlt_011CZkZDLs7fYzm1hXNPeRjv" ], "budget": { "max_list_cost": { "amount": "2500", "currency": "USD" }, "type": "limit" } } ``` ### Update Deployment `beta.deployments.update(deployment_id, **kwargs) -> BetaManagedAgentsDeployment` **POST** `/v1/deployments/{deployment_id}` Update Deployment #### Parameters - `deployment_id: str` (path parameter) Unique identifier of the deployment to update. - `agent: Optional[Agent]` Agent to deploy. Accepts the `agent` ID string, which re-pins to the latest version, or an `agent` object with both id and version specified. Omit to preserve. Cannot be cleared. - `str` - `class BetaManagedAgentsAgentParams` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version - `type: Literal["agent"]` - `id: str` The `agent` ID. minLength: 1, maxLength: 128 - `version: Optional[int]` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. format: int32 - `budget: Optional[BetaManagedAgentsBudgetLimitParam]` Spend ceiling for future sessions. Full replacement. Omit to preserve; send null to clear (sessions created afterwards are uncapped). The deployment agent's model must have a public list price, or the request is rejected; a multiagent roster is re-validated in full when each fire copies the cap, which fails closed the same way. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. - `description: Optional[str]` Description. Omit to preserve; send empty string or null to clear. maxLength: 2048 - `environment_id: Optional[str]` ID of the `environment` where sessions run. Omit to preserve. Cannot be cleared. maxLength: 128 - `initial_events: Optional[Iterable[BetaManagedAgentsDeploymentInitialEventParams]]` Initial events. Full replacement. Omit to preserve. Cannot be cleared. At least 1, maximum 50. - `class BetaManagedAgentsUserMessageEventParams` Parameters for sending a user message to the session. - `type: Literal["user.message"]` - `content: Iterable[Content]` Array of content blocks for the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `class BetaManagedAgentsUserDefineOutcomeEventParams` Parameters for defining an outcome the agent should work toward. The agent begins work on receipt. - `type: Literal["user.define_outcome"]` - `description: str` What the agent should produce. This is the task specification. - `rubric: Rubric` How to grade the outcome. Text or file reference. - `class BetaManagedAgentsFileRubricParams` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubricParams` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. Maximum 262144 characters. maxLength: 262144 - `max_iterations: Optional[int]` Eval→revision cycles before giving up. Default 3, max 20. format: int32 - `class BetaManagedAgentsSystemMessageEventParams` Privileged context for the accompanying turn and all subsequent turns, appended to the session's system context as a `role: "system"` turn rather than replacing the top-level system prompt. At most one per request: it must be the final event and immediately follow the `user.message`, `user.tool_result`, or `user.custom_tool_result` it accompanies. Only supported on models that accept mid-conversation system messages. - `type: Literal["system.message"]` - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks to append. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `metadata: Optional[Dict[str, Optional[str]]]` Metadata patch. Set a key to a string to upsert it, or to null to delete it. Omit the field to preserve. The stored bag is limited to 16 keys (up to 64 chars each) with values up to 512 chars. - `name: Optional[str]` Human-readable name. Must be non-empty. Omit to preserve. Cannot be cleared. maxLength: 256 - `resources: Optional[Iterable[Resource]]` Session resources. Full replacement. Omit to preserve; send empty array or null to clear. Maximum 500. - `class BetaManagedAgentsGitHubRepositoryResourceParams` Mount a GitHub repository into the session's container. - `type: Literal["github_repository"]` - `url: str` Github URL of the repository minLength: 1, maxLength: 2048 - `authorization_token: Optional[str]` GitHub authorization token used to clone the repository. Required for private repositories; optional for public ones. minLength: 1, maxLength: 4096 - `checkout: Optional[Checkout]` Branch or commit to check out. Defaults to the repository's default branch. - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/workspace/`. minLength: 1, maxLength: 4096 - `class BetaManagedAgentsFileResourceParams` Mount a file uploaded via the Files API into the session. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1, maxLength: 128 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/mnt/session/uploads/`. minLength: 1, maxLength: 4096 - `class BetaManagedAgentsMemoryStoreResourceParam` Parameters for attaching a memory store to an agent session. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to read_write. read_only mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. maxLength: 4096 - `schedule: Optional[BetaManagedAgentsScheduleParams]` Cron schedule. Full replacement. Omit to preserve; send null to clear (revert to manual-only). - `type: Literal["cron"]` - `expression: str` 5-field POSIX cron expression: minute hour day-of-month month day-of-week (e.g., "0 9 * * 1-5" for weekdays at 9am). Day-of-week is 0-7 where 0 and 7 both mean Sunday. Extended cron syntax - seconds or year fields, and the special characters L, W, #, and ? - is not supported, nor are predefined shortcuts (@daily). minLength: 1, maxLength: 256 - `timezone: str` Required. IANA timezone identifier (e.g., "America/Los_Angeles", "UTC"). Validated against the IANA timezone database. minLength: 1 - `vault_ids: Optional[Sequence[str]]` Vault IDs. Full replacement. Omit to preserve; send empty array or null to clear. Maximum 50. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeployment` A deployment is a configured instance of an agent — it binds the agent to everything needed to run it autonomously: an environment, credentials, initial events, and an optional schedule. - `type: Literal["deployment"]` - `id: str` Unique identifier for this deployment. - `agent: BetaManagedAgentsAgentReference` Reference to the agent this deployment runs, resolved to a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `archived_at: Optional[datetime]` Time the deployment was archived. Null if not archived. format: date-time - `created_at: datetime` Time the deployment was created. format: date-time - `description: Optional[str]` Description of what the deployment does. - `environment_id: str` ID of the `environment` where sessions run. - `initial_events: List[BetaManagedAgentsDeploymentInitialEvent]` Events sent to each session immediately after creation. - `class BetaManagedAgentsDeploymentUserMessageEvent` A user message sent to the session. - `type: Literal["user.message"]` - `content: List[Content]` Array of content blocks for the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `class BetaManagedAgentsDeploymentUserDefineOutcomeEvent` An outcome the agent should work toward. The agent begins work on receipt. - `type: Literal["user.define_outcome"]` - `description: str` What the agent should produce. This is the task specification. - `rubric: Rubric` How to grade the outcome. Text or file reference. - `class BetaManagedAgentsFileRubric` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubric` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. - `max_iterations: Optional[int]` Eval→revision cycles before giving up. Default 3, max 20. format: int32 - `class BetaManagedAgentsDeploymentSystemMessageEvent` Privileged context for the accompanying turn and all subsequent turns, appended to the session's system context as a `role: "system"` turn rather than replacing the top-level system prompt. - `type: Literal["system.message"]` - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks to append. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `metadata: Dict[str, str]` Arbitrary key-value metadata. Maximum 16 pairs. - `name: str` Human-readable name. - `paused_reason: Optional[BetaManagedAgentsDeploymentPausedReason]` Why the deployment is `paused`. Non-null exactly when `status` is `paused`; null otherwise. - `class BetaManagedAgentsManualDeploymentPausedReason` The caller invoked the pause endpoint on the deployment. - `type: Literal["manual"]` - `class BetaManagedAgentsErrorDeploymentPausedReason` A scheduled fire recorded a failed run whose error auto-pauses the deployment. - `type: Literal["error"]` - `error: BetaManagedAgentsDeploymentPausedReasonError` The failed run's error. - `class BetaManagedAgentsEnvironmentArchivedDeploymentPausedReasonError` The deployment's environment was archived. - `type: Literal["environment_archived_error"]` - `class BetaManagedAgentsAgentArchivedDeploymentPausedReasonError` The deployment's agent was archived. - `type: Literal["agent_archived_error"]` - `class BetaManagedAgentsEnvironmentNotFoundDeploymentPausedReasonError` The deployment's environment no longer exists. - `type: Literal["environment_not_found_error"]` - `class BetaManagedAgentsVaultNotFoundDeploymentPausedReasonError` A vault referenced by the deployment no longer exists. - `type: Literal["vault_not_found_error"]` - `class BetaManagedAgentsFileNotFoundDeploymentPausedReasonError` A file resource referenced by the deployment no longer exists. - `type: Literal["file_not_found_error"]` - `class BetaManagedAgentsSessionResourceNotFoundDeploymentPausedReasonError` A referenced resource no longer exists and its kind was not reported. - `type: Literal["session_resource_not_found_error"]` - `class BetaManagedAgentsWorkspaceArchivedDeploymentPausedReasonError` The deployment's workspace was archived. - `type: Literal["workspace_archived_error"]` - `class BetaManagedAgentsOrganizationDisabledDeploymentPausedReasonError` The deployment's organization is disabled. - `type: Literal["organization_disabled_error"]` - `class BetaManagedAgentsMemoryStoreArchivedDeploymentPausedReasonError` A memory store referenced by the deployment is archived. - `type: Literal["memory_store_archived_error"]` - `class BetaManagedAgentsSkillNotFoundDeploymentPausedReasonError` A skill referenced by the deployment's agent no longer exists. - `type: Literal["skill_not_found_error"]` - `class BetaManagedAgentsVaultArchivedDeploymentPausedReasonError` A vault referenced by the deployment is archived. - `type: Literal["vault_archived_error"]` - `class BetaManagedAgentsUnknownDeploymentPausedReasonError` An unrecognized error auto-paused the deployment. A fallback variant; matches a run whose `error.type` is `unknown_error`. - `type: Literal["unknown_error"]` - `class BetaManagedAgentsSelfHostedResourcesUnsupportedDeploymentPausedReasonError` The deployment configures resources, but its environment is self-hosted and cannot mount them. - `type: Literal["self_hosted_resources_unsupported_error"]` - `class BetaManagedAgentsMCPEgressBlockedDeploymentPausedReasonError` An MCP server host used by the deployment's agent is blocked by the environment's network policy. - `type: Literal["mcp_egress_blocked_error"]` - `resources: List[BetaManagedAgentsSessionResourceConfig]` Resources attached to sessions created from this deployment. Echoes the input minus write-only credentials. - `class BetaManagedAgentsGitHubRepositoryResourceConfig` A GitHub repository mounted into each session's container. The authorization token is write-only and never returned. - `type: Literal["github_repository"]` - `url: str` Github URL of the repository - `checkout: Optional[Checkout]` Branch or commit to check out. Defaults to the repository's default branch. - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/workspace/`. - `class BetaManagedAgentsFileResourceConfig` A file mounted into each session's container. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. - `mount_path: Optional[str]` Mount path in the container. Defaults to `/mnt/session/uploads/`. - `class BetaManagedAgentsMemoryStoreResourceConfig` A memory store attached to each session created from this deployment. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. - `schedule: Optional[BetaManagedAgentsSchedule]` Recurring cron schedule. Presence enables scheduled execution; null means manual-only. Includes computed timestamps (next fire times, last run) on the cron variant. - `type: Literal["cron"]` - `expression: str` 5-field POSIX cron expression: minute hour day-of-month month day-of-week (e.g., "0 9 * * 1-5" for weekdays at 9am). Day-of-week is 0-7 where 0 and 7 both mean Sunday. Extended cron syntax - seconds or year fields, and the special characters L, W, #, and ? - is not supported, nor are predefined shortcuts (@daily). minLength: 1, maxLength: 256 - `timezone: str` IANA timezone identifier (e.g., "America/Los_Angeles", "UTC"). minLength: 1 - `last_run_at: Optional[datetime]` Time the most recent scheduled run actually started. Null until one completes; preserved after the deployment is archived. Manual runs do not update this. format: date-time - `upcoming_runs_at: Optional[List[datetime]]` Up to 5 timestamps of upcoming cron occurrences. Non-empty for active and paused deployments (reflects what the schedule would do if unpaused); empty once the deployment is archived (`archived_at` set). Each fire is offset by a small per-schedule jitter, so a run will actually start at or shortly after its listed time. - `status: BetaManagedAgentsDeploymentStatus` Computed status of the deployment: `active` or `paused`. Archived deployments report `active` with `archived_at` set. - `"active"` The deployment is active and can run sessions. Archived deployments also report this status; check `archived_at` to distinguish them. - `"paused"` The deployment is paused. Autonomous triggers are suppressed; manual runs are still permitted. - `updated_at: datetime` Time the deployment was last updated. format: date-time - `vault_ids: List[str]` Vault IDs supplying stored credentials for sessions created from this deployment. - `budget: Optional[BetaManagedAgentsBudgetLimit]` Spend ceiling stamped onto each session created from this deployment. Absent when no budget is set. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deployment = client.beta.deployments.update( deployment_id="depl_011CZkZcDH3vPqd7xnEfwTai", ) print(beta_managed_agents_deployment.id) ``` ##### Response (200) ```json { "id": "depl_011CZkZcDH3vPqd7xnEfwTai", "agent": { "id": "agent_011CZkYpogX7uDKUyvBTophP", "type": "agent", "version": 1 }, "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "Compiles yesterday's orders into a report every weekday morning.", "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "initial_events": [ { "content": [ { "text": "Compile yesterday's orders into report.md.", "type": "text" } ], "type": "user.message" } ], "metadata": {}, "name": "Daily order report", "paused_reason": { "type": "manual" }, "resources": [ { "type": "github_repository", "url": "url", "checkout": { "name": "main", "type": "branch" }, "mount_path": "mount_path" } ], "schedule": { "expression": "0 9 * * 1-5", "timezone": "America/Los_Angeles", "type": "cron", "last_run_at": "2026-03-16T16:00:09Z", "upcoming_runs_at": [ "2026-03-17T16:00:00Z", "2026-03-18T16:00:00Z" ] }, "status": "active", "type": "deployment", "updated_at": "2026-03-15T10:00:00Z", "vault_ids": [ "vlt_011CZkZDLs7fYzm1hXNPeRjv" ], "budget": { "max_list_cost": { "amount": "2500", "currency": "USD" }, "type": "limit" } } ``` ### Archive Deployment `beta.deployments.archive(deployment_id, **kwargs) -> BetaManagedAgentsDeployment` **POST** `/v1/deployments/{deployment_id}/archive` Archive Deployment #### Parameters - `deployment_id: str` (path parameter) Unique identifier of the deployment to archive. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeployment` A deployment is a configured instance of an agent — it binds the agent to everything needed to run it autonomously: an environment, credentials, initial events, and an optional schedule. - `type: Literal["deployment"]` - `id: str` Unique identifier for this deployment. - `agent: BetaManagedAgentsAgentReference` Reference to the agent this deployment runs, resolved to a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `archived_at: Optional[datetime]` Time the deployment was archived. Null if not archived. format: date-time - `created_at: datetime` Time the deployment was created. format: date-time - `description: Optional[str]` Description of what the deployment does. - `environment_id: str` ID of the `environment` where sessions run. - `initial_events: List[BetaManagedAgentsDeploymentInitialEvent]` Events sent to each session immediately after creation. - `class BetaManagedAgentsDeploymentUserMessageEvent` A user message sent to the session. - `type: Literal["user.message"]` - `content: List[Content]` Array of content blocks for the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `class BetaManagedAgentsDeploymentUserDefineOutcomeEvent` An outcome the agent should work toward. The agent begins work on receipt. - `type: Literal["user.define_outcome"]` - `description: str` What the agent should produce. This is the task specification. - `rubric: Rubric` How to grade the outcome. Text or file reference. - `class BetaManagedAgentsFileRubric` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubric` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. - `max_iterations: Optional[int]` Eval→revision cycles before giving up. Default 3, max 20. format: int32 - `class BetaManagedAgentsDeploymentSystemMessageEvent` Privileged context for the accompanying turn and all subsequent turns, appended to the session's system context as a `role: "system"` turn rather than replacing the top-level system prompt. - `type: Literal["system.message"]` - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks to append. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `metadata: Dict[str, str]` Arbitrary key-value metadata. Maximum 16 pairs. - `name: str` Human-readable name. - `paused_reason: Optional[BetaManagedAgentsDeploymentPausedReason]` Why the deployment is `paused`. Non-null exactly when `status` is `paused`; null otherwise. - `class BetaManagedAgentsManualDeploymentPausedReason` The caller invoked the pause endpoint on the deployment. - `type: Literal["manual"]` - `class BetaManagedAgentsErrorDeploymentPausedReason` A scheduled fire recorded a failed run whose error auto-pauses the deployment. - `type: Literal["error"]` - `error: BetaManagedAgentsDeploymentPausedReasonError` The failed run's error. - `class BetaManagedAgentsEnvironmentArchivedDeploymentPausedReasonError` The deployment's environment was archived. - `type: Literal["environment_archived_error"]` - `class BetaManagedAgentsAgentArchivedDeploymentPausedReasonError` The deployment's agent was archived. - `type: Literal["agent_archived_error"]` - `class BetaManagedAgentsEnvironmentNotFoundDeploymentPausedReasonError` The deployment's environment no longer exists. - `type: Literal["environment_not_found_error"]` - `class BetaManagedAgentsVaultNotFoundDeploymentPausedReasonError` A vault referenced by the deployment no longer exists. - `type: Literal["vault_not_found_error"]` - `class BetaManagedAgentsFileNotFoundDeploymentPausedReasonError` A file resource referenced by the deployment no longer exists. - `type: Literal["file_not_found_error"]` - `class BetaManagedAgentsSessionResourceNotFoundDeploymentPausedReasonError` A referenced resource no longer exists and its kind was not reported. - `type: Literal["session_resource_not_found_error"]` - `class BetaManagedAgentsWorkspaceArchivedDeploymentPausedReasonError` The deployment's workspace was archived. - `type: Literal["workspace_archived_error"]` - `class BetaManagedAgentsOrganizationDisabledDeploymentPausedReasonError` The deployment's organization is disabled. - `type: Literal["organization_disabled_error"]` - `class BetaManagedAgentsMemoryStoreArchivedDeploymentPausedReasonError` A memory store referenced by the deployment is archived. - `type: Literal["memory_store_archived_error"]` - `class BetaManagedAgentsSkillNotFoundDeploymentPausedReasonError` A skill referenced by the deployment's agent no longer exists. - `type: Literal["skill_not_found_error"]` - `class BetaManagedAgentsVaultArchivedDeploymentPausedReasonError` A vault referenced by the deployment is archived. - `type: Literal["vault_archived_error"]` - `class BetaManagedAgentsUnknownDeploymentPausedReasonError` An unrecognized error auto-paused the deployment. A fallback variant; matches a run whose `error.type` is `unknown_error`. - `type: Literal["unknown_error"]` - `class BetaManagedAgentsSelfHostedResourcesUnsupportedDeploymentPausedReasonError` The deployment configures resources, but its environment is self-hosted and cannot mount them. - `type: Literal["self_hosted_resources_unsupported_error"]` - `class BetaManagedAgentsMCPEgressBlockedDeploymentPausedReasonError` An MCP server host used by the deployment's agent is blocked by the environment's network policy. - `type: Literal["mcp_egress_blocked_error"]` - `resources: List[BetaManagedAgentsSessionResourceConfig]` Resources attached to sessions created from this deployment. Echoes the input minus write-only credentials. - `class BetaManagedAgentsGitHubRepositoryResourceConfig` A GitHub repository mounted into each session's container. The authorization token is write-only and never returned. - `type: Literal["github_repository"]` - `url: str` Github URL of the repository - `checkout: Optional[Checkout]` Branch or commit to check out. Defaults to the repository's default branch. - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/workspace/`. - `class BetaManagedAgentsFileResourceConfig` A file mounted into each session's container. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. - `mount_path: Optional[str]` Mount path in the container. Defaults to `/mnt/session/uploads/`. - `class BetaManagedAgentsMemoryStoreResourceConfig` A memory store attached to each session created from this deployment. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. - `schedule: Optional[BetaManagedAgentsSchedule]` Recurring cron schedule. Presence enables scheduled execution; null means manual-only. Includes computed timestamps (next fire times, last run) on the cron variant. - `type: Literal["cron"]` - `expression: str` 5-field POSIX cron expression: minute hour day-of-month month day-of-week (e.g., "0 9 * * 1-5" for weekdays at 9am). Day-of-week is 0-7 where 0 and 7 both mean Sunday. Extended cron syntax - seconds or year fields, and the special characters L, W, #, and ? - is not supported, nor are predefined shortcuts (@daily). minLength: 1, maxLength: 256 - `timezone: str` IANA timezone identifier (e.g., "America/Los_Angeles", "UTC"). minLength: 1 - `last_run_at: Optional[datetime]` Time the most recent scheduled run actually started. Null until one completes; preserved after the deployment is archived. Manual runs do not update this. format: date-time - `upcoming_runs_at: Optional[List[datetime]]` Up to 5 timestamps of upcoming cron occurrences. Non-empty for active and paused deployments (reflects what the schedule would do if unpaused); empty once the deployment is archived (`archived_at` set). Each fire is offset by a small per-schedule jitter, so a run will actually start at or shortly after its listed time. - `status: BetaManagedAgentsDeploymentStatus` Computed status of the deployment: `active` or `paused`. Archived deployments report `active` with `archived_at` set. - `"active"` The deployment is active and can run sessions. Archived deployments also report this status; check `archived_at` to distinguish them. - `"paused"` The deployment is paused. Autonomous triggers are suppressed; manual runs are still permitted. - `updated_at: datetime` Time the deployment was last updated. format: date-time - `vault_ids: List[str]` Vault IDs supplying stored credentials for sessions created from this deployment. - `budget: Optional[BetaManagedAgentsBudgetLimit]` Spend ceiling stamped onto each session created from this deployment. Absent when no budget is set. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deployment = client.beta.deployments.archive( deployment_id="depl_011CZkZcDH3vPqd7xnEfwTai", ) print(beta_managed_agents_deployment.id) ``` ##### Response (200) ```json { "id": "depl_011CZkZcDH3vPqd7xnEfwTai", "agent": { "id": "agent_011CZkYpogX7uDKUyvBTophP", "type": "agent", "version": 1 }, "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "Compiles yesterday's orders into a report every weekday morning.", "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "initial_events": [ { "content": [ { "text": "Compile yesterday's orders into report.md.", "type": "text" } ], "type": "user.message" } ], "metadata": {}, "name": "Daily order report", "paused_reason": { "type": "manual" }, "resources": [ { "type": "github_repository", "url": "url", "checkout": { "name": "main", "type": "branch" }, "mount_path": "mount_path" } ], "schedule": { "expression": "0 9 * * 1-5", "timezone": "America/Los_Angeles", "type": "cron", "last_run_at": "2026-03-16T16:00:09Z", "upcoming_runs_at": [ "2026-03-17T16:00:00Z", "2026-03-18T16:00:00Z" ] }, "status": "active", "type": "deployment", "updated_at": "2026-03-15T10:00:00Z", "vault_ids": [ "vlt_011CZkZDLs7fYzm1hXNPeRjv" ], "budget": { "max_list_cost": { "amount": "2500", "currency": "USD" }, "type": "limit" } } ``` ### Run Deployment Now `beta.deployments.run(deployment_id, **kwargs) -> BetaManagedAgentsDeploymentRun` **POST** `/v1/deployments/{deployment_id}/run` Run Deployment Now #### Parameters - `deployment_id: str` (path parameter) Unique identifier of the deployment to run. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeploymentRun` A persistent, append-only record of a single deployment execution. Records session creation success or failure — no session lifecycle tracking. - `type: Literal["deployment_run"]` - `id: str` Unique identifier for this run (`drun_...`). - `agent: BetaManagedAgentsAgentReference` Snapshot of the agent at fire time. Always fully resolved — deployments pin agent + version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `created_at: datetime` Time this run record was persisted. format: date-time - `deployment_id: str` ID of the deployment that produced this run. - `error: Optional[Error]` Populated on creation failure. Null on success. Exactly one of `session_id` or `error` is non-null. - `class BetaManagedAgentsEnvironmentArchivedRunError` The deployment's environment was archived. - `type: Literal["environment_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsAgentArchivedRunError` The deployment's agent was archived. - `type: Literal["agent_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsEnvironmentNotFoundRunError` The deployment's environment no longer exists. - `type: Literal["environment_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsVaultNotFoundRunError` A vault referenced by the deployment no longer exists. - `type: Literal["vault_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsVaultArchivedRunError` A vault referenced by the deployment is archived. - `type: Literal["vault_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsFileNotFoundRunError` A file resource referenced by the deployment no longer exists. - `type: Literal["file_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsMemoryStoreArchivedRunError` A memory store referenced by the deployment is archived. - `type: Literal["memory_store_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSkillNotFoundRunError` A skill referenced by the deployment's agent no longer exists. - `type: Literal["skill_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSessionResourceNotFoundRunError` A referenced resource no longer exists and its kind was not reported. - `type: Literal["session_resource_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsWorkspaceArchivedRunError` The deployment's workspace was archived. - `type: Literal["workspace_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsOrganizationDisabledRunError` The deployment's organization is disabled. - `type: Literal["organization_disabled_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSessionRateLimitedRunError` Session creation was rejected due to rate limiting. The schedule keeps firing; subsequent runs may succeed. - `type: Literal["session_rate_limited_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSessionCreationRejectedRunError` The session create request was rejected with a non-retryable validation error. - `type: Literal["session_creation_rejected_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsUnknownRunError` An unknown or unexpected error caused the run to fail. A fallback variant; clients that do not recognize a new error type can match on message alone. - `type: Literal["unknown_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSelfHostedResourcesUnsupportedRunError` The deployment configures resources, but its environment is self-hosted and cannot mount them. - `type: Literal["self_hosted_resources_unsupported_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsMCPEgressBlockedRunError` An MCP server host used by the deployment's agent is blocked by the environment's network policy. - `type: Literal["mcp_egress_blocked_error"]` - `message: str` Human-readable error description. - `session_id: Optional[str]` Populated on success. Null on creation failure. Exactly one of `session_id` or `error` is non-null. - `trigger_context: BetaManagedAgentsTriggerContext` What triggered this run and trigger-specific metadata. - `class BetaManagedAgentsScheduleTriggerContext` The run was fired by the deployment's cron schedule. - `type: Literal["schedule"]` - `scheduled_at: datetime` The UTC instant at which the cron expression matched in the configured timezone, before jitter is applied. At most one run is recorded per (`deployment_id`, `scheduled_at`) pair. format: date-time - `class BetaManagedAgentsManualTriggerContext` The run was started manually by creating a session directly against the deployment. - `type: Literal["manual"]` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deployment_run = client.beta.deployments.run( deployment_id="depl_011CZkZcDH3vPqd7xnEfwTai", ) print(beta_managed_agents_deployment_run.id) ``` ##### Response (200) ```json { "id": "id", "agent": { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 }, "created_at": "2019-12-27T18:11:19.117Z", "deployment_id": "deployment_id", "error": { "message": "message", "type": "environment_archived_error" }, "session_id": "session_id", "trigger_context": { "scheduled_at": "2019-12-27T18:11:19.117Z", "type": "schedule" }, "type": "deployment_run" } ``` ### Pause Deployment `beta.deployments.pause(deployment_id, **kwargs) -> BetaManagedAgentsDeployment` **POST** `/v1/deployments/{deployment_id}/pause` Pause Deployment #### Parameters - `deployment_id: str` (path parameter) Unique identifier of the deployment to pause. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeployment` A deployment is a configured instance of an agent — it binds the agent to everything needed to run it autonomously: an environment, credentials, initial events, and an optional schedule. - `type: Literal["deployment"]` - `id: str` Unique identifier for this deployment. - `agent: BetaManagedAgentsAgentReference` Reference to the agent this deployment runs, resolved to a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `archived_at: Optional[datetime]` Time the deployment was archived. Null if not archived. format: date-time - `created_at: datetime` Time the deployment was created. format: date-time - `description: Optional[str]` Description of what the deployment does. - `environment_id: str` ID of the `environment` where sessions run. - `initial_events: List[BetaManagedAgentsDeploymentInitialEvent]` Events sent to each session immediately after creation. - `class BetaManagedAgentsDeploymentUserMessageEvent` A user message sent to the session. - `type: Literal["user.message"]` - `content: List[Content]` Array of content blocks for the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `class BetaManagedAgentsDeploymentUserDefineOutcomeEvent` An outcome the agent should work toward. The agent begins work on receipt. - `type: Literal["user.define_outcome"]` - `description: str` What the agent should produce. This is the task specification. - `rubric: Rubric` How to grade the outcome. Text or file reference. - `class BetaManagedAgentsFileRubric` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubric` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. - `max_iterations: Optional[int]` Eval→revision cycles before giving up. Default 3, max 20. format: int32 - `class BetaManagedAgentsDeploymentSystemMessageEvent` Privileged context for the accompanying turn and all subsequent turns, appended to the session's system context as a `role: "system"` turn rather than replacing the top-level system prompt. - `type: Literal["system.message"]` - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks to append. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `metadata: Dict[str, str]` Arbitrary key-value metadata. Maximum 16 pairs. - `name: str` Human-readable name. - `paused_reason: Optional[BetaManagedAgentsDeploymentPausedReason]` Why the deployment is `paused`. Non-null exactly when `status` is `paused`; null otherwise. - `class BetaManagedAgentsManualDeploymentPausedReason` The caller invoked the pause endpoint on the deployment. - `type: Literal["manual"]` - `class BetaManagedAgentsErrorDeploymentPausedReason` A scheduled fire recorded a failed run whose error auto-pauses the deployment. - `type: Literal["error"]` - `error: BetaManagedAgentsDeploymentPausedReasonError` The failed run's error. - `class BetaManagedAgentsEnvironmentArchivedDeploymentPausedReasonError` The deployment's environment was archived. - `type: Literal["environment_archived_error"]` - `class BetaManagedAgentsAgentArchivedDeploymentPausedReasonError` The deployment's agent was archived. - `type: Literal["agent_archived_error"]` - `class BetaManagedAgentsEnvironmentNotFoundDeploymentPausedReasonError` The deployment's environment no longer exists. - `type: Literal["environment_not_found_error"]` - `class BetaManagedAgentsVaultNotFoundDeploymentPausedReasonError` A vault referenced by the deployment no longer exists. - `type: Literal["vault_not_found_error"]` - `class BetaManagedAgentsFileNotFoundDeploymentPausedReasonError` A file resource referenced by the deployment no longer exists. - `type: Literal["file_not_found_error"]` - `class BetaManagedAgentsSessionResourceNotFoundDeploymentPausedReasonError` A referenced resource no longer exists and its kind was not reported. - `type: Literal["session_resource_not_found_error"]` - `class BetaManagedAgentsWorkspaceArchivedDeploymentPausedReasonError` The deployment's workspace was archived. - `type: Literal["workspace_archived_error"]` - `class BetaManagedAgentsOrganizationDisabledDeploymentPausedReasonError` The deployment's organization is disabled. - `type: Literal["organization_disabled_error"]` - `class BetaManagedAgentsMemoryStoreArchivedDeploymentPausedReasonError` A memory store referenced by the deployment is archived. - `type: Literal["memory_store_archived_error"]` - `class BetaManagedAgentsSkillNotFoundDeploymentPausedReasonError` A skill referenced by the deployment's agent no longer exists. - `type: Literal["skill_not_found_error"]` - `class BetaManagedAgentsVaultArchivedDeploymentPausedReasonError` A vault referenced by the deployment is archived. - `type: Literal["vault_archived_error"]` - `class BetaManagedAgentsUnknownDeploymentPausedReasonError` An unrecognized error auto-paused the deployment. A fallback variant; matches a run whose `error.type` is `unknown_error`. - `type: Literal["unknown_error"]` - `class BetaManagedAgentsSelfHostedResourcesUnsupportedDeploymentPausedReasonError` The deployment configures resources, but its environment is self-hosted and cannot mount them. - `type: Literal["self_hosted_resources_unsupported_error"]` - `class BetaManagedAgentsMCPEgressBlockedDeploymentPausedReasonError` An MCP server host used by the deployment's agent is blocked by the environment's network policy. - `type: Literal["mcp_egress_blocked_error"]` - `resources: List[BetaManagedAgentsSessionResourceConfig]` Resources attached to sessions created from this deployment. Echoes the input minus write-only credentials. - `class BetaManagedAgentsGitHubRepositoryResourceConfig` A GitHub repository mounted into each session's container. The authorization token is write-only and never returned. - `type: Literal["github_repository"]` - `url: str` Github URL of the repository - `checkout: Optional[Checkout]` Branch or commit to check out. Defaults to the repository's default branch. - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/workspace/`. - `class BetaManagedAgentsFileResourceConfig` A file mounted into each session's container. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. - `mount_path: Optional[str]` Mount path in the container. Defaults to `/mnt/session/uploads/`. - `class BetaManagedAgentsMemoryStoreResourceConfig` A memory store attached to each session created from this deployment. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. - `schedule: Optional[BetaManagedAgentsSchedule]` Recurring cron schedule. Presence enables scheduled execution; null means manual-only. Includes computed timestamps (next fire times, last run) on the cron variant. - `type: Literal["cron"]` - `expression: str` 5-field POSIX cron expression: minute hour day-of-month month day-of-week (e.g., "0 9 * * 1-5" for weekdays at 9am). Day-of-week is 0-7 where 0 and 7 both mean Sunday. Extended cron syntax - seconds or year fields, and the special characters L, W, #, and ? - is not supported, nor are predefined shortcuts (@daily). minLength: 1, maxLength: 256 - `timezone: str` IANA timezone identifier (e.g., "America/Los_Angeles", "UTC"). minLength: 1 - `last_run_at: Optional[datetime]` Time the most recent scheduled run actually started. Null until one completes; preserved after the deployment is archived. Manual runs do not update this. format: date-time - `upcoming_runs_at: Optional[List[datetime]]` Up to 5 timestamps of upcoming cron occurrences. Non-empty for active and paused deployments (reflects what the schedule would do if unpaused); empty once the deployment is archived (`archived_at` set). Each fire is offset by a small per-schedule jitter, so a run will actually start at or shortly after its listed time. - `status: BetaManagedAgentsDeploymentStatus` Computed status of the deployment: `active` or `paused`. Archived deployments report `active` with `archived_at` set. - `"active"` The deployment is active and can run sessions. Archived deployments also report this status; check `archived_at` to distinguish them. - `"paused"` The deployment is paused. Autonomous triggers are suppressed; manual runs are still permitted. - `updated_at: datetime` Time the deployment was last updated. format: date-time - `vault_ids: List[str]` Vault IDs supplying stored credentials for sessions created from this deployment. - `budget: Optional[BetaManagedAgentsBudgetLimit]` Spend ceiling stamped onto each session created from this deployment. Absent when no budget is set. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deployment = client.beta.deployments.pause( deployment_id="depl_011CZkZcDH3vPqd7xnEfwTai", ) print(beta_managed_agents_deployment.id) ``` ##### Response (200) ```json { "id": "depl_011CZkZcDH3vPqd7xnEfwTai", "agent": { "id": "agent_011CZkYpogX7uDKUyvBTophP", "type": "agent", "version": 1 }, "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "Compiles yesterday's orders into a report every weekday morning.", "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "initial_events": [ { "content": [ { "text": "Compile yesterday's orders into report.md.", "type": "text" } ], "type": "user.message" } ], "metadata": {}, "name": "Daily order report", "paused_reason": { "type": "manual" }, "resources": [ { "type": "github_repository", "url": "url", "checkout": { "name": "main", "type": "branch" }, "mount_path": "mount_path" } ], "schedule": { "expression": "0 9 * * 1-5", "timezone": "America/Los_Angeles", "type": "cron", "last_run_at": "2026-03-16T16:00:09Z", "upcoming_runs_at": [ "2026-03-17T16:00:00Z", "2026-03-18T16:00:00Z" ] }, "status": "active", "type": "deployment", "updated_at": "2026-03-15T10:00:00Z", "vault_ids": [ "vlt_011CZkZDLs7fYzm1hXNPeRjv" ], "budget": { "max_list_cost": { "amount": "2500", "currency": "USD" }, "type": "limit" } } ``` ### Unpause Deployment `beta.deployments.unpause(deployment_id, **kwargs) -> BetaManagedAgentsDeployment` **POST** `/v1/deployments/{deployment_id}/unpause` Unpause Deployment #### Parameters - `deployment_id: str` (path parameter) Unique identifier of the deployment to unpause. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeployment` A deployment is a configured instance of an agent — it binds the agent to everything needed to run it autonomously: an environment, credentials, initial events, and an optional schedule. - `type: Literal["deployment"]` - `id: str` Unique identifier for this deployment. - `agent: BetaManagedAgentsAgentReference` Reference to the agent this deployment runs, resolved to a concrete version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `archived_at: Optional[datetime]` Time the deployment was archived. Null if not archived. format: date-time - `created_at: datetime` Time the deployment was created. format: date-time - `description: Optional[str]` Description of what the deployment does. - `environment_id: str` ID of the `environment` where sessions run. - `initial_events: List[BetaManagedAgentsDeploymentInitialEvent]` Events sent to each session immediately after creation. - `class BetaManagedAgentsDeploymentUserMessageEvent` A user message sent to the session. - `type: Literal["user.message"]` - `content: List[Content]` Array of content blocks for the user message. - `class BetaManagedAgentsTextBlock` Regular text content. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `class BetaManagedAgentsImageBlock` Image content specified directly as base64 data or as a reference via a URL. - `type: Literal["image"]` - `source: Source` The source of the image data. - `class BetaManagedAgentsBase64ImageSource` Base64-encoded image data. - `type: Literal["base64"]` - `data: str` Base64-encoded image data. minLength: 1 - `media_type: str` MIME type of the image (e.g., "image/png", "image/jpeg", "image/gif", "image/webp"). minLength: 1 - `class BetaManagedAgentsURLImageSource` Image referenced by URL. - `type: Literal["url"]` - `url: str` URL of the image to fetch. minLength: 1 - `class BetaManagedAgentsFileImageSource` Image referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `class BetaManagedAgentsDocumentBlock` Document content, either specified directly as base64 data, as text, or as a reference via a URL. - `type: Literal["document"]` - `source: Source` The source of the document data. - `class BetaManagedAgentsBase64DocumentSource` Base64-encoded document data. - `type: Literal["base64"]` - `data: str` Base64-encoded document data. minLength: 1 - `media_type: str` MIME type of the document (e.g., "application/pdf"). minLength: 1 - `class BetaManagedAgentsPlainTextDocumentSource` Plain text document content. - `type: Literal["text"]` - `data: str` The plain text content. minLength: 1 - `media_type: Literal["text/plain"]` MIME type of the text content. Must be "text/plain". - `class BetaManagedAgentsURLDocumentSource` Document referenced by URL. - `type: Literal["url"]` - `url: str` URL of the document to fetch. minLength: 1 - `class BetaManagedAgentsFileDocumentSource` Document referenced by file ID. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. minLength: 1 - `context: Optional[str]` Additional context about the document for the model. - `title: Optional[str]` The title of the document. - `class BetaManagedAgentsRedactedBlock` Placeholder for content withheld by Anthropic model policy. - `type: Literal["redacted"]` - `class BetaManagedAgentsDeploymentUserDefineOutcomeEvent` An outcome the agent should work toward. The agent begins work on receipt. - `type: Literal["user.define_outcome"]` - `description: str` What the agent should produce. This is the task specification. - `rubric: Rubric` How to grade the outcome. Text or file reference. - `class BetaManagedAgentsFileRubric` Rubric referenced by a file uploaded via the Files API. - `type: Literal["file"]` - `file_id: str` ID of the rubric file. - `class BetaManagedAgentsTextRubric` Rubric content provided inline as text. - `type: Literal["text"]` - `content: str` Rubric content. Plain text or markdown — the grader treats it as freeform text. - `max_iterations: Optional[int]` Eval→revision cycles before giving up. Default 3, max 20. format: int32 - `class BetaManagedAgentsDeploymentSystemMessageEvent` Privileged context for the accompanying turn and all subsequent turns, appended to the session's system context as a `role: "system"` turn rather than replacing the top-level system prompt. - `type: Literal["system.message"]` - `content: List[BetaManagedAgentsSystemContentBlock]` System content blocks to append. Text-only. - `type: Literal["text"]` - `text: str` The text content. minLength: 1 - `metadata: Dict[str, str]` Arbitrary key-value metadata. Maximum 16 pairs. - `name: str` Human-readable name. - `paused_reason: Optional[BetaManagedAgentsDeploymentPausedReason]` Why the deployment is `paused`. Non-null exactly when `status` is `paused`; null otherwise. - `class BetaManagedAgentsManualDeploymentPausedReason` The caller invoked the pause endpoint on the deployment. - `type: Literal["manual"]` - `class BetaManagedAgentsErrorDeploymentPausedReason` A scheduled fire recorded a failed run whose error auto-pauses the deployment. - `type: Literal["error"]` - `error: BetaManagedAgentsDeploymentPausedReasonError` The failed run's error. - `class BetaManagedAgentsEnvironmentArchivedDeploymentPausedReasonError` The deployment's environment was archived. - `type: Literal["environment_archived_error"]` - `class BetaManagedAgentsAgentArchivedDeploymentPausedReasonError` The deployment's agent was archived. - `type: Literal["agent_archived_error"]` - `class BetaManagedAgentsEnvironmentNotFoundDeploymentPausedReasonError` The deployment's environment no longer exists. - `type: Literal["environment_not_found_error"]` - `class BetaManagedAgentsVaultNotFoundDeploymentPausedReasonError` A vault referenced by the deployment no longer exists. - `type: Literal["vault_not_found_error"]` - `class BetaManagedAgentsFileNotFoundDeploymentPausedReasonError` A file resource referenced by the deployment no longer exists. - `type: Literal["file_not_found_error"]` - `class BetaManagedAgentsSessionResourceNotFoundDeploymentPausedReasonError` A referenced resource no longer exists and its kind was not reported. - `type: Literal["session_resource_not_found_error"]` - `class BetaManagedAgentsWorkspaceArchivedDeploymentPausedReasonError` The deployment's workspace was archived. - `type: Literal["workspace_archived_error"]` - `class BetaManagedAgentsOrganizationDisabledDeploymentPausedReasonError` The deployment's organization is disabled. - `type: Literal["organization_disabled_error"]` - `class BetaManagedAgentsMemoryStoreArchivedDeploymentPausedReasonError` A memory store referenced by the deployment is archived. - `type: Literal["memory_store_archived_error"]` - `class BetaManagedAgentsSkillNotFoundDeploymentPausedReasonError` A skill referenced by the deployment's agent no longer exists. - `type: Literal["skill_not_found_error"]` - `class BetaManagedAgentsVaultArchivedDeploymentPausedReasonError` A vault referenced by the deployment is archived. - `type: Literal["vault_archived_error"]` - `class BetaManagedAgentsUnknownDeploymentPausedReasonError` An unrecognized error auto-paused the deployment. A fallback variant; matches a run whose `error.type` is `unknown_error`. - `type: Literal["unknown_error"]` - `class BetaManagedAgentsSelfHostedResourcesUnsupportedDeploymentPausedReasonError` The deployment configures resources, but its environment is self-hosted and cannot mount them. - `type: Literal["self_hosted_resources_unsupported_error"]` - `class BetaManagedAgentsMCPEgressBlockedDeploymentPausedReasonError` An MCP server host used by the deployment's agent is blocked by the environment's network policy. - `type: Literal["mcp_egress_blocked_error"]` - `resources: List[BetaManagedAgentsSessionResourceConfig]` Resources attached to sessions created from this deployment. Echoes the input minus write-only credentials. - `class BetaManagedAgentsGitHubRepositoryResourceConfig` A GitHub repository mounted into each session's container. The authorization token is write-only and never returned. - `type: Literal["github_repository"]` - `url: str` Github URL of the repository - `checkout: Optional[Checkout]` Branch or commit to check out. Defaults to the repository's default branch. - `class BetaManagedAgentsBranchCheckout` - `type: Literal["branch"]` - `name: str` Branch name to check out. minLength: 1, maxLength: 255 - `class BetaManagedAgentsCommitCheckout` - `type: Literal["commit"]` - `sha: str` Full commit SHA to check out. minLength: 7, maxLength: 64 - `mount_path: Optional[str]` Mount path in the container. Defaults to `/workspace/`. - `class BetaManagedAgentsFileResourceConfig` A file mounted into each session's container. - `type: Literal["file"]` - `file_id: str` ID of a previously uploaded file. - `mount_path: Optional[str]` Mount path in the container. Defaults to `/mnt/session/uploads/`. - `class BetaManagedAgentsMemoryStoreResourceConfig` A memory store attached to each session created from this deployment. - `type: Literal["memory_store"]` - `memory_store_id: str` The memory store ID (memstore_...). Must belong to the caller's organization and workspace. - `access: Optional[Literal["read_write", "read_only"]]` Access mode for the mounted store. Defaults to `read_write`. `read_only` mounts the store as a read-only filesystem. - `"read_write"` - `"read_only"` - `instructions: Optional[str]` Per-attachment guidance for the agent on how to use this store. Rendered into the memory section of the system prompt. Max 4096 chars. - `schedule: Optional[BetaManagedAgentsSchedule]` Recurring cron schedule. Presence enables scheduled execution; null means manual-only. Includes computed timestamps (next fire times, last run) on the cron variant. - `type: Literal["cron"]` - `expression: str` 5-field POSIX cron expression: minute hour day-of-month month day-of-week (e.g., "0 9 * * 1-5" for weekdays at 9am). Day-of-week is 0-7 where 0 and 7 both mean Sunday. Extended cron syntax - seconds or year fields, and the special characters L, W, #, and ? - is not supported, nor are predefined shortcuts (@daily). minLength: 1, maxLength: 256 - `timezone: str` IANA timezone identifier (e.g., "America/Los_Angeles", "UTC"). minLength: 1 - `last_run_at: Optional[datetime]` Time the most recent scheduled run actually started. Null until one completes; preserved after the deployment is archived. Manual runs do not update this. format: date-time - `upcoming_runs_at: Optional[List[datetime]]` Up to 5 timestamps of upcoming cron occurrences. Non-empty for active and paused deployments (reflects what the schedule would do if unpaused); empty once the deployment is archived (`archived_at` set). Each fire is offset by a small per-schedule jitter, so a run will actually start at or shortly after its listed time. - `status: BetaManagedAgentsDeploymentStatus` Computed status of the deployment: `active` or `paused`. Archived deployments report `active` with `archived_at` set. - `"active"` The deployment is active and can run sessions. Archived deployments also report this status; check `archived_at` to distinguish them. - `"paused"` The deployment is paused. Autonomous triggers are suppressed; manual runs are still permitted. - `updated_at: datetime` Time the deployment was last updated. format: date-time - `vault_ids: List[str]` Vault IDs supplying stored credentials for sessions created from this deployment. - `budget: Optional[BetaManagedAgentsBudgetLimit]` Spend ceiling stamped onto each session created from this deployment. Absent when no budget is set. - `type: Literal["limit"]` - `max_list_cost: BetaMonetaryAmount` Maximum list cost the session may accrue. List price is used regardless of any negotiated discount, so the cap fires at or before the actual charge. - `amount: str` Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied. - `currency: BetaCurrency` Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deployment = client.beta.deployments.unpause( deployment_id="depl_011CZkZcDH3vPqd7xnEfwTai", ) print(beta_managed_agents_deployment.id) ``` ##### Response (200) ```json { "id": "depl_011CZkZcDH3vPqd7xnEfwTai", "agent": { "id": "agent_011CZkYpogX7uDKUyvBTophP", "type": "agent", "version": 1 }, "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "Compiles yesterday's orders into a report every weekday morning.", "environment_id": "env_011CZkZ9X2dpNyB7HsEFoRfW", "initial_events": [ { "content": [ { "text": "Compile yesterday's orders into report.md.", "type": "text" } ], "type": "user.message" } ], "metadata": {}, "name": "Daily order report", "paused_reason": { "type": "manual" }, "resources": [ { "type": "github_repository", "url": "url", "checkout": { "name": "main", "type": "branch" }, "mount_path": "mount_path" } ], "schedule": { "expression": "0 9 * * 1-5", "timezone": "America/Los_Angeles", "type": "cron", "last_run_at": "2026-03-16T16:00:09Z", "upcoming_runs_at": [ "2026-03-17T16:00:00Z", "2026-03-18T16:00:00Z" ] }, "status": "active", "type": "deployment", "updated_at": "2026-03-15T10:00:00Z", "vault_ids": [ "vlt_011CZkZDLs7fYzm1hXNPeRjv" ], "budget": { "max_list_cost": { "amount": "2500", "currency": "USD" }, "type": "limit" } } ``` ## Beta › Deployment Runs ### List Deployment Runs `beta.deployment_runs.list(**kwargs) -> SyncPageCursor[BetaManagedAgentsDeploymentRun]` **GET** `/v1/deployment_runs` List Deployment Runs #### Parameters - `created_at_gt: Optional[Union[str, datetime]]` (query parameter) Return runs created strictly after this time (exclusive). format: date-time - `created_at_gte: Optional[Union[str, datetime]]` (query parameter) Return runs created at or after this time (inclusive). format: date-time - `created_at_lt: Optional[Union[str, datetime]]` (query parameter) Return runs created strictly before this time (exclusive). format: date-time - `created_at_lte: Optional[Union[str, datetime]]` (query parameter) Return runs created at or before this time (inclusive). format: date-time - `deployment_id: Optional[str]` (query parameter) Filter to a specific deployment. Omit to list across all deployments in the workspace. Filtering by a non-existent `deployment_id` returns 200 with empty data. - `has_error: Optional[bool]` (query parameter) Filter: true for runs with non-null `error`, false for runs with non-null `session_id`. Omit for all. - `limit: Optional[int]` (query parameter) Maximum results per page. Default 20, maximum 1000. format: int32 - `page: Optional[str]` (query parameter) Opaque pagination cursor. Pass `next_page` from the previous response. Invalid or expired cursors return 400. - `trigger_type: Optional[BetaManagedAgentsTriggerType]` (query parameter) Filter runs by what triggered them. Omit to return all runs. - `"schedule"` The run was fired by the deployment's cron schedule. - `"manual"` The run was started manually by creating a session directly against the deployment. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeploymentRun` A persistent, append-only record of a single deployment execution. Records session creation success or failure — no session lifecycle tracking. - `type: Literal["deployment_run"]` - `id: str` Unique identifier for this run (`drun_...`). - `agent: BetaManagedAgentsAgentReference` Snapshot of the agent at fire time. Always fully resolved — deployments pin agent + version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `created_at: datetime` Time this run record was persisted. format: date-time - `deployment_id: str` ID of the deployment that produced this run. - `error: Optional[Error]` Populated on creation failure. Null on success. Exactly one of `session_id` or `error` is non-null. - `class BetaManagedAgentsEnvironmentArchivedRunError` The deployment's environment was archived. - `type: Literal["environment_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsAgentArchivedRunError` The deployment's agent was archived. - `type: Literal["agent_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsEnvironmentNotFoundRunError` The deployment's environment no longer exists. - `type: Literal["environment_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsVaultNotFoundRunError` A vault referenced by the deployment no longer exists. - `type: Literal["vault_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsVaultArchivedRunError` A vault referenced by the deployment is archived. - `type: Literal["vault_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsFileNotFoundRunError` A file resource referenced by the deployment no longer exists. - `type: Literal["file_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsMemoryStoreArchivedRunError` A memory store referenced by the deployment is archived. - `type: Literal["memory_store_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSkillNotFoundRunError` A skill referenced by the deployment's agent no longer exists. - `type: Literal["skill_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSessionResourceNotFoundRunError` A referenced resource no longer exists and its kind was not reported. - `type: Literal["session_resource_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsWorkspaceArchivedRunError` The deployment's workspace was archived. - `type: Literal["workspace_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsOrganizationDisabledRunError` The deployment's organization is disabled. - `type: Literal["organization_disabled_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSessionRateLimitedRunError` Session creation was rejected due to rate limiting. The schedule keeps firing; subsequent runs may succeed. - `type: Literal["session_rate_limited_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSessionCreationRejectedRunError` The session create request was rejected with a non-retryable validation error. - `type: Literal["session_creation_rejected_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsUnknownRunError` An unknown or unexpected error caused the run to fail. A fallback variant; clients that do not recognize a new error type can match on message alone. - `type: Literal["unknown_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSelfHostedResourcesUnsupportedRunError` The deployment configures resources, but its environment is self-hosted and cannot mount them. - `type: Literal["self_hosted_resources_unsupported_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsMCPEgressBlockedRunError` An MCP server host used by the deployment's agent is blocked by the environment's network policy. - `type: Literal["mcp_egress_blocked_error"]` - `message: str` Human-readable error description. - `session_id: Optional[str]` Populated on success. Null on creation failure. Exactly one of `session_id` or `error` is non-null. - `trigger_context: BetaManagedAgentsTriggerContext` What triggered this run and trigger-specific metadata. - `class BetaManagedAgentsScheduleTriggerContext` The run was fired by the deployment's cron schedule. - `type: Literal["schedule"]` - `scheduled_at: datetime` The UTC instant at which the cron expression matched in the configured timezone, before jitter is applied. At most one run is recorded per (`deployment_id`, `scheduled_at`) pair. format: date-time - `class BetaManagedAgentsManualTriggerContext` The run was started manually by creating a session directly against the deployment. - `type: Literal["manual"]` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.deployment_runs.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "id", "agent": { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 }, "created_at": "2019-12-27T18:11:19.117Z", "deployment_id": "deployment_id", "error": { "message": "message", "type": "environment_archived_error" }, "session_id": "session_id", "trigger_context": { "scheduled_at": "2019-12-27T18:11:19.117Z", "type": "schedule" }, "type": "deployment_run" } ], "next_page": "next_page" } ``` ### Get Deployment Run `beta.deployment_runs.retrieve(deployment_run_id, **kwargs) -> BetaManagedAgentsDeploymentRun` **GET** `/v1/deployment_runs/{deployment_run_id}` Get Deployment Run #### Parameters - `deployment_run_id: str` (path parameter) Unique identifier of the deployment run. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeploymentRun` A persistent, append-only record of a single deployment execution. Records session creation success or failure — no session lifecycle tracking. - `type: Literal["deployment_run"]` - `id: str` Unique identifier for this run (`drun_...`). - `agent: BetaManagedAgentsAgentReference` Snapshot of the agent at fire time. Always fully resolved — deployments pin agent + version. - `type: Literal["agent"]` - `id: str` - `version: int` format: int32 - `created_at: datetime` Time this run record was persisted. format: date-time - `deployment_id: str` ID of the deployment that produced this run. - `error: Optional[Error]` Populated on creation failure. Null on success. Exactly one of `session_id` or `error` is non-null. - `class BetaManagedAgentsEnvironmentArchivedRunError` The deployment's environment was archived. - `type: Literal["environment_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsAgentArchivedRunError` The deployment's agent was archived. - `type: Literal["agent_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsEnvironmentNotFoundRunError` The deployment's environment no longer exists. - `type: Literal["environment_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsVaultNotFoundRunError` A vault referenced by the deployment no longer exists. - `type: Literal["vault_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsVaultArchivedRunError` A vault referenced by the deployment is archived. - `type: Literal["vault_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsFileNotFoundRunError` A file resource referenced by the deployment no longer exists. - `type: Literal["file_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsMemoryStoreArchivedRunError` A memory store referenced by the deployment is archived. - `type: Literal["memory_store_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSkillNotFoundRunError` A skill referenced by the deployment's agent no longer exists. - `type: Literal["skill_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSessionResourceNotFoundRunError` A referenced resource no longer exists and its kind was not reported. - `type: Literal["session_resource_not_found_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsWorkspaceArchivedRunError` The deployment's workspace was archived. - `type: Literal["workspace_archived_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsOrganizationDisabledRunError` The deployment's organization is disabled. - `type: Literal["organization_disabled_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSessionRateLimitedRunError` Session creation was rejected due to rate limiting. The schedule keeps firing; subsequent runs may succeed. - `type: Literal["session_rate_limited_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSessionCreationRejectedRunError` The session create request was rejected with a non-retryable validation error. - `type: Literal["session_creation_rejected_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsUnknownRunError` An unknown or unexpected error caused the run to fail. A fallback variant; clients that do not recognize a new error type can match on message alone. - `type: Literal["unknown_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsSelfHostedResourcesUnsupportedRunError` The deployment configures resources, but its environment is self-hosted and cannot mount them. - `type: Literal["self_hosted_resources_unsupported_error"]` - `message: str` Human-readable error description. - `class BetaManagedAgentsMCPEgressBlockedRunError` An MCP server host used by the deployment's agent is blocked by the environment's network policy. - `type: Literal["mcp_egress_blocked_error"]` - `message: str` Human-readable error description. - `session_id: Optional[str]` Populated on success. Null on creation failure. Exactly one of `session_id` or `error` is non-null. - `trigger_context: BetaManagedAgentsTriggerContext` What triggered this run and trigger-specific metadata. - `class BetaManagedAgentsScheduleTriggerContext` The run was fired by the deployment's cron schedule. - `type: Literal["schedule"]` - `scheduled_at: datetime` The UTC instant at which the cron expression matched in the configured timezone, before jitter is applied. At most one run is recorded per (`deployment_id`, `scheduled_at`) pair. format: date-time - `class BetaManagedAgentsManualTriggerContext` The run was started manually by creating a session directly against the deployment. - `type: Literal["manual"]` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deployment_run = client.beta.deployment_runs.retrieve( deployment_run_id="deployment_run_id", ) print(beta_managed_agents_deployment_run.id) ``` ##### Response (200) ```json { "id": "id", "agent": { "id": "agent_011CZkYqphY8vELVzwCUpqiQ", "type": "agent", "version": 1 }, "created_at": "2019-12-27T18:11:19.117Z", "deployment_id": "deployment_id", "error": { "message": "message", "type": "environment_archived_error" }, "session_id": "session_id", "trigger_context": { "scheduled_at": "2019-12-27T18:11:19.117Z", "type": "schedule" }, "type": "deployment_run" } ``` ## Beta › Vaults ### Create Vault `beta.vaults.create(**kwargs) -> BetaManagedAgentsVault` **POST** `/v1/vaults` Create Vault #### Parameters - `display_name: str` Human-readable name for the vault. 1-255 characters. minLength: 1, maxLength: 255 - `metadata: Optional[Dict[str, str]]` Arbitrary key-value metadata to attach to the vault. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsVault` A vault that stores credentials for use by agents during sessions. - `type: Literal["vault"]` - `id: str` Unique identifier for the vault. - `archived_at: Optional[datetime]` When the vault was archived. Null if not archived. format: date-time - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `display_name: str` Human-readable name for the vault. - `metadata: Dict[str, str]` Arbitrary key-value metadata attached to the vault. - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_vault = client.beta.vaults.create( display_name="Example vault", ) print(beta_managed_agents_vault.id) ``` ##### Response (200) ```json { "id": "vlt_011CZkZDLs7fYzm1hXNPeRjv", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "display_name": "Example vault", "metadata": { "environment": "production" }, "type": "vault", "updated_at": "2026-03-15T10:00:00Z" } ``` ### List Vaults `beta.vaults.list(**kwargs) -> SyncPageCursor[BetaManagedAgentsVault]` **GET** `/v1/vaults` List Vaults #### Parameters - `include_archived: Optional[bool]` (query parameter) Whether to include archived vaults in the results. - `limit: Optional[int]` (query parameter) Maximum number of vaults to return per page. Defaults to 20, maximum 100. format: int32 - `page: Optional[str]` (query parameter) Opaque pagination token from a previous `list_vaults` response. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsVault` A vault that stores credentials for use by agents during sessions. - `type: Literal["vault"]` - `id: str` Unique identifier for the vault. - `archived_at: Optional[datetime]` When the vault was archived. Null if not archived. format: date-time - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `display_name: str` Human-readable name for the vault. - `metadata: Dict[str, str]` Arbitrary key-value metadata attached to the vault. - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.vaults.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "vlt_011CZkZDLs7fYzm1hXNPeRjv", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "display_name": "Example vault", "metadata": { "environment": "production" }, "type": "vault", "updated_at": "2026-03-15T10:00:00Z" } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=" } ``` ### Get Vault `beta.vaults.retrieve(vault_id, **kwargs) -> BetaManagedAgentsVault` **GET** `/v1/vaults/{vault_id}` Get Vault #### Parameters - `vault_id: str` (path parameter) Unique identifier of the vault to retrieve. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsVault` A vault that stores credentials for use by agents during sessions. - `type: Literal["vault"]` - `id: str` Unique identifier for the vault. - `archived_at: Optional[datetime]` When the vault was archived. Null if not archived. format: date-time - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `display_name: str` Human-readable name for the vault. - `metadata: Dict[str, str]` Arbitrary key-value metadata attached to the vault. - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_vault = client.beta.vaults.retrieve( vault_id="vlt_011CZkZDLs7fYzm1hXNPeRjv", ) print(beta_managed_agents_vault.id) ``` ##### Response (200) ```json { "id": "vlt_011CZkZDLs7fYzm1hXNPeRjv", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "display_name": "Example vault", "metadata": { "environment": "production" }, "type": "vault", "updated_at": "2026-03-15T10:00:00Z" } ``` ### Update Vault `beta.vaults.update(vault_id, **kwargs) -> BetaManagedAgentsVault` **POST** `/v1/vaults/{vault_id}` Update Vault #### Parameters - `vault_id: str` (path parameter) Unique identifier of the vault to update. - `display_name: Optional[str]` Updated human-readable name for the vault. 1-255 characters. minLength: 1, maxLength: 255 - `metadata: Optional[Dict[str, Optional[str]]]` Metadata patch. Set a key to a string to upsert it, or to null to delete it. Omitted keys are preserved. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsVault` A vault that stores credentials for use by agents during sessions. - `type: Literal["vault"]` - `id: str` Unique identifier for the vault. - `archived_at: Optional[datetime]` When the vault was archived. Null if not archived. format: date-time - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `display_name: str` Human-readable name for the vault. - `metadata: Dict[str, str]` Arbitrary key-value metadata attached to the vault. - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_vault = client.beta.vaults.update( vault_id="vlt_011CZkZDLs7fYzm1hXNPeRjv", ) print(beta_managed_agents_vault.id) ``` ##### Response (200) ```json { "id": "vlt_011CZkZDLs7fYzm1hXNPeRjv", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "display_name": "Example vault", "metadata": { "environment": "production" }, "type": "vault", "updated_at": "2026-03-15T10:00:00Z" } ``` ### Delete Vault `beta.vaults.delete(vault_id, **kwargs) -> BetaManagedAgentsDeletedVault` **DELETE** `/v1/vaults/{vault_id}` Delete Vault #### Parameters - `vault_id: str` (path parameter) Unique identifier of the vault to delete. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeletedVault` Confirmation of a deleted vault. - `type: Literal["vault_deleted"]` - `id: str` Unique identifier of the deleted vault. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deleted_vault = client.beta.vaults.delete( vault_id="vlt_011CZkZDLs7fYzm1hXNPeRjv", ) print(beta_managed_agents_deleted_vault.id) ``` ##### Response (200) ```json { "id": "vlt_011CZkZDLs7fYzm1hXNPeRjv", "type": "vault_deleted" } ``` ### Archive Vault `beta.vaults.archive(vault_id, **kwargs) -> BetaManagedAgentsVault` **POST** `/v1/vaults/{vault_id}/archive` Archive Vault #### Parameters - `vault_id: str` (path parameter) Unique identifier of the vault to archive. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsVault` A vault that stores credentials for use by agents during sessions. - `type: Literal["vault"]` - `id: str` Unique identifier for the vault. - `archived_at: Optional[datetime]` When the vault was archived. Null if not archived. format: date-time - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `display_name: str` Human-readable name for the vault. - `metadata: Dict[str, str]` Arbitrary key-value metadata attached to the vault. - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_vault = client.beta.vaults.archive( vault_id="vlt_011CZkZDLs7fYzm1hXNPeRjv", ) print(beta_managed_agents_vault.id) ``` ##### Response (200) ```json { "id": "vlt_011CZkZDLs7fYzm1hXNPeRjv", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "display_name": "Example vault", "metadata": { "environment": "production" }, "type": "vault", "updated_at": "2026-03-15T10:00:00Z" } ``` ## Beta › Vaults › Credentials ### Create Credential `beta.vaults.credentials.create(vault_id, **kwargs) -> BetaManagedAgentsCredential` **POST** `/v1/vaults/{vault_id}/credentials` Create Credential #### Parameters - `vault_id: str` (path parameter) Identifier of the vault to create the credential in. - `auth: Auth` Authentication configuration for the credential. - `class BetaManagedAgentsMCPOAuthCreateParams` Parameters for creating an MCP OAuth credential. - `type: Literal["mcp_oauth"]` - `access_token: str` OAuth access token. minLength: 1, maxLength: 8192 - `mcp_server_url: str` URL of the MCP server this credential authenticates against. minLength: 1, maxLength: 2047 - `expires_at: Optional[datetime]` A timestamp in RFC 3339 format format: date-time - `refresh: Optional[BetaManagedAgentsMCPOAuthRefreshParams]` Refresh token configuration, if the credential supports token refresh. - `client_id: str` OAuth client ID. minLength: 1, maxLength: 1024 - `refresh_token: str` OAuth refresh token. minLength: 1, maxLength: 8192 - `token_endpoint: str` Token endpoint URL used to refresh the access token. minLength: 1, maxLength: 2047 - `token_endpoint_auth: TokenEndpointAuth` - `class BetaManagedAgentsTokenEndpointAuthNoneParam` Token endpoint requires no client authentication. - `type: Literal["none"]` - `class BetaManagedAgentsTokenEndpointAuthBasicParam` Token endpoint uses HTTP Basic authentication with client credentials. - `type: Literal["client_secret_basic"]` - `client_secret: str` OAuth client secret. minLength: 1, maxLength: 512 - `class BetaManagedAgentsTokenEndpointAuthPostParam` Token endpoint uses POST body authentication with client credentials. - `type: Literal["client_secret_post"]` - `client_secret: str` OAuth client secret. minLength: 1, maxLength: 512 - `resource: Optional[str]` OAuth resource indicator. minLength: 1, maxLength: 2047 - `scope: Optional[str]` OAuth scope for the refresh request. minLength: 1, maxLength: 8192 - `class BetaManagedAgentsStaticBearerCreateParams` Parameters for creating a static bearer token credential. - `type: Literal["static_bearer"]` - `token: str` Static bearer token value. minLength: 1, maxLength: 8192 - `mcp_server_url: str` URL of the MCP server this credential authenticates against. minLength: 1, maxLength: 2047 - `class BetaManagedAgentsEnvironmentVariableCreateParams` Parameters for creating an environment variable credential. - `type: Literal["environment_variable"]` - `networking: BetaManagedAgentsCredentialNetworkingParams` Outbound hosts the secret value is substituted on. - `class BetaManagedAgentsUnrestrictedCredentialNetworkingParams` Substitute the secret on any host the session's Environment network policy permits egress to. The Environment's network policy is the only boundary on where the secret can reach. - `type: Literal["unrestricted"]` - `class BetaManagedAgentsLimitedCredentialNetworkingParams` Substitute the secret only on requests to the listed hosts. - `type: Literal["limited"]` - `allowed_hosts: List[str]` Hostnames on which the secret will be substituted. Each entry is a bare hostname (`api.example.com`), an IPv4 address (`192.0.2.1`), or a `*.`-prefixed wildcard (`*.example.com`). URLs, ports, paths, and IPv6 addresses are not accepted. At most 16 entries. - `secret_name: str` Name of the environment variable. Immutable after create. minLength: 1, maxLength: 255 - `secret_value: str` Secret value. Write-only; never returned in responses. minLength: 1, maxLength: 4096 - `injection_location: Optional[BetaManagedAgentsInjectionLocationParams]` Where in the outbound request the secret value may be substituted. - `body: Optional[bool]` Substitute when the placeholder appears in the request body. - `header: Optional[bool]` Substitute when the placeholder appears in a request header value. - `display_name: Optional[str]` Human-readable name for the credential. Up to 255 characters. maxLength: 255 - `metadata: Optional[Dict[str, str]]` Arbitrary key-value metadata to attach to the credential. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsCredential` A credential stored in a vault. Sensitive fields are never returned in responses. - `type: Literal["vault_credential"]` - `id: str` Unique identifier for the credential. - `archived_at: Optional[datetime]` When the credential was archived. Null if not archived. format: date-time - `auth: Auth` Authentication configuration for this credential. - `class BetaManagedAgentsMCPOAuthAuthResponse` OAuth credential details for an MCP server. - `type: Literal["mcp_oauth"]` - `mcp_server_url: str` URL of the MCP server this credential authenticates against. - `expires_at: Optional[datetime]` A timestamp in RFC 3339 format format: date-time - `refresh: Optional[BetaManagedAgentsMCPOAuthRefreshResponse]` Refresh token configuration, if the credential supports token refresh. - `client_id: str` OAuth client ID. - `token_endpoint: str` Token endpoint URL used to refresh the access token. - `token_endpoint_auth: TokenEndpointAuth` - `class BetaManagedAgentsTokenEndpointAuthNoneResponse` Token endpoint requires no client authentication. - `type: Literal["none"]` - `class BetaManagedAgentsTokenEndpointAuthBasicResponse` Token endpoint uses HTTP Basic authentication with client credentials. - `type: Literal["client_secret_basic"]` - `class BetaManagedAgentsTokenEndpointAuthPostResponse` Token endpoint uses POST body authentication with client credentials. - `type: Literal["client_secret_post"]` - `resource: Optional[str]` OAuth resource indicator. - `scope: Optional[str]` OAuth scope for the refresh request. - `class BetaManagedAgentsStaticBearerAuthResponse` Static bearer token credential details for an MCP server. - `type: Literal["static_bearer"]` - `mcp_server_url: str` URL of the MCP server this credential authenticates against. - `class BetaManagedAgentsEnvironmentVariableAuthResponse` Environment variable credential details. The secret value is never returned. - `type: Literal["environment_variable"]` - `injection_location: BetaManagedAgentsInjectionLocationResponse` Where in the outbound request the secret value is substituted. - `body: bool` Whether the placeholder is substituted in the request body. - `header: bool` Whether the placeholder is substituted in request header values. - `networking: Networking` Outbound hosts the secret value is substituted on. - `class BetaManagedAgentsUnrestrictedCredentialNetworkingResponse` The secret is substituted on any host the session's Environment network policy permits egress to. - `type: Literal["unrestricted"]` - `class BetaManagedAgentsLimitedCredentialNetworkingResponse` The secret is substituted only on requests to the listed hosts. - `type: Literal["limited"]` - `allowed_hosts: List[str]` Hostnames on which the secret will be substituted. An entry matches the request host exactly; a `*.`-prefixed entry matches any subdomain of the named domain but not the domain itself. - `secret_name: str` Name of the environment variable. - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `metadata: Dict[str, str]` Arbitrary key-value metadata attached to the credential. - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `vault_id: str` Identifier of the vault this credential belongs to. - `display_name: Optional[str]` Human-readable name for the credential. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_credential = client.beta.vaults.credentials.create( vault_id="vlt_011CZkZDLs7fYzm1hXNPeRjv", auth={ "token": "bearer_exampletoken", "mcp_server_url": "https://example-server.modelcontextprotocol.io/sse", "type": "static_bearer", }, ) print(beta_managed_agents_credential.id) ``` ##### Response (200) ```json { "id": "vcrd_011CZkZEMt8gZan2iYPQfSkw", "archived_at": null, "auth": { "mcp_server_url": "https://example-server.modelcontextprotocol.io/sse", "type": "static_bearer" }, "created_at": "2026-03-15T10:00:00Z", "metadata": { "environment": "production" }, "type": "vault_credential", "updated_at": "2026-03-15T10:00:00Z", "vault_id": "vlt_011CZkZDLs7fYzm1hXNPeRjv", "display_name": "Example credential" } ``` ### List Credentials `beta.vaults.credentials.list(vault_id, **kwargs) -> SyncPageCursor[BetaManagedAgentsCredential]` **GET** `/v1/vaults/{vault_id}/credentials` List Credentials #### Parameters - `vault_id: str` (path parameter) Identifier of the vault to list credentials for. - `include_archived: Optional[bool]` (query parameter) Whether to include archived credentials in the results. - `limit: Optional[int]` (query parameter) Maximum number of credentials to return per page. Defaults to 20, maximum 100. format: int32 - `page: Optional[str]` (query parameter) Opaque pagination token from a previous `list_credentials` response. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsCredential` A credential stored in a vault. Sensitive fields are never returned in responses. - `type: Literal["vault_credential"]` - `id: str` Unique identifier for the credential. - `archived_at: Optional[datetime]` When the credential was archived. Null if not archived. format: date-time - `auth: Auth` Authentication configuration for this credential. - `class BetaManagedAgentsMCPOAuthAuthResponse` OAuth credential details for an MCP server. - `type: Literal["mcp_oauth"]` - `mcp_server_url: str` URL of the MCP server this credential authenticates against. - `expires_at: Optional[datetime]` A timestamp in RFC 3339 format format: date-time - `refresh: Optional[BetaManagedAgentsMCPOAuthRefreshResponse]` Refresh token configuration, if the credential supports token refresh. - `client_id: str` OAuth client ID. - `token_endpoint: str` Token endpoint URL used to refresh the access token. - `token_endpoint_auth: TokenEndpointAuth` - `class BetaManagedAgentsTokenEndpointAuthNoneResponse` Token endpoint requires no client authentication. - `type: Literal["none"]` - `class BetaManagedAgentsTokenEndpointAuthBasicResponse` Token endpoint uses HTTP Basic authentication with client credentials. - `type: Literal["client_secret_basic"]` - `class BetaManagedAgentsTokenEndpointAuthPostResponse` Token endpoint uses POST body authentication with client credentials. - `type: Literal["client_secret_post"]` - `resource: Optional[str]` OAuth resource indicator. - `scope: Optional[str]` OAuth scope for the refresh request. - `class BetaManagedAgentsStaticBearerAuthResponse` Static bearer token credential details for an MCP server. - `type: Literal["static_bearer"]` - `mcp_server_url: str` URL of the MCP server this credential authenticates against. - `class BetaManagedAgentsEnvironmentVariableAuthResponse` Environment variable credential details. The secret value is never returned. - `type: Literal["environment_variable"]` - `injection_location: BetaManagedAgentsInjectionLocationResponse` Where in the outbound request the secret value is substituted. - `body: bool` Whether the placeholder is substituted in the request body. - `header: bool` Whether the placeholder is substituted in request header values. - `networking: Networking` Outbound hosts the secret value is substituted on. - `class BetaManagedAgentsUnrestrictedCredentialNetworkingResponse` The secret is substituted on any host the session's Environment network policy permits egress to. - `type: Literal["unrestricted"]` - `class BetaManagedAgentsLimitedCredentialNetworkingResponse` The secret is substituted only on requests to the listed hosts. - `type: Literal["limited"]` - `allowed_hosts: List[str]` Hostnames on which the secret will be substituted. An entry matches the request host exactly; a `*.`-prefixed entry matches any subdomain of the named domain but not the domain itself. - `secret_name: str` Name of the environment variable. - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `metadata: Dict[str, str]` Arbitrary key-value metadata attached to the credential. - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `vault_id: str` Identifier of the vault this credential belongs to. - `display_name: Optional[str]` Human-readable name for the credential. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.vaults.credentials.list( vault_id="vlt_011CZkZDLs7fYzm1hXNPeRjv", ) page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "vcrd_011CZkZEMt8gZan2iYPQfSkw", "archived_at": null, "auth": { "mcp_server_url": "https://example-server.modelcontextprotocol.io/sse", "type": "static_bearer" }, "created_at": "2026-03-15T10:00:00Z", "metadata": { "environment": "production" }, "type": "vault_credential", "updated_at": "2026-03-15T10:00:00Z", "vault_id": "vlt_011CZkZDLs7fYzm1hXNPeRjv", "display_name": "Example credential" } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=" } ``` ### Get Credential `beta.vaults.credentials.retrieve(credential_id, **kwargs) -> BetaManagedAgentsCredential` **GET** `/v1/vaults/{vault_id}/credentials/{credential_id}` Get Credential #### Parameters - `vault_id: str` (path parameter) Identifier of the vault containing the credential. - `credential_id: str` (path parameter) Unique identifier of the credential to retrieve. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsCredential` A credential stored in a vault. Sensitive fields are never returned in responses. - `type: Literal["vault_credential"]` - `id: str` Unique identifier for the credential. - `archived_at: Optional[datetime]` When the credential was archived. Null if not archived. format: date-time - `auth: Auth` Authentication configuration for this credential. - `class BetaManagedAgentsMCPOAuthAuthResponse` OAuth credential details for an MCP server. - `type: Literal["mcp_oauth"]` - `mcp_server_url: str` URL of the MCP server this credential authenticates against. - `expires_at: Optional[datetime]` A timestamp in RFC 3339 format format: date-time - `refresh: Optional[BetaManagedAgentsMCPOAuthRefreshResponse]` Refresh token configuration, if the credential supports token refresh. - `client_id: str` OAuth client ID. - `token_endpoint: str` Token endpoint URL used to refresh the access token. - `token_endpoint_auth: TokenEndpointAuth` - `class BetaManagedAgentsTokenEndpointAuthNoneResponse` Token endpoint requires no client authentication. - `type: Literal["none"]` - `class BetaManagedAgentsTokenEndpointAuthBasicResponse` Token endpoint uses HTTP Basic authentication with client credentials. - `type: Literal["client_secret_basic"]` - `class BetaManagedAgentsTokenEndpointAuthPostResponse` Token endpoint uses POST body authentication with client credentials. - `type: Literal["client_secret_post"]` - `resource: Optional[str]` OAuth resource indicator. - `scope: Optional[str]` OAuth scope for the refresh request. - `class BetaManagedAgentsStaticBearerAuthResponse` Static bearer token credential details for an MCP server. - `type: Literal["static_bearer"]` - `mcp_server_url: str` URL of the MCP server this credential authenticates against. - `class BetaManagedAgentsEnvironmentVariableAuthResponse` Environment variable credential details. The secret value is never returned. - `type: Literal["environment_variable"]` - `injection_location: BetaManagedAgentsInjectionLocationResponse` Where in the outbound request the secret value is substituted. - `body: bool` Whether the placeholder is substituted in the request body. - `header: bool` Whether the placeholder is substituted in request header values. - `networking: Networking` Outbound hosts the secret value is substituted on. - `class BetaManagedAgentsUnrestrictedCredentialNetworkingResponse` The secret is substituted on any host the session's Environment network policy permits egress to. - `type: Literal["unrestricted"]` - `class BetaManagedAgentsLimitedCredentialNetworkingResponse` The secret is substituted only on requests to the listed hosts. - `type: Literal["limited"]` - `allowed_hosts: List[str]` Hostnames on which the secret will be substituted. An entry matches the request host exactly; a `*.`-prefixed entry matches any subdomain of the named domain but not the domain itself. - `secret_name: str` Name of the environment variable. - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `metadata: Dict[str, str]` Arbitrary key-value metadata attached to the credential. - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `vault_id: str` Identifier of the vault this credential belongs to. - `display_name: Optional[str]` Human-readable name for the credential. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_credential = client.beta.vaults.credentials.retrieve( credential_id="vcrd_011CZkZEMt8gZan2iYPQfSkw", vault_id="vlt_011CZkZDLs7fYzm1hXNPeRjv", ) print(beta_managed_agents_credential.id) ``` ##### Response (200) ```json { "id": "vcrd_011CZkZEMt8gZan2iYPQfSkw", "archived_at": null, "auth": { "mcp_server_url": "https://example-server.modelcontextprotocol.io/sse", "type": "static_bearer" }, "created_at": "2026-03-15T10:00:00Z", "metadata": { "environment": "production" }, "type": "vault_credential", "updated_at": "2026-03-15T10:00:00Z", "vault_id": "vlt_011CZkZDLs7fYzm1hXNPeRjv", "display_name": "Example credential" } ``` ### Update Credential `beta.vaults.credentials.update(credential_id, **kwargs) -> BetaManagedAgentsCredential` **POST** `/v1/vaults/{vault_id}/credentials/{credential_id}` Update Credential #### Parameters - `vault_id: str` (path parameter) Identifier of the vault containing the credential. - `credential_id: str` (path parameter) Unique identifier of the credential to update. - `auth: Optional[Auth]` Updated authentication configuration. The `type` is immutable; the variant sent must match the stored credential's type. - `class BetaManagedAgentsMCPOAuthUpdateParams` Parameters for updating an MCP OAuth credential. The `mcp_server_url` is immutable. - `type: Literal["mcp_oauth"]` - `access_token: Optional[str]` Updated OAuth access token. minLength: 1, maxLength: 8192 - `expires_at: Optional[datetime]` A timestamp in RFC 3339 format format: date-time - `refresh: Optional[BetaManagedAgentsMCPOAuthRefreshUpdateParams]` Updated refresh token configuration. - `refresh_token: Optional[str]` Updated OAuth refresh token. minLength: 1, maxLength: 8192 - `scope: Optional[str]` Updated OAuth scope for the refresh request. maxLength: 8192 - `token_endpoint_auth: Optional[TokenEndpointAuth]` - `class BetaManagedAgentsTokenEndpointAuthBasicUpdateParam` Updated HTTP Basic authentication parameters for the token endpoint. - `type: Literal["client_secret_basic"]` - `client_secret: Optional[str]` Updated OAuth client secret. minLength: 1, maxLength: 512 - `class BetaManagedAgentsTokenEndpointAuthPostUpdateParam` Updated POST body authentication parameters for the token endpoint. - `type: Literal["client_secret_post"]` - `client_secret: Optional[str]` Updated OAuth client secret. minLength: 1, maxLength: 512 - `class BetaManagedAgentsStaticBearerUpdateParams` Parameters for updating a static bearer token credential. The `mcp_server_url` is immutable. - `type: Literal["static_bearer"]` - `token: Optional[str]` Updated static bearer token value. minLength: 1, maxLength: 8192 - `class BetaManagedAgentsEnvironmentVariableUpdateParams` Parameters for updating an environment variable credential. `secret_name` is immutable. - `type: Literal["environment_variable"]` - `injection_location: Optional[BetaManagedAgentsInjectionLocationUpdateParams]` Updated injection location. - `body: Optional[bool]` Substitute when the placeholder appears in the request body. - `header: Optional[bool]` Substitute when the placeholder appears in a request header value. - `networking: Optional[BetaManagedAgentsCredentialNetworkingParams]` Updated networking scope. Full replacement. - `class BetaManagedAgentsUnrestrictedCredentialNetworkingParams` Substitute the secret on any host the session's Environment network policy permits egress to. The Environment's network policy is the only boundary on where the secret can reach. - `type: Literal["unrestricted"]` - `class BetaManagedAgentsLimitedCredentialNetworkingParams` Substitute the secret only on requests to the listed hosts. - `type: Literal["limited"]` - `allowed_hosts: List[str]` Hostnames on which the secret will be substituted. Each entry is a bare hostname (`api.example.com`), an IPv4 address (`192.0.2.1`), or a `*.`-prefixed wildcard (`*.example.com`). URLs, ports, paths, and IPv6 addresses are not accepted. At most 16 entries. - `secret_value: Optional[str]` Updated secret value. minLength: 1, maxLength: 4096 - `display_name: Optional[str]` Updated human-readable name for the credential. 1-255 characters. minLength: 1, maxLength: 255 - `metadata: Optional[Dict[str, Optional[str]]]` Metadata patch. Set a key to a string to upsert it, or to null to delete it. Omitted keys are preserved. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsCredential` A credential stored in a vault. Sensitive fields are never returned in responses. - `type: Literal["vault_credential"]` - `id: str` Unique identifier for the credential. - `archived_at: Optional[datetime]` When the credential was archived. Null if not archived. format: date-time - `auth: Auth` Authentication configuration for this credential. - `class BetaManagedAgentsMCPOAuthAuthResponse` OAuth credential details for an MCP server. - `type: Literal["mcp_oauth"]` - `mcp_server_url: str` URL of the MCP server this credential authenticates against. - `expires_at: Optional[datetime]` A timestamp in RFC 3339 format format: date-time - `refresh: Optional[BetaManagedAgentsMCPOAuthRefreshResponse]` Refresh token configuration, if the credential supports token refresh. - `client_id: str` OAuth client ID. - `token_endpoint: str` Token endpoint URL used to refresh the access token. - `token_endpoint_auth: TokenEndpointAuth` - `class BetaManagedAgentsTokenEndpointAuthNoneResponse` Token endpoint requires no client authentication. - `type: Literal["none"]` - `class BetaManagedAgentsTokenEndpointAuthBasicResponse` Token endpoint uses HTTP Basic authentication with client credentials. - `type: Literal["client_secret_basic"]` - `class BetaManagedAgentsTokenEndpointAuthPostResponse` Token endpoint uses POST body authentication with client credentials. - `type: Literal["client_secret_post"]` - `resource: Optional[str]` OAuth resource indicator. - `scope: Optional[str]` OAuth scope for the refresh request. - `class BetaManagedAgentsStaticBearerAuthResponse` Static bearer token credential details for an MCP server. - `type: Literal["static_bearer"]` - `mcp_server_url: str` URL of the MCP server this credential authenticates against. - `class BetaManagedAgentsEnvironmentVariableAuthResponse` Environment variable credential details. The secret value is never returned. - `type: Literal["environment_variable"]` - `injection_location: BetaManagedAgentsInjectionLocationResponse` Where in the outbound request the secret value is substituted. - `body: bool` Whether the placeholder is substituted in the request body. - `header: bool` Whether the placeholder is substituted in request header values. - `networking: Networking` Outbound hosts the secret value is substituted on. - `class BetaManagedAgentsUnrestrictedCredentialNetworkingResponse` The secret is substituted on any host the session's Environment network policy permits egress to. - `type: Literal["unrestricted"]` - `class BetaManagedAgentsLimitedCredentialNetworkingResponse` The secret is substituted only on requests to the listed hosts. - `type: Literal["limited"]` - `allowed_hosts: List[str]` Hostnames on which the secret will be substituted. An entry matches the request host exactly; a `*.`-prefixed entry matches any subdomain of the named domain but not the domain itself. - `secret_name: str` Name of the environment variable. - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `metadata: Dict[str, str]` Arbitrary key-value metadata attached to the credential. - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `vault_id: str` Identifier of the vault this credential belongs to. - `display_name: Optional[str]` Human-readable name for the credential. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_credential = client.beta.vaults.credentials.update( credential_id="vcrd_011CZkZEMt8gZan2iYPQfSkw", vault_id="vlt_011CZkZDLs7fYzm1hXNPeRjv", ) print(beta_managed_agents_credential.id) ``` ##### Response (200) ```json { "id": "vcrd_011CZkZEMt8gZan2iYPQfSkw", "archived_at": null, "auth": { "mcp_server_url": "https://example-server.modelcontextprotocol.io/sse", "type": "static_bearer" }, "created_at": "2026-03-15T10:00:00Z", "metadata": { "environment": "production" }, "type": "vault_credential", "updated_at": "2026-03-15T10:00:00Z", "vault_id": "vlt_011CZkZDLs7fYzm1hXNPeRjv", "display_name": "Example credential" } ``` ### Delete Credential `beta.vaults.credentials.delete(credential_id, **kwargs) -> BetaManagedAgentsDeletedCredential` **DELETE** `/v1/vaults/{vault_id}/credentials/{credential_id}` Delete Credential #### Parameters - `vault_id: str` (path parameter) Identifier of the vault containing the credential. - `credential_id: str` (path parameter) Unique identifier of the credential to delete. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeletedCredential` Confirmation of a deleted credential. - `type: Literal["vault_credential_deleted"]` - `id: str` Unique identifier of the deleted credential. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deleted_credential = client.beta.vaults.credentials.delete( credential_id="vcrd_011CZkZEMt8gZan2iYPQfSkw", vault_id="vlt_011CZkZDLs7fYzm1hXNPeRjv", ) print(beta_managed_agents_deleted_credential.id) ``` ##### Response (200) ```json { "id": "vcrd_011CZkZEMt8gZan2iYPQfSkw", "type": "vault_credential_deleted" } ``` ### Archive Credential `beta.vaults.credentials.archive(credential_id, **kwargs) -> BetaManagedAgentsCredential` **POST** `/v1/vaults/{vault_id}/credentials/{credential_id}/archive` Archive Credential #### Parameters - `vault_id: str` (path parameter) Identifier of the vault containing the credential. - `credential_id: str` (path parameter) Unique identifier of the credential to archive. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsCredential` A credential stored in a vault. Sensitive fields are never returned in responses. - `type: Literal["vault_credential"]` - `id: str` Unique identifier for the credential. - `archived_at: Optional[datetime]` When the credential was archived. Null if not archived. format: date-time - `auth: Auth` Authentication configuration for this credential. - `class BetaManagedAgentsMCPOAuthAuthResponse` OAuth credential details for an MCP server. - `type: Literal["mcp_oauth"]` - `mcp_server_url: str` URL of the MCP server this credential authenticates against. - `expires_at: Optional[datetime]` A timestamp in RFC 3339 format format: date-time - `refresh: Optional[BetaManagedAgentsMCPOAuthRefreshResponse]` Refresh token configuration, if the credential supports token refresh. - `client_id: str` OAuth client ID. - `token_endpoint: str` Token endpoint URL used to refresh the access token. - `token_endpoint_auth: TokenEndpointAuth` - `class BetaManagedAgentsTokenEndpointAuthNoneResponse` Token endpoint requires no client authentication. - `type: Literal["none"]` - `class BetaManagedAgentsTokenEndpointAuthBasicResponse` Token endpoint uses HTTP Basic authentication with client credentials. - `type: Literal["client_secret_basic"]` - `class BetaManagedAgentsTokenEndpointAuthPostResponse` Token endpoint uses POST body authentication with client credentials. - `type: Literal["client_secret_post"]` - `resource: Optional[str]` OAuth resource indicator. - `scope: Optional[str]` OAuth scope for the refresh request. - `class BetaManagedAgentsStaticBearerAuthResponse` Static bearer token credential details for an MCP server. - `type: Literal["static_bearer"]` - `mcp_server_url: str` URL of the MCP server this credential authenticates against. - `class BetaManagedAgentsEnvironmentVariableAuthResponse` Environment variable credential details. The secret value is never returned. - `type: Literal["environment_variable"]` - `injection_location: BetaManagedAgentsInjectionLocationResponse` Where in the outbound request the secret value is substituted. - `body: bool` Whether the placeholder is substituted in the request body. - `header: bool` Whether the placeholder is substituted in request header values. - `networking: Networking` Outbound hosts the secret value is substituted on. - `class BetaManagedAgentsUnrestrictedCredentialNetworkingResponse` The secret is substituted on any host the session's Environment network policy permits egress to. - `type: Literal["unrestricted"]` - `class BetaManagedAgentsLimitedCredentialNetworkingResponse` The secret is substituted only on requests to the listed hosts. - `type: Literal["limited"]` - `allowed_hosts: List[str]` Hostnames on which the secret will be substituted. An entry matches the request host exactly; a `*.`-prefixed entry matches any subdomain of the named domain but not the domain itself. - `secret_name: str` Name of the environment variable. - `created_at: datetime` A timestamp in RFC 3339 format format: date-time - `metadata: Dict[str, str]` Arbitrary key-value metadata attached to the credential. - `updated_at: datetime` A timestamp in RFC 3339 format format: date-time - `vault_id: str` Identifier of the vault this credential belongs to. - `display_name: Optional[str]` Human-readable name for the credential. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_credential = client.beta.vaults.credentials.archive( credential_id="vcrd_011CZkZEMt8gZan2iYPQfSkw", vault_id="vlt_011CZkZDLs7fYzm1hXNPeRjv", ) print(beta_managed_agents_credential.id) ``` ##### Response (200) ```json { "id": "vcrd_011CZkZEMt8gZan2iYPQfSkw", "archived_at": null, "auth": { "mcp_server_url": "https://example-server.modelcontextprotocol.io/sse", "type": "static_bearer" }, "created_at": "2026-03-15T10:00:00Z", "metadata": { "environment": "production" }, "type": "vault_credential", "updated_at": "2026-03-15T10:00:00Z", "vault_id": "vlt_011CZkZDLs7fYzm1hXNPeRjv", "display_name": "Example credential" } ``` ### Validate Credential `beta.vaults.credentials.mcp_oauth_validate(credential_id, **kwargs) -> BetaManagedAgentsCredentialValidation` **POST** `/v1/vaults/{vault_id}/credentials/{credential_id}/mcp_oauth_validate` Validate Credential #### Parameters - `vault_id: str` (path parameter) Identifier of the vault containing the credential. - `credential_id: str` (path parameter) Unique identifier of the credential to validate. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsCredentialValidation` Result of live-probing a credential against its configured MCP server. - `type: Literal["vault_credential_validation"]` - `credential_id: str` Unique identifier of the credential that was validated. - `has_refresh_token: bool` Whether the credential has a refresh token configured. - `mcp_probe: Optional[BetaManagedAgentsMCPProbe]` Details of the failing MCP probe step. Null when the probe succeeded. - `http_response: Optional[BetaManagedAgentsRefreshHTTPResponse]` The captured HTTP error response. Null when no HTTP response was received (timeout, DNS, TLS). - `body: str` Response body. May be truncated and has sensitive values scrubbed. - `body_truncated: bool` Whether `body` was truncated. - `content_type: str` Value of the `Content-Type` response header. - `status_code: int` HTTP status code. format: int32 - `method: str` The MCP method that failed (for example `initialize` or `tools/list`). - `refresh: Optional[BetaManagedAgentsRefreshObject]` Details of the refresh-token exchange attempted on a 401. Null when no refresh was attempted. - `http_response: Optional[BetaManagedAgentsRefreshHTTPResponse]` The captured HTTP error response from the token endpoint. Populated only when `status` is `failed`. - `status: Literal["succeeded", "failed", "connect_error", "no_refresh_token"]` Outcome of the refresh attempt. - `"succeeded"` The token endpoint returned a new access token. - `"failed"` The token endpoint returned an error response. See `http_response` for detail. - `"connect_error"` The token endpoint could not be reached (DNS, TLS, or connection error). - `"no_refresh_token"` No refresh token is stored for the credential, so no exchange was attempted. - `status: BetaManagedAgentsCredentialValidationStatus` Overall verdict of the validation probe. - `"valid"` The credential successfully authenticated against its MCP server. - `"invalid"` The probe reached the MCP server and was rejected, and a refresh (if attempted) did not recover it. - `"unknown"` The probe could not determine validity — for example, a transport error or a successful refresh that was not re-probed. - `validated_at: datetime` When the validation probe was performed. format: date-time - `vault_id: str` Identifier of the vault containing the credential. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_credential_validation = ( client.beta.vaults.credentials.mcp_oauth_validate( credential_id="vcrd_011CZkZEMt8gZan2iYPQfSkw", vault_id="vlt_011CZkZDLs7fYzm1hXNPeRjv", ) ) print(beta_managed_agents_credential_validation.credential_id) ``` ##### Response (200) ```json { "credential_id": "vcrd_011CZkZEMt8gZan2iYPQfSkw", "has_refresh_token": true, "mcp_probe": { "http_response": { "body": "body", "body_truncated": true, "content_type": "content_type", "status_code": 0 }, "method": "method" }, "refresh": { "http_response": { "body": "body", "body_truncated": true, "content_type": "content_type", "status_code": 0 }, "status": "succeeded" }, "status": "valid", "type": "vault_credential_validation", "validated_at": "2026-03-15T10:00:00Z", "vault_id": "vlt_011CZkZDLs7fYzm1hXNPeRjv" } ``` ## Beta › Memory Stores ### Create a memory store `beta.memory_stores.create(**kwargs) -> BetaManagedAgentsMemoryStore` **POST** `/v1/memory_stores` Create a memory store #### Parameters - `name: str` Human-readable name for the store. Required; 1–255 characters; no control characters. The mount-path slug under `/mnt/memory/` is derived from this name (lowercased, non-alphanumeric runs collapsed to a hyphen). Names need not be unique within a workspace. minLength: 1, maxLength: 255 - `description: Optional[str]` Free-text description of what the store contains, up to 1024 characters. Included in the agent's system prompt when the store is attached, so word it to be useful to the agent. maxLength: 1024 - `metadata: Optional[Dict[str, str]]` Arbitrary key-value tags for your own bookkeeping (such as the end user a store belongs to). Up to 16 pairs; keys 1–64 characters; values up to 512 characters. Not visible to the agent. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsMemoryStore` A `memory_store`: a named container for agent memories, scoped to a workspace. Attach a store to a session via `resources[]` to mount it as a directory the agent can read and write. - `type: Literal["memory_store"]` - `id: str` Unique identifier for the memory store (a `memstore_...` tagged ID). Use this when attaching the store to a session, or in the `{memory_store_id}` path parameter of subsequent calls. - `archived_at: Optional[datetime]` Timestamp when the store was archived, or `null` if active. Set once and never cleared; archiving is one-way. Archived stores are read-only and cannot be attached to new sessions. format: date-time - `created_at: datetime` Timestamp when the store was created. format: date-time - `description: str` Free-text description of what the store contains, up to 1024 characters. Included in the agent's system prompt when the store is attached, so word it to be useful to the agent. Empty string when unset. - `metadata: Dict[str, str]` Arbitrary key-value tags for your own bookkeeping (such as the end user a store belongs to). Up to 16 pairs; keys 1–64 characters; values up to 512 characters. Returned on retrieve/list but not filterable. - `name: str` Human-readable name for the store. 1–255 characters. The store's mount-path slug under `/mnt/memory/` is derived from this name. - `updated_at: datetime` Timestamp when the store's `name`, `description`, or `metadata` was last modified. Memory writes inside the store do not advance this. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_memory_store = client.beta.memory_stores.create( name="x", ) print(beta_managed_agents_memory_store.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "description": "description", "metadata": { "foo": "string" }, "name": "name", "type": "memory_store", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ### List memory stores `beta.memory_stores.list(**kwargs) -> SyncPageCursor[BetaManagedAgentsMemoryStore]` **GET** `/v1/memory_stores` List memory stores #### Parameters - `created_at_gte: Optional[Union[str, datetime]]` (query parameter) Return only stores whose `created_at` is at or after this time (inclusive). Sent on the wire as `created_at[gte]`. format: date-time - `created_at_lte: Optional[Union[str, datetime]]` (query parameter) Return only stores whose `created_at` is at or before this time (inclusive). Sent on the wire as `created_at[lte]`. format: date-time - `include_archived: Optional[bool]` (query parameter) When `true`, archived stores are included in the results. Defaults to `false` (archived stores are excluded). - `limit: Optional[int]` (query parameter) Maximum number of stores to return per page. Must be between 1 and 100. Defaults to 20 when omitted. format: int32 - `page: Optional[str]` (query parameter) Opaque pagination cursor (a `page_...` value). Pass the `next_page` value from a previous response to fetch the next page; omit for the first page. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsMemoryStore` A `memory_store`: a named container for agent memories, scoped to a workspace. Attach a store to a session via `resources[]` to mount it as a directory the agent can read and write. - `type: Literal["memory_store"]` - `id: str` Unique identifier for the memory store (a `memstore_...` tagged ID). Use this when attaching the store to a session, or in the `{memory_store_id}` path parameter of subsequent calls. - `archived_at: Optional[datetime]` Timestamp when the store was archived, or `null` if active. Set once and never cleared; archiving is one-way. Archived stores are read-only and cannot be attached to new sessions. format: date-time - `created_at: datetime` Timestamp when the store was created. format: date-time - `description: str` Free-text description of what the store contains, up to 1024 characters. Included in the agent's system prompt when the store is attached, so word it to be useful to the agent. Empty string when unset. - `metadata: Dict[str, str]` Arbitrary key-value tags for your own bookkeeping (such as the end user a store belongs to). Up to 16 pairs; keys 1–64 characters; values up to 512 characters. Returned on retrieve/list but not filterable. - `name: str` Human-readable name for the store. 1–255 characters. The store's mount-path slug under `/mnt/memory/` is derived from this name. - `updated_at: datetime` Timestamp when the store's `name`, `description`, or `metadata` was last modified. Memory writes inside the store do not advance this. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.memory_stores.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "memstore_01Wf3kQ8tZxB2mVr7HcJ4aNd", "archived_at": null, "created_at": "2026-03-15T10:00:00Z", "description": "Per-user preferences and project context.", "metadata": {}, "name": "User Preferences", "type": "memory_store", "updated_at": "2026-03-15T10:00:00Z" } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=" } ``` ### Retrieve a memory store `beta.memory_stores.retrieve(memory_store_id, **kwargs) -> BetaManagedAgentsMemoryStore` **GET** `/v1/memory_stores/{memory_store_id}` Retrieve a memory store #### Parameters - `memory_store_id: str` (path parameter) ID of the memory store to retrieve (a `memstore_...` identifier). Required. Enumerate IDs via `GET /v1/memory_stores`. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsMemoryStore` A `memory_store`: a named container for agent memories, scoped to a workspace. Attach a store to a session via `resources[]` to mount it as a directory the agent can read and write. - `type: Literal["memory_store"]` - `id: str` Unique identifier for the memory store (a `memstore_...` tagged ID). Use this when attaching the store to a session, or in the `{memory_store_id}` path parameter of subsequent calls. - `archived_at: Optional[datetime]` Timestamp when the store was archived, or `null` if active. Set once and never cleared; archiving is one-way. Archived stores are read-only and cannot be attached to new sessions. format: date-time - `created_at: datetime` Timestamp when the store was created. format: date-time - `description: str` Free-text description of what the store contains, up to 1024 characters. Included in the agent's system prompt when the store is attached, so word it to be useful to the agent. Empty string when unset. - `metadata: Dict[str, str]` Arbitrary key-value tags for your own bookkeeping (such as the end user a store belongs to). Up to 16 pairs; keys 1–64 characters; values up to 512 characters. Returned on retrieve/list but not filterable. - `name: str` Human-readable name for the store. 1–255 characters. The store's mount-path slug under `/mnt/memory/` is derived from this name. - `updated_at: datetime` Timestamp when the store's `name`, `description`, or `metadata` was last modified. Memory writes inside the store do not advance this. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_memory_store = client.beta.memory_stores.retrieve( memory_store_id="memory_store_id", ) print(beta_managed_agents_memory_store.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "description": "description", "metadata": { "foo": "string" }, "name": "name", "type": "memory_store", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ### Update a memory store `beta.memory_stores.update(memory_store_id, **kwargs) -> BetaManagedAgentsMemoryStore` **POST** `/v1/memory_stores/{memory_store_id}` Update a memory store #### Parameters - `memory_store_id: str` (path parameter) ID of the memory store to update (a `memstore_...` identifier). Required. Enumerate IDs via `GET /v1/memory_stores`. Updating an archived store returns 400. - `description: Optional[str]` New description for the store, up to 1024 characters. Pass an empty string to clear it. maxLength: 1024 - `metadata: Optional[Dict[str, Optional[str]]]` Metadata patch. Set a key to a string to upsert it, or to null to delete it. Omit the field to preserve. The stored bag is limited to 16 keys (up to 64 chars each) with values up to 512 chars. - `name: Optional[str]` New human-readable name for the store. 1–255 characters; no control characters. Renaming changes the slug used for the store's `mount_path` in sessions created after the update. minLength: 1, maxLength: 255 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsMemoryStore` A `memory_store`: a named container for agent memories, scoped to a workspace. Attach a store to a session via `resources[]` to mount it as a directory the agent can read and write. - `type: Literal["memory_store"]` - `id: str` Unique identifier for the memory store (a `memstore_...` tagged ID). Use this when attaching the store to a session, or in the `{memory_store_id}` path parameter of subsequent calls. - `archived_at: Optional[datetime]` Timestamp when the store was archived, or `null` if active. Set once and never cleared; archiving is one-way. Archived stores are read-only and cannot be attached to new sessions. format: date-time - `created_at: datetime` Timestamp when the store was created. format: date-time - `description: str` Free-text description of what the store contains, up to 1024 characters. Included in the agent's system prompt when the store is attached, so word it to be useful to the agent. Empty string when unset. - `metadata: Dict[str, str]` Arbitrary key-value tags for your own bookkeeping (such as the end user a store belongs to). Up to 16 pairs; keys 1–64 characters; values up to 512 characters. Returned on retrieve/list but not filterable. - `name: str` Human-readable name for the store. 1–255 characters. The store's mount-path slug under `/mnt/memory/` is derived from this name. - `updated_at: datetime` Timestamp when the store's `name`, `description`, or `metadata` was last modified. Memory writes inside the store do not advance this. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_memory_store = client.beta.memory_stores.update( memory_store_id="memory_store_id", ) print(beta_managed_agents_memory_store.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "description": "description", "metadata": { "foo": "string" }, "name": "name", "type": "memory_store", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ### Delete a memory store `beta.memory_stores.delete(memory_store_id, **kwargs) -> BetaManagedAgentsDeletedMemoryStore` **DELETE** `/v1/memory_stores/{memory_store_id}` Delete a memory store #### Parameters - `memory_store_id: str` (path parameter) ID of the memory store to permanently delete (a `memstore_...` identifier). Required. Deletion cascades to all memories and memory versions in the store and cannot be undone. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeletedMemoryStore` Confirmation that a `memory_store` was deleted. - `type: Literal["memory_store_deleted"]` - `id: str` ID of the deleted memory store (a `memstore_...` identifier). The store and all its memories and versions are no longer retrievable. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deleted_memory_store = client.beta.memory_stores.delete( memory_store_id="memory_store_id", ) print(beta_managed_agents_deleted_memory_store.id) ``` ##### Response (200) ```json { "id": "id", "type": "memory_store_deleted" } ``` ### Archive a memory store `beta.memory_stores.archive(memory_store_id, **kwargs) -> BetaManagedAgentsMemoryStore` **POST** `/v1/memory_stores/{memory_store_id}/archive` Archive a memory store #### Parameters - `memory_store_id: str` (path parameter) ID of the memory store to archive (a `memstore_...` identifier). Required. Archiving is one-way and idempotent; archived stores cannot be unarchived. Enumerate IDs via `GET /v1/memory_stores`. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsMemoryStore` A `memory_store`: a named container for agent memories, scoped to a workspace. Attach a store to a session via `resources[]` to mount it as a directory the agent can read and write. - `type: Literal["memory_store"]` - `id: str` Unique identifier for the memory store (a `memstore_...` tagged ID). Use this when attaching the store to a session, or in the `{memory_store_id}` path parameter of subsequent calls. - `archived_at: Optional[datetime]` Timestamp when the store was archived, or `null` if active. Set once and never cleared; archiving is one-way. Archived stores are read-only and cannot be attached to new sessions. format: date-time - `created_at: datetime` Timestamp when the store was created. format: date-time - `description: str` Free-text description of what the store contains, up to 1024 characters. Included in the agent's system prompt when the store is attached, so word it to be useful to the agent. Empty string when unset. - `metadata: Dict[str, str]` Arbitrary key-value tags for your own bookkeeping (such as the end user a store belongs to). Up to 16 pairs; keys 1–64 characters; values up to 512 characters. Returned on retrieve/list but not filterable. - `name: str` Human-readable name for the store. 1–255 characters. The store's mount-path slug under `/mnt/memory/` is derived from this name. - `updated_at: datetime` Timestamp when the store's `name`, `description`, or `metadata` was last modified. Memory writes inside the store do not advance this. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_memory_store = client.beta.memory_stores.archive( memory_store_id="memory_store_id", ) print(beta_managed_agents_memory_store.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "description": "description", "metadata": { "foo": "string" }, "name": "name", "type": "memory_store", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ## Beta › Memory Stores › Memories ### Create a memory `beta.memory_stores.memories.create(memory_store_id, **kwargs) -> BetaManagedAgentsMemory` **POST** `/v1/memory_stores/{memory_store_id}/memories` Create a memory #### Parameters - `memory_store_id: str` (path parameter) The ID of the memory store to create the memory in (`memstore_...`). - `content: Optional[str]` UTF-8 text content for the new memory. Maximum 100 kB (102,400 bytes). Required; pass `""` explicitly to create an empty memory. - `path: str` Hierarchical path for the new memory, e.g. `/projects/foo/notes.md`. Must start with `/`, contain at least one non-empty segment, and be at most 1,024 bytes. Must not contain empty segments, `.` or `..` segments, control or format characters, or the Unicode line and paragraph separators (U+2028, U+2029), and must be NFC-normalized. Paths are case-sensitive. minLength: 2, maxLength: 1024 - `view: Optional[BetaManagedAgentsMemoryView]` (query parameter) Selects which projection of a `memory` or `memory_version` the server returns. `basic` returns the object with `content` set to `null`; `full` populates `content`. When omitted, the default is endpoint-specific: retrieve operations default to `full`; list, create, and update operations default to `basic`. Listing with `view=full` caps `limit` at 20. - `"basic"` Return the object with `content` set to `null`. The `content_size_bytes` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps `limit` at 20. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsMemory` A `memory` object: a single text document at a hierarchical path inside a memory store. The `content` field is populated when `view=full` and `null` when `view=basic`; the `content_size_bytes` and `content_sha256` fields are always populated so sync clients can diff without fetching content. Memories are addressed by their `mem_...` ID; the path is the create key and can be changed via update. - `type: Literal["memory"]` - `id: str` Unique identifier for this memory (a `mem_...` value). Stable across renames; use this ID, not the path, to read, update, or delete the memory. - `content_sha256: str` Lowercase hex SHA-256 digest of the UTF-8 `content` bytes (64 characters). The server applies no normalization, so clients can compute the same hash locally for staleness checks and as the value for a `content_sha256` precondition on update. Always populated, regardless of `view`. - `content_size_bytes: int` Size of `content` in bytes (the UTF-8 plaintext length). Always populated, regardless of `view`. format: int32 - `created_at: datetime` When this memory was created, in RFC 3339 format. format: date-time - `memory_store_id: str` ID of the memory store this memory belongs to (a `memstore_...` value). - `memory_version_id: str` ID of the `memory_version` representing this memory's current content (a `memver_...` value). This is the authoritative head pointer; `memory_version` objects do not carry an `is_latest` flag, so compare against this field instead. Enumerate the history via [List memory versions](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/list?sdk_languages=python). - `path: str` Hierarchical path of the memory within the store, e.g. `/projects/foo/notes.md`. Always starts with `/`. Paths are case-sensitive and unique within a store. Maximum 1,024 bytes. - `updated_at: datetime` When this memory was last modified, in RFC 3339 format. Use this as a cheap freshness signal; for who made the change, look up the head version's `created_by` via [List memory versions](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/list?sdk_languages=python). format: date-time - `content: Optional[str]` The memory's UTF-8 text content. Populated when `view=full`; `null` when `view=basic`. Maximum 100 kB (102,400 bytes). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_memory = client.beta.memory_stores.memories.create( memory_store_id="memory_store_id", content="content", path="xx", ) print(beta_managed_agents_memory.id) ``` ##### Response (200) ```json { "id": "id", "content_sha256": "content_sha256", "content_size_bytes": 0, "created_at": "2019-12-27T18:11:19.117Z", "memory_store_id": "memory_store_id", "memory_version_id": "memory_version_id", "path": "path", "type": "memory", "updated_at": "2019-12-27T18:11:19.117Z", "content": "content" } ``` ### List memories `beta.memory_stores.memories.list(memory_store_id, **kwargs) -> SyncPageCursor[BetaManagedAgentsMemoryListItem]` **GET** `/v1/memory_stores/{memory_store_id}/memories` List memories #### Parameters - `memory_store_id: str` (path parameter) The ID of the memory store to list memories from (`memstore_...`). - `depth: Optional[int]` (query parameter) `0` (or omitted) returns all descendants below `path_prefix` (recursive). `1` returns immediate children only; deeper entries roll up as `memory_prefix` items. `depth=1` behaves like `ls`; omitting `depth` behaves like `find`. format: int32 - `limit: Optional[int]` (query parameter) Maximum number of items to return per page. Must be between 1 and 100. Defaults to 20 when omitted. Capped at 20 when `view=full`. Both `memory` and `memory_prefix` items count toward the limit. format: int32 - `page: Optional[str]` (query parameter) Opaque pagination cursor (a `page_...` value). Pass the `next_page` value from a previous response to fetch the next page; omit for the first page. - `path_prefix: Optional[str]` (query parameter) Optional path prefix filter. Must end with `/` (segment-aligned), e.g., `/notes/`. This value appears in request URLs. Do not include secrets or personally identifiable information. - `view: Optional[BetaManagedAgentsMemoryView]` (query parameter) Which projection of each `memory` to return. Defaults to `basic` (content omitted). `full` populates `content` on each item and caps `limit` at 20; use this as the bulk-read path for export and sync. - `"basic"` Return the object with `content` set to `null`. The `content_size_bytes` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps `limit` at 20. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `type BetaManagedAgentsMemoryListItem = ...` One item in a [List memories](https://platform.claude.com/docs/en/api/beta/memory_stores/memories/list?sdk_languages=python) response: either a `memory` object or, when `depth` is set, a `memory_prefix` rollup marker. - `class BetaManagedAgentsMemory` A `memory` object: a single text document at a hierarchical path inside a memory store. The `content` field is populated when `view=full` and `null` when `view=basic`; the `content_size_bytes` and `content_sha256` fields are always populated so sync clients can diff without fetching content. Memories are addressed by their `mem_...` ID; the path is the create key and can be changed via update. - `type: Literal["memory"]` - `id: str` Unique identifier for this memory (a `mem_...` value). Stable across renames; use this ID, not the path, to read, update, or delete the memory. - `content_sha256: str` Lowercase hex SHA-256 digest of the UTF-8 `content` bytes (64 characters). The server applies no normalization, so clients can compute the same hash locally for staleness checks and as the value for a `content_sha256` precondition on update. Always populated, regardless of `view`. - `content_size_bytes: int` Size of `content` in bytes (the UTF-8 plaintext length). Always populated, regardless of `view`. format: int32 - `created_at: datetime` When this memory was created, in RFC 3339 format. format: date-time - `memory_store_id: str` ID of the memory store this memory belongs to (a `memstore_...` value). - `memory_version_id: str` ID of the `memory_version` representing this memory's current content (a `memver_...` value). This is the authoritative head pointer; `memory_version` objects do not carry an `is_latest` flag, so compare against this field instead. Enumerate the history via [List memory versions](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/list?sdk_languages=python). - `path: str` Hierarchical path of the memory within the store, e.g. `/projects/foo/notes.md`. Always starts with `/`. Paths are case-sensitive and unique within a store. Maximum 1,024 bytes. - `updated_at: datetime` When this memory was last modified, in RFC 3339 format. Use this as a cheap freshness signal; for who made the change, look up the head version's `created_by` via [List memory versions](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/list?sdk_languages=python). format: date-time - `content: Optional[str]` The memory's UTF-8 text content. Populated when `view=full`; `null` when `view=basic`. Maximum 100 kB (102,400 bytes). - `class BetaManagedAgentsMemoryPrefix` A rolled-up directory marker returned by [List memories](https://platform.claude.com/docs/en/api/beta/memory_stores/memories/list?sdk_languages=python) when `depth` is set. Indicates that one or more memories exist deeper than the requested depth under this prefix. This is a list-time rollup, not a stored resource; it has no ID and no lifecycle. Each prefix counts toward the page `limit` and interleaves with `memory` items in path order. - `type: Literal["memory_prefix"]` - `path: str` The rolled-up path prefix, including a trailing `/` (e.g. `/projects/foo/`). Pass this value as `path_prefix` on a subsequent list call to drill into the directory. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.memory_stores.memories.list( memory_store_id="memory_store_id", ) page = page.data[0] print(page) ``` ##### Response (200) ```json { "data": [ { "id": "mem_011CZkZ9X2dpNyB6YbtxvB6e", "content_sha256": "ba7936d94c84d948a2232088f78228f175df6a8353b2d5bc9228eee5794a0024", "content_size_bytes": 28, "created_at": "2026-03-15T10:00:00Z", "memory_store_id": "memstore_01Wf3kQ8tZxB2mVr7HcJ4aNd", "memory_version_id": "memver_011CZkZBJq5dWxk9fVLNcPht", "path": "/preferences/formatting.md", "type": "memory", "updated_at": "2026-03-15T10:00:00Z", "content": null } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=" } ``` ### Retrieve a memory `beta.memory_stores.memories.retrieve(memory_id, **kwargs) -> BetaManagedAgentsMemory` **GET** `/v1/memory_stores/{memory_store_id}/memories/{memory_id}` Retrieve a memory #### Parameters - `memory_store_id: str` (path parameter) The ID of the memory store that holds the memory (`memstore_...`). - `memory_id: str` (path parameter) The ID of the memory to retrieve (`mem_...`). - `view: Optional[BetaManagedAgentsMemoryView]` (query parameter) Selects which projection of a `memory` or `memory_version` the server returns. `basic` returns the object with `content` set to `null`; `full` populates `content`. When omitted, the default is endpoint-specific: retrieve operations default to `full`; list, create, and update operations default to `basic`. Listing with `view=full` caps `limit` at 20. - `"basic"` Return the object with `content` set to `null`. The `content_size_bytes` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps `limit` at 20. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsMemory` A `memory` object: a single text document at a hierarchical path inside a memory store. The `content` field is populated when `view=full` and `null` when `view=basic`; the `content_size_bytes` and `content_sha256` fields are always populated so sync clients can diff without fetching content. Memories are addressed by their `mem_...` ID; the path is the create key and can be changed via update. - `type: Literal["memory"]` - `id: str` Unique identifier for this memory (a `mem_...` value). Stable across renames; use this ID, not the path, to read, update, or delete the memory. - `content_sha256: str` Lowercase hex SHA-256 digest of the UTF-8 `content` bytes (64 characters). The server applies no normalization, so clients can compute the same hash locally for staleness checks and as the value for a `content_sha256` precondition on update. Always populated, regardless of `view`. - `content_size_bytes: int` Size of `content` in bytes (the UTF-8 plaintext length). Always populated, regardless of `view`. format: int32 - `created_at: datetime` When this memory was created, in RFC 3339 format. format: date-time - `memory_store_id: str` ID of the memory store this memory belongs to (a `memstore_...` value). - `memory_version_id: str` ID of the `memory_version` representing this memory's current content (a `memver_...` value). This is the authoritative head pointer; `memory_version` objects do not carry an `is_latest` flag, so compare against this field instead. Enumerate the history via [List memory versions](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/list?sdk_languages=python). - `path: str` Hierarchical path of the memory within the store, e.g. `/projects/foo/notes.md`. Always starts with `/`. Paths are case-sensitive and unique within a store. Maximum 1,024 bytes. - `updated_at: datetime` When this memory was last modified, in RFC 3339 format. Use this as a cheap freshness signal; for who made the change, look up the head version's `created_by` via [List memory versions](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/list?sdk_languages=python). format: date-time - `content: Optional[str]` The memory's UTF-8 text content. Populated when `view=full`; `null` when `view=basic`. Maximum 100 kB (102,400 bytes). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_memory = client.beta.memory_stores.memories.retrieve( memory_id="memory_id", memory_store_id="memory_store_id", ) print(beta_managed_agents_memory.id) ``` ##### Response (200) ```json { "id": "id", "content_sha256": "content_sha256", "content_size_bytes": 0, "created_at": "2019-12-27T18:11:19.117Z", "memory_store_id": "memory_store_id", "memory_version_id": "memory_version_id", "path": "path", "type": "memory", "updated_at": "2019-12-27T18:11:19.117Z", "content": "content" } ``` ### Update a memory `beta.memory_stores.memories.update(memory_id, **kwargs) -> BetaManagedAgentsMemory` **POST** `/v1/memory_stores/{memory_store_id}/memories/{memory_id}` Update a memory #### Parameters - `memory_store_id: str` (path parameter) The ID of the memory store that holds the memory (`memstore_...`). - `memory_id: str` (path parameter) The ID of the memory to update (`mem_...`). - `view: Optional[BetaManagedAgentsMemoryView]` (query parameter) Selects which projection of a `memory` or `memory_version` the server returns. `basic` returns the object with `content` set to `null`; `full` populates `content`. When omitted, the default is endpoint-specific: retrieve operations default to `full`; list, create, and update operations default to `basic`. Listing with `view=full` caps `limit` at 20. - `"basic"` Return the object with `content` set to `null`. The `content_size_bytes` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps `limit` at 20. - `content: Optional[str]` New UTF-8 text content for the memory. Maximum 100 kB (102,400 bytes). Omit to leave the content unchanged (e.g., for a rename-only update). - `path: Optional[str]` New path for the memory (a rename). Must start with `/`, contain at least one non-empty segment, and be at most 1,024 bytes. Must not contain empty segments, `.` or `..` segments, control or format characters, or the Unicode line and paragraph separators (U+2028, U+2029), and must be NFC-normalized. Paths are case-sensitive. The memory's `id` is preserved across renames. Omit to leave the path unchanged. minLength: 2, maxLength: 1024 - `precondition: Optional[BetaManagedAgentsPreconditionParam]` Optional optimistic-concurrency precondition. When supplied, the update applies only if the memory's current state matches; on mismatch the request returns `memory_precondition_failed_error` (HTTP 409). When omitted, the update is unconditional. - `type: Literal["content_sha256"]` - `content_sha256: Optional[str]` Expected `content_sha256` of the stored memory (64 lowercase hexadecimal characters). Typically the `content_sha256` returned by a prior read or list call. Because the server applies no content normalization, clients can also compute this locally as the SHA-256 of the UTF-8 content bytes. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsMemory` A `memory` object: a single text document at a hierarchical path inside a memory store. The `content` field is populated when `view=full` and `null` when `view=basic`; the `content_size_bytes` and `content_sha256` fields are always populated so sync clients can diff without fetching content. Memories are addressed by their `mem_...` ID; the path is the create key and can be changed via update. - `type: Literal["memory"]` - `id: str` Unique identifier for this memory (a `mem_...` value). Stable across renames; use this ID, not the path, to read, update, or delete the memory. - `content_sha256: str` Lowercase hex SHA-256 digest of the UTF-8 `content` bytes (64 characters). The server applies no normalization, so clients can compute the same hash locally for staleness checks and as the value for a `content_sha256` precondition on update. Always populated, regardless of `view`. - `content_size_bytes: int` Size of `content` in bytes (the UTF-8 plaintext length). Always populated, regardless of `view`. format: int32 - `created_at: datetime` When this memory was created, in RFC 3339 format. format: date-time - `memory_store_id: str` ID of the memory store this memory belongs to (a `memstore_...` value). - `memory_version_id: str` ID of the `memory_version` representing this memory's current content (a `memver_...` value). This is the authoritative head pointer; `memory_version` objects do not carry an `is_latest` flag, so compare against this field instead. Enumerate the history via [List memory versions](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/list?sdk_languages=python). - `path: str` Hierarchical path of the memory within the store, e.g. `/projects/foo/notes.md`. Always starts with `/`. Paths are case-sensitive and unique within a store. Maximum 1,024 bytes. - `updated_at: datetime` When this memory was last modified, in RFC 3339 format. Use this as a cheap freshness signal; for who made the change, look up the head version's `created_by` via [List memory versions](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/list?sdk_languages=python). format: date-time - `content: Optional[str]` The memory's UTF-8 text content. Populated when `view=full`; `null` when `view=basic`. Maximum 100 kB (102,400 bytes). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_memory = client.beta.memory_stores.memories.update( memory_id="memory_id", memory_store_id="memory_store_id", ) print(beta_managed_agents_memory.id) ``` ##### Response (200) ```json { "id": "id", "content_sha256": "content_sha256", "content_size_bytes": 0, "created_at": "2019-12-27T18:11:19.117Z", "memory_store_id": "memory_store_id", "memory_version_id": "memory_version_id", "path": "path", "type": "memory", "updated_at": "2019-12-27T18:11:19.117Z", "content": "content" } ``` ### Delete a memory `beta.memory_stores.memories.delete(memory_id, **kwargs) -> BetaManagedAgentsDeletedMemory` **DELETE** `/v1/memory_stores/{memory_store_id}/memories/{memory_id}` Delete a memory #### Parameters - `memory_store_id: str` (path parameter) The ID of the memory store that holds the memory (`memstore_...`). - `memory_id: str` (path parameter) The ID of the memory to delete (`mem_...`). - `expected_content_sha256: Optional[str]` (query parameter) Delete the memory only if its current `content_sha256` equals this value, given as 64 lowercase hexadecimal characters. Omit it to delete unconditionally. If the hashes differ, the request fails with HTTP status 409 and nothing is deleted. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsDeletedMemory` Tombstone returned by [Delete a memory](https://platform.claude.com/docs/en/api/beta/memory_stores/memories/delete?sdk_languages=python). Deleting a memory does not erase its version history: its versions remain listable via [List memory versions](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/list?sdk_languages=python) while they are retained (each version is kept for at least the version retention period after it was written, unless the store itself is deleted). - `type: Literal["memory_deleted"]` - `id: str` ID of the deleted memory (a `mem_...` value). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_deleted_memory = client.beta.memory_stores.memories.delete( memory_id="memory_id", memory_store_id="memory_store_id", ) print(beta_managed_agents_deleted_memory.id) ``` ##### Response (200) ```json { "id": "id", "type": "memory_deleted" } ``` ## Beta › Memory Stores › Memory Versions ### List memory versions `beta.memory_stores.memory_versions.list(memory_store_id, **kwargs) -> SyncPageCursor[BetaManagedAgentsMemoryVersion]` **GET** `/v1/memory_stores/{memory_store_id}/memory_versions` List memory versions #### Parameters - `memory_store_id: str` (path parameter) The ID of the memory store whose version history to list (`memstore_...`). - `api_key_id: Optional[str]` (query parameter) Return only versions written with the API key that has this ID. - `created_at_gte: Optional[Union[str, datetime]]` (query parameter) Return versions created at or after this time (inclusive). format: date-time - `created_at_lte: Optional[Union[str, datetime]]` (query parameter) Return versions created at or before this time (inclusive). format: date-time - `limit: Optional[int]` (query parameter) The maximum number of versions to return per page. Defaults to 20. format: int32 - `memory_id: Optional[str]` (query parameter) Return only versions of the memory with this ID (`mem_...`). The filter still works after the memory is deleted. The results then include the version whose `operation` is `deleted`. - `operation: Optional[BetaManagedAgentsMemoryVersionOperation]` (query parameter) Return only versions that record this kind of change. - `"created"` The memory was created. The first version in any memory's lineage. - `"modified"` The memory's `content`, `path`, or both were changed via update. Writes the agent makes through the filesystem mount also appear as `modified`. - `"deleted"` The memory was deleted. The `content`, `content_size_bytes`, and `content_sha256` fields are `null` on this version. The preceding version, while it is retained, records the deleted content's size and hash. - `page: Optional[str]` (query parameter) The `next_page` value from a previous response, to get the next page. Omit it to get the first page. - `service_account_id: Optional[str]` (query parameter) Return only versions written by the service account with this ID (`svac_...`). - `session_id: Optional[str]` (query parameter) Return only versions written by the session with this ID. - `view: Optional[BetaManagedAgentsMemoryView]` (query parameter) Selects which projection of a `memory` or `memory_version` the server returns. `basic` returns the object with `content` set to `null`; `full` populates `content`. When omitted, the default is endpoint-specific: retrieve operations default to `full`; list, create, and update operations default to `basic`. Listing with `view=full` caps `limit` at 20. - `"basic"` Return the object with `content` set to `null`. The `content_size_bytes` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps `limit` at 20. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsMemoryVersion` A `memory_version` object: one immutable, attributed row in a memory's append-only history. Every non-no-op mutation to a memory produces a new version. Versions belong to the store (not the individual memory) and are not deleted with the memory; each version is retained for at least the version retention period after it was written, unless the store itself is deleted. Retrieving a redacted version returns 200 with `content`, `path`, `content_size_bytes`, and `content_sha256` set to `null`; branch on `redacted_at`, not HTTP status. - `type: Literal["memory_version"]` - `id: str` Unique identifier for this version (a `memver_...` value). - `created_at: datetime` When this version was written, in RFC 3339 format. format: date-time - `memory_id: str` ID of the memory this version snapshots (a `mem_...` value). Remains valid after the memory is deleted; pass it as `memory_id` to [List memory versions](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/list?sdk_languages=python) to retrieve the memory's retained versions, including the `deleted` row while the lineage is retained. - `memory_store_id: str` ID of the memory store this version belongs to (a `memstore_...` value). - `operation: BetaManagedAgentsMemoryVersionOperation` The kind of mutation this version records: `created`, `modified`, or `deleted`. - `"created"` The memory was created. The first version in any memory's lineage. - `"modified"` The memory's `content`, `path`, or both were changed via update. Writes the agent makes through the filesystem mount also appear as `modified`. - `"deleted"` The memory was deleted. The `content`, `content_size_bytes`, and `content_sha256` fields are `null` on this version. The preceding version, while it is retained, records the deleted content's size and hash. - `content: Optional[str]` The memory's UTF-8 text content as of this version. `null` when `view=basic`, when `operation` is `deleted`, or when `redacted_at` is set. - `content_sha256: Optional[str]` Lowercase hex SHA-256 digest of `content` as of this version (64 characters). `null` when `redacted_at` is set or `operation` is `deleted`. Populated regardless of `view` otherwise. - `content_size_bytes: Optional[int]` Size of `content` in bytes as of this version. `null` when `redacted_at` is set or `operation` is `deleted`. Populated regardless of `view` otherwise. format: int32 - `created_by: Optional[BetaManagedAgentsActor]` Who performed this write: one of `session_actor`, `api_actor`, `user_actor`, or `service_account_actor`; `null` when no writer is recorded. Captured at write time and preserved through redaction. A `session_actor` is an agent writing through the store's mounted filesystem at `/mnt/memory/`. The API key that created that session is not recorded on agent writes, so attribution names who made the write, not who is ultimately responsible; look up session provenance via the [Sessions API](https://platform.claude.com/docs/en/api/beta/sessions/retrieve?sdk_languages=python). - `class BetaManagedAgentsSessionActor` An agent acting during a session, for example through the session's mounted filesystem. It names the session itself, not the user or API key that started the session. - `type: Literal["session_actor"]` - `session_id: str` ID of the session (a `sesn_...` value). Look up the session via [Retrieve a session](https://platform.claude.com/docs/en/api/beta/sessions/retrieve?sdk_languages=python) for further provenance. minLength: 1 - `class BetaManagedAgentsAPIActor` A direct caller of the public API, identified by the API key that authenticated the request. - `type: Literal["api_actor"]` - `api_key_id: str` ID of the API key (an `apikey_...` value). This identifies the key, not the secret. minLength: 1 - `class BetaManagedAgentsUserActor` A human user, for example acting through the Anthropic Console. - `type: Literal["user_actor"]` - `user_id: str` ID of the user (a `user_...` value). minLength: 1 - `class BetaManagedAgentsServiceAccountActor` A workload authenticated as a service account, for example via Workload Identity Federation. - `type: Literal["service_account_actor"]` - `service_account_id: str` ID of the service account (a `svac_...` value). minLength: 1 - `path: Optional[str]` The memory's path at the time of this write. `null` if and only if `redacted_at` is set. - `redacted_at: Optional[datetime]` When this version was redacted, in RFC 3339 format, or `null` if it has not been redacted. When set, `content`, `path`, `content_size_bytes`, and `content_sha256` are all `null`. See [Redact a memory version](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/redact?sdk_languages=python). format: date-time - `redacted_by: Optional[BetaManagedAgentsActor]` Who redacted this version, or `null` if it has not been redacted. In practice always an `api_actor`, `user_actor`, or `service_account_actor` (agents do not have a redact capability). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.memory_stores.memory_versions.list( memory_store_id="memory_store_id", ) page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "memver_011CZkZBJq5dWxk9fVLNcPht", "created_at": "2026-03-15T10:00:00Z", "memory_id": "mem_011CZkZ9X2dpNyB6YbtxvB6e", "memory_store_id": "memstore_01Wf3kQ8tZxB2mVr7HcJ4aNd", "operation": "created", "type": "memory_version", "content": null, "content_sha256": "ba7936d94c84d948a2232088f78228f175df6a8353b2d5bc9228eee5794a0024", "content_size_bytes": 28, "created_by": { "session_id": "sesn_011CZkZAtmR3yMPDzynEDxu7", "type": "session_actor" }, "path": "/preferences/formatting.md", "redacted_at": null, "redacted_by": { "session_id": "x", "type": "session_actor" } } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=" } ``` ### Retrieve a memory version `beta.memory_stores.memory_versions.retrieve(memory_version_id, **kwargs) -> BetaManagedAgentsMemoryVersion` **GET** `/v1/memory_stores/{memory_store_id}/memory_versions/{memory_version_id}` Retrieve a memory version #### Parameters - `memory_store_id: str` (path parameter) The ID of the memory store that holds the version (`memstore_...`). - `memory_version_id: str` (path parameter) The ID of the memory version to retrieve (`memver_...`). - `view: Optional[BetaManagedAgentsMemoryView]` (query parameter) Selects which projection of a `memory` or `memory_version` the server returns. `basic` returns the object with `content` set to `null`; `full` populates `content`. When omitted, the default is endpoint-specific: retrieve operations default to `full`; list, create, and update operations default to `basic`. Listing with `view=full` caps `limit` at 20. - `"basic"` Return the object with `content` set to `null`. The `content_size_bytes` and `content_sha256` fields remain populated, so sync clients can diff without fetching content. - `"full"` Return the object with `content` populated. On list endpoints, `view=full` caps `limit` at 20. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsMemoryVersion` A `memory_version` object: one immutable, attributed row in a memory's append-only history. Every non-no-op mutation to a memory produces a new version. Versions belong to the store (not the individual memory) and are not deleted with the memory; each version is retained for at least the version retention period after it was written, unless the store itself is deleted. Retrieving a redacted version returns 200 with `content`, `path`, `content_size_bytes`, and `content_sha256` set to `null`; branch on `redacted_at`, not HTTP status. - `type: Literal["memory_version"]` - `id: str` Unique identifier for this version (a `memver_...` value). - `created_at: datetime` When this version was written, in RFC 3339 format. format: date-time - `memory_id: str` ID of the memory this version snapshots (a `mem_...` value). Remains valid after the memory is deleted; pass it as `memory_id` to [List memory versions](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/list?sdk_languages=python) to retrieve the memory's retained versions, including the `deleted` row while the lineage is retained. - `memory_store_id: str` ID of the memory store this version belongs to (a `memstore_...` value). - `operation: BetaManagedAgentsMemoryVersionOperation` The kind of mutation this version records: `created`, `modified`, or `deleted`. - `"created"` The memory was created. The first version in any memory's lineage. - `"modified"` The memory's `content`, `path`, or both were changed via update. Writes the agent makes through the filesystem mount also appear as `modified`. - `"deleted"` The memory was deleted. The `content`, `content_size_bytes`, and `content_sha256` fields are `null` on this version. The preceding version, while it is retained, records the deleted content's size and hash. - `content: Optional[str]` The memory's UTF-8 text content as of this version. `null` when `view=basic`, when `operation` is `deleted`, or when `redacted_at` is set. - `content_sha256: Optional[str]` Lowercase hex SHA-256 digest of `content` as of this version (64 characters). `null` when `redacted_at` is set or `operation` is `deleted`. Populated regardless of `view` otherwise. - `content_size_bytes: Optional[int]` Size of `content` in bytes as of this version. `null` when `redacted_at` is set or `operation` is `deleted`. Populated regardless of `view` otherwise. format: int32 - `created_by: Optional[BetaManagedAgentsActor]` Who performed this write: one of `session_actor`, `api_actor`, `user_actor`, or `service_account_actor`; `null` when no writer is recorded. Captured at write time and preserved through redaction. A `session_actor` is an agent writing through the store's mounted filesystem at `/mnt/memory/`. The API key that created that session is not recorded on agent writes, so attribution names who made the write, not who is ultimately responsible; look up session provenance via the [Sessions API](https://platform.claude.com/docs/en/api/beta/sessions/retrieve?sdk_languages=python). - `class BetaManagedAgentsSessionActor` An agent acting during a session, for example through the session's mounted filesystem. It names the session itself, not the user or API key that started the session. - `type: Literal["session_actor"]` - `session_id: str` ID of the session (a `sesn_...` value). Look up the session via [Retrieve a session](https://platform.claude.com/docs/en/api/beta/sessions/retrieve?sdk_languages=python) for further provenance. minLength: 1 - `class BetaManagedAgentsAPIActor` A direct caller of the public API, identified by the API key that authenticated the request. - `type: Literal["api_actor"]` - `api_key_id: str` ID of the API key (an `apikey_...` value). This identifies the key, not the secret. minLength: 1 - `class BetaManagedAgentsUserActor` A human user, for example acting through the Anthropic Console. - `type: Literal["user_actor"]` - `user_id: str` ID of the user (a `user_...` value). minLength: 1 - `class BetaManagedAgentsServiceAccountActor` A workload authenticated as a service account, for example via Workload Identity Federation. - `type: Literal["service_account_actor"]` - `service_account_id: str` ID of the service account (a `svac_...` value). minLength: 1 - `path: Optional[str]` The memory's path at the time of this write. `null` if and only if `redacted_at` is set. - `redacted_at: Optional[datetime]` When this version was redacted, in RFC 3339 format, or `null` if it has not been redacted. When set, `content`, `path`, `content_size_bytes`, and `content_sha256` are all `null`. See [Redact a memory version](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/redact?sdk_languages=python). format: date-time - `redacted_by: Optional[BetaManagedAgentsActor]` Who redacted this version, or `null` if it has not been redacted. In practice always an `api_actor`, `user_actor`, or `service_account_actor` (agents do not have a redact capability). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_memory_version = client.beta.memory_stores.memory_versions.retrieve( memory_version_id="memory_version_id", memory_store_id="memory_store_id", ) print(beta_managed_agents_memory_version.id) ``` ##### Response (200) ```json { "id": "id", "created_at": "2019-12-27T18:11:19.117Z", "memory_id": "memory_id", "memory_store_id": "memory_store_id", "operation": "created", "type": "memory_version", "content": "content", "content_sha256": "content_sha256", "content_size_bytes": 0, "created_by": { "session_id": "x", "type": "session_actor" }, "path": "path", "redacted_at": "2019-12-27T18:11:19.117Z", "redacted_by": { "session_id": "x", "type": "session_actor" } } ``` ### Redact a memory version `beta.memory_stores.memory_versions.redact(memory_version_id, **kwargs) -> BetaManagedAgentsMemoryVersion` **POST** `/v1/memory_stores/{memory_store_id}/memory_versions/{memory_version_id}/redact` Redact a memory version #### Parameters - `memory_store_id: str` (path parameter) The ID of the memory store that holds the version (`memstore_...`). - `memory_version_id: str` (path parameter) The ID of the memory version to redact (`memver_...`). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaManagedAgentsMemoryVersion` A `memory_version` object: one immutable, attributed row in a memory's append-only history. Every non-no-op mutation to a memory produces a new version. Versions belong to the store (not the individual memory) and are not deleted with the memory; each version is retained for at least the version retention period after it was written, unless the store itself is deleted. Retrieving a redacted version returns 200 with `content`, `path`, `content_size_bytes`, and `content_sha256` set to `null`; branch on `redacted_at`, not HTTP status. - `type: Literal["memory_version"]` - `id: str` Unique identifier for this version (a `memver_...` value). - `created_at: datetime` When this version was written, in RFC 3339 format. format: date-time - `memory_id: str` ID of the memory this version snapshots (a `mem_...` value). Remains valid after the memory is deleted; pass it as `memory_id` to [List memory versions](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/list?sdk_languages=python) to retrieve the memory's retained versions, including the `deleted` row while the lineage is retained. - `memory_store_id: str` ID of the memory store this version belongs to (a `memstore_...` value). - `operation: BetaManagedAgentsMemoryVersionOperation` The kind of mutation this version records: `created`, `modified`, or `deleted`. - `"created"` The memory was created. The first version in any memory's lineage. - `"modified"` The memory's `content`, `path`, or both were changed via update. Writes the agent makes through the filesystem mount also appear as `modified`. - `"deleted"` The memory was deleted. The `content`, `content_size_bytes`, and `content_sha256` fields are `null` on this version. The preceding version, while it is retained, records the deleted content's size and hash. - `content: Optional[str]` The memory's UTF-8 text content as of this version. `null` when `view=basic`, when `operation` is `deleted`, or when `redacted_at` is set. - `content_sha256: Optional[str]` Lowercase hex SHA-256 digest of `content` as of this version (64 characters). `null` when `redacted_at` is set or `operation` is `deleted`. Populated regardless of `view` otherwise. - `content_size_bytes: Optional[int]` Size of `content` in bytes as of this version. `null` when `redacted_at` is set or `operation` is `deleted`. Populated regardless of `view` otherwise. format: int32 - `created_by: Optional[BetaManagedAgentsActor]` Who performed this write: one of `session_actor`, `api_actor`, `user_actor`, or `service_account_actor`; `null` when no writer is recorded. Captured at write time and preserved through redaction. A `session_actor` is an agent writing through the store's mounted filesystem at `/mnt/memory/`. The API key that created that session is not recorded on agent writes, so attribution names who made the write, not who is ultimately responsible; look up session provenance via the [Sessions API](https://platform.claude.com/docs/en/api/beta/sessions/retrieve?sdk_languages=python). - `class BetaManagedAgentsSessionActor` An agent acting during a session, for example through the session's mounted filesystem. It names the session itself, not the user or API key that started the session. - `type: Literal["session_actor"]` - `session_id: str` ID of the session (a `sesn_...` value). Look up the session via [Retrieve a session](https://platform.claude.com/docs/en/api/beta/sessions/retrieve?sdk_languages=python) for further provenance. minLength: 1 - `class BetaManagedAgentsAPIActor` A direct caller of the public API, identified by the API key that authenticated the request. - `type: Literal["api_actor"]` - `api_key_id: str` ID of the API key (an `apikey_...` value). This identifies the key, not the secret. minLength: 1 - `class BetaManagedAgentsUserActor` A human user, for example acting through the Anthropic Console. - `type: Literal["user_actor"]` - `user_id: str` ID of the user (a `user_...` value). minLength: 1 - `class BetaManagedAgentsServiceAccountActor` A workload authenticated as a service account, for example via Workload Identity Federation. - `type: Literal["service_account_actor"]` - `service_account_id: str` ID of the service account (a `svac_...` value). minLength: 1 - `path: Optional[str]` The memory's path at the time of this write. `null` if and only if `redacted_at` is set. - `redacted_at: Optional[datetime]` When this version was redacted, in RFC 3339 format, or `null` if it has not been redacted. When set, `content`, `path`, `content_size_bytes`, and `content_sha256` are all `null`. See [Redact a memory version](https://platform.claude.com/docs/en/api/beta/memory_stores/memory_versions/redact?sdk_languages=python). format: date-time - `redacted_by: Optional[BetaManagedAgentsActor]` Who redacted this version, or `null` if it has not been redacted. In practice always an `api_actor`, `user_actor`, or `service_account_actor` (agents do not have a redact capability). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_managed_agents_memory_version = client.beta.memory_stores.memory_versions.redact( memory_version_id="memory_version_id", memory_store_id="memory_store_id", ) print(beta_managed_agents_memory_version.id) ``` ##### Response (200) ```json { "id": "id", "created_at": "2019-12-27T18:11:19.117Z", "memory_id": "memory_id", "memory_store_id": "memory_store_id", "operation": "created", "type": "memory_version", "content": "content", "content_sha256": "content_sha256", "content_size_bytes": 0, "created_by": { "session_id": "x", "type": "session_actor" }, "path": "path", "redacted_at": "2019-12-27T18:11:19.117Z", "redacted_by": { "session_id": "x", "type": "session_actor" } } ``` ## Beta › Files ### Upload File `beta.files.upload(**kwargs) -> BetaFileMetadata` **POST** `/v1/files` Upload File #### Parameters - `file: FileTypes` The file to upload. Only the final path component of the part's `filename` is kept; an absent or empty `filename` is replaced with `unnamed` plus the extension for the file's stored `mime_type`, when known. format: binary - `expires_in_seconds: Optional[int]` Seconds from upload until the file expires and its bytes become permanently unavailable. Must be between 3600 (one hour) and 7776000 (ninety days). minimum: 3600, maximum: 7776000 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaFileMetadata` - `type: Literal["file"]` Object type. For files, this is always `"file"`. - `id: str` Unique object identifier. The format and length of IDs may change over time. - `created_at: datetime` RFC 3339 datetime string representing when the file was created. format: date-time - `filename: str` Original filename of the uploaded file. minLength: 1, maxLength: 500 - `mime_type: str` MIME type of the file. minLength: 1, maxLength: 255 - `size_bytes: int` Size of the file in bytes. minimum: 0 - `downloadable: Optional[bool]` Whether the file can be downloaded. default: false - `expires_at: Optional[datetime]` RFC 3339 datetime string representing when the file will expire and become unavailable for download. Null if the file does not expire. For files uploaded with `expires_in_seconds`, this is the upload time plus that value. format: date-time - `scope: Optional[BetaFileScope]` The scope of this file, indicating the context in which it was created (e.g., a session). - `type: Literal["session"]` The type of scope (e.g., `"session"`). - `id: str` The ID of the scoping resource (e.g., the session ID). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_file_metadata = client.beta.files.upload( file=b"Example data", ) print(beta_file_metadata.id) ``` ##### Response (200) ```json { "id": "file_011CNha8iCJcU1wXNR6q4V8w", "created_at": "2025-04-15T18:37:24.100435Z", "filename": "document.pdf", "mime_type": "application/pdf", "size_bytes": 102400, "type": "file", "downloadable": false, "expires_at": "2025-05-15T18:37:24.100435Z", "scope": { "id": "id", "type": "session" } } ``` ### List Files `beta.files.list(**kwargs) -> SyncPageCursor[BetaFileMetadata]` **GET** `/v1/files` List Files #### Parameters - `ids: Optional[Sequence[str]]` (query parameter) Restrict the result set to Files whose `id` is in this list. At most 100 entries (after de-duplication). Mutually exclusive with `page` and `limit`. When supplied, the response is always a single page (`next_page` is null). IDs that do not resolve to a visible File — including deleted Files — are silently omitted. - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Opaque page cursor returned in a prior list response's `next_page`. Prefixed `page_`. - `scope_id: Optional[str]` (query parameter) Filter by scope ID. Only returns files associated with the specified scope (e.g., a session ID). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaFileMetadata` - `type: Literal["file"]` Object type. For files, this is always `"file"`. - `id: str` Unique object identifier. The format and length of IDs may change over time. - `created_at: datetime` RFC 3339 datetime string representing when the file was created. format: date-time - `filename: str` Original filename of the uploaded file. minLength: 1, maxLength: 500 - `mime_type: str` MIME type of the file. minLength: 1, maxLength: 255 - `size_bytes: int` Size of the file in bytes. minimum: 0 - `downloadable: Optional[bool]` Whether the file can be downloaded. default: false - `expires_at: Optional[datetime]` RFC 3339 datetime string representing when the file will expire and become unavailable for download. Null if the file does not expire. For files uploaded with `expires_in_seconds`, this is the upload time plus that value. format: date-time - `scope: Optional[BetaFileScope]` The scope of this file, indicating the context in which it was created (e.g., a session). - `type: Literal["session"]` The type of scope (e.g., `"session"`). - `id: str` The ID of the scoping resource (e.g., the session ID). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.files.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "file_011CNha8iCJcU1wXNR6q4V8w", "created_at": "2025-04-15T18:37:24.100435Z", "filename": "document.pdf", "mime_type": "application/pdf", "size_bytes": 102400, "type": "file", "downloadable": false, "expires_at": "2025-05-15T18:37:24.100435Z", "scope": { "id": "id", "type": "session" } } ], "next_page": "next_page" } ``` ### Download File `beta.files.download(file_id, **kwargs) -> BinaryResponseContent` **GET** `/v1/files/{file_id}/content` Download File #### Parameters - `file_id: str` (path parameter) ID of the File. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `BinaryResponseContent` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) response = client.beta.files.download( file_id="file_id", ) print(response) content = response.read() print(content) ``` ### Get File Metadata `beta.files.retrieve_metadata(file_id, **kwargs) -> BetaFileMetadata` **GET** `/v1/files/{file_id}` Get File Metadata #### Parameters - `file_id: str` (path parameter) ID of the File. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaFileMetadata` - `type: Literal["file"]` Object type. For files, this is always `"file"`. - `id: str` Unique object identifier. The format and length of IDs may change over time. - `created_at: datetime` RFC 3339 datetime string representing when the file was created. format: date-time - `filename: str` Original filename of the uploaded file. minLength: 1, maxLength: 500 - `mime_type: str` MIME type of the file. minLength: 1, maxLength: 255 - `size_bytes: int` Size of the file in bytes. minimum: 0 - `downloadable: Optional[bool]` Whether the file can be downloaded. default: false - `expires_at: Optional[datetime]` RFC 3339 datetime string representing when the file will expire and become unavailable for download. Null if the file does not expire. For files uploaded with `expires_in_seconds`, this is the upload time plus that value. format: date-time - `scope: Optional[BetaFileScope]` The scope of this file, indicating the context in which it was created (e.g., a session). - `type: Literal["session"]` The type of scope (e.g., `"session"`). - `id: str` The ID of the scoping resource (e.g., the session ID). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_file_metadata = client.beta.files.retrieve_metadata( file_id="file_id", ) print(beta_file_metadata.id) ``` ##### Response (200) ```json { "id": "file_011CNha8iCJcU1wXNR6q4V8w", "created_at": "2025-04-15T18:37:24.100435Z", "filename": "document.pdf", "mime_type": "application/pdf", "size_bytes": 102400, "type": "file", "downloadable": false, "expires_at": "2025-05-15T18:37:24.100435Z", "scope": { "id": "id", "type": "session" } } ``` ### Delete File `beta.files.delete(file_id, **kwargs) -> BetaDeletedFile` **DELETE** `/v1/files/{file_id}` Delete File #### Parameters - `file_id: str` (path parameter) ID of the File. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaDeletedFile` - `type: Optional[Literal["file_deleted"]]` Deleted object type. For file deletion, this is always `"file_deleted"`. default: file_deleted - `id: str` ID of the deleted file. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_deleted_file = client.beta.files.delete( file_id="file_id", ) print(beta_deleted_file.id) ``` ##### Response (200) ```json { "id": "file_011CNha8iCJcU1wXNR6q4V8w", "type": "file_deleted" } ``` ## Beta › Skills ### Create Skill `beta.skills.create(**kwargs) -> BetaSkill` **POST** `/v1/skills` Create Skill #### Parameters - `files: Sequence[FileTypes]` Files to upload for the skill. All files must be in the same top-level directory and must include a SKILL.md file at the root of that directory. - `display_name: Optional[str]` Human-readable, single-line label for the Skill. Maximum 255 characters. Always set: derived from the SKILL.md frontmatter `name` when omitted at creation. Not unique. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaSkill` - `type: Literal["skill"]` Object type. For Skills, this is always `"skill"`. default: skill - `id: str` Unique identifier for the skill. The format and length of IDs may change over time. - `created_at: datetime` ISO 8601 timestamp of when the skill was created. format: date-time - `display_name: str` Human-readable, single-line label for the Skill. Maximum 255 characters. Always set: derived from the SKILL.md frontmatter `name` when omitted at creation. Not unique. - `latest_version_id: str` ID of the newest Skill Version — what `latest` references resolve to. Always set: a Skill holds at least one version. - `source: BetaSkillSource` Where the Skill comes from. Possible values: * `"custom"`: authored by the platform user; private to their workspace * `"anthropic"`: published by Anthropic; shared and read-only * `"anthropic_example"`: Anthropic-published sample Skill * `"plugin"`: resolved from an installed plugin - `type: Literal["custom", "anthropic", "anthropic_example", "plugin"]` Where the Skill comes from. Possible values: * `"custom"`: authored by the platform user; private to their workspace * `"anthropic"`: published by Anthropic; shared and read-only * `"anthropic_example"`: Anthropic-published sample Skill * `"plugin"`: resolved from an installed plugin - `"custom"` - `"anthropic"` - `"anthropic_example"` - `"plugin"` - `updated_at: datetime` ISO 8601 timestamp of when the skill was last updated. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_skill = client.beta.skills.create( files=[b"Example data"], ) print(beta_skill.id) ``` ##### Response (200) ```json { "id": "skill_01JAbcdefghijklmnopqrstuvw", "created_at": "2024-10-30T23:58:27.427722Z", "display_name": "display_name", "latest_version_id": "latest_version_id", "source": { "type": "custom" }, "type": "skill", "updated_at": "2024-10-30T23:58:27.427722Z" } ``` ### List Skills `beta.skills.list(**kwargs) -> SyncPageCursor[BetaSkill]` **GET** `/v1/skills` List Skills #### Parameters - `limit: Optional[int]` (query parameter) Number of results to return per page. Ranges from `1` to `1000`. Defaults to `20`. default: 20, minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Pagination token for fetching a specific page of results. Pass the value from a previous response's `next_page` field to get the next page of results. - `source: Optional[str]` (query parameter) Filter skills by source. If provided, only skills from the specified source will be returned: * `"custom"`: only return user-created skills * `"anthropic"`: only return Anthropic-created skills - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaSkill` - `type: Literal["skill"]` Object type. For Skills, this is always `"skill"`. default: skill - `id: str` Unique identifier for the skill. The format and length of IDs may change over time. - `created_at: datetime` ISO 8601 timestamp of when the skill was created. format: date-time - `display_name: str` Human-readable, single-line label for the Skill. Maximum 255 characters. Always set: derived from the SKILL.md frontmatter `name` when omitted at creation. Not unique. - `latest_version_id: str` ID of the newest Skill Version — what `latest` references resolve to. Always set: a Skill holds at least one version. - `source: BetaSkillSource` Where the Skill comes from. Possible values: * `"custom"`: authored by the platform user; private to their workspace * `"anthropic"`: published by Anthropic; shared and read-only * `"anthropic_example"`: Anthropic-published sample Skill * `"plugin"`: resolved from an installed plugin - `type: Literal["custom", "anthropic", "anthropic_example", "plugin"]` Where the Skill comes from. Possible values: * `"custom"`: authored by the platform user; private to their workspace * `"anthropic"`: published by Anthropic; shared and read-only * `"anthropic_example"`: Anthropic-published sample Skill * `"plugin"`: resolved from an installed plugin - `"custom"` - `"anthropic"` - `"anthropic_example"` - `"plugin"` - `updated_at: datetime` ISO 8601 timestamp of when the skill was last updated. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.skills.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "skill_01JAbcdefghijklmnopqrstuvw", "created_at": "2024-10-30T23:58:27.427722Z", "display_name": "display_name", "latest_version_id": "latest_version_id", "source": { "type": "custom" }, "type": "skill", "updated_at": "2024-10-30T23:58:27.427722Z" } ], "next_page": "next_page" } ``` ### Get Skill `beta.skills.retrieve(skill_id, **kwargs) -> BetaSkill` **GET** `/v1/skills/{skill_id}` Get Skill #### Parameters - `skill_id: str` (path parameter) Unique identifier for the skill. The format and length of IDs may change over time. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaSkill` - `type: Literal["skill"]` Object type. For Skills, this is always `"skill"`. default: skill - `id: str` Unique identifier for the skill. The format and length of IDs may change over time. - `created_at: datetime` ISO 8601 timestamp of when the skill was created. format: date-time - `display_name: str` Human-readable, single-line label for the Skill. Maximum 255 characters. Always set: derived from the SKILL.md frontmatter `name` when omitted at creation. Not unique. - `latest_version_id: str` ID of the newest Skill Version — what `latest` references resolve to. Always set: a Skill holds at least one version. - `source: BetaSkillSource` Where the Skill comes from. Possible values: * `"custom"`: authored by the platform user; private to their workspace * `"anthropic"`: published by Anthropic; shared and read-only * `"anthropic_example"`: Anthropic-published sample Skill * `"plugin"`: resolved from an installed plugin - `type: Literal["custom", "anthropic", "anthropic_example", "plugin"]` Where the Skill comes from. Possible values: * `"custom"`: authored by the platform user; private to their workspace * `"anthropic"`: published by Anthropic; shared and read-only * `"anthropic_example"`: Anthropic-published sample Skill * `"plugin"`: resolved from an installed plugin - `"custom"` - `"anthropic"` - `"anthropic_example"` - `"plugin"` - `updated_at: datetime` ISO 8601 timestamp of when the skill was last updated. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_skill = client.beta.skills.retrieve( skill_id="skill_id", ) print(beta_skill.id) ``` ##### Response (200) ```json { "id": "skill_01JAbcdefghijklmnopqrstuvw", "created_at": "2024-10-30T23:58:27.427722Z", "display_name": "display_name", "latest_version_id": "latest_version_id", "source": { "type": "custom" }, "type": "skill", "updated_at": "2024-10-30T23:58:27.427722Z" } ``` ### Delete Skill `beta.skills.delete(skill_id, **kwargs) -> BetaDeletedSkill` **DELETE** `/v1/skills/{skill_id}` Delete Skill #### Parameters - `skill_id: str` (path parameter) Unique identifier for the skill. The format and length of IDs may change over time. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaDeletedSkill` - `type: Literal["skill_deleted"]` Deleted object type. For Skills, this is always `"skill_deleted"`. default: skill_deleted - `id: str` Unique identifier for the skill. The format and length of IDs may change over time. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_deleted_skill = client.beta.skills.delete( skill_id="skill_id", ) print(beta_deleted_skill.id) ``` ##### Response (200) ```json { "id": "skill_01JAbcdefghijklmnopqrstuvw", "type": "skill_deleted" } ``` ## Beta › Skills › Versions ### Create Skill Version `beta.skills.versions.create(skill_id, **kwargs) -> BetaSkillVersion` **POST** `/v1/skills/{skill_id}/versions` Create Skill Version #### Parameters - `skill_id: str` (path parameter) Unique identifier for the skill. The format and length of IDs may change over time. - `files: Sequence[FileTypes]` Files to upload for the skill. All files must be in the same top-level directory and must include a SKILL.md file at the root of that directory. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaSkillVersion` - `type: Literal["skill_version"]` Object type. For Skill Versions, this is always `"skill_version"`. default: skill_version - `id: str` Unique identifier for this Skill Version. The id addresses the version in paths and pins it in references. - `created_at: datetime` ISO 8601 timestamp of when the skill was created. format: date-time - `description: str` Description of the skill version. This is extracted from the SKILL.md file in the skill upload. - `name: str` The Skill's immutable kebab-case slug, set at creation from the first upload's SKILL.md frontmatter `name` (or its enclosing directory). Every later upload must resolve to the same value. Also the top-level directory of the Skill's mounted files and the base name of a downloaded archive. - `skill_id: str` Unique identifier for the skill. The format and length of IDs may change over time. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_skill_version = client.beta.skills.versions.create( skill_id="skill_id", files=[b"Example data"], ) print(beta_skill_version.id) ``` ##### Response (200) ```json { "id": "id", "created_at": "2024-10-30T23:58:27.427722Z", "description": "description", "name": "name", "skill_id": "skill_01JAbcdefghijklmnopqrstuvw", "type": "skill_version" } ``` ### List Skill Versions `beta.skills.versions.list(skill_id, **kwargs) -> SyncPageCursor[BetaSkillVersion]` **GET** `/v1/skills/{skill_id}/versions` List Skill Versions #### Parameters - `skill_id: str` (path parameter) Unique identifier for the skill. The format and length of IDs may change over time. - `limit: Optional[int]` (query parameter) Number of results to return per page. Ranges from `1` to `1000`. Defaults to `20`. default: 20, minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Optionally set to the `next_page` token from the previous response. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaSkillVersion` - `type: Literal["skill_version"]` Object type. For Skill Versions, this is always `"skill_version"`. default: skill_version - `id: str` Unique identifier for this Skill Version. The id addresses the version in paths and pins it in references. - `created_at: datetime` ISO 8601 timestamp of when the skill was created. format: date-time - `description: str` Description of the skill version. This is extracted from the SKILL.md file in the skill upload. - `name: str` The Skill's immutable kebab-case slug, set at creation from the first upload's SKILL.md frontmatter `name` (or its enclosing directory). Every later upload must resolve to the same value. Also the top-level directory of the Skill's mounted files and the base name of a downloaded archive. - `skill_id: str` Unique identifier for the skill. The format and length of IDs may change over time. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.skills.versions.list( skill_id="skill_id", ) page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "id", "created_at": "2024-10-30T23:58:27.427722Z", "description": "description", "name": "name", "skill_id": "skill_01JAbcdefghijklmnopqrstuvw", "type": "skill_version" } ], "next_page": "next_page" } ``` ### Download Skill Version Content `beta.skills.versions.download(version, **kwargs) -> BinaryResponseContent` **GET** `/v1/skills/{skill_id}/versions/{version}/content` Download a skill version's content as a zip archive. #### Parameters - `skill_id: str` (path parameter) Unique identifier for the skill. The format and length of IDs may change over time. - `version: str` (path parameter) Identifies the skill version by its version ID. Requests carrying the `skills-2025-10-02` beta header address versions by their Unix epoch timestamp instead (e.g., "1759178010641129"). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `BinaryResponseContent` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) response = client.beta.skills.versions.download( version="version", skill_id="skill_id", ) print(response) content = response.read() print(content) ``` ### Get Skill Version `beta.skills.versions.retrieve(version, **kwargs) -> BetaSkillVersion` **GET** `/v1/skills/{skill_id}/versions/{version}` Get Skill Version #### Parameters - `skill_id: str` (path parameter) Unique identifier for the skill. The format and length of IDs may change over time. - `version: str` (path parameter) Identifies the skill version: a version ID, or the literal `latest` for the skill's most recent version. Requests carrying the `skills-2025-10-02` beta header address versions by their Unix epoch timestamp instead (e.g., "1759178010641129"). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaSkillVersion` - `type: Literal["skill_version"]` Object type. For Skill Versions, this is always `"skill_version"`. default: skill_version - `id: str` Unique identifier for this Skill Version. The id addresses the version in paths and pins it in references. - `created_at: datetime` ISO 8601 timestamp of when the skill was created. format: date-time - `description: str` Description of the skill version. This is extracted from the SKILL.md file in the skill upload. - `name: str` The Skill's immutable kebab-case slug, set at creation from the first upload's SKILL.md frontmatter `name` (or its enclosing directory). Every later upload must resolve to the same value. Also the top-level directory of the Skill's mounted files and the base name of a downloaded archive. - `skill_id: str` Unique identifier for the skill. The format and length of IDs may change over time. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_skill_version = client.beta.skills.versions.retrieve( version="version", skill_id="skill_id", ) print(beta_skill_version.id) ``` ##### Response (200) ```json { "id": "id", "created_at": "2024-10-30T23:58:27.427722Z", "description": "description", "name": "name", "skill_id": "skill_01JAbcdefghijklmnopqrstuvw", "type": "skill_version" } ``` ### Delete Skill Version `beta.skills.versions.delete(version, **kwargs) -> BetaDeletedSkillVersion` **DELETE** `/v1/skills/{skill_id}/versions/{version}` Delete Skill Version #### Parameters - `skill_id: str` (path parameter) Unique identifier for the skill. The format and length of IDs may change over time. - `version: str` (path parameter) Identifies the skill version by its version ID. Requests carrying the `skills-2025-10-02` beta header address versions by their Unix epoch timestamp instead (e.g., "1759178010641129"). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaDeletedSkillVersion` - `type: Literal["skill_version_deleted"]` Deleted object type. For Skill Versions, this is always `"skill_version_deleted"`. default: skill_version_deleted - `id: str` Unique identifier for this Skill Version. The id addresses the version in paths and pins it in references. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_deleted_skill_version = client.beta.skills.versions.delete( version="version", skill_id="skill_id", ) print(beta_deleted_skill_version.id) ``` ##### Response (200) ```json { "id": "id", "type": "skill_version_deleted" } ``` ## Beta › User Profiles ### Create User Profile `beta.user_profiles.create(**kwargs) -> BetaUserProfile` **POST** `/v1/user_profiles` Create User Profile #### Parameters - `access_type: Optional[Literal["application", "passthrough"]]` How the platform uses the API for this entity. `application` (default): the profile represents an individual end-user of the platform's product. `passthrough`: the profile identifies a company the platform resells Claude access to. - `"application"` The user profile represents an individual end-user of a product that the platform builds on the API. New profiles get this value by default. - `"passthrough"` The user profile represents a company that the platform resells Claude access to. - `external_id: Optional[str]` Platform's own identifier for this user. Not enforced unique. Maximum 255 characters. Accepted under the `user-profiles-2026-03-24` and `user-profiles-2026-08-18` beta headers; under `user-profiles-2026-09-04` send `external_user_details.reference_id` instead. minLength: 1, maxLength: 255 - `external_user_details: Optional[BetaUserProfileExternalUserDetailsParams]` Details about the entity this profile represents, as the platform states them. Every field is optional. Accepted under the `user-profiles-2026-09-04` beta header only. - `account_status: Optional[Literal["active", "suspended", "blocked"]]` The status of the entity's account on the platform: `active`, `suspended` or `blocked`. - `"active"` The platform has neither restricted nor barred the account of the entity that the user profile represents. - `"suspended"` The platform has restricted the account of the entity that the user profile represents and may restore it. - `"blocked"` The platform has barred the account of the entity that the user profile represents. - `country: Optional[str]` The country of the entity (not of the platform), as the platform determines it: an ISO 3166-1 alpha-2 code in upper case, for example `US`. Only the form, two uppercase ASCII letters, is checked. - `email_hash: Optional[str]` A hash of the entity's email address, computed by the platform. Anthropic treats it as an opaque string and does not prescribe the hash function. 1 to 255 characters. minLength: 1, maxLength: 255 - `entity_type: Optional[Literal["individual", "business", "non_profit", "government"]]` What kind of entity the profile represents: `individual`, `business`, `non_profit` or `government`. - `"individual"` - `"business"` - `"non_profit"` - `"government"` - `name_hash: Optional[str]` A hash of the entity's name, computed by the platform. Anthropic treats it as an opaque string and does not prescribe the hash function. 1 to 255 characters. minLength: 1, maxLength: 255 - `onboarded_at: Optional[datetime]` When the entity opened its account with the platform, in RFC 3339 format: for an `application` profile, when the end-user signed up; for a `passthrough` profile, when the company became the platform's customer. Must be a complete timestamp no more than 1 minute in the future. format: date-time - `reference_id: Optional[str]` The platform's own reference for the entity, for example the key of the end-user's row in the platform's database. Not interpreted by Anthropic and not enforced unique. 1 to 255 characters. minLength: 1, maxLength: 255 - `external_user_onboarded_at: Optional[Union[str, datetime]]` When the entity this profile represents opened its account with the platform, in RFC 3339 format: for an `application` profile, when the end-user signed up; for a `passthrough` profile, when the company became the platform's customer. Must be a complete timestamp no more than 1 minute in the future. Optional. Accepted under the `user-profiles-2026-08-18` beta header; under `user-profiles-2026-09-04` send `external_user_details.onboarded_at` instead. format: date-time - `metadata: Optional[Dict[str, str]]` Free-form key-value data to attach to this user profile. Maximum 16 keys, with keys up to 64 characters and values up to 512 characters. Values must be non-empty strings. - `name: Optional[str]` Optional for all profiles. Real-world name of the entity this profile represents (company or individual); for a company the platform resells Claude access to (`access_type` `passthrough`), that company's name where known. Maximum 255 characters. minLength: 1, maxLength: 255 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaUserProfile` A record of an entity that the platform serves through the API, such as an end-user of the platform's product or a company that the platform resells Claude access to. A Messages, Message Batches or token counting request can send a profile's `id` in the `anthropic-user-profile-id` header to attribute the request to that entity. - `type: Literal["user_profile"]` Object type. Always `user_profile`. - `id: str` Unique identifier for this user profile, prefixed `uprof_`. - `created_at: datetime` When this user profile was created, in RFC 3339 format. format: date-time - `metadata: Dict[str, str]` Arbitrary key-value metadata. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars. - `trust_grants: Dict[str, BetaUserProfileTrustGrant]` Trust grants for this profile, keyed by grant name. Key omitted when no grant is active or in flight. - `status: Literal["active", "pending", "rejected"]` Status of the trust grant. - `"active"` - `"pending"` - `"rejected"` - `updated_at: datetime` When this user profile was last modified, in RFC 3339 format. Trust-grant status changes also bump this timestamp. format: date-time - `access_type: Optional[Literal["application", "passthrough"]]` How the platform uses the API for this entity: `application` (default) or `passthrough`. Present under the `user-profiles-2026-08-18` and later beta headers. - `"application"` The user profile represents an individual end-user of a product that the platform builds on the API. New profiles get this value by default. - `"passthrough"` The user profile represents a company that the platform resells Claude access to. - `external_id: Optional[str]` Platform's own identifier for this user. Not enforced unique. Present under the `user-profiles-2026-03-24` and `user-profiles-2026-08-18` beta headers; under `user-profiles-2026-09-04` the value is `external_user_details.reference_id`. - `external_user_details: Optional[BetaUserProfileExternalUserDetails]` Details about the entity this profile represents, as the platform states them; not verified by Anthropic. Present under the `user-profiles-2026-09-04` beta header, with every field present and `null` until the platform supplies a value; the earlier beta headers serve `reference_id` as the top-level `external_id`, and `user-profiles-2026-08-18` serves `onboarded_at` as `external_user_onboarded_at`. - `account_status: Optional[Literal["active", "suspended", "blocked"]]` The status of the entity's account on the platform: `active`, `suspended` or `blocked`. `null` until the platform supplies one. - `"active"` The platform has neither restricted nor barred the account of the entity that the user profile represents. - `"suspended"` The platform has restricted the account of the entity that the user profile represents and may restore it. - `"blocked"` The platform has barred the account of the entity that the user profile represents. - `country: Optional[str]` The country the platform associates with the entity, as an ISO 3166-1 alpha-2 code. `null` until the platform supplies one. - `email_hash: Optional[str]` The platform-computed hash of the entity's email address. `null` until the platform supplies one. - `entity_type: Optional[Literal["individual", "business", "non_profit", "government"]]` What kind of entity the profile represents: `individual`, `business`, `non_profit` or `government`. `null` until the platform supplies one. - `"individual"` - `"business"` - `"non_profit"` - `"government"` - `name_hash: Optional[str]` The platform-computed hash of the entity's name. `null` until the platform supplies one. - `onboarded_at: Optional[datetime]` When the entity opened its account with the platform, as stated by the platform, in RFC 3339 format (UTC). `null` until the platform supplies one. format: date-time - `reference_id: Optional[str]` The platform's own reference for the entity. `null` until the platform supplies one. - `external_user_onboarded_at: Optional[datetime]` When the entity this profile represents opened its account with the platform, as stated by the platform, in RFC 3339 format (UTC). `null` until the platform supplies one. Present under the `user-profiles-2026-08-18` beta header; under `user-profiles-2026-09-04` the value is `external_user_details.onboarded_at`. format: date-time - `name: Optional[str]` Real-world name of the entity this profile represents (company or individual). For a company the platform resells Claude access to (`access_type` `passthrough`) this is that company's name. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_user_profile = client.beta.user_profiles.create() print(beta_user_profile.id) ``` ##### Response (200) ```json { "id": "uprof_011CZkZCu8hGbp5mYRQgUmz9", "created_at": "2026-03-15T10:00:00Z", "metadata": {}, "trust_grants": { "cyber": { "status": "active" } }, "type": "user_profile", "updated_at": "2026-03-15T10:00:00Z", "access_type": "application", "external_id": "user_12345", "external_user_details": { "account_status": "active", "country": "country", "email_hash": "email_hash", "entity_type": "individual", "name_hash": "name_hash", "onboarded_at": "2019-12-27T18:11:19.117Z", "reference_id": "reference_id" }, "external_user_onboarded_at": "2024-11-02T08:15:00Z", "name": "Example User" } ``` ### List User Profiles `beta.user_profiles.list(**kwargs) -> SyncPageCursor[BetaUserProfile]` **GET** `/v1/user_profiles` List User Profiles #### Parameters - `limit: Optional[int]` (query parameter) The maximum number of user profiles to return, from 1 to 100. Defaults to 20. format: int32 - `order: Optional[Literal["asc", "desc"]]` (query parameter) The sort direction, applied to the field that `order_by` selects. Defaults to `desc`. - `"asc"` Oldest first when `order_by` is `created_at`, or names in ascending order when `order_by` is `name`. - `"desc"` Newest first when `order_by` is `created_at`, or names in descending order when `order_by` is `name`. This is the default. - `order_by: Optional[Literal["created_at", "name"]]` (query parameter) The field to sort user profiles by, in the direction that `order` sets. Defaults to `created_at`. - `"created_at"` Sort by when each user profile was created. This is the default. - `"name"` Sort by `name`, ignoring the case of ASCII letters. Profiles without a name come last in either direction. - `page: Optional[str]` (query parameter) The cursor for the page to return, taken from `next_page` in a previous response. Leave it out to get the first page. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaUserProfile` A record of an entity that the platform serves through the API, such as an end-user of the platform's product or a company that the platform resells Claude access to. A Messages, Message Batches or token counting request can send a profile's `id` in the `anthropic-user-profile-id` header to attribute the request to that entity. - `type: Literal["user_profile"]` Object type. Always `user_profile`. - `id: str` Unique identifier for this user profile, prefixed `uprof_`. - `created_at: datetime` When this user profile was created, in RFC 3339 format. format: date-time - `metadata: Dict[str, str]` Arbitrary key-value metadata. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars. - `trust_grants: Dict[str, BetaUserProfileTrustGrant]` Trust grants for this profile, keyed by grant name. Key omitted when no grant is active or in flight. - `status: Literal["active", "pending", "rejected"]` Status of the trust grant. - `"active"` - `"pending"` - `"rejected"` - `updated_at: datetime` When this user profile was last modified, in RFC 3339 format. Trust-grant status changes also bump this timestamp. format: date-time - `access_type: Optional[Literal["application", "passthrough"]]` How the platform uses the API for this entity: `application` (default) or `passthrough`. Present under the `user-profiles-2026-08-18` and later beta headers. - `"application"` The user profile represents an individual end-user of a product that the platform builds on the API. New profiles get this value by default. - `"passthrough"` The user profile represents a company that the platform resells Claude access to. - `external_id: Optional[str]` Platform's own identifier for this user. Not enforced unique. Present under the `user-profiles-2026-03-24` and `user-profiles-2026-08-18` beta headers; under `user-profiles-2026-09-04` the value is `external_user_details.reference_id`. - `external_user_details: Optional[BetaUserProfileExternalUserDetails]` Details about the entity this profile represents, as the platform states them; not verified by Anthropic. Present under the `user-profiles-2026-09-04` beta header, with every field present and `null` until the platform supplies a value; the earlier beta headers serve `reference_id` as the top-level `external_id`, and `user-profiles-2026-08-18` serves `onboarded_at` as `external_user_onboarded_at`. - `account_status: Optional[Literal["active", "suspended", "blocked"]]` The status of the entity's account on the platform: `active`, `suspended` or `blocked`. `null` until the platform supplies one. - `"active"` The platform has neither restricted nor barred the account of the entity that the user profile represents. - `"suspended"` The platform has restricted the account of the entity that the user profile represents and may restore it. - `"blocked"` The platform has barred the account of the entity that the user profile represents. - `country: Optional[str]` The country the platform associates with the entity, as an ISO 3166-1 alpha-2 code. `null` until the platform supplies one. - `email_hash: Optional[str]` The platform-computed hash of the entity's email address. `null` until the platform supplies one. - `entity_type: Optional[Literal["individual", "business", "non_profit", "government"]]` What kind of entity the profile represents: `individual`, `business`, `non_profit` or `government`. `null` until the platform supplies one. - `"individual"` - `"business"` - `"non_profit"` - `"government"` - `name_hash: Optional[str]` The platform-computed hash of the entity's name. `null` until the platform supplies one. - `onboarded_at: Optional[datetime]` When the entity opened its account with the platform, as stated by the platform, in RFC 3339 format (UTC). `null` until the platform supplies one. format: date-time - `reference_id: Optional[str]` The platform's own reference for the entity. `null` until the platform supplies one. - `external_user_onboarded_at: Optional[datetime]` When the entity this profile represents opened its account with the platform, as stated by the platform, in RFC 3339 format (UTC). `null` until the platform supplies one. Present under the `user-profiles-2026-08-18` beta header; under `user-profiles-2026-09-04` the value is `external_user_details.onboarded_at`. format: date-time - `name: Optional[str]` Real-world name of the entity this profile represents (company or individual). For a company the platform resells Claude access to (`access_type` `passthrough`) this is that company's name. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.user_profiles.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "uprof_011CZkZCu8hGbp5mYRQgUmz9", "created_at": "2026-03-15T10:00:00Z", "metadata": {}, "trust_grants": { "cyber": { "status": "active" } }, "type": "user_profile", "updated_at": "2026-03-15T10:00:00Z", "access_type": "application", "external_id": "user_12345", "external_user_details": { "account_status": "active", "country": "country", "email_hash": "email_hash", "entity_type": "individual", "name_hash": "name_hash", "onboarded_at": "2019-12-27T18:11:19.117Z", "reference_id": "reference_id" }, "external_user_onboarded_at": "2024-11-02T08:15:00Z", "name": "Example User" } ], "next_page": "page_MjAyNS0wNS0xNFQwMDowMDowMFo=" } ``` ### Get User Profile `beta.user_profiles.retrieve(user_profile_id, **kwargs) -> BetaUserProfile` **GET** `/v1/user_profiles/{user_profile_id}` Get User Profile #### Parameters - `user_profile_id: str` (path parameter) The ID of the user profile to get (`uprof_...`). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaUserProfile` A record of an entity that the platform serves through the API, such as an end-user of the platform's product or a company that the platform resells Claude access to. A Messages, Message Batches or token counting request can send a profile's `id` in the `anthropic-user-profile-id` header to attribute the request to that entity. - `type: Literal["user_profile"]` Object type. Always `user_profile`. - `id: str` Unique identifier for this user profile, prefixed `uprof_`. - `created_at: datetime` When this user profile was created, in RFC 3339 format. format: date-time - `metadata: Dict[str, str]` Arbitrary key-value metadata. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars. - `trust_grants: Dict[str, BetaUserProfileTrustGrant]` Trust grants for this profile, keyed by grant name. Key omitted when no grant is active or in flight. - `status: Literal["active", "pending", "rejected"]` Status of the trust grant. - `"active"` - `"pending"` - `"rejected"` - `updated_at: datetime` When this user profile was last modified, in RFC 3339 format. Trust-grant status changes also bump this timestamp. format: date-time - `access_type: Optional[Literal["application", "passthrough"]]` How the platform uses the API for this entity: `application` (default) or `passthrough`. Present under the `user-profiles-2026-08-18` and later beta headers. - `"application"` The user profile represents an individual end-user of a product that the platform builds on the API. New profiles get this value by default. - `"passthrough"` The user profile represents a company that the platform resells Claude access to. - `external_id: Optional[str]` Platform's own identifier for this user. Not enforced unique. Present under the `user-profiles-2026-03-24` and `user-profiles-2026-08-18` beta headers; under `user-profiles-2026-09-04` the value is `external_user_details.reference_id`. - `external_user_details: Optional[BetaUserProfileExternalUserDetails]` Details about the entity this profile represents, as the platform states them; not verified by Anthropic. Present under the `user-profiles-2026-09-04` beta header, with every field present and `null` until the platform supplies a value; the earlier beta headers serve `reference_id` as the top-level `external_id`, and `user-profiles-2026-08-18` serves `onboarded_at` as `external_user_onboarded_at`. - `account_status: Optional[Literal["active", "suspended", "blocked"]]` The status of the entity's account on the platform: `active`, `suspended` or `blocked`. `null` until the platform supplies one. - `"active"` The platform has neither restricted nor barred the account of the entity that the user profile represents. - `"suspended"` The platform has restricted the account of the entity that the user profile represents and may restore it. - `"blocked"` The platform has barred the account of the entity that the user profile represents. - `country: Optional[str]` The country the platform associates with the entity, as an ISO 3166-1 alpha-2 code. `null` until the platform supplies one. - `email_hash: Optional[str]` The platform-computed hash of the entity's email address. `null` until the platform supplies one. - `entity_type: Optional[Literal["individual", "business", "non_profit", "government"]]` What kind of entity the profile represents: `individual`, `business`, `non_profit` or `government`. `null` until the platform supplies one. - `"individual"` - `"business"` - `"non_profit"` - `"government"` - `name_hash: Optional[str]` The platform-computed hash of the entity's name. `null` until the platform supplies one. - `onboarded_at: Optional[datetime]` When the entity opened its account with the platform, as stated by the platform, in RFC 3339 format (UTC). `null` until the platform supplies one. format: date-time - `reference_id: Optional[str]` The platform's own reference for the entity. `null` until the platform supplies one. - `external_user_onboarded_at: Optional[datetime]` When the entity this profile represents opened its account with the platform, as stated by the platform, in RFC 3339 format (UTC). `null` until the platform supplies one. Present under the `user-profiles-2026-08-18` beta header; under `user-profiles-2026-09-04` the value is `external_user_details.onboarded_at`. format: date-time - `name: Optional[str]` Real-world name of the entity this profile represents (company or individual). For a company the platform resells Claude access to (`access_type` `passthrough`) this is that company's name. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_user_profile = client.beta.user_profiles.retrieve( user_profile_id="uprof_011CZkZCu8hGbp5mYRQgUmz9", ) print(beta_user_profile.id) ``` ##### Response (200) ```json { "id": "uprof_011CZkZCu8hGbp5mYRQgUmz9", "created_at": "2026-03-15T10:00:00Z", "metadata": {}, "trust_grants": { "cyber": { "status": "active" } }, "type": "user_profile", "updated_at": "2026-03-15T10:00:00Z", "access_type": "application", "external_id": "user_12345", "external_user_details": { "account_status": "active", "country": "country", "email_hash": "email_hash", "entity_type": "individual", "name_hash": "name_hash", "onboarded_at": "2019-12-27T18:11:19.117Z", "reference_id": "reference_id" }, "external_user_onboarded_at": "2024-11-02T08:15:00Z", "name": "Example User" } ``` ### Update User Profile `beta.user_profiles.update(user_profile_id, **kwargs) -> BetaUserProfile` **POST** `/v1/user_profiles/{user_profile_id}` Update User Profile #### Parameters - `user_profile_id: str` (path parameter) The ID of the user profile to update (`uprof_...`). - `access_type: Optional[Literal["application", "passthrough"]]` If present, replaces the stored access type. Omit to leave unchanged. - `"application"` The user profile represents an individual end-user of a product that the platform builds on the API. New profiles get this value by default. - `"passthrough"` The user profile represents a company that the platform resells Claude access to. - `external_id: Optional[str]` If present, replaces the stored external_id. Omit to leave unchanged. Maximum 255 characters. Accepted under the `user-profiles-2026-03-24` and `user-profiles-2026-08-18` beta headers; under `user-profiles-2026-09-04` send `external_user_details.reference_id` instead. minLength: 1, maxLength: 255 - `external_user_details: Optional[BetaUserProfileExternalUserDetailsParams]` Details about the entity this profile represents, as the platform states them. Each field sent replaces the stored value; omit a field to leave it unchanged. Once set, a value cannot be cleared and `null` is rejected. Accepted under the `user-profiles-2026-09-04` beta header only. - `account_status: Optional[Literal["active", "suspended", "blocked"]]` The status of the entity's account on the platform: `active`, `suspended` or `blocked`. - `"active"` The platform has neither restricted nor barred the account of the entity that the user profile represents. - `"suspended"` The platform has restricted the account of the entity that the user profile represents and may restore it. - `"blocked"` The platform has barred the account of the entity that the user profile represents. - `country: Optional[str]` The country of the entity (not of the platform), as the platform determines it: an ISO 3166-1 alpha-2 code in upper case, for example `US`. Only the form, two uppercase ASCII letters, is checked. - `email_hash: Optional[str]` A hash of the entity's email address, computed by the platform. Anthropic treats it as an opaque string and does not prescribe the hash function. 1 to 255 characters. minLength: 1, maxLength: 255 - `entity_type: Optional[Literal["individual", "business", "non_profit", "government"]]` What kind of entity the profile represents: `individual`, `business`, `non_profit` or `government`. - `"individual"` - `"business"` - `"non_profit"` - `"government"` - `name_hash: Optional[str]` A hash of the entity's name, computed by the platform. Anthropic treats it as an opaque string and does not prescribe the hash function. 1 to 255 characters. minLength: 1, maxLength: 255 - `onboarded_at: Optional[datetime]` When the entity opened its account with the platform, in RFC 3339 format: for an `application` profile, when the end-user signed up; for a `passthrough` profile, when the company became the platform's customer. Must be a complete timestamp no more than 1 minute in the future. format: date-time - `reference_id: Optional[str]` The platform's own reference for the entity, for example the key of the end-user's row in the platform's database. Not interpreted by Anthropic and not enforced unique. 1 to 255 characters. minLength: 1, maxLength: 255 - `external_user_onboarded_at: Optional[Union[str, datetime]]` If present, replaces the stored account creation time. Omit to leave unchanged; once set, the value cannot be cleared and `null` is rejected. Must be a complete RFC 3339 timestamp no more than 1 minute in the future. Accepted under the `user-profiles-2026-08-18` beta header; under `user-profiles-2026-09-04` send `external_user_details.onboarded_at` instead. format: date-time - `metadata: Optional[Dict[str, str]]` Key-value pairs to merge into the stored metadata. Keys provided overwrite existing values. To remove a key, set its value to an empty string. Keys not provided are left unchanged. Maximum 16 keys, with keys up to 64 characters and values up to 512 characters. - `name: Optional[str]` If present, replaces the stored name. Omit to leave unchanged. Maximum 255 characters. minLength: 1, maxLength: 255 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaUserProfile` A record of an entity that the platform serves through the API, such as an end-user of the platform's product or a company that the platform resells Claude access to. A Messages, Message Batches or token counting request can send a profile's `id` in the `anthropic-user-profile-id` header to attribute the request to that entity. - `type: Literal["user_profile"]` Object type. Always `user_profile`. - `id: str` Unique identifier for this user profile, prefixed `uprof_`. - `created_at: datetime` When this user profile was created, in RFC 3339 format. format: date-time - `metadata: Dict[str, str]` Arbitrary key-value metadata. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars. - `trust_grants: Dict[str, BetaUserProfileTrustGrant]` Trust grants for this profile, keyed by grant name. Key omitted when no grant is active or in flight. - `status: Literal["active", "pending", "rejected"]` Status of the trust grant. - `"active"` - `"pending"` - `"rejected"` - `updated_at: datetime` When this user profile was last modified, in RFC 3339 format. Trust-grant status changes also bump this timestamp. format: date-time - `access_type: Optional[Literal["application", "passthrough"]]` How the platform uses the API for this entity: `application` (default) or `passthrough`. Present under the `user-profiles-2026-08-18` and later beta headers. - `"application"` The user profile represents an individual end-user of a product that the platform builds on the API. New profiles get this value by default. - `"passthrough"` The user profile represents a company that the platform resells Claude access to. - `external_id: Optional[str]` Platform's own identifier for this user. Not enforced unique. Present under the `user-profiles-2026-03-24` and `user-profiles-2026-08-18` beta headers; under `user-profiles-2026-09-04` the value is `external_user_details.reference_id`. - `external_user_details: Optional[BetaUserProfileExternalUserDetails]` Details about the entity this profile represents, as the platform states them; not verified by Anthropic. Present under the `user-profiles-2026-09-04` beta header, with every field present and `null` until the platform supplies a value; the earlier beta headers serve `reference_id` as the top-level `external_id`, and `user-profiles-2026-08-18` serves `onboarded_at` as `external_user_onboarded_at`. - `account_status: Optional[Literal["active", "suspended", "blocked"]]` The status of the entity's account on the platform: `active`, `suspended` or `blocked`. `null` until the platform supplies one. - `"active"` The platform has neither restricted nor barred the account of the entity that the user profile represents. - `"suspended"` The platform has restricted the account of the entity that the user profile represents and may restore it. - `"blocked"` The platform has barred the account of the entity that the user profile represents. - `country: Optional[str]` The country the platform associates with the entity, as an ISO 3166-1 alpha-2 code. `null` until the platform supplies one. - `email_hash: Optional[str]` The platform-computed hash of the entity's email address. `null` until the platform supplies one. - `entity_type: Optional[Literal["individual", "business", "non_profit", "government"]]` What kind of entity the profile represents: `individual`, `business`, `non_profit` or `government`. `null` until the platform supplies one. - `"individual"` - `"business"` - `"non_profit"` - `"government"` - `name_hash: Optional[str]` The platform-computed hash of the entity's name. `null` until the platform supplies one. - `onboarded_at: Optional[datetime]` When the entity opened its account with the platform, as stated by the platform, in RFC 3339 format (UTC). `null` until the platform supplies one. format: date-time - `reference_id: Optional[str]` The platform's own reference for the entity. `null` until the platform supplies one. - `external_user_onboarded_at: Optional[datetime]` When the entity this profile represents opened its account with the platform, as stated by the platform, in RFC 3339 format (UTC). `null` until the platform supplies one. Present under the `user-profiles-2026-08-18` beta header; under `user-profiles-2026-09-04` the value is `external_user_details.onboarded_at`. format: date-time - `name: Optional[str]` Real-world name of the entity this profile represents (company or individual). For a company the platform resells Claude access to (`access_type` `passthrough`) this is that company's name. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_user_profile = client.beta.user_profiles.update( user_profile_id="uprof_011CZkZCu8hGbp5mYRQgUmz9", ) print(beta_user_profile.id) ``` ##### Response (200) ```json { "id": "uprof_011CZkZCu8hGbp5mYRQgUmz9", "created_at": "2026-03-15T10:00:00Z", "metadata": {}, "trust_grants": { "cyber": { "status": "active" } }, "type": "user_profile", "updated_at": "2026-03-15T10:00:00Z", "access_type": "application", "external_id": "user_12345", "external_user_details": { "account_status": "active", "country": "country", "email_hash": "email_hash", "entity_type": "individual", "name_hash": "name_hash", "onboarded_at": "2019-12-27T18:11:19.117Z", "reference_id": "reference_id" }, "external_user_onboarded_at": "2024-11-02T08:15:00Z", "name": "Example User" } ``` ### Create Enrollment URL `beta.user_profiles.create_enrollment_url(user_profile_id, **kwargs) -> BetaUserProfileEnrollmentURL` **POST** `/v1/user_profiles/{user_profile_id}/enrollment_url` Create Enrollment URL #### Parameters - `user_profile_id: str` (path parameter) The ID of the user profile to create an enrollment URL for (`uprof_...`). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaUserProfileEnrollmentURL` A URL to give to the entity that a user profile represents, so that the entity can enroll for a trust grant. - `type: Literal["enrollment_url"]` Object type. Always `enrollment_url`. - `expires_at: datetime` When this enrollment URL expires, in RFC 3339 format. format: date-time - `url: str` Enrollment URL to send to the end user. Valid until `expires_at`. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_user_profile_enrollment_url = client.beta.user_profiles.create_enrollment_url( user_profile_id="uprof_011CZkZCu8hGbp5mYRQgUmz9", ) print(beta_user_profile_enrollment_url.expires_at) ``` ##### Response (200) ```json { "expires_at": "2026-03-15T10:15:00Z", "type": "enrollment_url", "url": "https://platform.claude.com/user-profiles/enrollment/M3J0bGJxZ2ppMnptbnB1" } ``` ## Beta › Dreams ### Create a Dream `beta.dreams.create(**kwargs) -> BetaDream` **POST** `/v1/dreams` Start an asynchronous job that uses past sessions to produce a reorganized version of a memory store and get back the dream to poll for the result. By default the dream writes its result to a new memory store and doesn't change the input memory store. The response has `status` set to `pending` and an empty `outputs` array. Poll the dream until `status` is `completed`, `failed`, or `canceled`. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#create-a-dream) to learn more about creating dreams. #### Parameters - `inputs: Iterable[BetaDreamInputParam]` The memory store and sessions for the dream to read, as exactly one `memory_store` entry and exactly one `sessions` entry. - `class BetaDreamMemoryStoreInput` The memory store that a dream reads, given as an entry in `inputs`. With `output_behavior` set to `update_existing`, the dream writes its result into this memory store. Otherwise the dream doesn't change it. - `type: Literal["memory_store"]` - `memory_store_id: str` The ID of the memory store for the dream to read (`memstore_...`). The memory store must be in the same workspace as the dream and must not be archived. minLength: 1 - `class BetaDreamSessionsInput` The sessions that a dream reads, given as an entry in `inputs`. - `type: Literal["sessions"]` - `session_ids: List[str]` The IDs of the sessions whose transcripts the dream reads (`sesn_...`). Give 1 to 100 IDs, with no duplicates. Each session must be in the same workspace as the dream. Responses list the IDs in sorted order. The [limits table in the Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#limits) lists all the limits on a dream. - `model: Model` The model that runs a dream, given as a model ID or as an object with `id` and `speed`. In the object form, `speed` can only be `standard`. The [limits table in the Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#limits) lists the supported models. - `str` - `class BetaDreamModelConfigParam` The object form of `model` in a request to create a dream. - `id: str` The ID of the model to run the dream with. The ID can be 1 to 256 characters long. The [limits table in the Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#limits) lists the supported models. minLength: 1, maxLength: 256 - `speed: Optional[Literal["standard", "fast"]]` How fast the model generates output for the dream. Defaults to `standard`. Dreams accept only `standard`. - `"standard"` - `"fast"` - `instructions: Optional[str]` Guidance that steers how the dream reads the sessions and organizes the output memory store, from 1 to 4,096 characters. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#steer-with-instructions) for what kinds of instructions work well. minLength: 1, maxLength: 4096 - `output_behavior: Optional[BetaOutputBehaviorParam]` Which memory store a dream writes its result to. Defaults to `create_new` when left out of a create request. - `class BetaOutputBehaviorCreateNew` Write the result to a new memory store that starts as a copy of the input memory store. This is the default. The new memory store is in the same workspace as the dream. The dream doesn't change the input memory store. - `type: Literal["create_new"]` - `class BetaOutputBehaviorUpdateExisting` Write the result into the input memory store instead of a new memory store. The credential must be allowed to write memory stores, or the request returns a 403 error. While another `update_existing` dream on the same memory store hasn't fully stopped, the request returns a 409 error. - `type: Literal["update_existing"]` - `memory_store_id: str` The ID of the memory store for the dream to write its result to (`memstore_...`). It must be the memory store in the `memory_store` entry of `inputs`. minLength: 1 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaDream` An asynchronous job that reads a memory store and past sessions, then writes a reorganized version of that memory store. By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into the input memory store instead. The Dreams API is in research preview: the request and response shapes are volatile and may change without the deprecation period that applies to generally-available endpoints. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#how-it-works) for what a dream reads and produces. - `type: Literal["dream"]` - `id: str` The unique ID of the dream (`drm_...`). - `archived_at: Optional[datetime]` When the dream was archived, in RFC 3339, or `null` if it hasn't been archived. format: date-time - `created_at: datetime` When the dream was created, in RFC 3339. Lists of dreams are sorted by this time, newest first. format: date-time - `ended_at: Optional[datetime]` When the dream reached `completed`, `failed`, or `canceled`, in RFC 3339, or `null` if it is still `pending` or `running`. format: date-time - `error: Optional[BetaDreamError]` Why the dream failed, or `null` if `status` isn't `failed`. - `type: str` A code for why the dream failed, such as `timeout` or `internal_error`. The [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#errors) lists common error codes and when they occur. - `message: str` A human-readable explanation of why the dream failed. - `inputs: List[BetaDreamInput]` The sources that the dream reads, from the request that created it. - `class BetaDreamMemoryStoreInput` The memory store that a dream reads, given as an entry in `inputs`. With `output_behavior` set to `update_existing`, the dream writes its result into this memory store. Otherwise the dream doesn't change it. - `type: Literal["memory_store"]` - `memory_store_id: str` The ID of the memory store for the dream to read (`memstore_...`). The memory store must be in the same workspace as the dream and must not be archived. minLength: 1 - `class BetaDreamSessionsInput` The sessions that a dream reads, given as an entry in `inputs`. - `type: Literal["sessions"]` - `session_ids: List[str]` The IDs of the sessions whose transcripts the dream reads (`sesn_...`). Give 1 to 100 IDs, with no duplicates. Each session must be in the same workspace as the dream. Responses list the IDs in sorted order. The [limits table in the Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#limits) lists all the limits on a dream. - `instructions: Optional[str]` The guidance given when the dream was created, or `null` if none was given. - `model: BetaDreamModelConfig` The model that runs a dream, from the request that created it. The dream uses this model for all of its work. The response always gives the model as an object, even if the request gave only a model ID. - `id: str` The ID of the model that runs the dream, as given in the request that created it. minLength: 1, maxLength: 256 - `speed: Optional[Literal["standard", "fast"]]` How fast the model generates output for the dream. Always `standard`. - `"standard"` - `"fast"` - `output_behavior: BetaOutputBehavior` Where the dream writes its result, as set in the request that created the dream. If that request left out `output_behavior`, the dream used the `create_new` behavior. - `class BetaOutputBehaviorCreateNew` Write the result to a new memory store that starts as a copy of the input memory store. This is the default. The new memory store is in the same workspace as the dream. The dream doesn't change the input memory store. - `type: Literal["create_new"]` - `class BetaOutputBehaviorUpdateExisting` Write the result into the input memory store instead of a new memory store. The credential must be allowed to write memory stores, or the request returns a 403 error. While another `update_existing` dream on the same memory store hasn't fully stopped, the request returns a 409 error. - `type: Literal["update_existing"]` - `memory_store_id: str` The ID of the memory store for the dream to write its result to (`memstore_...`). It must be the memory store in the `memory_store` entry of `inputs`. minLength: 1 - `outputs: List[BetaDreamOutput]` The memory store that holds the dream's result, as a one-item array, or an empty array until the dream records that memory store. The array is empty while the dream is `pending` and for a short time after it starts `running`. It can stay empty if the dream fails or is canceled before then. The memory store holds the complete result only once `status` is `completed`. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#use-the-output) for how to review and use the result. - `type: Literal["memory_store"]` - `memory_store_id: str` The ID of the memory store that the dream writes its result to (`memstore_...`). With `output_behavior` set to `create_new`, this is a new memory store. With `update_existing`, it is the input memory store. - `session_id: Optional[str]` The ID of the session that runs the dream (`sesn_...`), or `null` if that session hasn't started. Stream that session's events to follow what the dream reads and writes. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#watch-the-pipeline-run) for how to watch a running dream. - `status: BetaDreamStatus` Where a dream is in its lifecycle. `completed`, `failed`, and `canceled` are final: once a dream has one of these statuses, its status doesn't change again. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#lifecycle) for what each status means. - `"pending"` The dream is waiting to start and hasn't read its inputs yet. `outputs` is empty and every `usage` count is zero. - `"running"` The dream is reading its inputs and writing its result. `usage` updates while the dream has this status. - `"completed"` The dream finished and its output memory store holds the complete result. - `"failed"` The dream stopped with an error, which `error` describes. If `outputs` references a memory store, that memory store keeps what the dream wrote before it stopped. - `"canceled"` A cancel request stopped the dream before it reached `completed` or `failed`. If `outputs` references a memory store, that memory store keeps what the dream wrote. `usage` can keep changing after the cancel. - `usage: BetaDreamUsage` The dream's token counts, which stop changing once its `status` is `completed` or `failed`. After a cancel, they can keep changing. - `cache_creation_input_tokens: int` The dream's input tokens that were written to the prompt cache, for both the 5-minute and 1-hour cache durations. format: int32 - `cache_read_input_tokens: int` The dream's input tokens that were read from the prompt cache. format: int32 - `input_tokens: int` The dream's input tokens that weren't read from or written to the prompt cache. format: int32 - `output_tokens: int` The tokens that the model generated for the dream. format: int32 #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_dream = client.beta.dreams.create( inputs=[ { "memory_store_id": "x", "type": "memory_store", } ], model="string", ) print(beta_dream.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "ended_at": "2019-12-27T18:11:19.117Z", "error": { "message": "message", "type": "type" }, "inputs": [ { "memory_store_id": "x", "type": "memory_store" } ], "instructions": "instructions", "model": { "id": "x", "speed": "standard" }, "output_behavior": { "type": "create_new" }, "outputs": [ { "memory_store_id": "memory_store_id", "type": "memory_store" } ], "session_id": "session_id", "status": "pending", "type": "dream", "usage": { "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "input_tokens": 0, "output_tokens": 0 } } ``` ### List Dreams `beta.dreams.list(**kwargs) -> SyncPageCursor[BetaDream]` **GET** `/v1/dreams` List the dreams in the workspace, newest first. Archived dreams are left out unless `include_archived` is `true`. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#list-dreams) for how to page through dreams. #### Parameters - `created_at_gt: Optional[Union[str, datetime]]` (query parameter) Return only dreams created after this time (exclusive), in RFC 3339. format: date-time - `created_at_lt: Optional[Union[str, datetime]]` (query parameter) Return only dreams created before this time (exclusive), in RFC 3339. format: date-time - `include_archived: Optional[bool]` (query parameter) Whether to include archived dreams. Defaults to `false`. - `limit: Optional[int]` (query parameter) The maximum number of dreams to return, from 1 to 100. Defaults to 20. format: int32 - `page: Optional[str]` (query parameter) The cursor for the page to return, taken from `next_page` in a previous response. Leave it out to get the first page. - `statuses: Optional[List[BetaDreamStatus]]` (query parameter) Return only dreams that have one of these statuses. Repeat the parameter to give more than one status. Leave it out to return dreams of every status. - `"pending"` The dream is waiting to start and hasn't read its inputs yet. `outputs` is empty and every `usage` count is zero. - `"running"` The dream is reading its inputs and writing its result. `usage` updates while the dream has this status. - `"completed"` The dream finished and its output memory store holds the complete result. - `"failed"` The dream stopped with an error, which `error` describes. If `outputs` references a memory store, that memory store keeps what the dream wrote before it stopped. - `"canceled"` A cancel request stopped the dream before it reached `completed` or `failed`. If `outputs` references a memory store, that memory store keeps what the dream wrote. `usage` can keep changing after the cancel. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaDream` An asynchronous job that reads a memory store and past sessions, then writes a reorganized version of that memory store. By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into the input memory store instead. The Dreams API is in research preview: the request and response shapes are volatile and may change without the deprecation period that applies to generally-available endpoints. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#how-it-works) for what a dream reads and produces. - `type: Literal["dream"]` - `id: str` The unique ID of the dream (`drm_...`). - `archived_at: Optional[datetime]` When the dream was archived, in RFC 3339, or `null` if it hasn't been archived. format: date-time - `created_at: datetime` When the dream was created, in RFC 3339. Lists of dreams are sorted by this time, newest first. format: date-time - `ended_at: Optional[datetime]` When the dream reached `completed`, `failed`, or `canceled`, in RFC 3339, or `null` if it is still `pending` or `running`. format: date-time - `error: Optional[BetaDreamError]` Why the dream failed, or `null` if `status` isn't `failed`. - `type: str` A code for why the dream failed, such as `timeout` or `internal_error`. The [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#errors) lists common error codes and when they occur. - `message: str` A human-readable explanation of why the dream failed. - `inputs: List[BetaDreamInput]` The sources that the dream reads, from the request that created it. - `class BetaDreamMemoryStoreInput` The memory store that a dream reads, given as an entry in `inputs`. With `output_behavior` set to `update_existing`, the dream writes its result into this memory store. Otherwise the dream doesn't change it. - `type: Literal["memory_store"]` - `memory_store_id: str` The ID of the memory store for the dream to read (`memstore_...`). The memory store must be in the same workspace as the dream and must not be archived. minLength: 1 - `class BetaDreamSessionsInput` The sessions that a dream reads, given as an entry in `inputs`. - `type: Literal["sessions"]` - `session_ids: List[str]` The IDs of the sessions whose transcripts the dream reads (`sesn_...`). Give 1 to 100 IDs, with no duplicates. Each session must be in the same workspace as the dream. Responses list the IDs in sorted order. The [limits table in the Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#limits) lists all the limits on a dream. - `instructions: Optional[str]` The guidance given when the dream was created, or `null` if none was given. - `model: BetaDreamModelConfig` The model that runs a dream, from the request that created it. The dream uses this model for all of its work. The response always gives the model as an object, even if the request gave only a model ID. - `id: str` The ID of the model that runs the dream, as given in the request that created it. minLength: 1, maxLength: 256 - `speed: Optional[Literal["standard", "fast"]]` How fast the model generates output for the dream. Always `standard`. - `"standard"` - `"fast"` - `output_behavior: BetaOutputBehavior` Where the dream writes its result, as set in the request that created the dream. If that request left out `output_behavior`, the dream used the `create_new` behavior. - `class BetaOutputBehaviorCreateNew` Write the result to a new memory store that starts as a copy of the input memory store. This is the default. The new memory store is in the same workspace as the dream. The dream doesn't change the input memory store. - `type: Literal["create_new"]` - `class BetaOutputBehaviorUpdateExisting` Write the result into the input memory store instead of a new memory store. The credential must be allowed to write memory stores, or the request returns a 403 error. While another `update_existing` dream on the same memory store hasn't fully stopped, the request returns a 409 error. - `type: Literal["update_existing"]` - `memory_store_id: str` The ID of the memory store for the dream to write its result to (`memstore_...`). It must be the memory store in the `memory_store` entry of `inputs`. minLength: 1 - `outputs: List[BetaDreamOutput]` The memory store that holds the dream's result, as a one-item array, or an empty array until the dream records that memory store. The array is empty while the dream is `pending` and for a short time after it starts `running`. It can stay empty if the dream fails or is canceled before then. The memory store holds the complete result only once `status` is `completed`. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#use-the-output) for how to review and use the result. - `type: Literal["memory_store"]` - `memory_store_id: str` The ID of the memory store that the dream writes its result to (`memstore_...`). With `output_behavior` set to `create_new`, this is a new memory store. With `update_existing`, it is the input memory store. - `session_id: Optional[str]` The ID of the session that runs the dream (`sesn_...`), or `null` if that session hasn't started. Stream that session's events to follow what the dream reads and writes. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#watch-the-pipeline-run) for how to watch a running dream. - `status: BetaDreamStatus` Where a dream is in its lifecycle. `completed`, `failed`, and `canceled` are final: once a dream has one of these statuses, its status doesn't change again. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#lifecycle) for what each status means. - `"pending"` The dream is waiting to start and hasn't read its inputs yet. `outputs` is empty and every `usage` count is zero. - `"running"` The dream is reading its inputs and writing its result. `usage` updates while the dream has this status. - `"completed"` The dream finished and its output memory store holds the complete result. - `"failed"` The dream stopped with an error, which `error` describes. If `outputs` references a memory store, that memory store keeps what the dream wrote before it stopped. - `"canceled"` A cancel request stopped the dream before it reached `completed` or `failed`. If `outputs` references a memory store, that memory store keeps what the dream wrote. `usage` can keep changing after the cancel. - `usage: BetaDreamUsage` The dream's token counts, which stop changing once its `status` is `completed` or `failed`. After a cancel, they can keep changing. - `cache_creation_input_tokens: int` The dream's input tokens that were written to the prompt cache, for both the 5-minute and 1-hour cache durations. format: int32 - `cache_read_input_tokens: int` The dream's input tokens that were read from the prompt cache. format: int32 - `input_tokens: int` The dream's input tokens that weren't read from or written to the prompt cache. format: int32 - `output_tokens: int` The tokens that the model generated for the dream. format: int32 #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.dreams.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "ended_at": "2019-12-27T18:11:19.117Z", "error": { "message": "message", "type": "type" }, "inputs": [ { "memory_store_id": "x", "type": "memory_store" } ], "instructions": "instructions", "model": { "id": "x", "speed": "standard" }, "output_behavior": { "type": "create_new" }, "outputs": [ { "memory_store_id": "memory_store_id", "type": "memory_store" } ], "session_id": "session_id", "status": "pending", "type": "dream", "usage": { "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "input_tokens": 0, "output_tokens": 0 } } ], "next_page": "next_page" } ``` ### Get a Dream `beta.dreams.retrieve(dream_id, **kwargs) -> BetaDream` **GET** `/v1/dreams/{dream_id}` Get a dream by ID to check its status, output memory store, and token usage. Archived dreams are returned too. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#track-progress) for how to poll a dream and what each status means. #### Parameters - `dream_id: str` (path parameter) The ID of the dream to get (`drm_...`). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaDream` An asynchronous job that reads a memory store and past sessions, then writes a reorganized version of that memory store. By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into the input memory store instead. The Dreams API is in research preview: the request and response shapes are volatile and may change without the deprecation period that applies to generally-available endpoints. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#how-it-works) for what a dream reads and produces. - `type: Literal["dream"]` - `id: str` The unique ID of the dream (`drm_...`). - `archived_at: Optional[datetime]` When the dream was archived, in RFC 3339, or `null` if it hasn't been archived. format: date-time - `created_at: datetime` When the dream was created, in RFC 3339. Lists of dreams are sorted by this time, newest first. format: date-time - `ended_at: Optional[datetime]` When the dream reached `completed`, `failed`, or `canceled`, in RFC 3339, or `null` if it is still `pending` or `running`. format: date-time - `error: Optional[BetaDreamError]` Why the dream failed, or `null` if `status` isn't `failed`. - `type: str` A code for why the dream failed, such as `timeout` or `internal_error`. The [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#errors) lists common error codes and when they occur. - `message: str` A human-readable explanation of why the dream failed. - `inputs: List[BetaDreamInput]` The sources that the dream reads, from the request that created it. - `class BetaDreamMemoryStoreInput` The memory store that a dream reads, given as an entry in `inputs`. With `output_behavior` set to `update_existing`, the dream writes its result into this memory store. Otherwise the dream doesn't change it. - `type: Literal["memory_store"]` - `memory_store_id: str` The ID of the memory store for the dream to read (`memstore_...`). The memory store must be in the same workspace as the dream and must not be archived. minLength: 1 - `class BetaDreamSessionsInput` The sessions that a dream reads, given as an entry in `inputs`. - `type: Literal["sessions"]` - `session_ids: List[str]` The IDs of the sessions whose transcripts the dream reads (`sesn_...`). Give 1 to 100 IDs, with no duplicates. Each session must be in the same workspace as the dream. Responses list the IDs in sorted order. The [limits table in the Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#limits) lists all the limits on a dream. - `instructions: Optional[str]` The guidance given when the dream was created, or `null` if none was given. - `model: BetaDreamModelConfig` The model that runs a dream, from the request that created it. The dream uses this model for all of its work. The response always gives the model as an object, even if the request gave only a model ID. - `id: str` The ID of the model that runs the dream, as given in the request that created it. minLength: 1, maxLength: 256 - `speed: Optional[Literal["standard", "fast"]]` How fast the model generates output for the dream. Always `standard`. - `"standard"` - `"fast"` - `output_behavior: BetaOutputBehavior` Where the dream writes its result, as set in the request that created the dream. If that request left out `output_behavior`, the dream used the `create_new` behavior. - `class BetaOutputBehaviorCreateNew` Write the result to a new memory store that starts as a copy of the input memory store. This is the default. The new memory store is in the same workspace as the dream. The dream doesn't change the input memory store. - `type: Literal["create_new"]` - `class BetaOutputBehaviorUpdateExisting` Write the result into the input memory store instead of a new memory store. The credential must be allowed to write memory stores, or the request returns a 403 error. While another `update_existing` dream on the same memory store hasn't fully stopped, the request returns a 409 error. - `type: Literal["update_existing"]` - `memory_store_id: str` The ID of the memory store for the dream to write its result to (`memstore_...`). It must be the memory store in the `memory_store` entry of `inputs`. minLength: 1 - `outputs: List[BetaDreamOutput]` The memory store that holds the dream's result, as a one-item array, or an empty array until the dream records that memory store. The array is empty while the dream is `pending` and for a short time after it starts `running`. It can stay empty if the dream fails or is canceled before then. The memory store holds the complete result only once `status` is `completed`. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#use-the-output) for how to review and use the result. - `type: Literal["memory_store"]` - `memory_store_id: str` The ID of the memory store that the dream writes its result to (`memstore_...`). With `output_behavior` set to `create_new`, this is a new memory store. With `update_existing`, it is the input memory store. - `session_id: Optional[str]` The ID of the session that runs the dream (`sesn_...`), or `null` if that session hasn't started. Stream that session's events to follow what the dream reads and writes. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#watch-the-pipeline-run) for how to watch a running dream. - `status: BetaDreamStatus` Where a dream is in its lifecycle. `completed`, `failed`, and `canceled` are final: once a dream has one of these statuses, its status doesn't change again. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#lifecycle) for what each status means. - `"pending"` The dream is waiting to start and hasn't read its inputs yet. `outputs` is empty and every `usage` count is zero. - `"running"` The dream is reading its inputs and writing its result. `usage` updates while the dream has this status. - `"completed"` The dream finished and its output memory store holds the complete result. - `"failed"` The dream stopped with an error, which `error` describes. If `outputs` references a memory store, that memory store keeps what the dream wrote before it stopped. - `"canceled"` A cancel request stopped the dream before it reached `completed` or `failed`. If `outputs` references a memory store, that memory store keeps what the dream wrote. `usage` can keep changing after the cancel. - `usage: BetaDreamUsage` The dream's token counts, which stop changing once its `status` is `completed` or `failed`. After a cancel, they can keep changing. - `cache_creation_input_tokens: int` The dream's input tokens that were written to the prompt cache, for both the 5-minute and 1-hour cache durations. format: int32 - `cache_read_input_tokens: int` The dream's input tokens that were read from the prompt cache. format: int32 - `input_tokens: int` The dream's input tokens that weren't read from or written to the prompt cache. format: int32 - `output_tokens: int` The tokens that the model generated for the dream. format: int32 #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_dream = client.beta.dreams.retrieve( dream_id="dream_id", ) print(beta_dream.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "ended_at": "2019-12-27T18:11:19.117Z", "error": { "message": "message", "type": "type" }, "inputs": [ { "memory_store_id": "x", "type": "memory_store" } ], "instructions": "instructions", "model": { "id": "x", "speed": "standard" }, "output_behavior": { "type": "create_new" }, "outputs": [ { "memory_store_id": "memory_store_id", "type": "memory_store" } ], "session_id": "session_id", "status": "pending", "type": "dream", "usage": { "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "input_tokens": 0, "output_tokens": 0 } } ``` ### Cancel a Dream `beta.dreams.cancel(dream_id, **kwargs) -> BetaDream` **POST** `/v1/dreams/{dream_id}/cancel` Stop a `pending` or `running` dream. The response shows `status` as `canceled`, unless the dream reached `completed` or `failed` first. `usage` can keep changing after the response. Canceling a `canceled` dream returns it unchanged. Canceling a `completed` or `failed` dream returns a 400 error. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#cancel-a-dream) to learn more about canceling dreams. #### Parameters - `dream_id: str` (path parameter) The ID of the dream to cancel (`drm_...`). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaDream` An asynchronous job that reads a memory store and past sessions, then writes a reorganized version of that memory store. By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into the input memory store instead. The Dreams API is in research preview: the request and response shapes are volatile and may change without the deprecation period that applies to generally-available endpoints. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#how-it-works) for what a dream reads and produces. - `type: Literal["dream"]` - `id: str` The unique ID of the dream (`drm_...`). - `archived_at: Optional[datetime]` When the dream was archived, in RFC 3339, or `null` if it hasn't been archived. format: date-time - `created_at: datetime` When the dream was created, in RFC 3339. Lists of dreams are sorted by this time, newest first. format: date-time - `ended_at: Optional[datetime]` When the dream reached `completed`, `failed`, or `canceled`, in RFC 3339, or `null` if it is still `pending` or `running`. format: date-time - `error: Optional[BetaDreamError]` Why the dream failed, or `null` if `status` isn't `failed`. - `type: str` A code for why the dream failed, such as `timeout` or `internal_error`. The [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#errors) lists common error codes and when they occur. - `message: str` A human-readable explanation of why the dream failed. - `inputs: List[BetaDreamInput]` The sources that the dream reads, from the request that created it. - `class BetaDreamMemoryStoreInput` The memory store that a dream reads, given as an entry in `inputs`. With `output_behavior` set to `update_existing`, the dream writes its result into this memory store. Otherwise the dream doesn't change it. - `type: Literal["memory_store"]` - `memory_store_id: str` The ID of the memory store for the dream to read (`memstore_...`). The memory store must be in the same workspace as the dream and must not be archived. minLength: 1 - `class BetaDreamSessionsInput` The sessions that a dream reads, given as an entry in `inputs`. - `type: Literal["sessions"]` - `session_ids: List[str]` The IDs of the sessions whose transcripts the dream reads (`sesn_...`). Give 1 to 100 IDs, with no duplicates. Each session must be in the same workspace as the dream. Responses list the IDs in sorted order. The [limits table in the Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#limits) lists all the limits on a dream. - `instructions: Optional[str]` The guidance given when the dream was created, or `null` if none was given. - `model: BetaDreamModelConfig` The model that runs a dream, from the request that created it. The dream uses this model for all of its work. The response always gives the model as an object, even if the request gave only a model ID. - `id: str` The ID of the model that runs the dream, as given in the request that created it. minLength: 1, maxLength: 256 - `speed: Optional[Literal["standard", "fast"]]` How fast the model generates output for the dream. Always `standard`. - `"standard"` - `"fast"` - `output_behavior: BetaOutputBehavior` Where the dream writes its result, as set in the request that created the dream. If that request left out `output_behavior`, the dream used the `create_new` behavior. - `class BetaOutputBehaviorCreateNew` Write the result to a new memory store that starts as a copy of the input memory store. This is the default. The new memory store is in the same workspace as the dream. The dream doesn't change the input memory store. - `type: Literal["create_new"]` - `class BetaOutputBehaviorUpdateExisting` Write the result into the input memory store instead of a new memory store. The credential must be allowed to write memory stores, or the request returns a 403 error. While another `update_existing` dream on the same memory store hasn't fully stopped, the request returns a 409 error. - `type: Literal["update_existing"]` - `memory_store_id: str` The ID of the memory store for the dream to write its result to (`memstore_...`). It must be the memory store in the `memory_store` entry of `inputs`. minLength: 1 - `outputs: List[BetaDreamOutput]` The memory store that holds the dream's result, as a one-item array, or an empty array until the dream records that memory store. The array is empty while the dream is `pending` and for a short time after it starts `running`. It can stay empty if the dream fails or is canceled before then. The memory store holds the complete result only once `status` is `completed`. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#use-the-output) for how to review and use the result. - `type: Literal["memory_store"]` - `memory_store_id: str` The ID of the memory store that the dream writes its result to (`memstore_...`). With `output_behavior` set to `create_new`, this is a new memory store. With `update_existing`, it is the input memory store. - `session_id: Optional[str]` The ID of the session that runs the dream (`sesn_...`), or `null` if that session hasn't started. Stream that session's events to follow what the dream reads and writes. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#watch-the-pipeline-run) for how to watch a running dream. - `status: BetaDreamStatus` Where a dream is in its lifecycle. `completed`, `failed`, and `canceled` are final: once a dream has one of these statuses, its status doesn't change again. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#lifecycle) for what each status means. - `"pending"` The dream is waiting to start and hasn't read its inputs yet. `outputs` is empty and every `usage` count is zero. - `"running"` The dream is reading its inputs and writing its result. `usage` updates while the dream has this status. - `"completed"` The dream finished and its output memory store holds the complete result. - `"failed"` The dream stopped with an error, which `error` describes. If `outputs` references a memory store, that memory store keeps what the dream wrote before it stopped. - `"canceled"` A cancel request stopped the dream before it reached `completed` or `failed`. If `outputs` references a memory store, that memory store keeps what the dream wrote. `usage` can keep changing after the cancel. - `usage: BetaDreamUsage` The dream's token counts, which stop changing once its `status` is `completed` or `failed`. After a cancel, they can keep changing. - `cache_creation_input_tokens: int` The dream's input tokens that were written to the prompt cache, for both the 5-minute and 1-hour cache durations. format: int32 - `cache_read_input_tokens: int` The dream's input tokens that were read from the prompt cache. format: int32 - `input_tokens: int` The dream's input tokens that weren't read from or written to the prompt cache. format: int32 - `output_tokens: int` The tokens that the model generated for the dream. format: int32 #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_dream = client.beta.dreams.cancel( dream_id="dream_id", ) print(beta_dream.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "ended_at": "2019-12-27T18:11:19.117Z", "error": { "message": "message", "type": "type" }, "inputs": [ { "memory_store_id": "x", "type": "memory_store" } ], "instructions": "instructions", "model": { "id": "x", "speed": "standard" }, "output_behavior": { "type": "create_new" }, "outputs": [ { "memory_store_id": "memory_store_id", "type": "memory_store" } ], "session_id": "session_id", "status": "pending", "type": "dream", "usage": { "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "input_tokens": 0, "output_tokens": 0 } } ``` ### Archive a Dream `beta.dreams.archive(dream_id, **kwargs) -> BetaDream` **POST** `/v1/dreams/{dream_id}/archive` Hide a `completed`, `failed`, or `canceled` dream from the default list of dreams. Archiving a `pending` or `running` dream returns a 400 error, so cancel it first. Archiving an archived dream returns it unchanged. An archived dream can still be fetched by ID. Archiving can't be undone. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#archive-a-dream) to learn more about archiving dreams. #### Parameters - `dream_id: str` (path parameter) The ID of the dream to archive (`drm_...`). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaDream` An asynchronous job that reads a memory store and past sessions, then writes a reorganized version of that memory store. By default the dream writes its result to a new memory store and doesn't change the input memory store. With `output_behavior` set to `update_existing`, it writes its result into the input memory store instead. The Dreams API is in research preview: the request and response shapes are volatile and may change without the deprecation period that applies to generally-available endpoints. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#how-it-works) for what a dream reads and produces. - `type: Literal["dream"]` - `id: str` The unique ID of the dream (`drm_...`). - `archived_at: Optional[datetime]` When the dream was archived, in RFC 3339, or `null` if it hasn't been archived. format: date-time - `created_at: datetime` When the dream was created, in RFC 3339. Lists of dreams are sorted by this time, newest first. format: date-time - `ended_at: Optional[datetime]` When the dream reached `completed`, `failed`, or `canceled`, in RFC 3339, or `null` if it is still `pending` or `running`. format: date-time - `error: Optional[BetaDreamError]` Why the dream failed, or `null` if `status` isn't `failed`. - `type: str` A code for why the dream failed, such as `timeout` or `internal_error`. The [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#errors) lists common error codes and when they occur. - `message: str` A human-readable explanation of why the dream failed. - `inputs: List[BetaDreamInput]` The sources that the dream reads, from the request that created it. - `class BetaDreamMemoryStoreInput` The memory store that a dream reads, given as an entry in `inputs`. With `output_behavior` set to `update_existing`, the dream writes its result into this memory store. Otherwise the dream doesn't change it. - `type: Literal["memory_store"]` - `memory_store_id: str` The ID of the memory store for the dream to read (`memstore_...`). The memory store must be in the same workspace as the dream and must not be archived. minLength: 1 - `class BetaDreamSessionsInput` The sessions that a dream reads, given as an entry in `inputs`. - `type: Literal["sessions"]` - `session_ids: List[str]` The IDs of the sessions whose transcripts the dream reads (`sesn_...`). Give 1 to 100 IDs, with no duplicates. Each session must be in the same workspace as the dream. Responses list the IDs in sorted order. The [limits table in the Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#limits) lists all the limits on a dream. - `instructions: Optional[str]` The guidance given when the dream was created, or `null` if none was given. - `model: BetaDreamModelConfig` The model that runs a dream, from the request that created it. The dream uses this model for all of its work. The response always gives the model as an object, even if the request gave only a model ID. - `id: str` The ID of the model that runs the dream, as given in the request that created it. minLength: 1, maxLength: 256 - `speed: Optional[Literal["standard", "fast"]]` How fast the model generates output for the dream. Always `standard`. - `"standard"` - `"fast"` - `output_behavior: BetaOutputBehavior` Where the dream writes its result, as set in the request that created the dream. If that request left out `output_behavior`, the dream used the `create_new` behavior. - `class BetaOutputBehaviorCreateNew` Write the result to a new memory store that starts as a copy of the input memory store. This is the default. The new memory store is in the same workspace as the dream. The dream doesn't change the input memory store. - `type: Literal["create_new"]` - `class BetaOutputBehaviorUpdateExisting` Write the result into the input memory store instead of a new memory store. The credential must be allowed to write memory stores, or the request returns a 403 error. While another `update_existing` dream on the same memory store hasn't fully stopped, the request returns a 409 error. - `type: Literal["update_existing"]` - `memory_store_id: str` The ID of the memory store for the dream to write its result to (`memstore_...`). It must be the memory store in the `memory_store` entry of `inputs`. minLength: 1 - `outputs: List[BetaDreamOutput]` The memory store that holds the dream's result, as a one-item array, or an empty array until the dream records that memory store. The array is empty while the dream is `pending` and for a short time after it starts `running`. It can stay empty if the dream fails or is canceled before then. The memory store holds the complete result only once `status` is `completed`. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#use-the-output) for how to review and use the result. - `type: Literal["memory_store"]` - `memory_store_id: str` The ID of the memory store that the dream writes its result to (`memstore_...`). With `output_behavior` set to `create_new`, this is a new memory store. With `update_existing`, it is the input memory store. - `session_id: Optional[str]` The ID of the session that runs the dream (`sesn_...`), or `null` if that session hasn't started. Stream that session's events to follow what the dream reads and writes. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#watch-the-pipeline-run) for how to watch a running dream. - `status: BetaDreamStatus` Where a dream is in its lifecycle. `completed`, `failed`, and `canceled` are final: once a dream has one of these statuses, its status doesn't change again. See the [Dreams guide](https://platform.claude.com/docs/en/managed-agents/dreams?sdk_languages=python#lifecycle) for what each status means. - `"pending"` The dream is waiting to start and hasn't read its inputs yet. `outputs` is empty and every `usage` count is zero. - `"running"` The dream is reading its inputs and writing its result. `usage` updates while the dream has this status. - `"completed"` The dream finished and its output memory store holds the complete result. - `"failed"` The dream stopped with an error, which `error` describes. If `outputs` references a memory store, that memory store keeps what the dream wrote before it stopped. - `"canceled"` A cancel request stopped the dream before it reached `completed` or `failed`. If `outputs` references a memory store, that memory store keeps what the dream wrote. `usage` can keep changing after the cancel. - `usage: BetaDreamUsage` The dream's token counts, which stop changing once its `status` is `completed` or `failed`. After a cancel, they can keep changing. - `cache_creation_input_tokens: int` The dream's input tokens that were written to the prompt cache, for both the 5-minute and 1-hour cache durations. format: int32 - `cache_read_input_tokens: int` The dream's input tokens that were read from the prompt cache. format: int32 - `input_tokens: int` The dream's input tokens that weren't read from or written to the prompt cache. format: int32 - `output_tokens: int` The tokens that the model generated for the dream. format: int32 #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_dream = client.beta.dreams.archive( dream_id="dream_id", ) print(beta_dream.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "ended_at": "2019-12-27T18:11:19.117Z", "error": { "message": "message", "type": "type" }, "inputs": [ { "memory_store_id": "x", "type": "memory_store" } ], "instructions": "instructions", "model": { "id": "x", "speed": "standard" }, "output_behavior": { "type": "create_new" }, "outputs": [ { "memory_store_id": "memory_store_id", "type": "memory_store" } ], "session_id": "session_id", "status": "pending", "type": "dream", "usage": { "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "input_tokens": 0, "output_tokens": 0 } } ``` ## Beta › Tunnels ### Create Tunnel `beta.tunnels.create(**kwargs) -> BetaTunnel` **POST** `/v1/tunnels` The Tunnels API is in research preview. It requires the `anthropic-beta: mcp-tunnels-2026-06-22` header and may change without a deprecation period. It supersedes the Admin API endpoints at `/v1/organizations/tunnels`, which remain available during a migration window. Creates a tunnel. Creation allocates a fresh hostname and provisions the tunnel; it is not idempotent. The new tunnel rejects MCP traffic until at least one CA certificate is added. #### Parameters - `display_name: Optional[str]` Optional human-readable name for the tunnel (1-255 characters). minLength: 1, maxLength: 255 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaTunnel` An MCP tunnel. - `type: Literal["tunnel"]` - `id: str` Unique identifier for the tunnel, prefixed with `tnl_`. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the tunnel was archived. Null if it is not archived. format: date-time - `created_at: datetime` RFC 3339 datetime string indicating when the tunnel was created. format: date-time - `display_name: Optional[str]` Human-readable name for the tunnel (1-255 characters). Null if unset. - `domain: str` Anthropic-assigned hostname for the tunnel. MCP server URLs whose host is a subdomain of this value are routed through the tunnel. Globally unique and never reused, even after the tunnel is archived. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_tunnel = client.beta.tunnels.create() print(beta_tunnel.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "display_name": "display_name", "domain": "domain", "type": "tunnel" } ``` ### Get Tunnel `beta.tunnels.retrieve(tunnel_id, **kwargs) -> BetaTunnel` **GET** `/v1/tunnels/{tunnel_id}` The Tunnels API is in research preview. It requires the `anthropic-beta: mcp-tunnels-2026-06-22` header and may change without a deprecation period. It supersedes the Admin API endpoints at `/v1/organizations/tunnels`, which remain available during a migration window. Fetches a tunnel by ID. #### Parameters - `tunnel_id: str` (path parameter) ID of the tunnel (`tnl_...`). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaTunnel` An MCP tunnel. - `type: Literal["tunnel"]` - `id: str` Unique identifier for the tunnel, prefixed with `tnl_`. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the tunnel was archived. Null if it is not archived. format: date-time - `created_at: datetime` RFC 3339 datetime string indicating when the tunnel was created. format: date-time - `display_name: Optional[str]` Human-readable name for the tunnel (1-255 characters). Null if unset. - `domain: str` Anthropic-assigned hostname for the tunnel. MCP server URLs whose host is a subdomain of this value are routed through the tunnel. Globally unique and never reused, even after the tunnel is archived. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_tunnel = client.beta.tunnels.retrieve( tunnel_id="tunnel_id", ) print(beta_tunnel.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "display_name": "display_name", "domain": "domain", "type": "tunnel" } ``` ### List Tunnels `beta.tunnels.list(**kwargs) -> SyncPageCursor[BetaTunnel]` **GET** `/v1/tunnels` The Tunnels API is in research preview. It requires the `anthropic-beta: mcp-tunnels-2026-06-22` header and may change without a deprecation period. It supersedes the Admin API endpoints at `/v1/organizations/tunnels`, which remain available during a migration window. Lists tunnels. Results are ordered by creation time, newest first; archived tunnels are excluded unless include_archived is set. #### Parameters - `include_archived: Optional[bool]` (query parameter) Whether to include archived tunnels in the results. Defaults to false. - `limit: Optional[int]` (query parameter) Maximum number of tunnels to return per page. Defaults to 20, maximum 1000. format: int32 - `page: Optional[str]` (query parameter) Opaque pagination cursor from a previous `list_tunnels` response. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaTunnel` An MCP tunnel. - `type: Literal["tunnel"]` - `id: str` Unique identifier for the tunnel, prefixed with `tnl_`. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the tunnel was archived. Null if it is not archived. format: date-time - `created_at: datetime` RFC 3339 datetime string indicating when the tunnel was created. format: date-time - `display_name: Optional[str]` Human-readable name for the tunnel (1-255 characters). Null if unset. - `domain: str` Anthropic-assigned hostname for the tunnel. MCP server URLs whose host is a subdomain of this value are routed through the tunnel. Globally unique and never reused, even after the tunnel is archived. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.tunnels.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "display_name": "display_name", "domain": "domain", "type": "tunnel" } ], "next_page": "next_page" } ``` ### Archive Tunnel `beta.tunnels.archive(tunnel_id, **kwargs) -> BetaTunnel` **POST** `/v1/tunnels/{tunnel_id}/archive` The Tunnels API is in research preview. It requires the `anthropic-beta: mcp-tunnels-2026-06-22` header and may change without a deprecation period. It supersedes the Admin API endpoints at `/v1/organizations/tunnels`, which remain available during a migration window. Archives a tunnel. Archival is irreversible: every non-archived certificate on the tunnel is archived in the same operation, the hostname is retired and never re-allocated, and the tunnel token is invalidated. Retrying against an already-archived tunnel returns the existing record unchanged. #### Parameters - `tunnel_id: str` (path parameter) ID of the tunnel (`tnl_...`). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaTunnel` An MCP tunnel. - `type: Literal["tunnel"]` - `id: str` Unique identifier for the tunnel, prefixed with `tnl_`. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the tunnel was archived. Null if it is not archived. format: date-time - `created_at: datetime` RFC 3339 datetime string indicating when the tunnel was created. format: date-time - `display_name: Optional[str]` Human-readable name for the tunnel (1-255 characters). Null if unset. - `domain: str` Anthropic-assigned hostname for the tunnel. MCP server URLs whose host is a subdomain of this value are routed through the tunnel. Globally unique and never reused, even after the tunnel is archived. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_tunnel = client.beta.tunnels.archive( tunnel_id="tunnel_id", ) print(beta_tunnel.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "display_name": "display_name", "domain": "domain", "type": "tunnel" } ``` ### Reveal Tunnel Token `beta.tunnels.reveal_token(tunnel_id, **kwargs) -> BetaTunnelToken` **POST** `/v1/tunnels/{tunnel_id}/reveal_token` The Tunnels API is in research preview. It requires the `anthropic-beta: mcp-tunnels-2026-06-22` header and may change without a deprecation period. It supersedes the Admin API endpoints at `/v1/organizations/tunnels`, which remain available during a migration window. Reveals a tunnel's connector token. The value is fetched live on each call; Anthropic does not store it. Repeated calls return the same value until the token is rotated. Exposed as POST so the token does not appear in intermediary access logs. #### Parameters - `tunnel_id: str` (path parameter) ID of the tunnel (`tnl_...`). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaTunnelToken` A tunnel's connector token. - `type: Literal["tunnel_token"]` - `id: str` Stable identifier for the current token value. Changes when the token is rotated. - `tunnel_token: str` The connector token used to run the tunnel. Treat as a credential. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_tunnel_token = client.beta.tunnels.reveal_token( tunnel_id="tunnel_id", ) print(beta_tunnel_token.id) ``` ##### Response (200) ```json { "id": "id", "tunnel_token": "tunnel_token", "type": "tunnel_token" } ``` ### Rotate Tunnel Token `beta.tunnels.rotate_token(tunnel_id, **kwargs) -> BetaTunnelToken` **POST** `/v1/tunnels/{tunnel_id}/rotate_token` The Tunnels API is in research preview. It requires the `anthropic-beta: mcp-tunnels-2026-06-22` header and may change without a deprecation period. It supersedes the Admin API endpoints at `/v1/organizations/tunnels`, which remain available during a migration window. Rotates a tunnel's connector token. Rotation invalidates the current token for new connections and returns a fresh value; established connections are not severed. A connector restarted after rotation must use the new value. #### Parameters - `tunnel_id: str` (path parameter) ID of the tunnel (`tnl_...`). - `reason: Optional[str]` Optional free-text reason for the rotation, recorded for audit. maxLength: 1024 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaTunnelToken` A tunnel's connector token. - `type: Literal["tunnel_token"]` - `id: str` Stable identifier for the current token value. Changes when the token is rotated. - `tunnel_token: str` The connector token used to run the tunnel. Treat as a credential. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_tunnel_token = client.beta.tunnels.rotate_token( tunnel_id="tunnel_id", ) print(beta_tunnel_token.id) ``` ##### Response (200) ```json { "id": "id", "tunnel_token": "tunnel_token", "type": "tunnel_token" } ``` ## Beta › Tunnels › Certificates ### Create Tunnel Certificate `beta.tunnels.certificates.create(tunnel_id, **kwargs) -> BetaTunnelCertificate` **POST** `/v1/tunnels/{tunnel_id}/certificates` The Tunnels API is in research preview. It requires the `anthropic-beta: mcp-tunnels-2026-06-22` header and may change without a deprecation period. It supersedes the Admin API endpoints at `/v1/organizations/tunnels`, which remain available during a migration window. Registers a public CA certificate on a tunnel. Anthropic verifies the gateway's server certificate against this CA when it terminates the inner TLS session. A tunnel holds at most two non-archived certificates. #### Parameters - `tunnel_id: str` (path parameter) ID of the tunnel (`tnl_...`). - `ca_certificate_pem: str` PEM-encoded X.509 CA certificate. Must contain exactly one certificate and no private-key material. Maximum 8KB. maxLength: 8192 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaTunnelCertificate` A CA certificate attached to a tunnel. - `type: Literal["tunnel_certificate"]` - `id: str` Unique identifier for the certificate, prefixed with `tcrt_`. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the certificate was archived. Null if it is still in the trusted set. format: date-time - `created_at: datetime` RFC 3339 datetime string indicating when the certificate was registered. format: date-time - `expires_at: Optional[datetime]` RFC 3339 datetime string indicating when the certificate expires, or `null` if it does not expire. format: date-time - `fingerprint: str` Lowercase hex SHA-256 fingerprint of the certificate's DER encoding. - `tunnel_id: str` ID of the tunnel the certificate is registered against. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_tunnel_certificate = client.beta.tunnels.certificates.create( tunnel_id="tunnel_id", ca_certificate_pem="ca_certificate_pem", ) print(beta_tunnel_certificate.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "expires_at": "2019-12-27T18:11:19.117Z", "fingerprint": "fingerprint", "tunnel_id": "tunnel_id", "type": "tunnel_certificate" } ``` ### Get Tunnel Certificate `beta.tunnels.certificates.retrieve(certificate_id, **kwargs) -> BetaTunnelCertificate` **GET** `/v1/tunnels/{tunnel_id}/certificates/{certificate_id}` The Tunnels API is in research preview. It requires the `anthropic-beta: mcp-tunnels-2026-06-22` header and may change without a deprecation period. It supersedes the Admin API endpoints at `/v1/organizations/tunnels`, which remain available during a migration window. Fetches a tunnel certificate by ID. #### Parameters - `tunnel_id: str` (path parameter) ID of the tunnel (`tnl_...`). - `certificate_id: str` (path parameter) ID of the certificate (`tcrt_...`). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaTunnelCertificate` A CA certificate attached to a tunnel. - `type: Literal["tunnel_certificate"]` - `id: str` Unique identifier for the certificate, prefixed with `tcrt_`. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the certificate was archived. Null if it is still in the trusted set. format: date-time - `created_at: datetime` RFC 3339 datetime string indicating when the certificate was registered. format: date-time - `expires_at: Optional[datetime]` RFC 3339 datetime string indicating when the certificate expires, or `null` if it does not expire. format: date-time - `fingerprint: str` Lowercase hex SHA-256 fingerprint of the certificate's DER encoding. - `tunnel_id: str` ID of the tunnel the certificate is registered against. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_tunnel_certificate = client.beta.tunnels.certificates.retrieve( certificate_id="certificate_id", tunnel_id="tunnel_id", ) print(beta_tunnel_certificate.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "expires_at": "2019-12-27T18:11:19.117Z", "fingerprint": "fingerprint", "tunnel_id": "tunnel_id", "type": "tunnel_certificate" } ``` ### List Tunnel Certificates `beta.tunnels.certificates.list(tunnel_id, **kwargs) -> SyncPageCursor[BetaTunnelCertificate]` **GET** `/v1/tunnels/{tunnel_id}/certificates` The Tunnels API is in research preview. It requires the `anthropic-beta: mcp-tunnels-2026-06-22` header and may change without a deprecation period. It supersedes the Admin API endpoints at `/v1/organizations/tunnels`, which remain available during a migration window. Lists the certificates registered on a tunnel. Archived certificates are excluded unless include_archived is set. #### Parameters - `tunnel_id: str` (path parameter) ID of the tunnel (`tnl_...`). - `include_archived: Optional[bool]` (query parameter) Whether to include archived certificates in the results. Defaults to false. - `limit: Optional[int]` (query parameter) Maximum number of certificates to return per page. Defaults to 20, maximum 1000. format: int32 - `page: Optional[str]` (query parameter) Opaque pagination cursor from a previous `list_tunnel_certificates` response. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaTunnelCertificate` A CA certificate attached to a tunnel. - `type: Literal["tunnel_certificate"]` - `id: str` Unique identifier for the certificate, prefixed with `tcrt_`. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the certificate was archived. Null if it is still in the trusted set. format: date-time - `created_at: datetime` RFC 3339 datetime string indicating when the certificate was registered. format: date-time - `expires_at: Optional[datetime]` RFC 3339 datetime string indicating when the certificate expires, or `null` if it does not expire. format: date-time - `fingerprint: str` Lowercase hex SHA-256 fingerprint of the certificate's DER encoding. - `tunnel_id: str` ID of the tunnel the certificate is registered against. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.tunnels.certificates.list( tunnel_id="tunnel_id", ) page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "expires_at": "2019-12-27T18:11:19.117Z", "fingerprint": "fingerprint", "tunnel_id": "tunnel_id", "type": "tunnel_certificate" } ], "next_page": "next_page" } ``` ### Archive Tunnel Certificate `beta.tunnels.certificates.archive(certificate_id, **kwargs) -> BetaTunnelCertificate` **POST** `/v1/tunnels/{tunnel_id}/certificates/{certificate_id}/archive` The Tunnels API is in research preview. It requires the `anthropic-beta: mcp-tunnels-2026-06-22` header and may change without a deprecation period. It supersedes the Admin API endpoints at `/v1/organizations/tunnels`, which remain available during a migration window. Archives a tunnel certificate, removing it from the set Anthropic trusts for the tunnel. The certificate record is retained. Archiving the last non-archived certificate is permitted; the tunnel rejects MCP traffic until a new certificate is added. #### Parameters - `tunnel_id: str` (path parameter) ID of the tunnel (`tnl_...`). - `certificate_id: str` (path parameter) ID of the certificate to archive (`tcrt_...`). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` - `workspace_id: Optional[str]` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. #### Returns - `class BetaTunnelCertificate` A CA certificate attached to a tunnel. - `type: Literal["tunnel_certificate"]` - `id: str` Unique identifier for the certificate, prefixed with `tcrt_`. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the certificate was archived. Null if it is still in the trusted set. format: date-time - `created_at: datetime` RFC 3339 datetime string indicating when the certificate was registered. format: date-time - `expires_at: Optional[datetime]` RFC 3339 datetime string indicating when the certificate expires, or `null` if it does not expire. format: date-time - `fingerprint: str` Lowercase hex SHA-256 fingerprint of the certificate's DER encoding. - `tunnel_id: str` ID of the tunnel the certificate is registered against. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_tunnel_certificate = client.beta.tunnels.certificates.archive( certificate_id="certificate_id", tunnel_id="tunnel_id", ) print(beta_tunnel_certificate.id) ``` ##### Response (200) ```json { "id": "id", "archived_at": "2019-12-27T18:11:19.117Z", "created_at": "2019-12-27T18:11:19.117Z", "expires_at": "2019-12-27T18:11:19.117Z", "fingerprint": "fingerprint", "tunnel_id": "tunnel_id", "type": "tunnel_certificate" } ``` ## Beta › Organization ### Get Current Organization `beta.organization.retrieve() -> BetaOrganization` **GET** `/v1/organizations/me` Retrieve information about the organization associated with the authenticated API key. #### Returns - `class BetaOrganization` - `type: Literal["organization"]` Object type. For Organizations, this is always `"organization"`. default: organization - `id: str` ID of the Organization. format: uuid - `name: str` Name of the Organization. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_organization = client.beta.organization.retrieve() print(beta_organization.id) ``` ##### Response (200) ```json { "id": "12345678-1234-5678-1234-567812345678", "name": "Organization Name", "type": "organization" } ``` ## Beta › Organization › API Keys ### List API Keys `beta.organization.api_keys.list(**kwargs) -> SyncPage[BetaAPIKey]` **GET** `/v1/organizations/api_keys` List API Keys #### Parameters - `after_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately after this object. - `before_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately before this object. - `created_by_user_id: Optional[str]` (query parameter) Filter by the ID of the User who created the object. - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 - `status: Optional[Literal["active", "archived", "expired", "inactive"]]` (query parameter) Filter by API key status. - `"active"` - `"archived"` - `"expired"` - `"inactive"` - `workspace_id: Optional[str]` (query parameter) Filter by Workspace ID. #### Returns - `class BetaAPIKey` - `type: Literal["api_key"]` Object type. For API Keys, this is always `"api_key"`. default: api_key - `id: str` ID of the API key. - `created_at: datetime` RFC 3339 datetime string indicating when the API Key was created. format: date-time - `created_by: Optional[BetaAPIKeyCreatedBy]` The ID and type of the actor that created the API key, or `null` when the creator is not recorded (legacy, workload-identity-federated, or system-created keys). - `type: Literal["service_account", "user"]` Type of the actor that created the object. - `"service_account"` - `"user"` - `id: str` ID of the actor that created the object. - `expires_at: Optional[datetime]` RFC 3339 datetime string indicating when the API Key expires, or `null` if it never expires. format: date-time - `name: str` Name of the API key. - `partial_key_hint: Optional[str]` Partially redacted hint for the API key. - `principal: Optional[Principal]` The principal the API key acts as (a User or a Service Account), or `null` if the API key is not bound to a principal. - `class BetaAPIKeyUserActor` - `type: Literal["user_actor"]` Principal type. Always `"user_actor"` for a User. default: user_actor - `user_id: str` ID of the User the API key acts as. - `class BetaAPIKeyServiceAccountActor` - `type: Literal["service_account_actor"]` Principal type. Always `"service_account_actor"` for a Service Account. default: service_account_actor - `service_account_id: str` ID of the Service Account the API key acts as. - `scope: Scope` Where the API key belongs: its Workspace (`{"type": "workspace", "workspace_id": "wrkspc_..."}`, with the Workspace's real ID even when it is the organization's default Workspace), or the organization (`{"type": "organization"}`) for a principal-bound API key that has no Workspace. - `class BetaAPIKeyOrganizationScope` - `type: Literal["organization"]` Scope type. Always `"organization"`: the API key has no Workspace. Only a principal-bound API key can have this scope. default: organization - `class BetaAPIKeyWorkspaceScope` - `type: Literal["workspace"]` Scope type. Always `"workspace"`: the API key belongs to one Workspace. default: workspace - `workspace_id: str` ID of the Workspace the API key belongs to. Unlike the deprecated top-level `workspace_id`, this is the Workspace's real ID even for the organization's default Workspace. - `status: Literal["active", "archived", "expired", "inactive"]` Status of the API key. - `"active"` - `"archived"` - `"expired"` - `"inactive"` - `workspace_id: Optional[str]` **Deprecated**: Use `scope` instead. `workspace_id` is `null` both for an API key in the default Workspace and for a principal-bound API key that has no Workspace. Deprecated: use `scope` instead. ID of the Workspace associated with the API key, or `null` if the API key belongs to the default Workspace. Also `null` for a principal-bound API key that has no Workspace; `scope` tells the two apart. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.api_keys.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "apikey_01Rj2N8SVvo6BePZj99NhmiT", "created_at": "2024-10-30T23:58:27.427722Z", "created_by": { "id": "user_01WCz1FkmYMm4gnmykNKUu3Q", "type": "user" }, "expires_at": "2024-10-30T23:58:27.427722Z", "name": "Developer Key", "partial_key_hint": "sk-ant-api03-R2D...igAA", "principal": { "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "scope": { "type": "workspace", "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ" }, "status": "active", "type": "api_key", "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ" } ], "first_id": "first_id", "has_more": true, "last_id": "last_id" } ``` ### Retrieve API Key (Admin API) `beta.organization.api_keys.retrieve(api_key_id) -> BetaAPIKey` **GET** `/v1/organizations/api_keys/{api_key_id}` Retrieve information about a single API key in your organization, looked up by its ID. This Admin API endpoint requires an Admin API key, is intended for programmatic key management, and never returns the key's secret value. To view or create your own API keys, go to [API keys](https://platform.claude.com/settings/keys) in the Claude Console. #### Parameters - `api_key_id: str` (path parameter) ID of the API key. #### Returns - `class BetaAPIKey` - `type: Literal["api_key"]` Object type. For API Keys, this is always `"api_key"`. default: api_key - `id: str` ID of the API key. - `created_at: datetime` RFC 3339 datetime string indicating when the API Key was created. format: date-time - `created_by: Optional[BetaAPIKeyCreatedBy]` The ID and type of the actor that created the API key, or `null` when the creator is not recorded (legacy, workload-identity-federated, or system-created keys). - `type: Literal["service_account", "user"]` Type of the actor that created the object. - `"service_account"` - `"user"` - `id: str` ID of the actor that created the object. - `expires_at: Optional[datetime]` RFC 3339 datetime string indicating when the API Key expires, or `null` if it never expires. format: date-time - `name: str` Name of the API key. - `partial_key_hint: Optional[str]` Partially redacted hint for the API key. - `principal: Optional[Principal]` The principal the API key acts as (a User or a Service Account), or `null` if the API key is not bound to a principal. - `class BetaAPIKeyUserActor` - `type: Literal["user_actor"]` Principal type. Always `"user_actor"` for a User. default: user_actor - `user_id: str` ID of the User the API key acts as. - `class BetaAPIKeyServiceAccountActor` - `type: Literal["service_account_actor"]` Principal type. Always `"service_account_actor"` for a Service Account. default: service_account_actor - `service_account_id: str` ID of the Service Account the API key acts as. - `scope: Scope` Where the API key belongs: its Workspace (`{"type": "workspace", "workspace_id": "wrkspc_..."}`, with the Workspace's real ID even when it is the organization's default Workspace), or the organization (`{"type": "organization"}`) for a principal-bound API key that has no Workspace. - `class BetaAPIKeyOrganizationScope` - `type: Literal["organization"]` Scope type. Always `"organization"`: the API key has no Workspace. Only a principal-bound API key can have this scope. default: organization - `class BetaAPIKeyWorkspaceScope` - `type: Literal["workspace"]` Scope type. Always `"workspace"`: the API key belongs to one Workspace. default: workspace - `workspace_id: str` ID of the Workspace the API key belongs to. Unlike the deprecated top-level `workspace_id`, this is the Workspace's real ID even for the organization's default Workspace. - `status: Literal["active", "archived", "expired", "inactive"]` Status of the API key. - `"active"` - `"archived"` - `"expired"` - `"inactive"` - `workspace_id: Optional[str]` **Deprecated**: Use `scope` instead. `workspace_id` is `null` both for an API key in the default Workspace and for a principal-bound API key that has no Workspace. Deprecated: use `scope` instead. ID of the Workspace associated with the API key, or `null` if the API key belongs to the default Workspace. Also `null` for a principal-bound API key that has no Workspace; `scope` tells the two apart. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_api_key = client.beta.organization.api_keys.retrieve( "api_key_id", ) print(beta_api_key.id) ``` ##### Response (200) ```json { "id": "apikey_01Rj2N8SVvo6BePZj99NhmiT", "created_at": "2024-10-30T23:58:27.427722Z", "created_by": { "id": "user_01WCz1FkmYMm4gnmykNKUu3Q", "type": "user" }, "expires_at": "2024-10-30T23:58:27.427722Z", "name": "Developer Key", "partial_key_hint": "sk-ant-api03-R2D...igAA", "principal": { "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "scope": { "type": "workspace", "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ" }, "status": "active", "type": "api_key", "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ" } ``` ### Update API Key `beta.organization.api_keys.update(api_key_id, **kwargs) -> BetaAPIKey` **POST** `/v1/organizations/api_keys/{api_key_id}` Update API Key #### Parameters - `api_key_id: str` (path parameter) ID of the API key. - `name: Optional[str]` Name of the API key. minLength: 1, maxLength: 500 - `status: Optional[Literal["active", "archived", "inactive"]]` Status of the API key. - `"active"` - `"archived"` - `"inactive"` #### Returns - `class BetaAPIKey` - `type: Literal["api_key"]` Object type. For API Keys, this is always `"api_key"`. default: api_key - `id: str` ID of the API key. - `created_at: datetime` RFC 3339 datetime string indicating when the API Key was created. format: date-time - `created_by: Optional[BetaAPIKeyCreatedBy]` The ID and type of the actor that created the API key, or `null` when the creator is not recorded (legacy, workload-identity-federated, or system-created keys). - `type: Literal["service_account", "user"]` Type of the actor that created the object. - `"service_account"` - `"user"` - `id: str` ID of the actor that created the object. - `expires_at: Optional[datetime]` RFC 3339 datetime string indicating when the API Key expires, or `null` if it never expires. format: date-time - `name: str` Name of the API key. - `partial_key_hint: Optional[str]` Partially redacted hint for the API key. - `principal: Optional[Principal]` The principal the API key acts as (a User or a Service Account), or `null` if the API key is not bound to a principal. - `class BetaAPIKeyUserActor` - `type: Literal["user_actor"]` Principal type. Always `"user_actor"` for a User. default: user_actor - `user_id: str` ID of the User the API key acts as. - `class BetaAPIKeyServiceAccountActor` - `type: Literal["service_account_actor"]` Principal type. Always `"service_account_actor"` for a Service Account. default: service_account_actor - `service_account_id: str` ID of the Service Account the API key acts as. - `scope: Scope` Where the API key belongs: its Workspace (`{"type": "workspace", "workspace_id": "wrkspc_..."}`, with the Workspace's real ID even when it is the organization's default Workspace), or the organization (`{"type": "organization"}`) for a principal-bound API key that has no Workspace. - `class BetaAPIKeyOrganizationScope` - `type: Literal["organization"]` Scope type. Always `"organization"`: the API key has no Workspace. Only a principal-bound API key can have this scope. default: organization - `class BetaAPIKeyWorkspaceScope` - `type: Literal["workspace"]` Scope type. Always `"workspace"`: the API key belongs to one Workspace. default: workspace - `workspace_id: str` ID of the Workspace the API key belongs to. Unlike the deprecated top-level `workspace_id`, this is the Workspace's real ID even for the organization's default Workspace. - `status: Literal["active", "archived", "expired", "inactive"]` Status of the API key. - `"active"` - `"archived"` - `"expired"` - `"inactive"` - `workspace_id: Optional[str]` **Deprecated**: Use `scope` instead. `workspace_id` is `null` both for an API key in the default Workspace and for a principal-bound API key that has no Workspace. Deprecated: use `scope` instead. ID of the Workspace associated with the API key, or `null` if the API key belongs to the default Workspace. Also `null` for a principal-bound API key that has no Workspace; `scope` tells the two apart. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_api_key = client.beta.organization.api_keys.update( api_key_id="api_key_id", ) print(beta_api_key.id) ``` ##### Response (200) ```json { "id": "apikey_01Rj2N8SVvo6BePZj99NhmiT", "created_at": "2024-10-30T23:58:27.427722Z", "created_by": { "id": "user_01WCz1FkmYMm4gnmykNKUu3Q", "type": "user" }, "expires_at": "2024-10-30T23:58:27.427722Z", "name": "Developer Key", "partial_key_hint": "sk-ant-api03-R2D...igAA", "principal": { "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "scope": { "type": "workspace", "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ" }, "status": "active", "type": "api_key", "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ" } ``` ## Beta › Organization › External Keys ### Create External Key `beta.organization.external_keys.create(**kwargs) -> BetaExternalKey` **POST** `/v1/organizations/external_keys` Create an external key config owned by the caller's organization. #### Parameters - `provider_config: ProviderConfig` KMS provider identity and auth coordinates. - `class BetaAWSExternalKeyConfig` - `type: Literal["aws"]` - `kms_arn: str` Full ARN of the AWS KMS key. On Claude Platform on AWS the key must be a single-Region key in your organization's own AWS account; cross-account keys, multi-Region keys, and alias ARNs are rejected. maxLength: 2048 - `region: Optional[str]` AWS region. Derived from `kms_arn` if omitted. - `role_arn: Optional[str]` **Deprecated** IAM role ARN. Deprecated — Anthropic reaches the KMS key through its own intermediate role (or, on Claude Platform on AWS, with credentials AWS issues for the Workspace); this field is ignored. - `class BetaGCPExternalKeyConfig` - `type: Literal["gcp"]` - `key_name: str` Full resource name of the Cloud KMS key. - `class BetaAzureExternalKeyConfigParam` Azure Key Vault provider configuration. - `type: Literal["azure"]` - `key_name: str` Name of the key within the vault. - `tenant_id: str` Azure AD tenant ID. - `vault_uri: str` Key Vault data-plane URI — `https://{vault-name}.vault.azure.net` or `https://{hsm-name}.managedhsm.azure.net`. - `client_id: Optional[str]` Azure AD application (client) ID. Omit to use Anthropic's multitenant app. Provide only if using a single-tenant app registration in the customer's directory. - `display_name: Optional[str]` Human-friendly display name. minLength: 1, maxLength: 255 - `geo: Optional[Literal["us"]]` Data residency geo. Only `us` is supported. #### Returns - `class BetaExternalKey` CMEK external key config belonging to the caller's organization. Configs are organization-scoped. Workspaces attach to a config; once any workspace references it, the provider fields become effectively immutable (existing encrypted data needs the config for decrypt). - `type: Literal["external_key"]` default: external_key - `id: str` Identifier of the external key config. A tagged ID prefixed `ekey_`, or — for organizations on the Claude Platform on AWS — the AWS KMS key ARN. - `attachment: Attachment` Whether any workspace uses this config to encrypt its data — counting live and archived workspaces (an archived workspace's data remains encrypted under the config), excluding deleted ones. Only an attached config is used by the encryption path; an `unattached` config is inert and can be deleted. - `class BetaExternalKeyAttachedAttachment` - `type: Literal["attached"]` default: attached - `class BetaExternalKeyUnattachedAttachment` - `type: Literal["unattached"]` default: unattached - `created_at: datetime` format: date-time - `display_name: Optional[str]` Human-friendly display name. Null if none was set. - `geo: str` Data residency geo. Selects which regional validator handles this key's encrypt/decrypt roundtrips. - `provider_config: ProviderConfig` KMS provider identity and auth coordinates. - `class BetaAWSExternalKeyConfig` - `type: Literal["aws"]` - `kms_arn: str` Full ARN of the AWS KMS key. On Claude Platform on AWS the key must be a single-Region key in your organization's own AWS account; cross-account keys, multi-Region keys, and alias ARNs are rejected. maxLength: 2048 - `region: Optional[str]` AWS region. Derived from `kms_arn` if omitted. - `role_arn: Optional[str]` **Deprecated** IAM role ARN. Deprecated — Anthropic reaches the KMS key through its own intermediate role (or, on Claude Platform on AWS, with credentials AWS issues for the Workspace); this field is ignored. - `class BetaGCPExternalKeyConfig` - `type: Literal["gcp"]` - `key_name: str` Full resource name of the Cloud KMS key. - `class BetaAzureExternalKeyConfig` - `type: Literal["azure"]` - `key_name: str` Name of the key within the vault. - `tenant_id: str` Azure AD tenant ID. - `vault_uri: str` Key Vault data-plane URI — `https://{vault-name}.vault.azure.net` or `https://{hsm-name}.managedhsm.azure.net`. - `client_id: Optional[str]` Azure AD application (client) ID. Omit to use Anthropic's multitenant app. Provide only if using a single-tenant app registration in the customer's directory. - `updated_at: datetime` format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_external_key = client.beta.organization.external_keys.create( provider_config={ "kms_arn": "arn:aws:kms:us-east-1:111122223333:key/abcd1234-5678-90ab-cdef-000011112222", "type": "aws", }, ) print(beta_external_key.id) ``` ##### Response (200) ```json { "id": "ekey_01SDCCSbTxrXDpWc1phhtcfK", "attachment": { "type": "attached" }, "created_at": "2024-10-30T23:58:27.427722Z", "display_name": "prod-us-key", "geo": "us", "provider_config": { "kms_arn": "arn:aws:kms:us-east-1:111122223333:key/abcd1234-5678-90ab-cdef-000011112222", "type": "aws", "region": "us-east-1", "role_arn": "arn:aws:iam::111122223333:role/anthropic-cmek" }, "type": "external_key", "updated_at": "2024-10-30T23:58:27.427722Z" } ``` ### List External Keys `beta.organization.external_keys.list(**kwargs) -> SyncPageCursor[BetaExternalKey]` **GET** `/v1/organizations/external_keys` List external key configs in the caller's organization. Results are ordered by creation time (newest first). Use the `next_page` cursor from the response to fetch subsequent pages. #### Parameters - `limit: Optional[int]` (query parameter) Number of results per page. default: 20, minimum: 1, maximum: 100 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page`. #### Returns - `class BetaExternalKey` CMEK external key config belonging to the caller's organization. Configs are organization-scoped. Workspaces attach to a config; once any workspace references it, the provider fields become effectively immutable (existing encrypted data needs the config for decrypt). - `type: Literal["external_key"]` default: external_key - `id: str` Identifier of the external key config. A tagged ID prefixed `ekey_`, or — for organizations on the Claude Platform on AWS — the AWS KMS key ARN. - `attachment: Attachment` Whether any workspace uses this config to encrypt its data — counting live and archived workspaces (an archived workspace's data remains encrypted under the config), excluding deleted ones. Only an attached config is used by the encryption path; an `unattached` config is inert and can be deleted. - `class BetaExternalKeyAttachedAttachment` - `type: Literal["attached"]` default: attached - `class BetaExternalKeyUnattachedAttachment` - `type: Literal["unattached"]` default: unattached - `created_at: datetime` format: date-time - `display_name: Optional[str]` Human-friendly display name. Null if none was set. - `geo: str` Data residency geo. Selects which regional validator handles this key's encrypt/decrypt roundtrips. - `provider_config: ProviderConfig` KMS provider identity and auth coordinates. - `class BetaAWSExternalKeyConfig` - `type: Literal["aws"]` - `kms_arn: str` Full ARN of the AWS KMS key. On Claude Platform on AWS the key must be a single-Region key in your organization's own AWS account; cross-account keys, multi-Region keys, and alias ARNs are rejected. maxLength: 2048 - `region: Optional[str]` AWS region. Derived from `kms_arn` if omitted. - `role_arn: Optional[str]` **Deprecated** IAM role ARN. Deprecated — Anthropic reaches the KMS key through its own intermediate role (or, on Claude Platform on AWS, with credentials AWS issues for the Workspace); this field is ignored. - `class BetaGCPExternalKeyConfig` - `type: Literal["gcp"]` - `key_name: str` Full resource name of the Cloud KMS key. - `class BetaAzureExternalKeyConfig` - `type: Literal["azure"]` - `key_name: str` Name of the key within the vault. - `tenant_id: str` Azure AD tenant ID. - `vault_uri: str` Key Vault data-plane URI — `https://{vault-name}.vault.azure.net` or `https://{hsm-name}.managedhsm.azure.net`. - `client_id: Optional[str]` Azure AD application (client) ID. Omit to use Anthropic's multitenant app. Provide only if using a single-tenant app registration in the customer's directory. - `updated_at: datetime` format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.external_keys.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "ekey_01SDCCSbTxrXDpWc1phhtcfK", "attachment": { "type": "attached" }, "created_at": "2024-10-30T23:58:27.427722Z", "display_name": "prod-us-key", "geo": "us", "provider_config": { "kms_arn": "arn:aws:kms:us-east-1:111122223333:key/abcd1234-5678-90ab-cdef-000011112222", "type": "aws", "region": "us-east-1", "role_arn": "arn:aws:iam::111122223333:role/anthropic-cmek" }, "type": "external_key", "updated_at": "2024-10-30T23:58:27.427722Z" } ], "next_page": "next_page" } ``` ### Get External Key `beta.organization.external_keys.retrieve(external_key_id) -> BetaExternalKey` **GET** `/v1/organizations/external_keys/{external_key_id}` Retrieve a single external key config in the caller's organization by ID. #### Parameters - `external_key_id: str` (path parameter) ID of the External Key. maxLength: 2048 #### Returns - `class BetaExternalKey` CMEK external key config belonging to the caller's organization. Configs are organization-scoped. Workspaces attach to a config; once any workspace references it, the provider fields become effectively immutable (existing encrypted data needs the config for decrypt). - `type: Literal["external_key"]` default: external_key - `id: str` Identifier of the external key config. A tagged ID prefixed `ekey_`, or — for organizations on the Claude Platform on AWS — the AWS KMS key ARN. - `attachment: Attachment` Whether any workspace uses this config to encrypt its data — counting live and archived workspaces (an archived workspace's data remains encrypted under the config), excluding deleted ones. Only an attached config is used by the encryption path; an `unattached` config is inert and can be deleted. - `class BetaExternalKeyAttachedAttachment` - `type: Literal["attached"]` default: attached - `class BetaExternalKeyUnattachedAttachment` - `type: Literal["unattached"]` default: unattached - `created_at: datetime` format: date-time - `display_name: Optional[str]` Human-friendly display name. Null if none was set. - `geo: str` Data residency geo. Selects which regional validator handles this key's encrypt/decrypt roundtrips. - `provider_config: ProviderConfig` KMS provider identity and auth coordinates. - `class BetaAWSExternalKeyConfig` - `type: Literal["aws"]` - `kms_arn: str` Full ARN of the AWS KMS key. On Claude Platform on AWS the key must be a single-Region key in your organization's own AWS account; cross-account keys, multi-Region keys, and alias ARNs are rejected. maxLength: 2048 - `region: Optional[str]` AWS region. Derived from `kms_arn` if omitted. - `role_arn: Optional[str]` **Deprecated** IAM role ARN. Deprecated — Anthropic reaches the KMS key through its own intermediate role (or, on Claude Platform on AWS, with credentials AWS issues for the Workspace); this field is ignored. - `class BetaGCPExternalKeyConfig` - `type: Literal["gcp"]` - `key_name: str` Full resource name of the Cloud KMS key. - `class BetaAzureExternalKeyConfig` - `type: Literal["azure"]` - `key_name: str` Name of the key within the vault. - `tenant_id: str` Azure AD tenant ID. - `vault_uri: str` Key Vault data-plane URI — `https://{vault-name}.vault.azure.net` or `https://{hsm-name}.managedhsm.azure.net`. - `client_id: Optional[str]` Azure AD application (client) ID. Omit to use Anthropic's multitenant app. Provide only if using a single-tenant app registration in the customer's directory. - `updated_at: datetime` format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_external_key = client.beta.organization.external_keys.retrieve( "external_key_id", ) print(beta_external_key.id) ``` ##### Response (200) ```json { "id": "ekey_01SDCCSbTxrXDpWc1phhtcfK", "attachment": { "type": "attached" }, "created_at": "2024-10-30T23:58:27.427722Z", "display_name": "prod-us-key", "geo": "us", "provider_config": { "kms_arn": "arn:aws:kms:us-east-1:111122223333:key/abcd1234-5678-90ab-cdef-000011112222", "type": "aws", "region": "us-east-1", "role_arn": "arn:aws:iam::111122223333:role/anthropic-cmek" }, "type": "external_key", "updated_at": "2024-10-30T23:58:27.427722Z" } ``` ### Update External Key `beta.organization.external_keys.update(external_key_id, **kwargs) -> BetaExternalKey` **POST** `/v1/organizations/external_keys/{external_key_id}` Partially update an external key config. Omitted fields are left unchanged. `display_name` is always editable. `geo` and `provider_config` cannot be changed once any workspace references this config, because previously encrypted data requires the original key identity to decrypt. #### Parameters - `external_key_id: str` (path parameter) ID of the External Key. maxLength: 2048 - `display_name: Optional[str]` Human-friendly display name. minLength: 1, maxLength: 255 - `geo: Optional[Literal["us"]]` Data residency geo. Only `us` is supported. - `provider_config: Optional[ProviderConfig]` KMS provider identity and auth coordinates. - `class BetaAWSExternalKeyConfig` - `type: Literal["aws"]` - `kms_arn: str` Full ARN of the AWS KMS key. On Claude Platform on AWS the key must be a single-Region key in your organization's own AWS account; cross-account keys, multi-Region keys, and alias ARNs are rejected. maxLength: 2048 - `region: Optional[str]` AWS region. Derived from `kms_arn` if omitted. - `role_arn: Optional[str]` **Deprecated** IAM role ARN. Deprecated — Anthropic reaches the KMS key through its own intermediate role (or, on Claude Platform on AWS, with credentials AWS issues for the Workspace); this field is ignored. - `class BetaGCPExternalKeyConfig` - `type: Literal["gcp"]` - `key_name: str` Full resource name of the Cloud KMS key. - `class BetaAzureExternalKeyConfigParam` Azure Key Vault provider configuration. - `type: Literal["azure"]` - `key_name: str` Name of the key within the vault. - `tenant_id: str` Azure AD tenant ID. - `vault_uri: str` Key Vault data-plane URI — `https://{vault-name}.vault.azure.net` or `https://{hsm-name}.managedhsm.azure.net`. - `client_id: Optional[str]` Azure AD application (client) ID. Omit to use Anthropic's multitenant app. Provide only if using a single-tenant app registration in the customer's directory. #### Returns - `class BetaExternalKey` CMEK external key config belonging to the caller's organization. Configs are organization-scoped. Workspaces attach to a config; once any workspace references it, the provider fields become effectively immutable (existing encrypted data needs the config for decrypt). - `type: Literal["external_key"]` default: external_key - `id: str` Identifier of the external key config. A tagged ID prefixed `ekey_`, or — for organizations on the Claude Platform on AWS — the AWS KMS key ARN. - `attachment: Attachment` Whether any workspace uses this config to encrypt its data — counting live and archived workspaces (an archived workspace's data remains encrypted under the config), excluding deleted ones. Only an attached config is used by the encryption path; an `unattached` config is inert and can be deleted. - `class BetaExternalKeyAttachedAttachment` - `type: Literal["attached"]` default: attached - `class BetaExternalKeyUnattachedAttachment` - `type: Literal["unattached"]` default: unattached - `created_at: datetime` format: date-time - `display_name: Optional[str]` Human-friendly display name. Null if none was set. - `geo: str` Data residency geo. Selects which regional validator handles this key's encrypt/decrypt roundtrips. - `provider_config: ProviderConfig` KMS provider identity and auth coordinates. - `class BetaAWSExternalKeyConfig` - `type: Literal["aws"]` - `kms_arn: str` Full ARN of the AWS KMS key. On Claude Platform on AWS the key must be a single-Region key in your organization's own AWS account; cross-account keys, multi-Region keys, and alias ARNs are rejected. maxLength: 2048 - `region: Optional[str]` AWS region. Derived from `kms_arn` if omitted. - `role_arn: Optional[str]` **Deprecated** IAM role ARN. Deprecated — Anthropic reaches the KMS key through its own intermediate role (or, on Claude Platform on AWS, with credentials AWS issues for the Workspace); this field is ignored. - `class BetaGCPExternalKeyConfig` - `type: Literal["gcp"]` - `key_name: str` Full resource name of the Cloud KMS key. - `class BetaAzureExternalKeyConfig` - `type: Literal["azure"]` - `key_name: str` Name of the key within the vault. - `tenant_id: str` Azure AD tenant ID. - `vault_uri: str` Key Vault data-plane URI — `https://{vault-name}.vault.azure.net` or `https://{hsm-name}.managedhsm.azure.net`. - `client_id: Optional[str]` Azure AD application (client) ID. Omit to use Anthropic's multitenant app. Provide only if using a single-tenant app registration in the customer's directory. - `updated_at: datetime` format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_external_key = client.beta.organization.external_keys.update( external_key_id="external_key_id", ) print(beta_external_key.id) ``` ##### Response (200) ```json { "id": "ekey_01SDCCSbTxrXDpWc1phhtcfK", "attachment": { "type": "attached" }, "created_at": "2024-10-30T23:58:27.427722Z", "display_name": "prod-us-key", "geo": "us", "provider_config": { "kms_arn": "arn:aws:kms:us-east-1:111122223333:key/abcd1234-5678-90ab-cdef-000011112222", "type": "aws", "region": "us-east-1", "role_arn": "arn:aws:iam::111122223333:role/anthropic-cmek" }, "type": "external_key", "updated_at": "2024-10-30T23:58:27.427722Z" } ``` ### Delete External Key `beta.organization.external_keys.delete(external_key_id) -> ExternalKeyDeleteResponse` **DELETE** `/v1/organizations/external_keys/{external_key_id}` Delete an external key config. The request is rejected if any workspace still references this config. #### Parameters - `external_key_id: str` (path parameter) ID of the External Key. maxLength: 2048 #### Returns - `class ExternalKeyDeleteResponse` - `type: Literal["external_key_deleted"]` default: external_key_deleted - `id: str` ID of the deleted External Key. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) external_key = client.beta.organization.external_keys.delete( "external_key_id", ) print(external_key.id) ``` ##### Response (200) ```json { "id": "ekey_01AbCdEfGhIjKlMnOpQrStUv", "type": "external_key_deleted" } ``` ### Validate External Key `beta.organization.external_keys.validate(external_key_id) -> ExternalKeyValidateResponse` **POST** `/v1/organizations/external_keys/{external_key_id}/validate` Validate an external key config against the customer's KMS. Anthropic performs an encrypt/decrypt roundtrip against the configured KMS key and waits up to 30 seconds for the result. The response status is `success` if the roundtrip succeeded, or `failure` with an error message if it failed or timed out. #### Parameters - `external_key_id: str` (path parameter) ID of the External Key. maxLength: 2048 #### Returns - `class ExternalKeyValidateResponse` Result of a validation roundtrip against the customer's KMS. HTTP 200 for both outcomes — the operation completed; `status` says whether the key works. - `type: Literal["external_key_validation"]` default: external_key_validation - `error: Optional[str]` Error message when status is `failure`. Null otherwise. - `status: Literal["failure", "success"]` `success` — encrypt/decrypt roundtrip succeeded. `failure` — the roundtrip failed or timed out; see `error`. - `"failure"` - `"success"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) response = client.beta.organization.external_keys.validate( "external_key_id", ) print(response.error) ``` ##### Response (200) ```json { "error": "error", "status": "failure", "type": "external_key_validation" } ``` ## Beta › Organization › Federation › Issuers ### Create Federation Issuer `beta.organization.federation.issuers.create(**kwargs) -> BetaFederationIssuer` **POST** `/v1/organizations/federation_issuers` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Register an OIDC issuer that Anthropic will trust for workload identity federation in your organization. The `jwks` field controls how the issuer's signing keys are obtained and takes one of three shapes selected by `type`: `discovery` (resolve keys through OIDC discovery), `explicit_url` (fetch keys from a fixed JWKS URL), or `inline` (provide a static key set). When `jwks.type` is `discovery` and no `discovery_base` is set, the issuer URL must be publicly reachable over HTTPS so Anthropic can fetch the discovery document; for `explicit_url` and `inline` modes the issuer URL is only matched as the JWT's `iss` claim and is not fetched. #### Parameters - `issuer_url: str` The `iss` claim value to match against. minLength: 1 - `name: str` Slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409. minLength: 1, maxLength: 255 - `check_jti: Optional[bool]` Whether the jwt-bearer exchange enforces JTI single-use (replay protection) for tokens from this issuer. Defaults to true. Applies only to assertions carrying a `jti` claim; tokens without one are accepted without single-use enforcement. - `jwks: Optional[JWKS]` How signing keys are obtained. Defaults to OIDC discovery. - `class BetaJWKSDiscovery` JWKS via the issuer's OIDC discovery document. - `type: Literal["discovery"]` - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `discovery_base: Optional[str]` Set when the discovery URL differs from `issuer_url`. - `class BetaJWKSExplicitURL` JWKS fetched from a fixed endpoint. - `type: Literal["explicit_url"]` - `url: str` JWKS endpoint. minLength: 1 - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `class BetaJWKSInline` JWKS supplied directly; no network fetch. - `type: Literal["inline"]` - `keys: List[Dict[str, object]]` Inline JWK objects. minItems: 1 - `max_jwt_lifetime_seconds: Optional[int]` Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Defaults to 3600 (1h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected. minimum: 1, maximum: 176400 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaFederationIssuer` Registered external OIDC identity provider. Records an external IdP the organization trusts for the RFC 7523 jwt-bearer grant. The `issuer_url` must match the JWT `iss` claim exactly. - `type: Literal["federation_issuer"]` default: federation_issuer - `id: str` Tagged ID of the federation issuer. - `archived_at: Optional[datetime]` If set, all rules referencing this issuer reject token exchange. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this issuer. - `check_jti: bool` Whether the jwt-bearer exchange enforces JTI single-use (replay protection) for tokens from this issuer. Applies only to assertions carrying a `jti` claim; tokens without one are accepted without single-use enforcement. - `created_at: datetime` When this issuer was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this issuer. - `issuer_url: str` The `iss` claim value. Incoming JWTs must match exactly. - `jwks: JWKS` How signing keys are obtained for signature verification. - `class BetaJWKSDiscovery` JWKS via the issuer's OIDC discovery document. - `type: Literal["discovery"]` - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `discovery_base: Optional[str]` Set when the discovery URL differs from `issuer_url`. - `class BetaJWKSExplicitURL` JWKS fetched from a fixed endpoint. - `type: Literal["explicit_url"]` - `url: str` JWKS endpoint. minLength: 1 - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `class BetaJWKSInline` JWKS supplied directly; no network fetch. - `type: Literal["inline"]` - `keys: List[Dict[str, object]]` Inline JWK objects. minItems: 1 - `jwks_polling_disabled_at: Optional[datetime]` If set, Anthropic's JWKS poller has paused polling for this issuer after repeated fetch failures. Re-enable by sending `jwks_polling_disabled: false` via the issuer update endpoint (POST) once the upstream JWKS endpoint is fixed. An OAuth caller cannot send this when the issuer backs a rule with any scope other than `workspace:developer` or `workspace:inference`; use a Console session. format: date-time - `max_jwt_lifetime_seconds: int` Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected. - `name: str` Admin-chosen slug identifier. - `poll_status: Optional[BetaFederationIssuerPollStatus]` Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet. - `consecutive_failures: int` Consecutive fetch failures since the last success. - `last_fetched_at: Optional[datetime]` When the last successful fetch completed. format: date-time - `next_poll_at: Optional[datetime]` When the next fetch is scheduled. Null if paused. format: date-time - `updated_at: datetime` When this issuer was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this issuer. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_federation_issuer = client.beta.organization.federation.issuers.create( issuer_url="x", name="x", ) print(beta_federation_issuer.id) ``` ##### Response (200) ```json { "id": "fdis_01SDCCSbTxrXDpWc1phhtcfK", "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "check_jti": true, "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "issuer_url": "https://token.actions.githubusercontent.com", "jwks": { "type": "discovery", "ca_cert_pem": "ca_cert_pem", "discovery_base": "discovery_base" }, "jwks_polling_disabled_at": "2019-12-27T18:11:19.117Z", "max_jwt_lifetime_seconds": 0, "name": "github-actions", "poll_status": { "consecutive_failures": 0, "last_fetched_at": "2019-12-27T18:11:19.117Z", "next_poll_at": "2019-12-27T18:11:19.117Z" }, "type": "federation_issuer", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id" } ``` ### List Federation Issuers `beta.organization.federation.issuers.list(**kwargs) -> SyncPageCursor[BetaFederationIssuer]` **GET** `/v1/organizations/federation_issuers` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). List federation issuers in your organization. Archived issuers are excluded unless `include_archived=true`. #### Parameters - `include_archived: Optional[bool]` (query parameter) Include archived resources. Defaults to false. default: false - `limit: Optional[int]` (query parameter) Number of results per page. default: 20, minimum: 1, maximum: 100 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page`. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaFederationIssuer` Registered external OIDC identity provider. Records an external IdP the organization trusts for the RFC 7523 jwt-bearer grant. The `issuer_url` must match the JWT `iss` claim exactly. - `type: Literal["federation_issuer"]` default: federation_issuer - `id: str` Tagged ID of the federation issuer. - `archived_at: Optional[datetime]` If set, all rules referencing this issuer reject token exchange. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this issuer. - `check_jti: bool` Whether the jwt-bearer exchange enforces JTI single-use (replay protection) for tokens from this issuer. Applies only to assertions carrying a `jti` claim; tokens without one are accepted without single-use enforcement. - `created_at: datetime` When this issuer was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this issuer. - `issuer_url: str` The `iss` claim value. Incoming JWTs must match exactly. - `jwks: JWKS` How signing keys are obtained for signature verification. - `class BetaJWKSDiscovery` JWKS via the issuer's OIDC discovery document. - `type: Literal["discovery"]` - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `discovery_base: Optional[str]` Set when the discovery URL differs from `issuer_url`. - `class BetaJWKSExplicitURL` JWKS fetched from a fixed endpoint. - `type: Literal["explicit_url"]` - `url: str` JWKS endpoint. minLength: 1 - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `class BetaJWKSInline` JWKS supplied directly; no network fetch. - `type: Literal["inline"]` - `keys: List[Dict[str, object]]` Inline JWK objects. minItems: 1 - `jwks_polling_disabled_at: Optional[datetime]` If set, Anthropic's JWKS poller has paused polling for this issuer after repeated fetch failures. Re-enable by sending `jwks_polling_disabled: false` via the issuer update endpoint (POST) once the upstream JWKS endpoint is fixed. An OAuth caller cannot send this when the issuer backs a rule with any scope other than `workspace:developer` or `workspace:inference`; use a Console session. format: date-time - `max_jwt_lifetime_seconds: int` Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected. - `name: str` Admin-chosen slug identifier. - `poll_status: Optional[BetaFederationIssuerPollStatus]` Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet. - `consecutive_failures: int` Consecutive fetch failures since the last success. - `last_fetched_at: Optional[datetime]` When the last successful fetch completed. format: date-time - `next_poll_at: Optional[datetime]` When the next fetch is scheduled. Null if paused. format: date-time - `updated_at: datetime` When this issuer was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this issuer. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.federation.issuers.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "fdis_01SDCCSbTxrXDpWc1phhtcfK", "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "check_jti": true, "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "issuer_url": "https://token.actions.githubusercontent.com", "jwks": { "type": "discovery", "ca_cert_pem": "ca_cert_pem", "discovery_base": "discovery_base" }, "jwks_polling_disabled_at": "2019-12-27T18:11:19.117Z", "max_jwt_lifetime_seconds": 0, "name": "github-actions", "poll_status": { "consecutive_failures": 0, "last_fetched_at": "2019-12-27T18:11:19.117Z", "next_poll_at": "2019-12-27T18:11:19.117Z" }, "type": "federation_issuer", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id" } ], "next_page": "next_page" } ``` ### Get Federation Issuer `beta.organization.federation.issuers.retrieve(federation_issuer_id, **kwargs) -> BetaFederationIssuer` **GET** `/v1/organizations/federation_issuers/{federation_issuer_id}` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Retrieve a federation issuer by its ID (`fdis_...`). #### Parameters - `federation_issuer_id: str` (path parameter) ID of the federation issuer. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaFederationIssuer` Registered external OIDC identity provider. Records an external IdP the organization trusts for the RFC 7523 jwt-bearer grant. The `issuer_url` must match the JWT `iss` claim exactly. - `type: Literal["federation_issuer"]` default: federation_issuer - `id: str` Tagged ID of the federation issuer. - `archived_at: Optional[datetime]` If set, all rules referencing this issuer reject token exchange. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this issuer. - `check_jti: bool` Whether the jwt-bearer exchange enforces JTI single-use (replay protection) for tokens from this issuer. Applies only to assertions carrying a `jti` claim; tokens without one are accepted without single-use enforcement. - `created_at: datetime` When this issuer was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this issuer. - `issuer_url: str` The `iss` claim value. Incoming JWTs must match exactly. - `jwks: JWKS` How signing keys are obtained for signature verification. - `class BetaJWKSDiscovery` JWKS via the issuer's OIDC discovery document. - `type: Literal["discovery"]` - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `discovery_base: Optional[str]` Set when the discovery URL differs from `issuer_url`. - `class BetaJWKSExplicitURL` JWKS fetched from a fixed endpoint. - `type: Literal["explicit_url"]` - `url: str` JWKS endpoint. minLength: 1 - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `class BetaJWKSInline` JWKS supplied directly; no network fetch. - `type: Literal["inline"]` - `keys: List[Dict[str, object]]` Inline JWK objects. minItems: 1 - `jwks_polling_disabled_at: Optional[datetime]` If set, Anthropic's JWKS poller has paused polling for this issuer after repeated fetch failures. Re-enable by sending `jwks_polling_disabled: false` via the issuer update endpoint (POST) once the upstream JWKS endpoint is fixed. An OAuth caller cannot send this when the issuer backs a rule with any scope other than `workspace:developer` or `workspace:inference`; use a Console session. format: date-time - `max_jwt_lifetime_seconds: int` Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected. - `name: str` Admin-chosen slug identifier. - `poll_status: Optional[BetaFederationIssuerPollStatus]` Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet. - `consecutive_failures: int` Consecutive fetch failures since the last success. - `last_fetched_at: Optional[datetime]` When the last successful fetch completed. format: date-time - `next_poll_at: Optional[datetime]` When the next fetch is scheduled. Null if paused. format: date-time - `updated_at: datetime` When this issuer was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this issuer. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_federation_issuer = client.beta.organization.federation.issuers.retrieve( federation_issuer_id="federation_issuer_id", ) print(beta_federation_issuer.id) ``` ##### Response (200) ```json { "id": "fdis_01SDCCSbTxrXDpWc1phhtcfK", "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "check_jti": true, "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "issuer_url": "https://token.actions.githubusercontent.com", "jwks": { "type": "discovery", "ca_cert_pem": "ca_cert_pem", "discovery_base": "discovery_base" }, "jwks_polling_disabled_at": "2019-12-27T18:11:19.117Z", "max_jwt_lifetime_seconds": 0, "name": "github-actions", "poll_status": { "consecutive_failures": 0, "last_fetched_at": "2019-12-27T18:11:19.117Z", "next_poll_at": "2019-12-27T18:11:19.117Z" }, "type": "federation_issuer", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id" } ``` ### Update Federation Issuer `beta.organization.federation.issuers.update(federation_issuer_id, **kwargs) -> BetaFederationIssuer` **POST** `/v1/organizations/federation_issuers/{federation_issuer_id}` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Partially update a federation issuer. Setting `jwks` replaces the full JWKS shape at once. Archived issuers cannot be updated; this returns 400. Create a new issuer instead. Updating an issuer that backs a rule with a scope outside `workspace:developer` or `workspace:inference` requires a Console session. #### Parameters - `federation_issuer_id: str` (path parameter) ID of the federation issuer to update. - `check_jti: Optional[bool]` Whether the jwt-bearer exchange enforces JTI single-use (replay protection) for tokens from this issuer. Applies only to assertions carrying a `jti` claim; tokens without one are accepted without single-use enforcement. - `issuer_url: Optional[str]` Replaces the `iss` claim value to match against. For discovery-mode issuers without a `discovery_base`, this is also the URL Anthropic fetches the OIDC discovery document and signing keys from, so changing it repoints the JWKS source. Changing the issuer URL to a well-known shared platform is rejected while any live rule under this issuer would not constrain tenant identity. minLength: 1 - `jwks: Optional[JWKS]` Replaces the entire JWKS configuration. - `class BetaJWKSDiscovery` JWKS via the issuer's OIDC discovery document. - `type: Literal["discovery"]` - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `discovery_base: Optional[str]` Set when the discovery URL differs from `issuer_url`. - `class BetaJWKSExplicitURL` JWKS fetched from a fixed endpoint. - `type: Literal["explicit_url"]` - `url: str` JWKS endpoint. minLength: 1 - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `class BetaJWKSInline` JWKS supplied directly; no network fetch. - `type: Literal["inline"]` - `keys: List[Dict[str, object]]` Inline JWK objects. minItems: 1 - `jwks_polling_disabled: Optional[bool]` Only `false` is accepted, to re-enable polling after the system pauses it. Polling is paused automatically; sending `true` is rejected. - `max_jwt_lifetime_seconds: Optional[int]` Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected. minimum: 1, maximum: 176400 - `name: Optional[str]` Replaces the slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409. minLength: 1, maxLength: 255 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaFederationIssuer` Registered external OIDC identity provider. Records an external IdP the organization trusts for the RFC 7523 jwt-bearer grant. The `issuer_url` must match the JWT `iss` claim exactly. - `type: Literal["federation_issuer"]` default: federation_issuer - `id: str` Tagged ID of the federation issuer. - `archived_at: Optional[datetime]` If set, all rules referencing this issuer reject token exchange. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this issuer. - `check_jti: bool` Whether the jwt-bearer exchange enforces JTI single-use (replay protection) for tokens from this issuer. Applies only to assertions carrying a `jti` claim; tokens without one are accepted without single-use enforcement. - `created_at: datetime` When this issuer was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this issuer. - `issuer_url: str` The `iss` claim value. Incoming JWTs must match exactly. - `jwks: JWKS` How signing keys are obtained for signature verification. - `class BetaJWKSDiscovery` JWKS via the issuer's OIDC discovery document. - `type: Literal["discovery"]` - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `discovery_base: Optional[str]` Set when the discovery URL differs from `issuer_url`. - `class BetaJWKSExplicitURL` JWKS fetched from a fixed endpoint. - `type: Literal["explicit_url"]` - `url: str` JWKS endpoint. minLength: 1 - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `class BetaJWKSInline` JWKS supplied directly; no network fetch. - `type: Literal["inline"]` - `keys: List[Dict[str, object]]` Inline JWK objects. minItems: 1 - `jwks_polling_disabled_at: Optional[datetime]` If set, Anthropic's JWKS poller has paused polling for this issuer after repeated fetch failures. Re-enable by sending `jwks_polling_disabled: false` via the issuer update endpoint (POST) once the upstream JWKS endpoint is fixed. An OAuth caller cannot send this when the issuer backs a rule with any scope other than `workspace:developer` or `workspace:inference`; use a Console session. format: date-time - `max_jwt_lifetime_seconds: int` Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected. - `name: str` Admin-chosen slug identifier. - `poll_status: Optional[BetaFederationIssuerPollStatus]` Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet. - `consecutive_failures: int` Consecutive fetch failures since the last success. - `last_fetched_at: Optional[datetime]` When the last successful fetch completed. format: date-time - `next_poll_at: Optional[datetime]` When the next fetch is scheduled. Null if paused. format: date-time - `updated_at: datetime` When this issuer was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this issuer. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_federation_issuer = client.beta.organization.federation.issuers.update( federation_issuer_id="federation_issuer_id", ) print(beta_federation_issuer.id) ``` ##### Response (200) ```json { "id": "fdis_01SDCCSbTxrXDpWc1phhtcfK", "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "check_jti": true, "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "issuer_url": "https://token.actions.githubusercontent.com", "jwks": { "type": "discovery", "ca_cert_pem": "ca_cert_pem", "discovery_base": "discovery_base" }, "jwks_polling_disabled_at": "2019-12-27T18:11:19.117Z", "max_jwt_lifetime_seconds": 0, "name": "github-actions", "poll_status": { "consecutive_failures": 0, "last_fetched_at": "2019-12-27T18:11:19.117Z", "next_poll_at": "2019-12-27T18:11:19.117Z" }, "type": "federation_issuer", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id" } ``` ### Archive Federation Issuer `beta.organization.federation.issuers.archive(federation_issuer_id, **kwargs) -> BetaFederationIssuer` **POST** `/v1/organizations/federation_issuers/{federation_issuer_id}/archive` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Archive a federation issuer. Idempotent; re-archiving returns the issuer with its original `archived_at`. Rejected with 400 if any live (non-archived) federation rule still references the issuer; archive those rules first (a rule's issuer cannot be changed), or recreate them against another issuer. #### Parameters - `federation_issuer_id: str` (path parameter) ID of the federation issuer to archive. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaFederationIssuer` Registered external OIDC identity provider. Records an external IdP the organization trusts for the RFC 7523 jwt-bearer grant. The `issuer_url` must match the JWT `iss` claim exactly. - `type: Literal["federation_issuer"]` default: federation_issuer - `id: str` Tagged ID of the federation issuer. - `archived_at: Optional[datetime]` If set, all rules referencing this issuer reject token exchange. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this issuer. - `check_jti: bool` Whether the jwt-bearer exchange enforces JTI single-use (replay protection) for tokens from this issuer. Applies only to assertions carrying a `jti` claim; tokens without one are accepted without single-use enforcement. - `created_at: datetime` When this issuer was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this issuer. - `issuer_url: str` The `iss` claim value. Incoming JWTs must match exactly. - `jwks: JWKS` How signing keys are obtained for signature verification. - `class BetaJWKSDiscovery` JWKS via the issuer's OIDC discovery document. - `type: Literal["discovery"]` - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `discovery_base: Optional[str]` Set when the discovery URL differs from `issuer_url`. - `class BetaJWKSExplicitURL` JWKS fetched from a fixed endpoint. - `type: Literal["explicit_url"]` - `url: str` JWKS endpoint. minLength: 1 - `ca_cert_pem: Optional[str]` Optional custom CA (PEM) for TLS verification of the JWKS fetch. maxLength: 8192 - `class BetaJWKSInline` JWKS supplied directly; no network fetch. - `type: Literal["inline"]` - `keys: List[Dict[str, object]]` Inline JWK objects. minItems: 1 - `jwks_polling_disabled_at: Optional[datetime]` If set, Anthropic's JWKS poller has paused polling for this issuer after repeated fetch failures. Re-enable by sending `jwks_polling_disabled: false` via the issuer update endpoint (POST) once the upstream JWKS endpoint is fixed. An OAuth caller cannot send this when the issuer backs a rule with any scope other than `workspace:developer` or `workspace:inference`; use a Console session. format: date-time - `max_jwt_lifetime_seconds: int` Maximum allowed iat→exp spread for assertions from this issuer (1-176400 seconds, i.e. up to 49h). Assertions must carry both `iat` and `exp`; a missing `iat` is rejected. - `name: str` Admin-chosen slug identifier. - `poll_status: Optional[BetaFederationIssuerPollStatus]` Live state of Anthropic's JWKS polling for this issuer. Populated on both single-issuer retrieval and list responses, including archived issuers. Typically null for inline-key issuers (no polling), or when poll status is temporarily unavailable or polling has not started yet. - `consecutive_failures: int` Consecutive fetch failures since the last success. - `last_fetched_at: Optional[datetime]` When the last successful fetch completed. format: date-time - `next_poll_at: Optional[datetime]` When the next fetch is scheduled. Null if paused. format: date-time - `updated_at: datetime` When this issuer was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this issuer. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_federation_issuer = client.beta.organization.federation.issuers.archive( federation_issuer_id="federation_issuer_id", ) print(beta_federation_issuer.id) ``` ##### Response (200) ```json { "id": "fdis_01SDCCSbTxrXDpWc1phhtcfK", "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "check_jti": true, "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "issuer_url": "https://token.actions.githubusercontent.com", "jwks": { "type": "discovery", "ca_cert_pem": "ca_cert_pem", "discovery_base": "discovery_base" }, "jwks_polling_disabled_at": "2019-12-27T18:11:19.117Z", "max_jwt_lifetime_seconds": 0, "name": "github-actions", "poll_status": { "consecutive_failures": 0, "last_fetched_at": "2019-12-27T18:11:19.117Z", "next_poll_at": "2019-12-27T18:11:19.117Z" }, "type": "federation_issuer", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id" } ``` ## Beta › Organization › Federation › Rules ### Create Federation Rule `beta.organization.federation.rules.create(**kwargs) -> BetaFederationRule` **POST** `/v1/organizations/federation_rules` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Create a federation rule owned by your organization. The referenced issuer and the target service account must already exist in the same organization; invalid references are rejected with a 400 error. The workspace reference is validated. Membership is not checked at rule creation: token exchange resolves a single enabled workspace per call and is rejected unless the target service account is a member of that workspace (it is implicitly a member of the default workspace). Rules on well-known shared issuers (GitHub Actions, GitLab, Buildkite, Terraform Cloud, Google) must constrain tenant identity via an identity-bearing claim, a tenant-pinning subject prefix (such as `repo:YOUR_ORG/...`), or a CEL condition referencing one of those identity claims (e.g. `claims.repository_owner`). OAuth callers may only manage rules whose `oauth_scope` is `workspace:developer` or `workspace:inference`; other scopes require a Console session. #### Parameters - `issuer_id: str` Tagged ID of the federation issuer. - `match: BetaFederationRuleMatchParam` Conditions the verified JWT must satisfy for this rule to apply. At least one of `subject_prefix` (other than a wildcard-only value like `*`), `claims`, or `condition` is required; `audience` alone is not sufficient. - `audience: Optional[str]` Exact match against the `aud` claim (any element if array). When omitted, the JWT's `aud` must still equal Anthropic's expected audience for the issuer; setting this field overrides that default. maxLength: 1024 - `claims: Optional[Dict[str, str]]` Exact-match `{claim: value}` pairs against top-level claims. Only string-valued claims can be matched; use `condition` for non-string claims. - `condition: Optional[str]` CEL expression over claims for logic the structural fields can't express. Must evaluate to a boolean and may reference only the `claims` variable; a constant-true expression (such as `true`) is rejected with 400. maxLength: 4096 - `subject_prefix: Optional[str]` Match the verified JWT `sub` claim. Exact match unless the value ends with `*`, in which case it is a prefix match. Example: `repo:my-org/my-repo:ref:refs/heads/main`. maxLength: 1024 - `name: str` Slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409. minLength: 1, maxLength: 255 - `oauth_scope: str` Space-separated OAuth scopes. OAuth callers may only set `workspace:developer` or `workspace:inference`; other scopes (such as `org:admin`) require a Console session. minLength: 1 - `target: BetaServiceAccountTargetParam` Identity that tokens minted via this rule act as. Currently always a `service_account` target. - `type: Literal["service_account"]` - `service_account_id: str` Tagged ID of the service account to mint tokens for. - `service_account_name: Optional[str]` Service account's display name at read time. Ignored on writes. - `applies_to_all_workspaces: Optional[bool]` When true, enable this rule for every workspace in the org (including workspaces created later). - `attributes: Optional[Dict[str, str]]` CEL expressions `{name: expr}` extracting named values from claims. Not yet supported; any non-empty value is rejected with 400. - `description: Optional[str]` Optional free-text description. maxLength: 2000 - `token_lifetime_seconds: Optional[int]` Lifetime in seconds for access tokens minted via this rule (60-86400). Defaults to 3600 (1h). Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds. minimum: 60, maximum: 86400 - `workspace_id: Optional[str]` Tagged ID of the workspace to enable this rule for. Required unless `applies_to_all_workspaces` is true. Additional workspaces can be added via the `/federation_rules/{federation_rule_id}/workspaces` sub-resource. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaFederationRule` Authorization rule binding an external OIDC identity to Anthropic. Evaluates the match conditions and mints an OAuth access token for the resolved target, scoped to a single workspace where the rule is enabled (chosen by the caller at exchange time when the rule is enabled for more than one). For rules enabled via `workspace_ids` or `applies_to_all_workspaces`, the target service account must be a member of that workspace (it is implicitly a member of the default workspace); rules carrying only the legacy `workspace_id` binding do not enforce this. - `type: Literal["federation_rule"]` default: federation_rule - `id: str` Tagged ID of the federation rule. - `applies_to_all_workspaces: bool` When true, this rule is enabled for every workspace in the org (including ones created after the rule). `workspace_ids` is ignored at exchange time. - `archived_at: Optional[datetime]` If set, this rule is archived and rejects token exchange. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this rule. - `attributes: Optional[Dict[str, str]]` CEL expressions extracting named values from claims. Not yet supported; always null. - `created_at: datetime` When this rule was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this rule. - `description: Optional[str]` Optional free-text description. - `issuer_id: str` Tagged ID of the issuer whose tokens this rule accepts. - `issuer_name: Optional[str]` Issuer's display name at read time. - `match: BetaFederationRuleMatch` Conditions the verified JWT must satisfy for this rule to apply. All populated matcher fields must pass. - `audience: Optional[str]` Exact match against the `aud` claim (any element if array). When omitted, the JWT's `aud` must still equal Anthropic's expected audience for the issuer; setting this field overrides that default. maxLength: 1024 - `claims: Optional[Dict[str, str]]` Exact-match `{claim: value}` pairs against top-level claims. Only string-valued claims can be matched; use `condition` for non-string claims. - `condition: Optional[str]` CEL expression over claims for logic the structural fields can't express. Must evaluate to a boolean and may reference only the `claims` variable; a constant-true expression (such as `true`) is rejected with 400. maxLength: 4096 - `subject_prefix: Optional[str]` Match the verified JWT `sub` claim. Exact match unless the value ends with `*`, in which case it is a prefix match. Example: `repo:my-org/my-repo:ref:refs/heads/main`. maxLength: 1024 - `name: str` Admin-chosen slug identifier. - `oauth_scope: str` Space-separated OAuth scopes granted on the minted token. - `target: BetaServiceAccountTarget` What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account. - `type: Literal["service_account"]` - `service_account_id: str` Tagged ID of the service account to mint tokens for. - `service_account_name: Optional[str]` Service account's display name at read time. Ignored on writes. - `token_lifetime_seconds: int` Lifetime in seconds of access tokens minted via this rule. Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds. - `updated_at: datetime` When this rule was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this rule. - `workspace_id: Optional[str]` Legacy single-workspace binding. Prefer `workspace_ids` and the `/federation_rules/{federation_rule_id}/workspaces` sub-resource for managing workspace enablement. - `workspace_ids: List[str]` Tagged IDs of the workspaces this rule is enabled for. May be empty for older rules that only carry the legacy `workspace_id` binding. Ignored at exchange time when `applies_to_all_workspaces` is true (the list may still be non-empty). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_federation_rule = client.beta.organization.federation.rules.create( issuer_id="issuer_id", match={}, name="x", oauth_scope="x", target={ "service_account_id": "svac_01SDCCSbTxrXDpWc1phhtcfK", "type": "service_account", }, ) print(beta_federation_rule.id) ``` ##### Response (200) ```json { "id": "fdrl_01SDCCSbTxrXDpWc1phhtcfK", "applies_to_all_workspaces": true, "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "attributes": { "foo": "string" }, "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "description": "description", "issuer_id": "issuer_id", "issuer_name": "issuer_name", "match": { "audience": "audience", "claims": { "foo": "string" }, "condition": "condition", "subject_prefix": "subject_prefix" }, "name": "prod-deploy-pipeline", "oauth_scope": "oauth_scope", "target": { "service_account_id": "svac_01SDCCSbTxrXDpWc1phhtcfK", "type": "service_account", "service_account_name": "service_account_name" }, "token_lifetime_seconds": 0, "type": "federation_rule", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id", "workspace_id": "workspace_id", "workspace_ids": [ "string" ] } ``` ### List Federation Rules `beta.organization.federation.rules.list(**kwargs) -> SyncPageCursor[BetaFederationRule]` **GET** `/v1/organizations/federation_rules` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). List federation rules in your organization. Optionally filter by issuer with `issuer_id`. Archived rules are excluded unless `include_archived=true`. #### Parameters - `include_archived: Optional[bool]` (query parameter) Include archived resources. Defaults to false. default: false - `issuer_id: Optional[str]` (query parameter) Filter to rules referencing this federation issuer. - `limit: Optional[int]` (query parameter) Number of results per page. default: 20, minimum: 1, maximum: 100 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page`. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaFederationRule` Authorization rule binding an external OIDC identity to Anthropic. Evaluates the match conditions and mints an OAuth access token for the resolved target, scoped to a single workspace where the rule is enabled (chosen by the caller at exchange time when the rule is enabled for more than one). For rules enabled via `workspace_ids` or `applies_to_all_workspaces`, the target service account must be a member of that workspace (it is implicitly a member of the default workspace); rules carrying only the legacy `workspace_id` binding do not enforce this. - `type: Literal["federation_rule"]` default: federation_rule - `id: str` Tagged ID of the federation rule. - `applies_to_all_workspaces: bool` When true, this rule is enabled for every workspace in the org (including ones created after the rule). `workspace_ids` is ignored at exchange time. - `archived_at: Optional[datetime]` If set, this rule is archived and rejects token exchange. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this rule. - `attributes: Optional[Dict[str, str]]` CEL expressions extracting named values from claims. Not yet supported; always null. - `created_at: datetime` When this rule was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this rule. - `description: Optional[str]` Optional free-text description. - `issuer_id: str` Tagged ID of the issuer whose tokens this rule accepts. - `issuer_name: Optional[str]` Issuer's display name at read time. - `match: BetaFederationRuleMatch` Conditions the verified JWT must satisfy for this rule to apply. All populated matcher fields must pass. - `audience: Optional[str]` Exact match against the `aud` claim (any element if array). When omitted, the JWT's `aud` must still equal Anthropic's expected audience for the issuer; setting this field overrides that default. maxLength: 1024 - `claims: Optional[Dict[str, str]]` Exact-match `{claim: value}` pairs against top-level claims. Only string-valued claims can be matched; use `condition` for non-string claims. - `condition: Optional[str]` CEL expression over claims for logic the structural fields can't express. Must evaluate to a boolean and may reference only the `claims` variable; a constant-true expression (such as `true`) is rejected with 400. maxLength: 4096 - `subject_prefix: Optional[str]` Match the verified JWT `sub` claim. Exact match unless the value ends with `*`, in which case it is a prefix match. Example: `repo:my-org/my-repo:ref:refs/heads/main`. maxLength: 1024 - `name: str` Admin-chosen slug identifier. - `oauth_scope: str` Space-separated OAuth scopes granted on the minted token. - `target: BetaServiceAccountTarget` What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account. - `type: Literal["service_account"]` - `service_account_id: str` Tagged ID of the service account to mint tokens for. - `service_account_name: Optional[str]` Service account's display name at read time. Ignored on writes. - `token_lifetime_seconds: int` Lifetime in seconds of access tokens minted via this rule. Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds. - `updated_at: datetime` When this rule was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this rule. - `workspace_id: Optional[str]` Legacy single-workspace binding. Prefer `workspace_ids` and the `/federation_rules/{federation_rule_id}/workspaces` sub-resource for managing workspace enablement. - `workspace_ids: List[str]` Tagged IDs of the workspaces this rule is enabled for. May be empty for older rules that only carry the legacy `workspace_id` binding. Ignored at exchange time when `applies_to_all_workspaces` is true (the list may still be non-empty). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.federation.rules.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "fdrl_01SDCCSbTxrXDpWc1phhtcfK", "applies_to_all_workspaces": true, "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "attributes": { "foo": "string" }, "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "description": "description", "issuer_id": "issuer_id", "issuer_name": "issuer_name", "match": { "audience": "audience", "claims": { "foo": "string" }, "condition": "condition", "subject_prefix": "subject_prefix" }, "name": "prod-deploy-pipeline", "oauth_scope": "oauth_scope", "target": { "service_account_id": "svac_01SDCCSbTxrXDpWc1phhtcfK", "type": "service_account", "service_account_name": "service_account_name" }, "token_lifetime_seconds": 0, "type": "federation_rule", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id", "workspace_id": "workspace_id", "workspace_ids": [ "string" ] } ], "next_page": "next_page" } ``` ### Get Federation Rule `beta.organization.federation.rules.retrieve(federation_rule_id, **kwargs) -> BetaFederationRule` **GET** `/v1/organizations/federation_rules/{federation_rule_id}` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Retrieve a federation rule by its ID (`fdrl_...`). #### Parameters - `federation_rule_id: str` (path parameter) ID of the federation rule. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaFederationRule` Authorization rule binding an external OIDC identity to Anthropic. Evaluates the match conditions and mints an OAuth access token for the resolved target, scoped to a single workspace where the rule is enabled (chosen by the caller at exchange time when the rule is enabled for more than one). For rules enabled via `workspace_ids` or `applies_to_all_workspaces`, the target service account must be a member of that workspace (it is implicitly a member of the default workspace); rules carrying only the legacy `workspace_id` binding do not enforce this. - `type: Literal["federation_rule"]` default: federation_rule - `id: str` Tagged ID of the federation rule. - `applies_to_all_workspaces: bool` When true, this rule is enabled for every workspace in the org (including ones created after the rule). `workspace_ids` is ignored at exchange time. - `archived_at: Optional[datetime]` If set, this rule is archived and rejects token exchange. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this rule. - `attributes: Optional[Dict[str, str]]` CEL expressions extracting named values from claims. Not yet supported; always null. - `created_at: datetime` When this rule was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this rule. - `description: Optional[str]` Optional free-text description. - `issuer_id: str` Tagged ID of the issuer whose tokens this rule accepts. - `issuer_name: Optional[str]` Issuer's display name at read time. - `match: BetaFederationRuleMatch` Conditions the verified JWT must satisfy for this rule to apply. All populated matcher fields must pass. - `audience: Optional[str]` Exact match against the `aud` claim (any element if array). When omitted, the JWT's `aud` must still equal Anthropic's expected audience for the issuer; setting this field overrides that default. maxLength: 1024 - `claims: Optional[Dict[str, str]]` Exact-match `{claim: value}` pairs against top-level claims. Only string-valued claims can be matched; use `condition` for non-string claims. - `condition: Optional[str]` CEL expression over claims for logic the structural fields can't express. Must evaluate to a boolean and may reference only the `claims` variable; a constant-true expression (such as `true`) is rejected with 400. maxLength: 4096 - `subject_prefix: Optional[str]` Match the verified JWT `sub` claim. Exact match unless the value ends with `*`, in which case it is a prefix match. Example: `repo:my-org/my-repo:ref:refs/heads/main`. maxLength: 1024 - `name: str` Admin-chosen slug identifier. - `oauth_scope: str` Space-separated OAuth scopes granted on the minted token. - `target: BetaServiceAccountTarget` What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account. - `type: Literal["service_account"]` - `service_account_id: str` Tagged ID of the service account to mint tokens for. - `service_account_name: Optional[str]` Service account's display name at read time. Ignored on writes. - `token_lifetime_seconds: int` Lifetime in seconds of access tokens minted via this rule. Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds. - `updated_at: datetime` When this rule was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this rule. - `workspace_id: Optional[str]` Legacy single-workspace binding. Prefer `workspace_ids` and the `/federation_rules/{federation_rule_id}/workspaces` sub-resource for managing workspace enablement. - `workspace_ids: List[str]` Tagged IDs of the workspaces this rule is enabled for. May be empty for older rules that only carry the legacy `workspace_id` binding. Ignored at exchange time when `applies_to_all_workspaces` is true (the list may still be non-empty). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_federation_rule = client.beta.organization.federation.rules.retrieve( federation_rule_id="federation_rule_id", ) print(beta_federation_rule.id) ``` ##### Response (200) ```json { "id": "fdrl_01SDCCSbTxrXDpWc1phhtcfK", "applies_to_all_workspaces": true, "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "attributes": { "foo": "string" }, "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "description": "description", "issuer_id": "issuer_id", "issuer_name": "issuer_name", "match": { "audience": "audience", "claims": { "foo": "string" }, "condition": "condition", "subject_prefix": "subject_prefix" }, "name": "prod-deploy-pipeline", "oauth_scope": "oauth_scope", "target": { "service_account_id": "svac_01SDCCSbTxrXDpWc1phhtcfK", "type": "service_account", "service_account_name": "service_account_name" }, "token_lifetime_seconds": 0, "type": "federation_rule", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id", "workspace_id": "workspace_id", "workspace_ids": [ "string" ] } ``` ### Update Federation Rule `beta.organization.federation.rules.update(federation_rule_id, **kwargs) -> BetaFederationRule` **POST** `/v1/organizations/federation_rules/{federation_rule_id}` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Partially update a federation rule. `issuer_id` is immutable. `match` and `target` are replaced as whole objects when set. Referenced service accounts and workspaces must exist in your organization; invalid references are rejected with a 400 error. Archived rules cannot be updated; this returns 400. Create a new rule instead. Rules on well-known shared issuers (GitHub Actions, GitLab, Buildkite, Terraform Cloud, Google) must constrain tenant identity via an identity-bearing claim, a tenant-pinning subject prefix (such as `repo:YOUR_ORG/...`), or a CEL condition referencing one of those identity claims (e.g. `claims.repository_owner`). On these issuers the requirement is re-checked on every update; if an existing rule's stored match does not yet constrain tenant identity, any update (even a rename or description change) must also supply a conforming `match` in the same request. OAuth callers may only manage rules whose `oauth_scope` is `workspace:developer` or `workspace:inference`; other scopes require a Console session. #### Parameters - `federation_rule_id: str` (path parameter) ID of the federation rule to update. - `applies_to_all_workspaces: Optional[bool]` When true, enables this rule for every workspace in the org (including workspaces created later). Setting `false` is rejected with 400 if no workspace would remain enabled; a rule with only a legacy `workspace_id` binding continues to mint. - `attributes: Optional[Dict[str, str]]` Replaces the CEL expressions `{name: expr}` extracting named values from claims. Send null to clear them. Not yet supported; any non-empty value is rejected with 400. - `description: Optional[str]` Replaces the description. Omit to leave unchanged; send `null` to clear (the field is stored as an empty string). maxLength: 2000 - `match: Optional[BetaFederationRuleMatchParam]` Replaces the entire match object. All populated matcher fields must pass. - `audience: Optional[str]` Exact match against the `aud` claim (any element if array). When omitted, the JWT's `aud` must still equal Anthropic's expected audience for the issuer; setting this field overrides that default. maxLength: 1024 - `claims: Optional[Dict[str, str]]` Exact-match `{claim: value}` pairs against top-level claims. Only string-valued claims can be matched; use `condition` for non-string claims. - `condition: Optional[str]` CEL expression over claims for logic the structural fields can't express. Must evaluate to a boolean and may reference only the `claims` variable; a constant-true expression (such as `true`) is rejected with 400. maxLength: 4096 - `subject_prefix: Optional[str]` Match the verified JWT `sub` claim. Exact match unless the value ends with `*`, in which case it is a prefix match. Example: `repo:my-org/my-repo:ref:refs/heads/main`. maxLength: 1024 - `name: Optional[str]` Replaces the slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409. minLength: 1, maxLength: 255 - `oauth_scope: Optional[str]` Replaces the space-separated OAuth scopes granted on minted tokens. OAuth callers may only set `workspace:developer` or `workspace:inference`; other scopes (such as `org:admin`) require a Console session. minLength: 1 - `target: Optional[BetaServiceAccountTargetParam]` Replaces the entire target object. Currently always a `service_account` target. - `type: Literal["service_account"]` - `service_account_id: str` Tagged ID of the service account to mint tokens for. - `service_account_name: Optional[str]` Service account's display name at read time. Ignored on writes. - `token_lifetime_seconds: Optional[int]` Replaces the lifetime in seconds for access tokens minted via this rule (60-86400). Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds. minimum: 60, maximum: 86400 - `workspace_id: Optional[str]` Replaces the existing single workspace enablement (the previous one is removed). Rejected with 400 if the rule is enabled for more than one workspace; use the `/federation_rules/{federation_rule_id}/workspaces` sub-resource instead. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaFederationRule` Authorization rule binding an external OIDC identity to Anthropic. Evaluates the match conditions and mints an OAuth access token for the resolved target, scoped to a single workspace where the rule is enabled (chosen by the caller at exchange time when the rule is enabled for more than one). For rules enabled via `workspace_ids` or `applies_to_all_workspaces`, the target service account must be a member of that workspace (it is implicitly a member of the default workspace); rules carrying only the legacy `workspace_id` binding do not enforce this. - `type: Literal["federation_rule"]` default: federation_rule - `id: str` Tagged ID of the federation rule. - `applies_to_all_workspaces: bool` When true, this rule is enabled for every workspace in the org (including ones created after the rule). `workspace_ids` is ignored at exchange time. - `archived_at: Optional[datetime]` If set, this rule is archived and rejects token exchange. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this rule. - `attributes: Optional[Dict[str, str]]` CEL expressions extracting named values from claims. Not yet supported; always null. - `created_at: datetime` When this rule was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this rule. - `description: Optional[str]` Optional free-text description. - `issuer_id: str` Tagged ID of the issuer whose tokens this rule accepts. - `issuer_name: Optional[str]` Issuer's display name at read time. - `match: BetaFederationRuleMatch` Conditions the verified JWT must satisfy for this rule to apply. All populated matcher fields must pass. - `audience: Optional[str]` Exact match against the `aud` claim (any element if array). When omitted, the JWT's `aud` must still equal Anthropic's expected audience for the issuer; setting this field overrides that default. maxLength: 1024 - `claims: Optional[Dict[str, str]]` Exact-match `{claim: value}` pairs against top-level claims. Only string-valued claims can be matched; use `condition` for non-string claims. - `condition: Optional[str]` CEL expression over claims for logic the structural fields can't express. Must evaluate to a boolean and may reference only the `claims` variable; a constant-true expression (such as `true`) is rejected with 400. maxLength: 4096 - `subject_prefix: Optional[str]` Match the verified JWT `sub` claim. Exact match unless the value ends with `*`, in which case it is a prefix match. Example: `repo:my-org/my-repo:ref:refs/heads/main`. maxLength: 1024 - `name: str` Admin-chosen slug identifier. - `oauth_scope: str` Space-separated OAuth scopes granted on the minted token. - `target: BetaServiceAccountTarget` What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account. - `type: Literal["service_account"]` - `service_account_id: str` Tagged ID of the service account to mint tokens for. - `service_account_name: Optional[str]` Service account's display name at read time. Ignored on writes. - `token_lifetime_seconds: int` Lifetime in seconds of access tokens minted via this rule. Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds. - `updated_at: datetime` When this rule was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this rule. - `workspace_id: Optional[str]` Legacy single-workspace binding. Prefer `workspace_ids` and the `/federation_rules/{federation_rule_id}/workspaces` sub-resource for managing workspace enablement. - `workspace_ids: List[str]` Tagged IDs of the workspaces this rule is enabled for. May be empty for older rules that only carry the legacy `workspace_id` binding. Ignored at exchange time when `applies_to_all_workspaces` is true (the list may still be non-empty). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_federation_rule = client.beta.organization.federation.rules.update( federation_rule_id="federation_rule_id", ) print(beta_federation_rule.id) ``` ##### Response (200) ```json { "id": "fdrl_01SDCCSbTxrXDpWc1phhtcfK", "applies_to_all_workspaces": true, "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "attributes": { "foo": "string" }, "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "description": "description", "issuer_id": "issuer_id", "issuer_name": "issuer_name", "match": { "audience": "audience", "claims": { "foo": "string" }, "condition": "condition", "subject_prefix": "subject_prefix" }, "name": "prod-deploy-pipeline", "oauth_scope": "oauth_scope", "target": { "service_account_id": "svac_01SDCCSbTxrXDpWc1phhtcfK", "type": "service_account", "service_account_name": "service_account_name" }, "token_lifetime_seconds": 0, "type": "federation_rule", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id", "workspace_id": "workspace_id", "workspace_ids": [ "string" ] } ``` ### Archive Federation Rule `beta.organization.federation.rules.archive(federation_rule_id, **kwargs) -> BetaFederationRule` **POST** `/v1/organizations/federation_rules/{federation_rule_id}/archive` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Archive a federation rule. Token exchange through this rule stops immediately. Idempotent; re-archiving returns the rule with its original `archived_at`. Archiving clears the rule's workspace targeting (`workspace_id` and `workspace_ids` are emptied). Tokens already minted before archive remain valid until they expire. OAuth callers may only manage rules whose `oauth_scope` is `workspace:developer` or `workspace:inference`; other scopes require a Console session. #### Parameters - `federation_rule_id: str` (path parameter) ID of the federation rule to archive. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaFederationRule` Authorization rule binding an external OIDC identity to Anthropic. Evaluates the match conditions and mints an OAuth access token for the resolved target, scoped to a single workspace where the rule is enabled (chosen by the caller at exchange time when the rule is enabled for more than one). For rules enabled via `workspace_ids` or `applies_to_all_workspaces`, the target service account must be a member of that workspace (it is implicitly a member of the default workspace); rules carrying only the legacy `workspace_id` binding do not enforce this. - `type: Literal["federation_rule"]` default: federation_rule - `id: str` Tagged ID of the federation rule. - `applies_to_all_workspaces: bool` When true, this rule is enabled for every workspace in the org (including ones created after the rule). `workspace_ids` is ignored at exchange time. - `archived_at: Optional[datetime]` If set, this rule is archived and rejects token exchange. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this rule. - `attributes: Optional[Dict[str, str]]` CEL expressions extracting named values from claims. Not yet supported; always null. - `created_at: datetime` When this rule was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this rule. - `description: Optional[str]` Optional free-text description. - `issuer_id: str` Tagged ID of the issuer whose tokens this rule accepts. - `issuer_name: Optional[str]` Issuer's display name at read time. - `match: BetaFederationRuleMatch` Conditions the verified JWT must satisfy for this rule to apply. All populated matcher fields must pass. - `audience: Optional[str]` Exact match against the `aud` claim (any element if array). When omitted, the JWT's `aud` must still equal Anthropic's expected audience for the issuer; setting this field overrides that default. maxLength: 1024 - `claims: Optional[Dict[str, str]]` Exact-match `{claim: value}` pairs against top-level claims. Only string-valued claims can be matched; use `condition` for non-string claims. - `condition: Optional[str]` CEL expression over claims for logic the structural fields can't express. Must evaluate to a boolean and may reference only the `claims` variable; a constant-true expression (such as `true`) is rejected with 400. maxLength: 4096 - `subject_prefix: Optional[str]` Match the verified JWT `sub` claim. Exact match unless the value ends with `*`, in which case it is a prefix match. Example: `repo:my-org/my-repo:ref:refs/heads/main`. maxLength: 1024 - `name: str` Admin-chosen slug identifier. - `oauth_scope: str` Space-separated OAuth scopes granted on the minted token. - `target: BetaServiceAccountTarget` What this rule targets. Check `type` before reading the other fields. Tokens minted via a rule whose target `type` is `service_account` act as that service account. - `type: Literal["service_account"]` - `service_account_id: str` Tagged ID of the service account to mint tokens for. - `service_account_name: Optional[str]` Service account's display name at read time. Ignored on writes. - `token_lifetime_seconds: int` Lifetime in seconds of access tokens minted via this rule. Minted tokens are capped at `max(60, min(this value, 2 × remaining assertion validity))` seconds. - `updated_at: datetime` When this rule was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this rule. - `workspace_id: Optional[str]` Legacy single-workspace binding. Prefer `workspace_ids` and the `/federation_rules/{federation_rule_id}/workspaces` sub-resource for managing workspace enablement. - `workspace_ids: List[str]` Tagged IDs of the workspaces this rule is enabled for. May be empty for older rules that only carry the legacy `workspace_id` binding. Ignored at exchange time when `applies_to_all_workspaces` is true (the list may still be non-empty). #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_federation_rule = client.beta.organization.federation.rules.archive( federation_rule_id="federation_rule_id", ) print(beta_federation_rule.id) ``` ##### Response (200) ```json { "id": "fdrl_01SDCCSbTxrXDpWc1phhtcfK", "applies_to_all_workspaces": true, "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "attributes": { "foo": "string" }, "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "description": "description", "issuer_id": "issuer_id", "issuer_name": "issuer_name", "match": { "audience": "audience", "claims": { "foo": "string" }, "condition": "condition", "subject_prefix": "subject_prefix" }, "name": "prod-deploy-pipeline", "oauth_scope": "oauth_scope", "target": { "service_account_id": "svac_01SDCCSbTxrXDpWc1phhtcfK", "type": "service_account", "service_account_name": "service_account_name" }, "token_lifetime_seconds": 0, "type": "federation_rule", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id", "workspace_id": "workspace_id", "workspace_ids": [ "string" ] } ``` ## Beta › Organization › Federation › Rules › Workspaces ### Add Federation Rule Workspace `beta.organization.federation.rules.workspaces.add(federation_rule_id, **kwargs) -> BetaFederationRuleWorkspace` **POST** `/v1/organizations/federation_rules/{federation_rule_id}/workspaces` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Enable a federation rule for a workspace. Idempotent; re-enabling returns the existing enablement. The rule and workspace must both belong to your organization. Membership of the rule's target service account in this workspace is not checked at enablement: token exchange into this workspace is rejected unless the target is a member (it is implicitly a member of the default workspace). Archived rules are rejected with 400. OAuth callers may only manage rules whose `oauth_scope` is `workspace:developer` or `workspace:inference`; other scopes require a Console session. #### Parameters - `federation_rule_id: str` (path parameter) ID of the federation rule. - `workspace_id: str` Tagged ID of the workspace to enable this rule for. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaFederationRuleWorkspace` - `type: Literal["federation_rule_workspace"]` default: federation_rule_workspace - `created_at: datetime` When this workspace was enabled for the rule. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_...` or `svac_...`) of the actor that enabled this workspace for the rule, if known. - `federation_rule_id: str` Tagged ID of the federation rule. - `workspace_id: str` Tagged ID of the workspace this rule is enabled for. - `workspace_name: Optional[str]` Workspace display name. Populated when listing; null in the enable response. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_federation_rule_workspace = ( client.beta.organization.federation.rules.workspaces.add( federation_rule_id="federation_rule_id", workspace_id="workspace_id", ) ) print(beta_federation_rule_workspace.created_by_actor_id) ``` ##### Response (200) ```json { "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "federation_rule_id": "federation_rule_id", "type": "federation_rule_workspace", "workspace_id": "workspace_id", "workspace_name": "workspace_name" } ``` ### List Federation Rule Workspaces `beta.organization.federation.rules.workspaces.list(federation_rule_id, **kwargs) -> SyncPageCursor[BetaFederationRuleWorkspace]` **GET** `/v1/organizations/federation_rules/{federation_rule_id}/workspaces` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). List workspaces where this federation rule is enabled. Returns all workspace enablements in a single response; the `limit` and `page` parameters are accepted but have no effect, and `next_page` is always `null`. Returns explicit per-workspace enablements only; for rules with `applies_to_all_workspaces` or a legacy single `workspace_id`, check those fields on the rule itself. #### Parameters - `federation_rule_id: str` (path parameter) ID of the federation rule. - `limit: Optional[int]` (query parameter) Number of results per page. default: 20, minimum: 1, maximum: 100 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page`. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaFederationRuleWorkspace` - `type: Literal["federation_rule_workspace"]` default: federation_rule_workspace - `created_at: datetime` When this workspace was enabled for the rule. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_...` or `svac_...`) of the actor that enabled this workspace for the rule, if known. - `federation_rule_id: str` Tagged ID of the federation rule. - `workspace_id: str` Tagged ID of the workspace this rule is enabled for. - `workspace_name: Optional[str]` Workspace display name. Populated when listing; null in the enable response. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.federation.rules.workspaces.list( federation_rule_id="federation_rule_id", ) page = page.data[0] print(page.created_by_actor_id) ``` ##### Response (200) ```json { "data": [ { "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "federation_rule_id": "federation_rule_id", "type": "federation_rule_workspace", "workspace_id": "workspace_id", "workspace_name": "workspace_name" } ], "next_page": "next_page" } ``` ### Remove Federation Rule Workspace `beta.organization.federation.rules.workspaces.remove(workspace_id, **kwargs) -> WorkspaceRemoveResponse` **DELETE** `/v1/organizations/federation_rules/{federation_rule_id}/workspaces/{workspace_id}` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Disable a federation rule for a workspace. Idempotent; succeeds even if the enablement was already removed. OAuth callers may only manage rules whose `oauth_scope` is `workspace:developer` or `workspace:inference`; other scopes require a Console session. #### Parameters - `federation_rule_id: str` (path parameter) ID of the federation rule. - `workspace_id: str` (path parameter) ID of the workspace to disable for. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class WorkspaceRemoveResponse` - `type: Literal["federation_rule_workspace_deleted"]` default: federation_rule_workspace_deleted - `federation_rule_id: str` Tagged ID of the federation rule. - `workspace_id: str` Tagged ID of the workspace named in the delete request. Removal is idempotent. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) workspace = client.beta.organization.federation.rules.workspaces.remove( workspace_id="workspace_id", federation_rule_id="federation_rule_id", ) print(workspace.federation_rule_id) ``` ##### Response (200) ```json { "federation_rule_id": "federation_rule_id", "type": "federation_rule_workspace_deleted", "workspace_id": "workspace_id" } ``` ## Beta › Organization › Invites ### Create Invite `beta.organization.invites.create(**kwargs) -> BetaOrganizationInvite` **POST** `/v1/organizations/invites` Invite a user to join the organization by email. On plans that draw members from a finite pool of purchased seats, the invite automatically consumes a seat from the lowest tier with availability; there is no seat-tier parameter. When no seat is free the request fails with a 400 error rather than purchasing a seat. #### Parameters - `email: str` Email of the User. format: email - `role: Literal["billing", "claude_code_user", "developer", 2 more]` Role for the invited User. The accepted values depend on the organization type. Console and API organizations accept `user`, `developer`, `billing`, and `claude_code_user`; `admin` cannot be assigned through the API. Claude Enterprise organizations accept `user` and `managed`. - `"billing"` - `"claude_code_user"` - `"developer"` - `"managed"` - `"user"` - `rbac_group_ids: Optional[Sequence[str]]` RBAC group IDs to assign to the User when the Invite is accepted. A non-empty array is accepted only for a Claude Enterprise organization with RBAC groups, and requires the key to carry the `write:rbac_groups` scope. maxItems: 100 #### Returns - `class BetaOrganizationInvite` - `type: Literal["invite"]` Object type. For Invites, this is always `"invite"`. default: invite - `id: str` ID of the Invite. - `accepted_at: Optional[datetime]` RFC 3339 datetime string indicating when the Invite was accepted, or null. format: date-time - `email: str` Email of the User being invited. - `expires_at: datetime` RFC 3339 datetime string indicating when the Invite expires. format: date-time - `invited_at: datetime` RFC 3339 datetime string indicating when the Invite was created. format: date-time - `rbac_group_ids: List[str]` RBAC group IDs recorded on the Invite (Claude Enterprise organizations), to be assigned to the User when the Invite is accepted. `[]` when none. - `role: BetaOrganizationRole` Organization role of the User. - `"admin"` - `"billing"` - `"claude_code_user"` - `"developer"` - `"managed"` - `"membership_admin"` - `"owner"` - `"primary_owner"` - `"user"` - `status: Literal["accepted", "deleted", "expired", "pending"]` Status of the Invite. - `"accepted"` - `"deleted"` - `"expired"` - `"pending"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_organization_invite = client.beta.organization.invites.create( email="user@emaildomain.com", role="user", ) print(beta_organization_invite.id) ``` ##### Response (200) ```json { "id": "invite_015gWxCN9Hfg2QhZwTK7Mdeu", "accepted_at": "2019-12-27T18:11:19.117Z", "email": "user@emaildomain.com", "expires_at": "2024-11-20T23:58:27.427722Z", "invited_at": "2024-10-30T23:58:27.427722Z", "rbac_group_ids": [ "string" ], "role": "admin", "status": "pending", "type": "invite" } ``` ### List Invites `beta.organization.invites.list(**kwargs) -> SyncPage[BetaOrganizationInvite]` **GET** `/v1/organizations/invites` List the organization's invites. #### Parameters - `after_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately after this object. - `before_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately before this object. - `email: Optional[str]` (query parameter) Filter by the email address the Invite was sent to. Matches the same way as the Users list's `email` filter (normalized, case-insensitive). format: email - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 - `roles: Optional[Sequence[str]]` (query parameter) Filter to items whose `role` equals one of the supplied values. Repeatable; values are OR'ed together. Accepted values depend on the organization type: Console and API organizations accept `user`, `developer`, `billing`, `admin`, and `claude_code_user`; Claude Enterprise organizations accept `user`, `owner`, `primary_owner`, `membership_admin`, and `managed`. - `statuses: Optional[List[Literal["accepted", "expired", "pending"]]]` (query parameter) Filter by Invite status. Repeatable; values are OR'ed together. Omit to return `pending`, `accepted`, and `expired` Invites alike. - `"accepted"` - `"expired"` - `"pending"` #### Returns - `class BetaOrganizationInvite` - `type: Literal["invite"]` Object type. For Invites, this is always `"invite"`. default: invite - `id: str` ID of the Invite. - `accepted_at: Optional[datetime]` RFC 3339 datetime string indicating when the Invite was accepted, or null. format: date-time - `email: str` Email of the User being invited. - `expires_at: datetime` RFC 3339 datetime string indicating when the Invite expires. format: date-time - `invited_at: datetime` RFC 3339 datetime string indicating when the Invite was created. format: date-time - `rbac_group_ids: List[str]` RBAC group IDs recorded on the Invite (Claude Enterprise organizations), to be assigned to the User when the Invite is accepted. `[]` when none. - `role: BetaOrganizationRole` Organization role of the User. - `"admin"` - `"billing"` - `"claude_code_user"` - `"developer"` - `"managed"` - `"membership_admin"` - `"owner"` - `"primary_owner"` - `"user"` - `status: Literal["accepted", "deleted", "expired", "pending"]` Status of the Invite. - `"accepted"` - `"deleted"` - `"expired"` - `"pending"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.invites.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "invite_015gWxCN9Hfg2QhZwTK7Mdeu", "accepted_at": "2019-12-27T18:11:19.117Z", "email": "user@emaildomain.com", "expires_at": "2024-11-20T23:58:27.427722Z", "invited_at": "2024-10-30T23:58:27.427722Z", "rbac_group_ids": [ "string" ], "role": "admin", "status": "pending", "type": "invite" } ], "first_id": "first_id", "has_more": true, "last_id": "last_id" } ``` ### Get Invite `beta.organization.invites.retrieve(invite_id) -> BetaOrganizationInvite` **GET** `/v1/organizations/invites/{invite_id}` Retrieve an invite by ID. #### Parameters - `invite_id: str` (path parameter) ID of the Invite. #### Returns - `class BetaOrganizationInvite` - `type: Literal["invite"]` Object type. For Invites, this is always `"invite"`. default: invite - `id: str` ID of the Invite. - `accepted_at: Optional[datetime]` RFC 3339 datetime string indicating when the Invite was accepted, or null. format: date-time - `email: str` Email of the User being invited. - `expires_at: datetime` RFC 3339 datetime string indicating when the Invite expires. format: date-time - `invited_at: datetime` RFC 3339 datetime string indicating when the Invite was created. format: date-time - `rbac_group_ids: List[str]` RBAC group IDs recorded on the Invite (Claude Enterprise organizations), to be assigned to the User when the Invite is accepted. `[]` when none. - `role: BetaOrganizationRole` Organization role of the User. - `"admin"` - `"billing"` - `"claude_code_user"` - `"developer"` - `"managed"` - `"membership_admin"` - `"owner"` - `"primary_owner"` - `"user"` - `status: Literal["accepted", "deleted", "expired", "pending"]` Status of the Invite. - `"accepted"` - `"deleted"` - `"expired"` - `"pending"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_organization_invite = client.beta.organization.invites.retrieve( "invite_id", ) print(beta_organization_invite.id) ``` ##### Response (200) ```json { "id": "invite_015gWxCN9Hfg2QhZwTK7Mdeu", "accepted_at": "2019-12-27T18:11:19.117Z", "email": "user@emaildomain.com", "expires_at": "2024-11-20T23:58:27.427722Z", "invited_at": "2024-10-30T23:58:27.427722Z", "rbac_group_ids": [ "string" ], "role": "admin", "status": "pending", "type": "invite" } ``` ### Delete Invite `beta.organization.invites.delete(invite_id) -> InviteDeleteResponse` **DELETE** `/v1/organizations/invites/{invite_id}` Delete a pending invite. #### Parameters - `invite_id: str` (path parameter) ID of the Invite. #### Returns - `class InviteDeleteResponse` - `type: Literal["invite_deleted"]` Deleted object type. For Invites, this is always `"invite_deleted"`. default: invite_deleted - `id: str` ID of the Invite. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) invite = client.beta.organization.invites.delete( "invite_id", ) print(invite.id) ``` ##### Response (200) ```json { "id": "invite_015gWxCN9Hfg2QhZwTK7Mdeu", "type": "invite_deleted" } ``` ## Beta › Organization › Service Accounts ### Create Service Account `beta.organization.service_accounts.create(**kwargs) -> BetaServiceAccount` **POST** `/v1/organizations/service_accounts` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Create a service account. A service account is a named workload identity that federation rules target. `organization_role` is `developer` (default) or `admin`; a rule may only be created or retargeted to grant `org:admin` scope when the target's `organization_role` is `admin`. Creating an `admin`-role service account requires an interactive credential (a user OAuth token or a Console session) — a workload may only create `developer`-role service accounts. #### Parameters - `name: str` Slug identifier (lowercase, digits, hyphens). Unique within the organization; a duplicate name returns 409. minLength: 1, maxLength: 255 - `description: Optional[str]` Optional free-text description. maxLength: 2000 - `organization_role: Optional[Literal["admin", "developer"]]` Org-level role. Defaults to `developer`. - `"admin"` - `"developer"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaServiceAccount` Named non-human identity within the caller's organization. A service account is a pure identity: name + org. Authorization lives on whatever references it (federation rules). - `type: Literal["service_account"]` default: service_account - `id: str` Tagged ID of the service account. - `archived_at: Optional[datetime]` If set, this service account is archived. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this service account. - `created_at: datetime` When this service account was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this service account. - `description: Optional[str]` Optional free-text description. - `name: str` Admin-chosen slug identifier. - `organization_role: Literal["admin", "developer"]` Org-level role. A federation rule may only be created or retargeted to grant `org:admin` scope when this is `admin`. A rule granting `org:admin` whose target is later demoted to `developer` is rejected at token exchange. Rules granting `org:admin` are managed in the Console. - `"admin"` - `"developer"` - `updated_at: datetime` When this service account was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this service account. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_service_account = client.beta.organization.service_accounts.create( name="ci-deploy-bot", ) print(beta_service_account.id) ``` ##### Response (200) ```json { "id": "svac_01SDCCSbTxrXDpWc1phhtcfK", "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "description": "description", "name": "ci-deploy-bot", "organization_role": "admin", "type": "service_account", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id" } ``` ### List Service Accounts `beta.organization.service_accounts.list(**kwargs) -> SyncPageCursor[BetaServiceAccount]` **GET** `/v1/organizations/service_accounts` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). List service accounts in the caller's organization. Results are ordered by creation time, newest first. Use `limit` and the `next_page` cursor to paginate; set `include_archived=true` to include archived service accounts. #### Parameters - `include_archived: Optional[bool]` (query parameter) Include archived resources. Defaults to false. default: false - `limit: Optional[int]` (query parameter) Number of results per page. default: 20, minimum: 1, maximum: 100 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page`. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaServiceAccount` Named non-human identity within the caller's organization. A service account is a pure identity: name + org. Authorization lives on whatever references it (federation rules). - `type: Literal["service_account"]` default: service_account - `id: str` Tagged ID of the service account. - `archived_at: Optional[datetime]` If set, this service account is archived. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this service account. - `created_at: datetime` When this service account was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this service account. - `description: Optional[str]` Optional free-text description. - `name: str` Admin-chosen slug identifier. - `organization_role: Literal["admin", "developer"]` Org-level role. A federation rule may only be created or retargeted to grant `org:admin` scope when this is `admin`. A rule granting `org:admin` whose target is later demoted to `developer` is rejected at token exchange. Rules granting `org:admin` are managed in the Console. - `"admin"` - `"developer"` - `updated_at: datetime` When this service account was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this service account. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.service_accounts.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "svac_01SDCCSbTxrXDpWc1phhtcfK", "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "description": "description", "name": "ci-deploy-bot", "organization_role": "admin", "type": "service_account", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id" } ], "next_page": "next_page" } ``` ### Get Service Account `beta.organization.service_accounts.retrieve(service_account_id, **kwargs) -> BetaServiceAccount` **GET** `/v1/organizations/service_accounts/{service_account_id}` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Retrieve a service account by its ID (`svac_...`). #### Parameters - `service_account_id: str` (path parameter) ID of the service account. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaServiceAccount` Named non-human identity within the caller's organization. A service account is a pure identity: name + org. Authorization lives on whatever references it (federation rules). - `type: Literal["service_account"]` default: service_account - `id: str` Tagged ID of the service account. - `archived_at: Optional[datetime]` If set, this service account is archived. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this service account. - `created_at: datetime` When this service account was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this service account. - `description: Optional[str]` Optional free-text description. - `name: str` Admin-chosen slug identifier. - `organization_role: Literal["admin", "developer"]` Org-level role. A federation rule may only be created or retargeted to grant `org:admin` scope when this is `admin`. A rule granting `org:admin` whose target is later demoted to `developer` is rejected at token exchange. Rules granting `org:admin` are managed in the Console. - `"admin"` - `"developer"` - `updated_at: datetime` When this service account was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this service account. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_service_account = client.beta.organization.service_accounts.retrieve( service_account_id="service_account_id", ) print(beta_service_account.id) ``` ##### Response (200) ```json { "id": "svac_01SDCCSbTxrXDpWc1phhtcfK", "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "description": "description", "name": "ci-deploy-bot", "organization_role": "admin", "type": "service_account", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id" } ``` ### Update Service Account `beta.organization.service_accounts.update(service_account_id, **kwargs) -> BetaServiceAccount` **POST** `/v1/organizations/service_accounts/{service_account_id}` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Update a service account. Only `description` and `organization_role` are mutable; `name` cannot be changed. Archived service accounts cannot be updated; this returns 400. Setting `organization_role` to `admin` (even when unchanged) requires an interactive credential (a user OAuth token or a Console session). #### Parameters - `service_account_id: str` (path parameter) ID of the service account to update. - `description: Optional[str]` Replaces the description. Omit to leave unchanged; send `null` to clear (the field is stored as an empty string). maxLength: 2000 - `organization_role: Optional[Literal["admin", "developer"]]` Replaces the org-level role. Omit or send `null` to leave unchanged. - `"admin"` - `"developer"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaServiceAccount` Named non-human identity within the caller's organization. A service account is a pure identity: name + org. Authorization lives on whatever references it (federation rules). - `type: Literal["service_account"]` default: service_account - `id: str` Tagged ID of the service account. - `archived_at: Optional[datetime]` If set, this service account is archived. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this service account. - `created_at: datetime` When this service account was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this service account. - `description: Optional[str]` Optional free-text description. - `name: str` Admin-chosen slug identifier. - `organization_role: Literal["admin", "developer"]` Org-level role. A federation rule may only be created or retargeted to grant `org:admin` scope when this is `admin`. A rule granting `org:admin` whose target is later demoted to `developer` is rejected at token exchange. Rules granting `org:admin` are managed in the Console. - `"admin"` - `"developer"` - `updated_at: datetime` When this service account was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this service account. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_service_account = client.beta.organization.service_accounts.update( service_account_id="service_account_id", ) print(beta_service_account.id) ``` ##### Response (200) ```json { "id": "svac_01SDCCSbTxrXDpWc1phhtcfK", "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "description": "description", "name": "ci-deploy-bot", "organization_role": "admin", "type": "service_account", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id" } ``` ### Archive Service Account `beta.organization.service_accounts.archive(service_account_id, **kwargs) -> BetaServiceAccount` **POST** `/v1/organizations/service_accounts/{service_account_id}/archive` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Archive a service account. Idempotent; re-archiving returns the service account with its original `archived_at`. Rejected with 400 if any live (non-archived) federation rule still targets this service account, same as issuer archival; archive those rules first or change their target to another service account. #### Parameters - `service_account_id: str` (path parameter) ID of the service account to archive. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaServiceAccount` Named non-human identity within the caller's organization. A service account is a pure identity: name + org. Authorization lives on whatever references it (federation rules). - `type: Literal["service_account"]` default: service_account - `id: str` Tagged ID of the service account. - `archived_at: Optional[datetime]` If set, this service account is archived. format: date-time - `archived_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that archived this service account. - `created_at: datetime` When this service account was created. format: date-time - `created_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that created this service account. - `description: Optional[str]` Optional free-text description. - `name: str` Admin-chosen slug identifier. - `organization_role: Literal["admin", "developer"]` Org-level role. A federation rule may only be created or retargeted to grant `org:admin` scope when this is `admin`. A rule granting `org:admin` whose target is later demoted to `developer` is rejected at token exchange. Rules granting `org:admin` are managed in the Console. - `"admin"` - `"developer"` - `updated_at: datetime` When this service account was last updated. format: date-time - `updated_by_actor_id: Optional[str]` Tagged ID (`user_`/`svac_`) of the actor that last updated this service account. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_service_account = client.beta.organization.service_accounts.archive( service_account_id="service_account_id", ) print(beta_service_account.id) ``` ##### Response (200) ```json { "id": "svac_01SDCCSbTxrXDpWc1phhtcfK", "archived_at": "2019-12-27T18:11:19.117Z", "archived_by_actor_id": "archived_by_actor_id", "created_at": "2024-10-30T23:58:27.427722Z", "created_by_actor_id": "created_by_actor_id", "description": "description", "name": "ci-deploy-bot", "organization_role": "admin", "type": "service_account", "updated_at": "2024-10-30T23:58:27.427722Z", "updated_by_actor_id": "updated_by_actor_id" } ``` ## Beta › Organization › Service Accounts › Workspaces ### Add Workspace To Service Account `beta.organization.service_accounts.workspaces.add(service_account_id, **kwargs) -> BetaServiceAccountWorkspaceMember` **POST** `/v1/organizations/service_accounts/{service_account_id}/workspaces` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Add a service account to a workspace with the given `workspace_role`. Mirror of `POST /workspaces/{workspace_id}/service_accounts`, addressed from the service-account side; both create the same membership. If the service account is already an explicit member of the workspace, its `workspace_role` is replaced with the value supplied here. Archived workspaces return 400. Archived service accounts cannot be added and are rejected. #### Parameters - `service_account_id: str` (path parameter) ID of the service account. - `workspace_id: str` Tagged workspace ID to add the service account to. - `workspace_role: BetaNoBillingWorkspaceRole` Role to assign to the service account in this workspace. - `"workspace_admin"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaServiceAccountWorkspaceMember` - `type: Literal["service_account_workspace_member"]` default: service_account_workspace_member - `created_by_actor_id: Optional[str]` Tagged ID (`user_...`/`svac_...`) of the actor who created this membership. - `implicit: Optional[bool]` True when this is the implicit default-workspace membership every service account has when no explicit membership exists. Implicit memberships have role `workspace_user` and cannot be removed. - `service_account_id: str` Tagged service account ID (`svac_...`). - `workspace_id: str` Tagged workspace ID (`wrkspc_...`). - `workspace_role: BetaWorkspaceRole` Role of the service account in this workspace. Service accounts cannot hold the `workspace_billing` role. - `"workspace_admin"` - `"workspace_billing"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_service_account_workspace_member = ( client.beta.organization.service_accounts.workspaces.add( service_account_id="service_account_id", workspace_id="workspace_id", workspace_role="workspace_admin", ) ) print(beta_service_account_workspace_member.created_by_actor_id) ``` ##### Response (200) ```json { "created_by_actor_id": "created_by_actor_id", "implicit": true, "service_account_id": "service_account_id", "type": "service_account_workspace_member", "workspace_id": "workspace_id", "workspace_role": "workspace_admin" } ``` ### List Workspaces For Service Account `beta.organization.service_accounts.workspaces.list(service_account_id, **kwargs) -> SyncPageCursor[BetaServiceAccountWorkspaceMember]` **GET** `/v1/organizations/service_accounts/{service_account_id}/workspaces` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). List the workspaces a service account is a member of. Each entry includes the service account's `workspace_role` in that workspace. Use `limit` and the `next_page` cursor to paginate. When the service account has no explicit default-workspace membership, the implicit (`implicit: true`) membership is returned as the first entry on the first page; with `limit=1` the first page may return up to 2 entries (the implicit entry plus one explicit membership) so a pagination cursor can be derived. Memberships are returned only while the service account is active. Without a `page` cursor, an archived service account returns an empty list. A `page` cursor that does not match an active membership returns a 400 invalid-request error. A cursor stops matching when the membership is removed, the workspace is deleted, or the service account is archived. Restart pagination from the first page to recover. #### Parameters - `service_account_id: str` (path parameter) ID of the service account. - `limit: Optional[int]` (query parameter) Number of results per page. default: 20, minimum: 1, maximum: 100 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page`. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaServiceAccountWorkspaceMember` - `type: Literal["service_account_workspace_member"]` default: service_account_workspace_member - `created_by_actor_id: Optional[str]` Tagged ID (`user_...`/`svac_...`) of the actor who created this membership. - `implicit: Optional[bool]` True when this is the implicit default-workspace membership every service account has when no explicit membership exists. Implicit memberships have role `workspace_user` and cannot be removed. - `service_account_id: str` Tagged service account ID (`svac_...`). - `workspace_id: str` Tagged workspace ID (`wrkspc_...`). - `workspace_role: BetaWorkspaceRole` Role of the service account in this workspace. Service accounts cannot hold the `workspace_billing` role. - `"workspace_admin"` - `"workspace_billing"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.service_accounts.workspaces.list( service_account_id="service_account_id", ) page = page.data[0] print(page.created_by_actor_id) ``` ##### Response (200) ```json { "data": [ { "created_by_actor_id": "created_by_actor_id", "implicit": true, "service_account_id": "service_account_id", "type": "service_account_workspace_member", "workspace_id": "workspace_id", "workspace_role": "workspace_admin" } ], "next_page": "next_page" } ``` ### Remove Workspace From Service Account `beta.organization.service_accounts.workspaces.remove(workspace_id, **kwargs) -> WorkspaceRemoveResponse` **DELETE** `/v1/organizations/service_accounts/{service_account_id}/workspaces/{workspace_id}` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Remove a service account from a workspace. Mirror of `DELETE /workspaces/{workspace_id}/service_accounts/{service_account_id}`, addressed from the service-account side. Removal is idempotent (returns 200 even if the membership was already removed). A DELETE against the implicit default-workspace membership returns 200 but is a no-op and the membership persists; deleting an explicit default-workspace row reverts to the implicit `workspace_user` membership. Archived workspaces return 400. #### Parameters - `service_account_id: str` (path parameter) ID of the service account. - `workspace_id: str` (path parameter) ID of the workspace. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class WorkspaceRemoveResponse` - `type: Literal["service_account_workspace_member_deleted"]` default: service_account_workspace_member_deleted - `service_account_id: str` Tagged service account ID (`svac_...`) named in the delete request. Removal is idempotent; see the endpoint description for the implicit-membership no-op. - `workspace_id: str` Tagged workspace ID (`wrkspc_...`) named in the delete request. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) workspace = client.beta.organization.service_accounts.workspaces.remove( workspace_id="workspace_id", service_account_id="service_account_id", ) print(workspace.service_account_id) ``` ##### Response (200) ```json { "service_account_id": "service_account_id", "type": "service_account_workspace_member_deleted", "workspace_id": "workspace_id" } ``` ## Beta › Organization › Users ### List Users `beta.organization.users.list(**kwargs) -> SyncPage[BetaOrganizationUser]` **GET** `/v1/organizations/users` List the organization's members. #### Parameters - `after_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately after this object. - `before_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately before this object. - `email: Optional[str]` (query parameter) Filter by user email. format: email - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 - `roles: Optional[Sequence[str]]` (query parameter) Filter to items whose `role` equals one of the supplied values. Repeatable; values are OR'ed together. Accepted values depend on the organization type: Console and API organizations accept `user`, `developer`, `billing`, `admin`, and `claude_code_user`; Claude Enterprise organizations accept `user`, `owner`, `primary_owner`, `membership_admin`, and `managed`. #### Returns - `class BetaOrganizationUser` - `type: Literal["user"]` Object type. For Users, this is always `"user"`. default: user - `id: str` ID of the User. - `added_at: datetime` RFC 3339 datetime string indicating when the User joined the Organization. format: date-time - `email: str` Email of the User. - `name: str` Name of the User. - `role: BetaOrganizationRole` Organization role of the User. - `"admin"` - `"billing"` - `"claude_code_user"` - `"developer"` - `"managed"` - `"membership_admin"` - `"owner"` - `"primary_owner"` - `"user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.users.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "user_01WCz1FkmYMm4gnmykNKUu3Q", "added_at": "2024-10-30T23:58:27.427722Z", "email": "user@emaildomain.com", "name": "Jane Doe", "role": "admin", "type": "user" } ], "first_id": "first_id", "has_more": true, "last_id": "last_id" } ``` ### Get User `beta.organization.users.retrieve(user_id) -> BetaOrganizationUser` **GET** `/v1/organizations/users/{user_id}` Retrieve a member of the organization by user ID. #### Parameters - `user_id: str` (path parameter) ID of the User. #### Returns - `class BetaOrganizationUser` - `type: Literal["user"]` Object type. For Users, this is always `"user"`. default: user - `id: str` ID of the User. - `added_at: datetime` RFC 3339 datetime string indicating when the User joined the Organization. format: date-time - `email: str` Email of the User. - `name: str` Name of the User. - `role: BetaOrganizationRole` Organization role of the User. - `"admin"` - `"billing"` - `"claude_code_user"` - `"developer"` - `"managed"` - `"membership_admin"` - `"owner"` - `"primary_owner"` - `"user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_organization_user = client.beta.organization.users.retrieve( "user_id", ) print(beta_organization_user.id) ``` ##### Response (200) ```json { "id": "user_01WCz1FkmYMm4gnmykNKUu3Q", "added_at": "2024-10-30T23:58:27.427722Z", "email": "user@emaildomain.com", "name": "Jane Doe", "role": "admin", "type": "user" } ``` ### Update User `beta.organization.users.update(user_id, **kwargs) -> BetaOrganizationUser` **POST** `/v1/organizations/users/{user_id}` Update a member's organization role. #### Parameters - `user_id: str` (path parameter) ID of the User. - `role: Literal["billing", "claude_code_user", "developer", 2 more]` New role for the User. The accepted values depend on the organization type. Console and API organizations accept `user`, `developer`, `billing`, and `claude_code_user`; `admin` cannot be assigned through the API. Claude Enterprise organizations accept `user` and `managed`. - `"billing"` - `"claude_code_user"` - `"developer"` - `"managed"` - `"user"` #### Returns - `class BetaOrganizationUser` - `type: Literal["user"]` Object type. For Users, this is always `"user"`. default: user - `id: str` ID of the User. - `added_at: datetime` RFC 3339 datetime string indicating when the User joined the Organization. format: date-time - `email: str` Email of the User. - `name: str` Name of the User. - `role: BetaOrganizationRole` Organization role of the User. - `"admin"` - `"billing"` - `"claude_code_user"` - `"developer"` - `"managed"` - `"membership_admin"` - `"owner"` - `"primary_owner"` - `"user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_organization_user = client.beta.organization.users.update( user_id="user_id", role="user", ) print(beta_organization_user.id) ``` ##### Response (200) ```json { "id": "user_01WCz1FkmYMm4gnmykNKUu3Q", "added_at": "2024-10-30T23:58:27.427722Z", "email": "user@emaildomain.com", "name": "Jane Doe", "role": "admin", "type": "user" } ``` ### Remove User `beta.organization.users.remove(user_id) -> UserRemoveResponse` **DELETE** `/v1/organizations/users/{user_id}` Remove a member from the organization. #### Parameters - `user_id: str` (path parameter) ID of the User. #### Returns - `class UserRemoveResponse` - `type: Literal["user_deleted"]` Deleted object type. For Users, this is always `"user_deleted"`. default: user_deleted - `id: str` ID of the User. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) user = client.beta.organization.users.remove( "user_id", ) print(user.id) ``` ##### Response (200) ```json { "id": "user_01WCz1FkmYMm4gnmykNKUu3Q", "type": "user_deleted" } ``` ## Beta › Organization › Workspaces ### List Workspaces `beta.organization.workspaces.list(**kwargs) -> SyncPage[BetaWorkspace]` **GET** `/v1/organizations/workspaces` List Workspaces #### Parameters - `after_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately after this object. - `before_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately before this object. - `include_archived: Optional[bool]` (query parameter) Whether to include Workspaces that have been archived in the response default: false - `include_default: Optional[bool]` (query parameter) Whether to include the organization's default Workspace in the response default: false - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 #### Returns - `class BetaWorkspace` - `type: Literal["workspace"]` Object type. For Workspaces, this is always `"workspace"`. default: workspace - `id: str` ID of the Workspace. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the Workspace was archived, or `null` if the Workspace is not archived. format: date-time - `compartment_id: str` Identifier for this Workspace's encryption compartment. When you configure a customer-managed encryption key (CMEK) on AWS, reference this value in your KMS key-policy condition so the key is scoped to this compartment. On GCP and Azure, Anthropic enforces the compartment binding automatically; you do not need to reference this value in your key configuration. See the CMEK integration guide for the required key configuration; unless your organization is on Claude Platform on AWS, it includes a separate value used during key validation. On Claude Platform on AWS there is no separate validation value: the key is validated against this Workspace's own value when it is attached, so if your key policy uses the compartment condition, add this value to it before attaching the key. - `created_at: datetime` RFC 3339 datetime string indicating when the Workspace was created. format: date-time - `data_residency: BetaDataResidency` Data residency configuration. - `allowed_inference_geos: Union[List[BetaAllowedInferenceGeo], Literal["unrestricted"]]` Permitted inference geo values. 'unrestricted' means all geos are allowed. - `List[BetaAllowedInferenceGeo]` - `"global"` - `"us"` - `"unrestricted"` - `default_inference_geo: Literal["global", "us"]` Default inference geo applied when requests omit the parameter. - `"global"` - `"us"` - `workspace_geo: Literal["us"]` Geographic region for workspace data storage. Immutable after creation. - `display_color: str` Hex color code representing the Workspace in the Anthropic Console. - `external_key_id: Optional[str]` ID of the customer-managed encryption key (CMEK) configuration to use for this Workspace. Setting this field requires CMEK to be enabled for your organization. When set, data stored for this Workspace is encrypted with the referenced key. Create key configurations with the External Keys API. On Claude Platform on AWS the value is the AWS KMS key ARN, and the key must be a single-Region key in the same AWS account and Region as the Workspace. On that platform the key is validated against this Workspace when it is attached, so a key-policy problem is reported as an error on this request. This field is write-once: once a key is attached to a Workspace it cannot be detached or replaced. To rotate key material, rotate the underlying key on your cloud KMS; the `external_key_id` stays the same. - `name: str` Name of the Workspace. - `tags: Dict[str, str]` User-defined tags as string key-value pairs. Keys may not begin with `anthropic`. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.workspaces.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ", "archived_at": "2024-11-01T23:59:27.427722Z", "compartment_id": "f8a7b6c5-4d3e-4f1a-8b9c-0d1e2f3a4b5c", "created_at": "2024-10-30T23:58:27.427722Z", "data_residency": { "allowed_inference_geos": "unrestricted", "default_inference_geo": "global", "workspace_geo": "us" }, "display_color": "#6C5BB9", "external_key_id": "ekey_01SDCCSbTxrXDpWc1phhtcfK", "name": "Workspace Name", "tags": { "env": "prod", "team": "platform" }, "type": "workspace" } ], "first_id": "first_id", "has_more": true, "last_id": "last_id" } ``` ### Create Workspace `beta.organization.workspaces.create(**kwargs) -> BetaWorkspace` **POST** `/v1/organizations/workspaces` Create Workspace #### Parameters - `name: str` Name of the Workspace. minLength: 1, maxLength: 255 - `data_residency: Optional[BetaDataResidencyCreateConfigParam]` Data residency configuration for the workspace. If omitted, defaults to `workspace_geo: "us"`, `allowed_inference_geos: "unrestricted"`, and `default_inference_geo: "global"`. - `allowed_inference_geos: Optional[Union[List[BetaAllowedInferenceGeo], Literal["unrestricted"], null]]` Permitted inference geo values. Defaults to 'unrestricted' if omitted, which allows all geos. Use the string 'unrestricted' to allow all geos, or a list of specific geos. - `List[BetaAllowedInferenceGeo]` - `"global"` - `"us"` - `"unrestricted"` - `default_inference_geo: Optional[Literal["global", "us"]]` Default inference geo applied when requests omit the parameter. Defaults to 'global' if omitted. Must be a member of `allowed_inference_geos` unless `allowed_inference_geos` is `"unrestricted"`. - `"global"` - `"us"` - `workspace_geo: Optional[Literal["us"]]` Geographic region for workspace data storage. Immutable after creation. Defaults to 'us' if omitted. - `display_color: Optional[str]` Hex color code representing the Workspace in the Anthropic Console. maxLength: 7, pattern: ^#[0-9A-Fa-f]{6}$ - `external_key_id: Optional[str]` ID of the customer-managed encryption key (CMEK) configuration to use for this Workspace. Setting this field requires CMEK to be enabled for your organization. When set, data stored for this Workspace is encrypted with the referenced key. Create key configurations with the External Keys API. On Claude Platform on AWS the value is the AWS KMS key ARN, and the key must be a single-Region key in the same AWS account and Region as the Workspace. On that platform the key is validated against this Workspace when it is attached, so a key-policy problem is reported as an error on this request. This field is write-once: once a key is attached to a Workspace it cannot be detached or replaced. To rotate key material, rotate the underlying key on your cloud KMS; the `external_key_id` stays the same. - `tags: Optional[Dict[str, str]]` User-defined tags as string key-value pairs. Keys may not begin with `anthropic`. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaWorkspace` - `type: Literal["workspace"]` Object type. For Workspaces, this is always `"workspace"`. default: workspace - `id: str` ID of the Workspace. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the Workspace was archived, or `null` if the Workspace is not archived. format: date-time - `compartment_id: str` Identifier for this Workspace's encryption compartment. When you configure a customer-managed encryption key (CMEK) on AWS, reference this value in your KMS key-policy condition so the key is scoped to this compartment. On GCP and Azure, Anthropic enforces the compartment binding automatically; you do not need to reference this value in your key configuration. See the CMEK integration guide for the required key configuration; unless your organization is on Claude Platform on AWS, it includes a separate value used during key validation. On Claude Platform on AWS there is no separate validation value: the key is validated against this Workspace's own value when it is attached, so if your key policy uses the compartment condition, add this value to it before attaching the key. - `created_at: datetime` RFC 3339 datetime string indicating when the Workspace was created. format: date-time - `data_residency: BetaDataResidency` Data residency configuration. - `allowed_inference_geos: Union[List[BetaAllowedInferenceGeo], Literal["unrestricted"]]` Permitted inference geo values. 'unrestricted' means all geos are allowed. - `List[BetaAllowedInferenceGeo]` - `"global"` - `"us"` - `"unrestricted"` - `default_inference_geo: Literal["global", "us"]` Default inference geo applied when requests omit the parameter. - `"global"` - `"us"` - `workspace_geo: Literal["us"]` Geographic region for workspace data storage. Immutable after creation. - `display_color: str` Hex color code representing the Workspace in the Anthropic Console. - `external_key_id: Optional[str]` ID of the customer-managed encryption key (CMEK) configuration to use for this Workspace. Setting this field requires CMEK to be enabled for your organization. When set, data stored for this Workspace is encrypted with the referenced key. Create key configurations with the External Keys API. On Claude Platform on AWS the value is the AWS KMS key ARN, and the key must be a single-Region key in the same AWS account and Region as the Workspace. On that platform the key is validated against this Workspace when it is attached, so a key-policy problem is reported as an error on this request. This field is write-once: once a key is attached to a Workspace it cannot be detached or replaced. To rotate key material, rotate the underlying key on your cloud KMS; the `external_key_id` stays the same. - `name: str` Name of the Workspace. - `tags: Dict[str, str]` User-defined tags as string key-value pairs. Keys may not begin with `anthropic`. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_workspace = client.beta.organization.workspaces.create( name="x", ) print(beta_workspace.id) ``` ##### Response (200) ```json { "id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ", "archived_at": "2024-11-01T23:59:27.427722Z", "compartment_id": "f8a7b6c5-4d3e-4f1a-8b9c-0d1e2f3a4b5c", "created_at": "2024-10-30T23:58:27.427722Z", "data_residency": { "allowed_inference_geos": "unrestricted", "default_inference_geo": "global", "workspace_geo": "us" }, "display_color": "#6C5BB9", "external_key_id": "ekey_01SDCCSbTxrXDpWc1phhtcfK", "name": "Workspace Name", "tags": { "env": "prod", "team": "platform" }, "type": "workspace" } ``` ### Get Workspace `beta.organization.workspaces.retrieve(workspace_id) -> BetaWorkspace` **GET** `/v1/organizations/workspaces/{workspace_id}` Get Workspace #### Parameters - `workspace_id: str` (path parameter) ID of the Workspace. #### Returns - `class BetaWorkspace` - `type: Literal["workspace"]` Object type. For Workspaces, this is always `"workspace"`. default: workspace - `id: str` ID of the Workspace. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the Workspace was archived, or `null` if the Workspace is not archived. format: date-time - `compartment_id: str` Identifier for this Workspace's encryption compartment. When you configure a customer-managed encryption key (CMEK) on AWS, reference this value in your KMS key-policy condition so the key is scoped to this compartment. On GCP and Azure, Anthropic enforces the compartment binding automatically; you do not need to reference this value in your key configuration. See the CMEK integration guide for the required key configuration; unless your organization is on Claude Platform on AWS, it includes a separate value used during key validation. On Claude Platform on AWS there is no separate validation value: the key is validated against this Workspace's own value when it is attached, so if your key policy uses the compartment condition, add this value to it before attaching the key. - `created_at: datetime` RFC 3339 datetime string indicating when the Workspace was created. format: date-time - `data_residency: BetaDataResidency` Data residency configuration. - `allowed_inference_geos: Union[List[BetaAllowedInferenceGeo], Literal["unrestricted"]]` Permitted inference geo values. 'unrestricted' means all geos are allowed. - `List[BetaAllowedInferenceGeo]` - `"global"` - `"us"` - `"unrestricted"` - `default_inference_geo: Literal["global", "us"]` Default inference geo applied when requests omit the parameter. - `"global"` - `"us"` - `workspace_geo: Literal["us"]` Geographic region for workspace data storage. Immutable after creation. - `display_color: str` Hex color code representing the Workspace in the Anthropic Console. - `external_key_id: Optional[str]` ID of the customer-managed encryption key (CMEK) configuration to use for this Workspace. Setting this field requires CMEK to be enabled for your organization. When set, data stored for this Workspace is encrypted with the referenced key. Create key configurations with the External Keys API. On Claude Platform on AWS the value is the AWS KMS key ARN, and the key must be a single-Region key in the same AWS account and Region as the Workspace. On that platform the key is validated against this Workspace when it is attached, so a key-policy problem is reported as an error on this request. This field is write-once: once a key is attached to a Workspace it cannot be detached or replaced. To rotate key material, rotate the underlying key on your cloud KMS; the `external_key_id` stays the same. - `name: str` Name of the Workspace. - `tags: Dict[str, str]` User-defined tags as string key-value pairs. Keys may not begin with `anthropic`. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_workspace = client.beta.organization.workspaces.retrieve( "workspace_id", ) print(beta_workspace.id) ``` ##### Response (200) ```json { "id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ", "archived_at": "2024-11-01T23:59:27.427722Z", "compartment_id": "f8a7b6c5-4d3e-4f1a-8b9c-0d1e2f3a4b5c", "created_at": "2024-10-30T23:58:27.427722Z", "data_residency": { "allowed_inference_geos": "unrestricted", "default_inference_geo": "global", "workspace_geo": "us" }, "display_color": "#6C5BB9", "external_key_id": "ekey_01SDCCSbTxrXDpWc1phhtcfK", "name": "Workspace Name", "tags": { "env": "prod", "team": "platform" }, "type": "workspace" } ``` ### Update Workspace `beta.organization.workspaces.update(workspace_id, **kwargs) -> BetaWorkspace` **POST** `/v1/organizations/workspaces/{workspace_id}` Update Workspace #### Parameters - `workspace_id: str` (path parameter) - `data_residency: Optional[BetaDataResidencyUpdateConfigParam]` Data residency configuration for the workspace. - `allowed_inference_geos: Optional[Union[List[BetaAllowedInferenceGeo], Literal["unrestricted"], null]]` Permitted inference geo values. Use 'unrestricted' to allow all geos, or a list of specific geos. - `List[BetaAllowedInferenceGeo]` - `"global"` - `"us"` - `"unrestricted"` - `default_inference_geo: Optional[Literal["global", "us"]]` Default inference geo applied when requests omit the parameter. Must be a member of `allowed_inference_geos` unless `allowed_inference_geos` is `"unrestricted"`. - `"global"` - `"us"` - `display_color: Optional[str]` Hex color code representing the Workspace in the Anthropic Console. maxLength: 7, pattern: ^#[0-9A-Fa-f]{6}$ - `external_key_id: Optional[str]` ID of the customer-managed encryption key (CMEK) configuration to use for this Workspace. Setting this field requires CMEK to be enabled for your organization. When set, data stored for this Workspace is encrypted with the referenced key. Create key configurations with the External Keys API. On Claude Platform on AWS the value is the AWS KMS key ARN, and the key must be a single-Region key in the same AWS account and Region as the Workspace. On that platform the key is validated against this Workspace when it is attached, so a key-policy problem is reported as an error on this request. This field is write-once: once a key is attached to a Workspace it cannot be detached or replaced. To rotate key material, rotate the underlying key on your cloud KMS; the `external_key_id` stays the same. - `name: Optional[str]` Name of the Workspace. minLength: 1, maxLength: 255 - `tags: Optional[Dict[str, Optional[str]]]` User-defined tags as string key-value pairs. Keys may not begin with `anthropic`. #### Returns - `class BetaWorkspace` - `type: Literal["workspace"]` Object type. For Workspaces, this is always `"workspace"`. default: workspace - `id: str` ID of the Workspace. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the Workspace was archived, or `null` if the Workspace is not archived. format: date-time - `compartment_id: str` Identifier for this Workspace's encryption compartment. When you configure a customer-managed encryption key (CMEK) on AWS, reference this value in your KMS key-policy condition so the key is scoped to this compartment. On GCP and Azure, Anthropic enforces the compartment binding automatically; you do not need to reference this value in your key configuration. See the CMEK integration guide for the required key configuration; unless your organization is on Claude Platform on AWS, it includes a separate value used during key validation. On Claude Platform on AWS there is no separate validation value: the key is validated against this Workspace's own value when it is attached, so if your key policy uses the compartment condition, add this value to it before attaching the key. - `created_at: datetime` RFC 3339 datetime string indicating when the Workspace was created. format: date-time - `data_residency: BetaDataResidency` Data residency configuration. - `allowed_inference_geos: Union[List[BetaAllowedInferenceGeo], Literal["unrestricted"]]` Permitted inference geo values. 'unrestricted' means all geos are allowed. - `List[BetaAllowedInferenceGeo]` - `"global"` - `"us"` - `"unrestricted"` - `default_inference_geo: Literal["global", "us"]` Default inference geo applied when requests omit the parameter. - `"global"` - `"us"` - `workspace_geo: Literal["us"]` Geographic region for workspace data storage. Immutable after creation. - `display_color: str` Hex color code representing the Workspace in the Anthropic Console. - `external_key_id: Optional[str]` ID of the customer-managed encryption key (CMEK) configuration to use for this Workspace. Setting this field requires CMEK to be enabled for your organization. When set, data stored for this Workspace is encrypted with the referenced key. Create key configurations with the External Keys API. On Claude Platform on AWS the value is the AWS KMS key ARN, and the key must be a single-Region key in the same AWS account and Region as the Workspace. On that platform the key is validated against this Workspace when it is attached, so a key-policy problem is reported as an error on this request. This field is write-once: once a key is attached to a Workspace it cannot be detached or replaced. To rotate key material, rotate the underlying key on your cloud KMS; the `external_key_id` stays the same. - `name: str` Name of the Workspace. - `tags: Dict[str, str]` User-defined tags as string key-value pairs. Keys may not begin with `anthropic`. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_workspace = client.beta.organization.workspaces.update( workspace_id="workspace_id", ) print(beta_workspace.id) ``` ##### Response (200) ```json { "id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ", "archived_at": "2024-11-01T23:59:27.427722Z", "compartment_id": "f8a7b6c5-4d3e-4f1a-8b9c-0d1e2f3a4b5c", "created_at": "2024-10-30T23:58:27.427722Z", "data_residency": { "allowed_inference_geos": "unrestricted", "default_inference_geo": "global", "workspace_geo": "us" }, "display_color": "#6C5BB9", "external_key_id": "ekey_01SDCCSbTxrXDpWc1phhtcfK", "name": "Workspace Name", "tags": { "env": "prod", "team": "platform" }, "type": "workspace" } ``` ### Archive Workspace `beta.organization.workspaces.archive(workspace_id) -> BetaWorkspace` **POST** `/v1/organizations/workspaces/{workspace_id}/archive` Archive Workspace #### Parameters - `workspace_id: str` (path parameter) #### Returns - `class BetaWorkspace` - `type: Literal["workspace"]` Object type. For Workspaces, this is always `"workspace"`. default: workspace - `id: str` ID of the Workspace. - `archived_at: Optional[datetime]` RFC 3339 datetime string indicating when the Workspace was archived, or `null` if the Workspace is not archived. format: date-time - `compartment_id: str` Identifier for this Workspace's encryption compartment. When you configure a customer-managed encryption key (CMEK) on AWS, reference this value in your KMS key-policy condition so the key is scoped to this compartment. On GCP and Azure, Anthropic enforces the compartment binding automatically; you do not need to reference this value in your key configuration. See the CMEK integration guide for the required key configuration; unless your organization is on Claude Platform on AWS, it includes a separate value used during key validation. On Claude Platform on AWS there is no separate validation value: the key is validated against this Workspace's own value when it is attached, so if your key policy uses the compartment condition, add this value to it before attaching the key. - `created_at: datetime` RFC 3339 datetime string indicating when the Workspace was created. format: date-time - `data_residency: BetaDataResidency` Data residency configuration. - `allowed_inference_geos: Union[List[BetaAllowedInferenceGeo], Literal["unrestricted"]]` Permitted inference geo values. 'unrestricted' means all geos are allowed. - `List[BetaAllowedInferenceGeo]` - `"global"` - `"us"` - `"unrestricted"` - `default_inference_geo: Literal["global", "us"]` Default inference geo applied when requests omit the parameter. - `"global"` - `"us"` - `workspace_geo: Literal["us"]` Geographic region for workspace data storage. Immutable after creation. - `display_color: str` Hex color code representing the Workspace in the Anthropic Console. - `external_key_id: Optional[str]` ID of the customer-managed encryption key (CMEK) configuration to use for this Workspace. Setting this field requires CMEK to be enabled for your organization. When set, data stored for this Workspace is encrypted with the referenced key. Create key configurations with the External Keys API. On Claude Platform on AWS the value is the AWS KMS key ARN, and the key must be a single-Region key in the same AWS account and Region as the Workspace. On that platform the key is validated against this Workspace when it is attached, so a key-policy problem is reported as an error on this request. This field is write-once: once a key is attached to a Workspace it cannot be detached or replaced. To rotate key material, rotate the underlying key on your cloud KMS; the `external_key_id` stays the same. - `name: str` Name of the Workspace. - `tags: Dict[str, str]` User-defined tags as string key-value pairs. Keys may not begin with `anthropic`. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_workspace = client.beta.organization.workspaces.archive( "workspace_id", ) print(beta_workspace.id) ``` ##### Response (200) ```json { "id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ", "archived_at": "2024-11-01T23:59:27.427722Z", "compartment_id": "f8a7b6c5-4d3e-4f1a-8b9c-0d1e2f3a4b5c", "created_at": "2024-10-30T23:58:27.427722Z", "data_residency": { "allowed_inference_geos": "unrestricted", "default_inference_geo": "global", "workspace_geo": "us" }, "display_color": "#6C5BB9", "external_key_id": "ekey_01SDCCSbTxrXDpWc1phhtcfK", "name": "Workspace Name", "tags": { "env": "prod", "team": "platform" }, "type": "workspace" } ``` ## Beta › Organization › Workspaces › Rate Limits ### List Workspace Rate Limits `beta.organization.workspaces.rate_limits.list(workspace_id, **kwargs) -> SyncPageCursor[BetaWorkspaceRateLimit]` **GET** `/v1/organizations/workspaces/{workspace_id}/rate_limits` List a workspace's rate limits. By default, returns only the groups and limiter types that have a workspace-level override. With `include_inherited=true`, returns every group with organization-level limits the workspace can see, listing for each the values it inherits from the organization as well as its own overrides. Each value's `source` says which it is. When `limit` is omitted, every matching entry is returned in a single page; when `limit` truncates the result, follow `next_page` to fetch the remaining entries. #### Parameters - `workspace_id: str` (path parameter) The ID of the workspace. - `group_type: Optional[Literal["batch", "files", "model_group", 3 more]]` (query parameter) Filter by group type. - `"batch"` - `"files"` - `"model_group"` - `"skills"` - `"token_count"` - `"web_search"` - `include_inherited: Optional[bool]` (query parameter) Also list the limiter values the workspace inherits from the organization, including groups with no workspace-level override. default: false - `limit: Optional[int]` (query parameter) Maximum number of items to return per page. Ranges from `1` to `1000`. When omitted, every remaining entry is returned in a single page and `next_page` is `null`. minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page`. #### Returns - `class BetaWorkspaceRateLimit` - `type: Literal["workspace_rate_limit"]` Object type. Always `workspace_rate_limit` for workspace rate-limit entries. default: workspace_rate_limit - `group: Group` The rate-limit group this entry's limits apply to. Its `type` equals `group_type`. - `class BetaOrganizationRateLimitModelGroup` - `type: Literal["model_group"]` Always `model_group`: a family of models. default: model_group - `id: str` Opaque identifier of the rate-limit group (for example, `rlg_01VPTCmyiu5ZLsWkcxYG2pY8`). It is the same in every organization and never changes, unlike the entry's own identifier, which differs per organization. - `display_name: str` Human-readable name of the model group (for example, `Claude Sonnet 4.x`). For display only; it may change. - `class BetaOrganizationRateLimitBatchGroup` - `type: Literal["batch"]` Always `batch`: the Message Batches API. default: batch - `id: str` Opaque identifier of the rate-limit group (for example, `rlg_01VPTCmyiu5ZLsWkcxYG2pY8`). It is the same in every organization and never changes, unlike the entry's own identifier, which differs per organization. - `class BetaOrganizationRateLimitTokenCountGroup` - `type: Literal["token_count"]` Always `token_count`: the Token Count API. default: token_count - `id: str` Opaque identifier of the rate-limit group (for example, `rlg_01VPTCmyiu5ZLsWkcxYG2pY8`). It is the same in every organization and never changes, unlike the entry's own identifier, which differs per organization. - `class BetaOrganizationRateLimitFilesGroup` - `type: Literal["files"]` Always `files`: the Files API. default: files - `id: str` Opaque identifier of the rate-limit group (for example, `rlg_01VPTCmyiu5ZLsWkcxYG2pY8`). It is the same in every organization and never changes, unlike the entry's own identifier, which differs per organization. - `class BetaOrganizationRateLimitSkillsGroup` - `type: Literal["skills"]` Always `skills`: the Skills API. default: skills - `id: str` Opaque identifier of the rate-limit group (for example, `rlg_01VPTCmyiu5ZLsWkcxYG2pY8`). It is the same in every organization and never changes, unlike the entry's own identifier, which differs per organization. - `class BetaOrganizationRateLimitWebSearchGroup` - `type: Literal["web_search"]` Always `web_search`: the Messages API web search tool. default: web_search - `id: str` Opaque identifier of the rate-limit group (for example, `rlg_01VPTCmyiu5ZLsWkcxYG2pY8`). It is the same in every organization and never changes, unlike the entry's own identifier, which differs per organization. - `limits: List[BetaWorkspaceRateLimitValue]` The workspace's limiter values for this group. By default only the limiter types with a workspace-level override are listed. With `include_inherited` set to `true`, the limiter types the workspace inherits from the organization are listed too, each marked by `source`. - `type: str` The limiter type (for example, `requests_per_minute` or `input_tokens_per_minute`). - `org_limit: Optional[int]` The organization-level value for the same limiter type, for reference. `null` when the organization has no limit configured for this limiter type. - `source: Source` Where `value` comes from. `organization` values are listed only when `include_inherited` is `true`, and then `value` equals `org_limit`. - `class BetaWorkspaceRateLimitWorkspaceSource` - `type: Literal["workspace"]` Always `workspace`: a workspace-level override is stored. default: workspace - `class BetaWorkspaceRateLimitOrganizationSource` - `type: Literal["organization"]` Always `organization`: no workspace-level override is stored, so the organization's value applies. default: organization - `value: int` The workspace's value for this limiter type: the workspace-level override when `source.type` is `workspace`, otherwise the organization's value. - `models: Optional[List[str]]` Model names this entry's limits apply to, including aliases. `null` when `group_type` is not `"model_group"`. - `rate_limit_id: str` The `id` of the organization's RateLimit entry this entry applies to. - `workspace_id: str` ID of the Workspace this entry applies to. - `group_type: Literal["batch", "files", "model_group", 3 more]` **Deprecated**: Use `group.type` instead. `group_type` is still returned and always equals `group.type`. Deprecated: use `group.type` instead. The kind of rate-limit group this entry represents. `model_group` entries apply to a family of models (listed in `models`); other values apply to an API-surface category and have `models` set to `null`. Always equal to `group.type`. - `"batch"` - `"files"` - `"model_group"` - `"skills"` - `"token_count"` - `"web_search"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.workspaces.rate_limits.list( workspace_id="workspace_id", ) page = page.data[0] print(page.rate_limit_id) ``` ##### Response (200) ```json { "data": [ { "group": { "id": "id", "display_name": "display_name", "type": "model_group" }, "group_type": "batch", "limits": [ { "org_limit": 0, "source": { "type": "workspace" }, "type": "type", "value": 0 } ], "models": [ "string" ], "rate_limit_id": "rate_limit_id", "type": "workspace_rate_limit", "workspace_id": "workspace_id" } ], "next_page": "next_page" } ``` ## Beta › Organization › Workspaces › Members ### List Workspace Members `beta.organization.workspaces.members.list(workspace_id, **kwargs) -> SyncPage[BetaWorkspaceMember]` **GET** `/v1/organizations/workspaces/{workspace_id}/members` List Workspace Members #### Parameters - `workspace_id: str` (path parameter) ID of the Workspace. - `after_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately after this object. - `before_id: Optional[str]` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately before this object. - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 #### Returns - `class BetaWorkspaceMember` - `type: Literal["workspace_member"]` Object type. For Workspace Members, this is always `"workspace_member"`. default: workspace_member - `user_id: str` ID of the User. - `workspace_id: str` ID of the Workspace. - `workspace_role: BetaWorkspaceRole` Role of the Workspace Member. - `"workspace_admin"` - `"workspace_billing"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.workspaces.members.list( workspace_id="workspace_id", ) page = page.data[0] print(page.user_id) ``` ##### Response (200) ```json { "data": [ { "type": "workspace_member", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q", "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ", "workspace_role": "workspace_admin" } ], "first_id": "first_id", "has_more": true, "last_id": "last_id" } ``` ### Create Workspace Member `beta.organization.workspaces.members.add(workspace_id, **kwargs) -> BetaWorkspaceMember` **POST** `/v1/organizations/workspaces/{workspace_id}/members` Create Workspace Member #### Parameters - `workspace_id: str` (path parameter) ID of the Workspace. - `user_id: str` ID of the User. - `workspace_role: BetaNoBillingWorkspaceRole` Role of the new Workspace Member. Cannot be `workspace_billing`. - `"workspace_admin"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` #### Returns - `class BetaWorkspaceMember` - `type: Literal["workspace_member"]` Object type. For Workspace Members, this is always `"workspace_member"`. default: workspace_member - `user_id: str` ID of the User. - `workspace_id: str` ID of the Workspace. - `workspace_role: BetaWorkspaceRole` Role of the Workspace Member. - `"workspace_admin"` - `"workspace_billing"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_workspace_member = client.beta.organization.workspaces.members.add( workspace_id="workspace_id", user_id="user_01WCz1FkmYMm4gnmykNKUu3Q", workspace_role="workspace_admin", ) print(beta_workspace_member.user_id) ``` ##### Response (200) ```json { "type": "workspace_member", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q", "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ", "workspace_role": "workspace_admin" } ``` ### Get Workspace Member `beta.organization.workspaces.members.retrieve(user_id, **kwargs) -> BetaWorkspaceMember` **GET** `/v1/organizations/workspaces/{workspace_id}/members/{user_id}` Get Workspace Member #### Parameters - `workspace_id: str` (path parameter) ID of the Workspace. - `user_id: str` (path parameter) ID of the User. #### Returns - `class BetaWorkspaceMember` - `type: Literal["workspace_member"]` Object type. For Workspace Members, this is always `"workspace_member"`. default: workspace_member - `user_id: str` ID of the User. - `workspace_id: str` ID of the Workspace. - `workspace_role: BetaWorkspaceRole` Role of the Workspace Member. - `"workspace_admin"` - `"workspace_billing"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_workspace_member = client.beta.organization.workspaces.members.retrieve( user_id="user_id", workspace_id="workspace_id", ) print(beta_workspace_member.user_id) ``` ##### Response (200) ```json { "type": "workspace_member", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q", "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ", "workspace_role": "workspace_admin" } ``` ### Update Workspace Member `beta.organization.workspaces.members.update(user_id, **kwargs) -> BetaWorkspaceMember` **POST** `/v1/organizations/workspaces/{workspace_id}/members/{user_id}` Update Workspace Member #### Parameters - `workspace_id: str` (path parameter) ID of the Workspace. - `user_id: str` (path parameter) ID of the User. - `workspace_role: BetaWorkspaceRole` New workspace role for the User. - `"workspace_admin"` - `"workspace_billing"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` #### Returns - `class BetaWorkspaceMember` - `type: Literal["workspace_member"]` Object type. For Workspace Members, this is always `"workspace_member"`. default: workspace_member - `user_id: str` ID of the User. - `workspace_id: str` ID of the Workspace. - `workspace_role: BetaWorkspaceRole` Role of the Workspace Member. - `"workspace_admin"` - `"workspace_billing"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_workspace_member = client.beta.organization.workspaces.members.update( user_id="user_id", workspace_id="workspace_id", workspace_role="workspace_admin", ) print(beta_workspace_member.user_id) ``` ##### Response (200) ```json { "type": "workspace_member", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q", "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ", "workspace_role": "workspace_admin" } ``` ### Delete Workspace Member `beta.organization.workspaces.members.remove(user_id, **kwargs) -> MemberRemoveResponse` **DELETE** `/v1/organizations/workspaces/{workspace_id}/members/{user_id}` Delete Workspace Member #### Parameters - `workspace_id: str` (path parameter) ID of the Workspace. - `user_id: str` (path parameter) ID of the User. #### Returns - `class MemberRemoveResponse` - `type: Literal["workspace_member_deleted"]` Deleted object type. For Workspace Members, this is always `"workspace_member_deleted"`. default: workspace_member_deleted - `user_id: str` ID of the User. - `workspace_id: str` ID of the Workspace. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) member = client.beta.organization.workspaces.members.remove( user_id="user_id", workspace_id="workspace_id", ) print(member.user_id) ``` ##### Response (200) ```json { "type": "workspace_member_deleted", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q", "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ" } ``` ## Beta › Organization › Workspaces › Service Accounts ### List Service Account Workspace Members `beta.organization.workspaces.service_accounts.list(workspace_id, **kwargs) -> SyncPageCursor[BetaServiceAccountWorkspaceMember]` **GET** `/v1/organizations/workspaces/{workspace_id}/service_accounts` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). List the service accounts that are members of a workspace. Each entry includes the service account's `workspace_role`. Use `limit` and the `next_page` cursor to paginate. Archived workspaces return 400; use `GET /service_accounts/{id}/workspaces` to audit memberships of an archived workspace. The implicit default-workspace membership is not included in this list. Memberships of archived service accounts are omitted from the results. #### Parameters - `workspace_id: str` (path parameter) ID of the workspace. - `limit: Optional[int]` (query parameter) Number of results per page. default: 20, minimum: 1, maximum: 100 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page`. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaServiceAccountWorkspaceMember` - `type: Literal["service_account_workspace_member"]` default: service_account_workspace_member - `created_by_actor_id: Optional[str]` Tagged ID (`user_...`/`svac_...`) of the actor who created this membership. - `implicit: Optional[bool]` True when this is the implicit default-workspace membership every service account has when no explicit membership exists. Implicit memberships have role `workspace_user` and cannot be removed. - `service_account_id: str` Tagged service account ID (`svac_...`). - `workspace_id: str` Tagged workspace ID (`wrkspc_...`). - `workspace_role: BetaWorkspaceRole` Role of the service account in this workspace. Service accounts cannot hold the `workspace_billing` role. - `"workspace_admin"` - `"workspace_billing"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.workspaces.service_accounts.list( workspace_id="workspace_id", ) page = page.data[0] print(page.created_by_actor_id) ``` ##### Response (200) ```json { "data": [ { "created_by_actor_id": "created_by_actor_id", "implicit": true, "service_account_id": "service_account_id", "type": "service_account_workspace_member", "workspace_id": "workspace_id", "workspace_role": "workspace_admin" } ], "next_page": "next_page" } ``` ### Create Service Account Workspace Member `beta.organization.workspaces.service_accounts.add(workspace_id, **kwargs) -> BetaServiceAccountWorkspaceMember` **POST** `/v1/organizations/workspaces/{workspace_id}/service_accounts` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Add a service account to a workspace with the given `workspace_role`. The role determines what the service account can do in the workspace and which workspace-scoped permissions it can be granted when authenticating through federation. Every service account is already an implicit `workspace_user` member of the default workspace; adding it explicitly assigns a chosen role. If the service account is already an explicit member of the workspace, its `workspace_role` is replaced with the value supplied here. Archived workspaces return 400. Archived service accounts cannot be added and are rejected. #### Parameters - `workspace_id: str` (path parameter) ID of the workspace. - `service_account_id: str` Tagged service account ID to add. - `workspace_role: BetaNoBillingWorkspaceRole` Role to assign to the service account in this workspace. - `"workspace_admin"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaServiceAccountWorkspaceMember` - `type: Literal["service_account_workspace_member"]` default: service_account_workspace_member - `created_by_actor_id: Optional[str]` Tagged ID (`user_...`/`svac_...`) of the actor who created this membership. - `implicit: Optional[bool]` True when this is the implicit default-workspace membership every service account has when no explicit membership exists. Implicit memberships have role `workspace_user` and cannot be removed. - `service_account_id: str` Tagged service account ID (`svac_...`). - `workspace_id: str` Tagged workspace ID (`wrkspc_...`). - `workspace_role: BetaWorkspaceRole` Role of the service account in this workspace. Service accounts cannot hold the `workspace_billing` role. - `"workspace_admin"` - `"workspace_billing"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_service_account_workspace_member = ( client.beta.organization.workspaces.service_accounts.add( workspace_id="workspace_id", service_account_id="service_account_id", workspace_role="workspace_admin", ) ) print(beta_service_account_workspace_member.created_by_actor_id) ``` ##### Response (200) ```json { "created_by_actor_id": "created_by_actor_id", "implicit": true, "service_account_id": "service_account_id", "type": "service_account_workspace_member", "workspace_id": "workspace_id", "workspace_role": "workspace_admin" } ``` ### Get Service Account Workspace Member `beta.organization.workspaces.service_accounts.retrieve(service_account_id, **kwargs) -> BetaServiceAccountWorkspaceMember` **GET** `/v1/organizations/workspaces/{workspace_id}/service_accounts/{service_account_id}` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Retrieve a service account's membership in a workspace. Returns the membership record, including the service account's `workspace_role` in this workspace. Archived workspaces return 400. For the default workspace, returns the implicit (`implicit: true`) membership when no explicit membership exists; an explicitly added membership is returned with its assigned role. An archived service account returns 404. #### Parameters - `workspace_id: str` (path parameter) ID of the workspace. - `service_account_id: str` (path parameter) ID of the service account. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaServiceAccountWorkspaceMember` - `type: Literal["service_account_workspace_member"]` default: service_account_workspace_member - `created_by_actor_id: Optional[str]` Tagged ID (`user_...`/`svac_...`) of the actor who created this membership. - `implicit: Optional[bool]` True when this is the implicit default-workspace membership every service account has when no explicit membership exists. Implicit memberships have role `workspace_user` and cannot be removed. - `service_account_id: str` Tagged service account ID (`svac_...`). - `workspace_id: str` Tagged workspace ID (`wrkspc_...`). - `workspace_role: BetaWorkspaceRole` Role of the service account in this workspace. Service accounts cannot hold the `workspace_billing` role. - `"workspace_admin"` - `"workspace_billing"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_service_account_workspace_member = ( client.beta.organization.workspaces.service_accounts.retrieve( service_account_id="service_account_id", workspace_id="workspace_id", ) ) print(beta_service_account_workspace_member.created_by_actor_id) ``` ##### Response (200) ```json { "created_by_actor_id": "created_by_actor_id", "implicit": true, "service_account_id": "service_account_id", "type": "service_account_workspace_member", "workspace_id": "workspace_id", "workspace_role": "workspace_admin" } ``` ### Update Service Account Workspace Member `beta.organization.workspaces.service_accounts.update(service_account_id, **kwargs) -> BetaServiceAccountWorkspaceMember` **POST** `/v1/organizations/workspaces/{workspace_id}/service_accounts/{service_account_id}` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Change a service account's role in a workspace. The new `workspace_role` replaces the current one. Only explicit memberships can be updated; to set a role on the implicit default-workspace membership, add the service account explicitly with `POST /workspaces/{workspace_id}/service_accounts`. Archived workspaces return 400. Archived service accounts cannot be updated and are rejected. #### Parameters - `workspace_id: str` (path parameter) ID of the workspace. - `service_account_id: str` (path parameter) ID of the service account. - `workspace_role: BetaNoBillingWorkspaceRole` New role for the service account in this workspace. - `"workspace_admin"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaServiceAccountWorkspaceMember` - `type: Literal["service_account_workspace_member"]` default: service_account_workspace_member - `created_by_actor_id: Optional[str]` Tagged ID (`user_...`/`svac_...`) of the actor who created this membership. - `implicit: Optional[bool]` True when this is the implicit default-workspace membership every service account has when no explicit membership exists. Implicit memberships have role `workspace_user` and cannot be removed. - `service_account_id: str` Tagged service account ID (`svac_...`). - `workspace_id: str` Tagged workspace ID (`wrkspc_...`). - `workspace_role: BetaWorkspaceRole` Role of the service account in this workspace. Service accounts cannot hold the `workspace_billing` role. - `"workspace_admin"` - `"workspace_billing"` - `"workspace_developer"` - `"workspace_restricted_developer"` - `"workspace_user"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_service_account_workspace_member = ( client.beta.organization.workspaces.service_accounts.update( service_account_id="service_account_id", workspace_id="workspace_id", workspace_role="workspace_admin", ) ) print(beta_service_account_workspace_member.created_by_actor_id) ``` ##### Response (200) ```json { "created_by_actor_id": "created_by_actor_id", "implicit": true, "service_account_id": "service_account_id", "type": "service_account_workspace_member", "workspace_id": "workspace_id", "workspace_role": "workspace_admin" } ``` ### Delete Service Account Workspace Member `beta.organization.workspaces.service_accounts.remove(service_account_id, **kwargs) -> ServiceAccountRemoveResponse` **DELETE** `/v1/organizations/workspaces/{workspace_id}/service_accounts/{service_account_id}` **Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=python). Remove a service account from a workspace. Removal is idempotent (returns 200 even if the membership was already removed). A DELETE against the implicit default-workspace membership returns 200 but is a no-op and the membership persists; deleting an explicit default-workspace row reverts to the implicit `workspace_user` membership. Archived workspaces return 400. #### Parameters - `workspace_id: str` (path parameter) ID of the workspace. - `service_account_id: str` (path parameter) ID of the service account. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class ServiceAccountRemoveResponse` - `type: Literal["service_account_workspace_member_deleted"]` default: service_account_workspace_member_deleted - `service_account_id: str` Tagged service account ID (`svac_...`) named in the delete request. Removal is idempotent; see the endpoint description for the implicit-membership no-op. - `workspace_id: str` Tagged workspace ID (`wrkspc_...`) named in the delete request. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) service_account = client.beta.organization.workspaces.service_accounts.remove( service_account_id="service_account_id", workspace_id="workspace_id", ) print(service_account.service_account_id) ``` ##### Response (200) ```json { "service_account_id": "service_account_id", "type": "service_account_workspace_member_deleted", "workspace_id": "workspace_id" } ``` ## Beta › Organization › Rate Limits ### List Organization Rate Limits `beta.organization.rate_limits.list(**kwargs) -> SyncPageCursor[BetaOrganizationRateLimit]` **GET** `/v1/organizations/rate_limits` List Messages API rate limits for your organization. Each entry corresponds to one rate-limit group (either a model family or an API-surface category such as the Message Batches API or the web search tool) and contains the set of limiter values that apply to it. When `limit` is omitted, every matching entry is returned in a single page; when `limit` truncates the result, follow `next_page` to fetch the remaining entries. #### Parameters - `group_type: Optional[Literal["batch", "files", "model_group", 3 more]]` (query parameter) Filter by group type. - `"batch"` - `"files"` - `"model_group"` - `"skills"` - `"token_count"` - `"web_search"` - `limit: Optional[int]` (query parameter) Maximum number of items to return per page. Ranges from `1` to `1000`. When omitted, every remaining entry is returned in a single page and `next_page` is `null`. minimum: 1, maximum: 1000 - `model: Optional[str]` (query parameter) Filter to the single entry containing this model. Accepts full model names and aliases. Returns 404 if the model is not found or has no rate limits for this organization. - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page`. #### Returns - `class BetaOrganizationRateLimit` - `type: Literal["rate_limit"]` Object type. Always `rate_limit` for organization rate-limit entries. default: rate_limit - `id: str` Identifier of this rate-limit entry. It is stable within the organization and differs between organizations; the group's own identifier is `group.id`. - `group: Group` The rate-limit group this entry's limits apply to. Its `type` equals `group_type`. - `class BetaOrganizationRateLimitModelGroup` - `type: Literal["model_group"]` Always `model_group`: a family of models. default: model_group - `id: str` Opaque identifier of the rate-limit group (for example, `rlg_01VPTCmyiu5ZLsWkcxYG2pY8`). It is the same in every organization and never changes, unlike the entry's own identifier, which differs per organization. - `display_name: str` Human-readable name of the model group (for example, `Claude Sonnet 4.x`). For display only; it may change. - `class BetaOrganizationRateLimitBatchGroup` - `type: Literal["batch"]` Always `batch`: the Message Batches API. default: batch - `id: str` Opaque identifier of the rate-limit group (for example, `rlg_01VPTCmyiu5ZLsWkcxYG2pY8`). It is the same in every organization and never changes, unlike the entry's own identifier, which differs per organization. - `class BetaOrganizationRateLimitTokenCountGroup` - `type: Literal["token_count"]` Always `token_count`: the Token Count API. default: token_count - `id: str` Opaque identifier of the rate-limit group (for example, `rlg_01VPTCmyiu5ZLsWkcxYG2pY8`). It is the same in every organization and never changes, unlike the entry's own identifier, which differs per organization. - `class BetaOrganizationRateLimitFilesGroup` - `type: Literal["files"]` Always `files`: the Files API. default: files - `id: str` Opaque identifier of the rate-limit group (for example, `rlg_01VPTCmyiu5ZLsWkcxYG2pY8`). It is the same in every organization and never changes, unlike the entry's own identifier, which differs per organization. - `class BetaOrganizationRateLimitSkillsGroup` - `type: Literal["skills"]` Always `skills`: the Skills API. default: skills - `id: str` Opaque identifier of the rate-limit group (for example, `rlg_01VPTCmyiu5ZLsWkcxYG2pY8`). It is the same in every organization and never changes, unlike the entry's own identifier, which differs per organization. - `class BetaOrganizationRateLimitWebSearchGroup` - `type: Literal["web_search"]` Always `web_search`: the Messages API web search tool. default: web_search - `id: str` Opaque identifier of the rate-limit group (for example, `rlg_01VPTCmyiu5ZLsWkcxYG2pY8`). It is the same in every organization and never changes, unlike the entry's own identifier, which differs per organization. - `limits: List[BetaOrganizationRateLimitValue]` The limiter values that apply to this group. - `type: str` The limiter type (for example, `requests_per_minute` or `input_tokens_per_minute`). - `value: int` The configured limit value for this limiter type. - `models: Optional[List[str]]` Model names this entry's limits apply to, including aliases. `null` when `group_type` is not `"model_group"`. - `group_type: Literal["batch", "files", "model_group", 3 more]` **Deprecated**: Use `group.type` instead. `group_type` is still returned and always equals `group.type`. Deprecated: use `group.type` instead. The kind of rate-limit group this entry represents. `model_group` entries apply to a family of models (listed in `models`); other values apply to an API-surface category and have `models` set to `null`. Always equal to `group.type`. - `"batch"` - `"files"` - `"model_group"` - `"skills"` - `"token_count"` - `"web_search"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.rate_limits.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "id", "group": { "id": "id", "display_name": "display_name", "type": "model_group" }, "group_type": "batch", "limits": [ { "type": "type", "value": 0 } ], "models": [ "string" ], "type": "rate_limit" } ], "next_page": "next_page" } ``` ## Beta › Organization › Compliance Settings ### Get Compliance Settings `beta.organization.compliance_settings.retrieve() -> BetaComplianceSettings` **GET** `/v1/organizations/compliance_settings` Retrieve your organization's Compliance Settings. Compliance Settings is a singleton resource: there is exactly one per organization, addressed without an identifier. The `state` field reflects whether the Compliance API is enabled. An organization with a parent organization reads the state inherited from the parent's configuration. #### Returns - `class BetaComplianceSettings` - `type: Literal["compliance_settings"]` default: compliance_settings - `state: BetaComplianceSettingsState` Whether the Compliance API is enabled for this organization. - `class BetaComplianceSettingsStateEnabled` - `type: Literal["enabled"]` default: enabled - `class BetaComplianceSettingsStateDisabled` - `type: Literal["disabled"]` default: disabled #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_compliance_settings = client.beta.organization.compliance_settings.retrieve() print(beta_compliance_settings.state) ``` ##### Response (200) ```json { "state": { "type": "enabled" }, "type": "compliance_settings" } ``` ### Update Compliance Settings `beta.organization.compliance_settings.update(**kwargs) -> BetaComplianceSettings` **POST** `/v1/organizations/compliance_settings` Update your organization's Compliance Settings. Setting `state` to `enabled` turns on the Compliance API and begins capturing organization activity events. Setting it to `disabled` turns both off. `state` reflects whether the Compliance API is enabled. A request that sets `state` to its current value succeeds and leaves the resource unchanged. A `disabled` request stays in effect until a later `enabled` request or the organization's next provisioning action that enables Access Transparency: enabling Access Transparency also enables the Compliance API, which serves its activity events, so such provisioning (including re-runs) re-enables the Compliance API even after a `disabled` request. Automated provisioning never disables compliance settings. #### Parameters - `state: BetaComplianceSettingsStateParam` Desired state. Accepts the string shorthand "enabled" or "disabled" in place of the object form; the response always returns the canonical object form. - `class BetaComplianceSettingsStateEnabledParam` - `type: Literal["enabled"]` - `class BetaComplianceSettingsStateDisabledParam` - `type: Literal["disabled"]` #### Returns - `class BetaComplianceSettings` - `type: Literal["compliance_settings"]` default: compliance_settings - `state: BetaComplianceSettingsState` Whether the Compliance API is enabled for this organization. - `class BetaComplianceSettingsStateEnabled` - `type: Literal["enabled"]` default: enabled - `class BetaComplianceSettingsStateDisabled` - `type: Literal["disabled"]` default: disabled #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_compliance_settings = client.beta.organization.compliance_settings.update( state={"type": "enabled"}, ) print(beta_compliance_settings.state) ``` ##### Response (200) ```json { "state": { "type": "enabled" }, "type": "compliance_settings" } ``` ## Beta › Organization › Analytics › Summaries ### Get Activity Summaries `beta.organization.analytics.summaries.list(**kwargs) -> SyncPageCursor[BetaAnalyticsSingleDayActivitySummary]` **GET** `/v1/organizations/analytics/summaries` Get organization-wide activity summaries for a date range. Returns one entry per day from `starting_date` (inclusive) to `ending_date` (exclusive) in `data`, the same `data` / `next_page` envelope as the other analytics list endpoints; the series is currently returned in full, so `next_page` is always null. Data is typically available with a 1-day lag and may be revised by a few percent over the following days: when `ending_date` is omitted it defaults to the most recent available day + 1, so the last entry covers the most recent available day. The series can be scoped to an RBAC group via `filter[]=rbac_group_id:{id}`. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope. #### Parameters - `starting_date: Union[null, null]` (query parameter) UTC date in YYYY-MM-DD format. Start of the date range (inclusive). Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01. format: date - `ending_date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. End of the date range (exclusive). Data is typically available with a 1-day lag, so this can be at most today — which is also the default when omitted, making the last entry cover the most recent available day. Data may be revised by a few percent over the following days. The range may span at most 366 days. format: date - `filter: Optional[Sequence[str]]` (query parameter) Filters as `dimension:value`. Only `rbac_group_id` is supported (e.g. `filter[]=rbac_group_id:{id}`); repeat the param to OR across groups. Scopes the whole day series to members of the matching group(s), re-aggregated from member-level activity — org-wide seat/invite fields and the adoption rates derived from them are null on scoped rows. `rbac_group_id` accepts the tagged id (`rbac_group_...`, as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each UTC day (time-of-usage attribution). At most 100 entries. maxItems: 100 - `limit: Optional[int]` (query parameter) Number of results per page (1-1000, default 100). The day series (at most 366 entries) is currently returned in full in a single page, so `limit` does not yet shorten it. minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. `next_page` is currently always null, so there is never a cursor to send. #### Returns - `class BetaAnalyticsSingleDayActivitySummary` Per-day entry in the /summaries response. - `assigned_seat_count: Optional[int]` Number of seats currently assigned to members. Null when the response is scoped to an RBAC group — seat assignment is org-wide and has no per-group analogue. - `cowork_daily_active_user_count: int` Number of users with Cowork activity on the requested day - `cowork_monthly_active_user_count: int` Number of users with Cowork activity in the 30-day rolling window - `cowork_weekly_active_user_count: int` Number of users with Cowork activity in the 7-day rolling window - `daily_active_user_count: int` Number of users with token consumption on the requested day - `daily_adoption_rate: Optional[float]` Percentage of assigned seats with activity on the requested day (`DAU / assigned_seat_count * 100`). Null when the response is scoped to an RBAC group. - `ending_at: datetime` End of the aggregation period (exclusive), UTC midnight in RFC 3339 format (e.g. `2026-01-16T00:00:00Z`). format: date-time - `monthly_active_user_count: int` Number of users with token consumption in the 30-day rolling window - `monthly_adoption_rate: Optional[float]` Percentage of assigned seats with activity in the 30-day rolling window (`MAU / assigned_seat_count * 100`). Null when the response is scoped to an RBAC group. - `pending_invite_count: Optional[int]` Number of pending invitations to join the organization. Null when the response is scoped to an RBAC group. - `starting_at: datetime` Start of the aggregation period (inclusive), UTC midnight in RFC 3339 format (e.g. `2026-01-15T00:00:00Z`). format: date-time - `weekly_active_user_count: int` Number of users with token consumption in the 7-day rolling window - `weekly_adoption_rate: Optional[float]` Percentage of assigned seats with activity in the 7-day rolling window (`WAU / assigned_seat_count * 100`). Null when the response is scoped to an RBAC group. - `chat_cowork_unified_daily_active_user_count: Optional[int]` Number of users with activity in Chat and Cowork unified on the requested day. Omitted from the response on deployments that do not offer Chat and Cowork unified. - `chat_cowork_unified_monthly_active_user_count: Optional[int]` Number of users with activity in Chat and Cowork unified in the 28-day rolling window (30 days when the request filters by `rbac_group_id`). Omitted from the response on deployments that do not offer Chat and Cowork unified. - `chat_cowork_unified_weekly_active_user_count: Optional[int]` Number of users with activity in Chat and Cowork unified in the 7-day rolling window. Omitted from the response on deployments that do not offer Chat and Cowork unified. - `chat_daily_active_user_count: Optional[int]` Number of users with claude.ai (chat) activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization. - `chat_monthly_active_user_count: Optional[int]` Number of users with claude.ai (chat) activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization. - `chat_weekly_active_user_count: Optional[int]` Number of users with claude.ai (chat) activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization. - `claude_code_daily_active_user_count: Optional[int]` Number of users with Claude Code activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization. - `claude_code_monthly_active_user_count: Optional[int]` Number of users with Claude Code activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization. - `claude_code_weekly_active_user_count: Optional[int]` Number of users with Claude Code activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization. - `claude_design_daily_active_user_count: Optional[int]` Number of users with Claude Design activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization. - `claude_design_monthly_active_user_count: Optional[int]` Number of users with Claude Design activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization. - `claude_design_weekly_active_user_count: Optional[int]` Number of users with Claude Design activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization. - `office_agent_daily_active_user_count: Optional[int]` Number of users with Claude in Office activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization. - `office_agent_monthly_active_user_count: Optional[int]` Number of users with Claude in Office activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization. - `office_agent_weekly_active_user_count: Optional[int]` Number of users with Claude in Office activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization. - `science_daily_active_user_count: Optional[int]` Number of users with Claude Science activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization. - `science_entitled_user_count: Optional[int]` Number of users with a Claude Science seat entitlement (per-seat RBAC) at the time of the daily snapshot. The funnel top; independent of the org-level Claude Science toggle. Null when the response is scoped to an RBAC group — entitlement is org-wide and has no per-group analogue. Omitted from the response while the per-product breakdown is not enabled for this organization. - `science_monthly_active_user_count: Optional[int]` Number of users with Claude Science activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization. - `science_weekly_active_user_count: Optional[int]` Number of users with Claude Science activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization. #### Example ```python import os from datetime import date from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.analytics.summaries.list( starting_date=date.fromisoformat("2019-12-27"), ) page = page.data[0] print(page.assigned_seat_count) ``` ##### Response (200) ```json { "data": [ { "assigned_seat_count": 0, "cowork_daily_active_user_count": 0, "cowork_monthly_active_user_count": 0, "cowork_weekly_active_user_count": 0, "daily_active_user_count": 0, "daily_adoption_rate": 0, "ending_at": "2019-12-27T18:11:19.117Z", "monthly_active_user_count": 0, "monthly_adoption_rate": 0, "pending_invite_count": 0, "starting_at": "2019-12-27T18:11:19.117Z", "weekly_active_user_count": 0, "weekly_adoption_rate": 0, "chat_cowork_unified_daily_active_user_count": 0, "chat_cowork_unified_monthly_active_user_count": 0, "chat_cowork_unified_weekly_active_user_count": 0, "chat_daily_active_user_count": 0, "chat_monthly_active_user_count": 0, "chat_weekly_active_user_count": 0, "claude_code_daily_active_user_count": 0, "claude_code_monthly_active_user_count": 0, "claude_code_weekly_active_user_count": 0, "claude_design_daily_active_user_count": 0, "claude_design_monthly_active_user_count": 0, "claude_design_weekly_active_user_count": 0, "office_agent_daily_active_user_count": 0, "office_agent_monthly_active_user_count": 0, "office_agent_weekly_active_user_count": 0, "science_daily_active_user_count": 0, "science_entitled_user_count": 0, "science_monthly_active_user_count": 0, "science_weekly_active_user_count": 0 } ], "next_page": "next_page", "summaries": [ { "assigned_seat_count": 0, "cowork_daily_active_user_count": 0, "cowork_monthly_active_user_count": 0, "cowork_weekly_active_user_count": 0, "daily_active_user_count": 0, "daily_adoption_rate": 0, "ending_at": "2019-12-27T18:11:19.117Z", "monthly_active_user_count": 0, "monthly_adoption_rate": 0, "pending_invite_count": 0, "starting_at": "2019-12-27T18:11:19.117Z", "weekly_active_user_count": 0, "weekly_adoption_rate": 0, "chat_cowork_unified_daily_active_user_count": 0, "chat_cowork_unified_monthly_active_user_count": 0, "chat_cowork_unified_weekly_active_user_count": 0, "chat_daily_active_user_count": 0, "chat_monthly_active_user_count": 0, "chat_weekly_active_user_count": 0, "claude_code_daily_active_user_count": 0, "claude_code_monthly_active_user_count": 0, "claude_code_weekly_active_user_count": 0, "claude_design_daily_active_user_count": 0, "claude_design_monthly_active_user_count": 0, "claude_design_weekly_active_user_count": 0, "office_agent_daily_active_user_count": 0, "office_agent_monthly_active_user_count": 0, "office_agent_weekly_active_user_count": 0, "science_daily_active_user_count": 0, "science_entitled_user_count": 0, "science_monthly_active_user_count": 0, "science_weekly_active_user_count": 0 } ] } ``` ## Beta › Organization › Analytics › Users ### List User Activity `beta.organization.analytics.users.list(**kwargs) -> SyncPageCursor[BetaAnalyticsUserActivity]` **GET** `/v1/organizations/analytics/users` Get per-user activity for a given day, with cursor-based pagination. Returns activity metrics for each user in the organization, sorted by email address. Use `group_by[]` for per-RBAC-group aggregates, or `filter[]` to scope results to specific members, groups, or a chat project. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope. #### Parameters - `date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. The day to get user activity for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01. format: date - `ending_date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. End of the date range (exclusive); only valid with `starting_date`. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day), so this can be at most today — which is also the default when omitted, resolved once when the first page is served and reused for the rest of the pagination sequence. At most 366 days after `starting_date`. format: date - `filter: Optional[Sequence[str]]` (query parameter) Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: `project_id`, `rbac_group_id`, `user_id`. Value forms: `project_id` takes a tagged project id (`claude_proj_...`); `rbac_group_id` takes the tagged id (`rbac_group_...`, as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); `user_id` takes a tagged user id (`user_...`), as emitted in responses. An unsupported dimension returns 400. At most 100 entries. A `project_id` filter limits each member's row to their claude.ai chat activity in that project and cannot be combined with `group_by[]` or an `rbac_group_id` filter. On these rows, every count in `chat_cowork_unified_metrics.sessions` is 0, because sessions are not measured per project. On any day a member sent a chat message in Chat and Cowork unified, all of that member's project activity for the day is counted in `chat_cowork_unified_metrics.chat` instead of `chat_metrics`. maxItems: 100 - `group_by: Optional[List[Literal["rbac_group_id"]]]` (query parameter) Dimensions to break results out by (e.g. `group_by[]=rbac_group_id`). Supported on this endpoint: `rbac_group_id`. Rows are already per-member, so the one supported grouping aggregates them per RBAC group instead. Grouped rows carry the requested dimension values as additional fields and paginate like ungrouped responses via `next_page`; an unsupported dimension returns 400. `rbac_group_id` attributes a user to every group they held at any point during each covered UTC day, so grouped rows are not an exclusive partition and can sum above org-level totals. At most 100 entries. maxItems: 100 - `limit: Optional[int]` (query parameter) Number of results per page (1-1000, default 100). minimum: 1, maximum: 1000 - `order: Optional[Literal["asc", "desc"]]` (query parameter) Sort direction: `asc` or `desc`. Defaults to `asc` for the endpoint's sort column and to `desc` when `order_by` names a metric (a top-N ranking). Applies to `order_by`, or to the endpoint's default sort field when `order_by` is omitted. - `"asc"` - `"desc"` - `order_by: Optional[str]` (query parameter) Sort field. Restricted to the endpoint's sort column plus its rankable metrics (metrics default to descending; a few metrics rank in date-range mode only, per the endpoint's documented orderable set). - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. - `starting_date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. Start of a date range (inclusive). Enables rollup mode: one row per entity aggregated over the whole range — addable counters are summed across days, and a distinct count is never summed where summing could double-count (a field's range value is recomputed exactly over the window, approximate via HLL with typical error under 2%, null, or — for the creation-event counts, whose per-day values cannot overlap — a per-day sum that is itself exact; each field's own description says which). Use either `date` or `starting_date`, not both. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01. format: date #### Returns - `class BetaAnalyticsUserActivity` Per-user activity data for a given day. - `chat_metrics: BetaAnalyticsChatMetrics` Claude.ai activity metrics for a single user on a given day. - `connectors_used_count: int` Number of MCP connector invocations. - `distinct_artifacts_created_count: int` Number of distinct artifacts created. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it. - `distinct_connectors_used_count: Optional[int]` Distinct claude.ai connectors this user used. Excludes calls whose connector could not be identified and all calls from organizations with zero data retention. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_conversation_count: Optional[int]` Number of distinct conversations the user participated in. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_files_uploaded_count: Optional[int]` Number of distinct files uploaded. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_projects_created_count: int` Number of distinct projects created. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it. - `distinct_projects_used_count: Optional[int]` Number of distinct projects used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_shared_artifacts_viewed_count: Optional[int]` Number of distinct shared artifacts the user viewed. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_skills_used_count: Optional[int]` Number of distinct skills used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `message_count: int` Number of messages sent - `shared_conversations_viewed_count: int` Number of times the user opened a shared conversation in a project - `thinking_message_count: int` Number of messages that used extended thinking - `claude_code_metrics: BetaAnalyticsClaudeCodeMetrics` Claude Code activity metrics for a single user on a given day. - `core_metrics: BetaAnalyticsCoreCodeMetrics` Core Claude Code activity metrics for a single user on a given day. - `artifacts_created_count: int` Number of artifacts created in Claude Code sessions: an artifact counts once, on the day a session first saves it. Counted from 2026-08-17; 0 on earlier days. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it. - `commit_count: int` Number of commits made via Claude Code - `distinct_session_count: Optional[int]` Number of distinct Claude Code sessions. On aggregated rows and in date-range mode: summed per-day distinct counts. A session essentially never spans a UTC day, so the sum is in practice the true distinct count. - `lines_of_code: BetaAnalyticsLinesOfCode` Lines of code added and removed via Claude Code. - `added_count: int` Lines of code added - `removed_count: int` Lines of code removed - `pull_request_count: int` Number of pull requests created via Claude Code - `tool_actions: BetaAnalyticsToolActions` Per-tool accepted/rejected counts for Claude Code file modification tools. - `edit_tool: BetaAnalyticsToolActionCounts` Accepted/rejected counts for a single Claude Code tool type. - `accepted_count: int` Number of tool proposals accepted - `rejected_count: int` Number of tool proposals rejected - `multi_edit_tool: BetaAnalyticsToolActionCounts` Accepted/rejected counts for a single Claude Code tool type. - `notebook_edit_tool: BetaAnalyticsToolActionCounts` Accepted/rejected counts for a single Claude Code tool type. - `write_tool: BetaAnalyticsToolActionCounts` Accepted/rejected counts for a single Claude Code tool type. - `cowork_metrics: BetaAnalyticsCoworkMetrics` Cowork activity metrics for a single user on a given day. - `action_count: int` Number of tool actions completed in Cowork sessions - `artifacts_created_count: int` Number of artifacts created in Cowork sessions: an artifact counts once, on the day a session first saves it. Counted from 2026-08-17; 0 on earlier days. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it. - `connectors_used_count: int` Total number of connector invocations in Cowork sessions - `dispatch_turn_count: int` Number of Dispatch (background agent) turns completed - `distinct_connectors_used_count: Optional[int]` Number of distinct connectors used in Cowork sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_session_count: Optional[int]` Number of distinct Cowork sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_skills_used_count: Optional[int]` Number of distinct skills used in Cowork sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `message_count: int` Number of messages sent in Cowork sessions - `skills_used_count: int` Total number of skill invocations in Cowork sessions - `distinct_plugins_used_count: Optional[int]` Number of distinct plugins used in Cowork sessions. Null while Cowork plugin-use metrics are not enabled for this organization. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `edit_tool_count: Optional[int]` Number of successful Edit tool calls in Cowork sessions. Null while the file-edit metrics are not enabled for this organization. - `file_edit_count: Optional[int]` Number of successful file-edit tool calls (Edit, MultiEdit, Write, NotebookEdit) in Cowork sessions. Null, never 0, while the file-edit metrics are not enabled for this organization. - `multi_edit_tool_count: Optional[int]` Number of successful MultiEdit tool calls in Cowork sessions. Null while the file-edit metrics are not enabled for this organization. - `notebook_edit_tool_count: Optional[int]` Number of successful NotebookEdit tool calls in Cowork sessions. Null while the file-edit metrics are not enabled for this organization. - `plugins_used_count: Optional[int]` Total number of plugin invocations in Cowork sessions. Null while Cowork plugin-use metrics are not enabled for this organization. - `sessions_with_file_edits_count: Optional[int]` Number of distinct Cowork sessions with at least one successful file-edit tool call. Null while the file-edit metrics are not enabled for this organization. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `write_tool_count: Optional[int]` Number of successful Write tool calls in Cowork sessions. Null while the file-edit metrics are not enabled for this organization. - `design_metrics: BetaAnalyticsDesignMetrics` Claude Design activity metrics for a single user on a given day. - `distinct_projects_created_count: int` Number of distinct Claude Design projects created. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it. - `distinct_projects_used_count: Optional[int]` Number of distinct Claude Design projects the user worked in. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_session_count: Optional[int]` Number of distinct Claude Design sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `message_count: int` Number of messages sent in Claude Design sessions - `office_metrics: BetaAnalyticsOfficeMetrics` Office Agent activity metrics for a single user on a given day, broken out by Office product. - `excel: BetaAnalyticsOfficeProductMetrics` Office Agent activity metrics for a single user on a given day within one Office product. - `connectors_used_count: int` Number of MCP connector invocations - `distinct_connectors_used_count: Optional[int]` Number of distinct MCP connectors used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_session_count: Optional[int]` Number of distinct Office Agent sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_skills_used_count: Optional[int]` Number of distinct skills used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `message_count: int` Number of messages sent - `skills_used_count: int` Number of skill invocations - `outlook: BetaAnalyticsOfficeProductMetrics` Office Agent activity metrics for a single user on a given day within one Office product. - `powerpoint: BetaAnalyticsOfficeProductMetrics` Office Agent activity metrics for a single user on a given day within one Office product. - `word: BetaAnalyticsOfficeProductMetrics` Office Agent activity metrics for a single user on a given day within one Office product. - `science_metrics: BetaAnalyticsScienceMetrics` Claude Science activity metrics for a single user on a given day. - `delegation_count: int` Number of delegations (handoffs to a specialized agent) in Claude Science sessions - `distinct_session_count: Optional[int]` Number of distinct Claude Science sessions. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `message_count: int` Number of messages sent in Claude Science sessions - `remote_compute_job_count: int` Number of remote compute jobs launched from Claude Science sessions - `skills_used_count: int` Total number of skill invocations in Claude Science sessions - `web_search_count: int` Number of web searches performed - `chat_cowork_unified_metrics: Optional[ChatCoworkUnifiedMetrics]` Activity recorded while the member had Chat and Cowork unified (Cowork's features inside claude.ai chat) turned on, split into `chat` (chat activity) and `sessions` (Cowork activity). Omitted from the response on deployments that do not offer Chat and Cowork unified. - `chat: BetaAnalyticsChatCoworkUnifiedChatMetrics` Chat activity recorded while members had Chat and Cowork unified turned on. - `connectors_used_count: int` Same measure as `chat_metrics.connectors_used_count`, for activity recorded while members had Chat and Cowork unified turned on. - `distinct_artifacts_created_count: int` Same measure as `chat_metrics.distinct_artifacts_created_count`, for activity recorded while members had Chat and Cowork unified turned on. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it. - `distinct_connectors_used_count: Optional[int]` Same measure as `chat_metrics.distinct_connectors_used_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_conversation_count: Optional[int]` Same measure as `chat_metrics.distinct_conversation_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_files_uploaded_count: Optional[int]` Same measure as `chat_metrics.distinct_files_uploaded_count`, for activity recorded while members had Chat and Cowork unified turned on. It counts uploaded files as well as files Claude created and images returned by Claude's tools, such as screenshots. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_projects_created_count: int` Same measure as `chat_metrics.distinct_projects_created_count`, for activity recorded while members had Chat and Cowork unified turned on. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it. - `distinct_projects_used_count: Optional[int]` Same measure as `chat_metrics.distinct_projects_used_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_shared_artifacts_viewed_count: Optional[int]` Always null: shared-artifact views are not currently measured. - `distinct_skills_used_count: Optional[int]` Same measure as `chat_metrics.distinct_skills_used_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `message_count: int` Same measure as `chat_metrics.message_count`, for activity recorded while members had Chat and Cowork unified turned on. - `shared_conversations_viewed_count: int` Same measure as `chat_metrics.shared_conversations_viewed_count`, for activity recorded while members had Chat and Cowork unified turned on. - `thinking_message_count: int` Same measure as `chat_metrics.thinking_message_count`, for activity recorded while members had Chat and Cowork unified turned on. - `sessions: BetaAnalyticsChatCoworkUnifiedSessionsMetrics` Cowork session activity recorded while members had Chat and Cowork unified turned on. - `action_count: int` Same measure as `cowork_metrics.action_count`, for activity recorded while members had Chat and Cowork unified turned on. - `artifacts_created_count: int` Same measure as `cowork_metrics.artifacts_created_count`, for activity recorded while members had Chat and Cowork unified turned on. Exact in date-range mode: a creation belongs to exactly one day, so the per-day counts never overlap and their sum over the window is the exact count of distinct creations in it. - `connectors_used_count: int` Same measure as `cowork_metrics.connectors_used_count`, for activity recorded while members had Chat and Cowork unified turned on. - `dispatch_turn_count: int` Same measure as `cowork_metrics.dispatch_turn_count`, for activity recorded while members had Chat and Cowork unified turned on. - `distinct_connectors_used_count: Optional[int]` Same measure as `cowork_metrics.distinct_connectors_used_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_plugins_used_count: Optional[int]` Same measure as `cowork_metrics.distinct_plugins_used_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_session_count: Optional[int]` Same measure as `cowork_metrics.distinct_session_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_skills_used_count: Optional[int]` Same measure as `cowork_metrics.distinct_skills_used_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `edit_tool_count: Optional[int]` Same measure as `cowork_metrics.edit_tool_count`, for activity recorded while members had Chat and Cowork unified turned on. - `file_edit_count: Optional[int]` Same measure as `cowork_metrics.file_edit_count`, for activity recorded while members had Chat and Cowork unified turned on. - `message_count: int` Same measure as `cowork_metrics.message_count`, for activity recorded while members had Chat and Cowork unified turned on. - `multi_edit_tool_count: Optional[int]` Same measure as `cowork_metrics.multi_edit_tool_count`, for activity recorded while members had Chat and Cowork unified turned on. Claude no longer has a multi-edit tool, so expect 0 when not null; each edit is now a separate Edit tool call, counted in `edit_tool_count` and `file_edit_count`. - `notebook_edit_tool_count: Optional[int]` Same measure as `cowork_metrics.notebook_edit_tool_count`, for activity recorded while members had Chat and Cowork unified turned on. - `plugins_used_count: Optional[int]` Same measure as `cowork_metrics.plugins_used_count`, for activity recorded while members had Chat and Cowork unified turned on. - `sessions_with_file_edits_count: Optional[int]` Same measure as `cowork_metrics.sessions_with_file_edits_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `skills_used_count: int` Same measure as `cowork_metrics.skills_used_count`, for activity recorded while members had Chat and Cowork unified turned on. - `write_tool_count: Optional[int]` Same measure as `cowork_metrics.write_tool_count`, for activity recorded while members had Chat and Cowork unified turned on. - `distinct_user_count: Optional[int]` Number of distinct active users represented by this row. Only set for grouped rollups (`group_by[]`); null for per-user rows. In date-range mode, recomputed as an exact distinct count of the group's active members over the requested window, never a sum of per-day values. - `last_activity_date: Optional[date]` Most recent UTC day (YYYY-MM-DD) on which the user had any counted activity, within the requested window: equal to the requested `date` in single-day mode, and to the latest active day from `starting_date` (inclusive) to `ending_date` (exclusive) in date-range rollup mode — never a day earlier than the window start. On filtered requests (`filter[]`) only days matching the filter count: with `filter[]=rbac_group_id:{id}` it is the last day the user was active while a member of that group, consistent with the row's other metrics. On grouped (`group_by[]`) rows it is the latest day any member of the group was active (the requested `date` in single-day mode). Omitted from the response while last-activity reporting is not enabled for this organization. format: date - `rbac_group_id: Optional[str]` Tagged RBAC group identifier (`rbac_group_...`), matching the spend-limits API spelling. Present only when the request grouped by `rbac_group_id`. - `rbac_group_name: Optional[str]` Resolved RBAC group display name, alongside `rbac_group_id` when name resolution is available. Null if the group has been deleted or its name could not be resolved; `rbac_group_id` remains the stable key. - `user: Optional[BetaAnalyticsUser]` The user this row describes. Null on rows aggregated across users. - `type: Literal["user"]` Object type. Always `user`. default: user - `id: str` Tagged user identifier (e.g. `user_...`) - `email_address: str` Email address of the user #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.analytics.users.list() page = page.data[0] print(page.rbac_group_id) ``` ##### Response (200) ```json { "data": [ { "chat_metrics": { "connectors_used_count": 0, "distinct_artifacts_created_count": 0, "distinct_connectors_used_count": 0, "distinct_conversation_count": 0, "distinct_files_uploaded_count": 0, "distinct_projects_created_count": 0, "distinct_projects_used_count": 0, "distinct_shared_artifacts_viewed_count": 0, "distinct_skills_used_count": 0, "message_count": 0, "shared_conversations_viewed_count": 0, "thinking_message_count": 0 }, "claude_code_metrics": { "core_metrics": { "artifacts_created_count": 0, "commit_count": 0, "distinct_session_count": 0, "lines_of_code": { "added_count": 0, "removed_count": 0 }, "pull_request_count": 0 }, "tool_actions": { "edit_tool": { "accepted_count": 0, "rejected_count": 0 }, "multi_edit_tool": { "accepted_count": 0, "rejected_count": 0 }, "notebook_edit_tool": { "accepted_count": 0, "rejected_count": 0 }, "write_tool": { "accepted_count": 0, "rejected_count": 0 } } }, "cowork_metrics": { "action_count": 0, "artifacts_created_count": 0, "connectors_used_count": 0, "dispatch_turn_count": 0, "distinct_connectors_used_count": 0, "distinct_session_count": 0, "distinct_skills_used_count": 0, "message_count": 0, "skills_used_count": 0, "distinct_plugins_used_count": 0, "edit_tool_count": 0, "file_edit_count": 0, "multi_edit_tool_count": 0, "notebook_edit_tool_count": 0, "plugins_used_count": 0, "sessions_with_file_edits_count": 0, "write_tool_count": 0 }, "design_metrics": { "distinct_projects_created_count": 0, "distinct_projects_used_count": 0, "distinct_session_count": 0, "message_count": 0 }, "office_metrics": { "excel": { "connectors_used_count": 0, "distinct_connectors_used_count": 0, "distinct_session_count": 0, "distinct_skills_used_count": 0, "message_count": 0, "skills_used_count": 0 }, "outlook": { "connectors_used_count": 0, "distinct_connectors_used_count": 0, "distinct_session_count": 0, "distinct_skills_used_count": 0, "message_count": 0, "skills_used_count": 0 }, "powerpoint": { "connectors_used_count": 0, "distinct_connectors_used_count": 0, "distinct_session_count": 0, "distinct_skills_used_count": 0, "message_count": 0, "skills_used_count": 0 }, "word": { "connectors_used_count": 0, "distinct_connectors_used_count": 0, "distinct_session_count": 0, "distinct_skills_used_count": 0, "message_count": 0, "skills_used_count": 0 } }, "science_metrics": { "delegation_count": 0, "distinct_session_count": 0, "message_count": 0, "remote_compute_job_count": 0, "skills_used_count": 0 }, "web_search_count": 0, "chat_cowork_unified_metrics": { "chat": { "connectors_used_count": 0, "distinct_artifacts_created_count": 0, "distinct_connectors_used_count": 0, "distinct_conversation_count": 0, "distinct_files_uploaded_count": 0, "distinct_projects_created_count": 0, "distinct_projects_used_count": 0, "distinct_shared_artifacts_viewed_count": 0, "distinct_skills_used_count": 0, "message_count": 0, "shared_conversations_viewed_count": 0, "thinking_message_count": 0 }, "sessions": { "action_count": 0, "artifacts_created_count": 0, "connectors_used_count": 0, "dispatch_turn_count": 0, "distinct_connectors_used_count": 0, "distinct_plugins_used_count": 0, "distinct_session_count": 0, "distinct_skills_used_count": 0, "edit_tool_count": 0, "file_edit_count": 0, "message_count": 0, "multi_edit_tool_count": 0, "notebook_edit_tool_count": 0, "plugins_used_count": 0, "sessions_with_file_edits_count": 0, "skills_used_count": 0, "write_tool_count": 0 } }, "distinct_user_count": 0, "last_activity_date": "2019-12-27", "rbac_group_id": "rbac_group_id", "rbac_group_name": "rbac_group_name", "user": { "id": "id", "email_address": "email_address", "type": "user" } } ], "next_page": "next_page" } ``` ## Beta › Organization › Analytics › Apps › Chat › Projects ### Get Chat Project Usage `beta.organization.analytics.apps.chat.projects.list(**kwargs) -> SyncPageCursor[BetaAnalyticsProjectActivity]` **GET** `/v1/organizations/analytics/apps/chat/projects` Get per-project activity for a given day, with cursor-based pagination. Returns activity metrics for each project in the organization, sorted by project ID. Use `group_by[]` to break projects out per member or per RBAC group, and `filter[]` to scope results; the parameter descriptions list the supported dimensions. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope. #### Parameters - `date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. The day to get project activity for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01. format: date - `ending_date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. End of the date range (exclusive); only valid with `starting_date`. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day), so this can be at most today — which is also the default when omitted, resolved once when the first page is served and reused for the rest of the pagination sequence. At most 366 days after `starting_date`. format: date - `filter: Optional[Sequence[str]]` (query parameter) Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: `project_id`, `rbac_group_id`, `user_id`. Value forms: `project_id` takes a tagged project id (`claude_proj_...`); `rbac_group_id` takes the tagged id (`rbac_group_...`, as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); `user_id` takes a tagged user id (`user_...`), as emitted in responses. An unsupported dimension returns 400. At most 100 entries. maxItems: 100 - `group_by: Optional[List[Literal["rbac_group_id", "user_id"]]]` (query parameter) Dimensions to break results out by (e.g. `group_by[]=user_id`). Supported on this endpoint: `rbac_group_id`, `user_id`. Grouped rows carry the requested dimension values as additional fields and paginate like ungrouped responses via `next_page`; an unsupported dimension returns 400. `rbac_group_id` attributes a user to every group they held at any point during each covered UTC day, so grouped rows are not an exclusive partition and can sum above org-level totals. At most 100 entries. maxItems: 100 - `"rbac_group_id"` - `"user_id"` - `limit: Optional[int]` (query parameter) Number of results per page (1-1000, default 100). minimum: 1, maximum: 1000 - `order: Optional[Literal["asc", "desc"]]` (query parameter) Sort direction: `asc` or `desc`. Defaults to `asc` for the endpoint's sort column and to `desc` when `order_by` names a metric (a top-N ranking). Applies to `order_by`, or to the endpoint's default sort field when `order_by` is omitted. - `"asc"` - `"desc"` - `order_by: Optional[str]` (query parameter) Sort field. Restricted to the endpoint's sort column plus its rankable metrics (metrics default to descending; a few metrics rank in date-range mode only, per the endpoint's documented orderable set). - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. - `starting_date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. Start of a date range (inclusive). Enables rollup mode: one row per entity aggregated over the whole range — addable counters are summed across days, and a distinct count is never summed where summing could double-count (a field's range value is recomputed exactly over the window, approximate via HLL with typical error under 2%, null, or — for the creation-event counts, whose per-day values cannot overlap — a per-day sum that is itself exact; each field's own description says which). Use either `date` or `starting_date`, not both. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01. format: date #### Returns - `class BetaAnalyticsProjectActivity` Per-project activity data for a given day. - `distinct_user_count: int` Number of distinct users who used the project on the requested day, or, in date-range mode, over the requested window — recomputed as an exact distinct count over the window's per-member daily rows, never a sum of per-day values. - `message_count: int` Number of messages sent in the project on the requested day - `project_id: str` Tagged project identifier (e.g. `claude_proj_...`) - `project_name: str` Name of the project - `created_at: Optional[datetime]` Project creation timestamp in RFC 3339 format. Null if the project was deleted before attribution was recorded. format: date-time - `created_by: Optional[BetaAnalyticsUser]` User who created the project. Null if the project was deleted before attribution was recorded, or if the creator's account no longer exists. - `type: Literal["user"]` Object type. Always `user`. default: user - `id: str` Tagged user identifier (e.g. `user_...`) - `email_address: str` Email address of the user - `distinct_conversation_count: Optional[int]` Number of distinct conversations in the project. Null on aggregated rows where a distinct count cannot be computed. - `product: Optional[str]` Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, `office_agent`, or `chat_cowork_unified` (Chat and Cowork unified). These are the canonical Cost & Usage product names; an `office_agent` row's per-surface breakdown is in its `office_metrics`. On `/plugins` only `cowork`, `claude_code` and `chat_cowork_unified` occur (the only surfaces with plugin attribution); on `/artifacts` only `chat`, `claude_code`, `cowork` and `chat_cowork_unified` occur (the surfaces that create artifacts); `/apps/chat/projects` does not support the product dimension (a `product` entry in `group_by[]` or `filter[]` there is rejected). Present only when the request grouped by `product`. - `rbac_group_id: Optional[str]` Tagged RBAC group identifier (`rbac_group_...`), matching the spend-limits API spelling. Present only when the request grouped by `rbac_group_id`. - `rbac_group_name: Optional[str]` Resolved RBAC group display name, alongside `rbac_group_id` when name resolution is available. Null if the group has been deleted or its name could not be resolved; `rbac_group_id` remains the stable key. - `user_id: Optional[str]` Tagged user identifier (e.g. `user_...`). Present only when the request grouped by `user_id`. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.analytics.apps.chat.projects.list() page = page.data[0] print(page.project_id) ``` ##### Response (200) ```json { "data": [ { "distinct_user_count": 0, "message_count": 0, "project_id": "project_id", "project_name": "project_name", "created_at": "2019-12-27T18:11:19.117Z", "created_by": { "id": "id", "email_address": "email_address", "type": "user" }, "distinct_conversation_count": 0, "product": "product", "rbac_group_id": "rbac_group_id", "rbac_group_name": "rbac_group_name", "user_id": "user_id" } ], "next_page": "next_page" } ``` ## Beta › Organization › Analytics › Connectors ### Get Connector Usage `beta.organization.analytics.connectors.list(**kwargs) -> SyncPageCursor[BetaAnalyticsConnectorActivity]` **GET** `/v1/organizations/analytics/connectors` Get per-connector usage for a given day, with cursor-based pagination. Returns connector usage metrics for the organization, sorted by connector name. Connector names are normalized from their various sources — for example, "Atlassian MCP server" and "mcp-atlassian" both appear as "atlassian". Use `group_by[]` to break usage out per member, per RBAC group, or per product surface, and `filter[]` to scope results; the parameter descriptions list the supported dimensions. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope. #### Parameters - `date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. The day to get connector usage for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01. format: date - `ending_date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. End of the date range (exclusive); only valid with `starting_date`. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day), so this can be at most today — which is also the default when omitted, resolved once when the first page is served and reused for the rest of the pagination sequence. At most 366 days after `starting_date`. format: date - `filter: Optional[Sequence[str]]` (query parameter) Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: `connector_name`, `product`, `rbac_group_id`, `user_id`. Value forms: `connector_name` matches case-insensitively, a display name such as 'GitHub MCP' also matches its normalized stored form ('github'), and for rows whose `connector_name` is an opaque connector id the connector's display name (`connector_display_name`) also matches; `product` is one of `chat_cowork_unified`, `chat`, `claude_code`, `cowork`, or `office_agent`; `rbac_group_id` takes the tagged id (`rbac_group_...`, as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); `user_id` takes a tagged user id (`user_...`), as emitted in responses. An unsupported dimension returns 400. At most 100 entries. `chat_cowork_unified` is accepted as a `product` value only on deployments that offer Chat and Cowork unified. maxItems: 100 - `group_by: Optional[List[Literal["product", "rbac_group_id", "user_id"]]]` (query parameter) Dimensions to break results out by (e.g. `group_by[]=user_id`). Supported on this endpoint: `product`, `rbac_group_id`, `user_id`. Grouped rows carry the requested dimension values as additional fields and paginate like ungrouped responses via `next_page`; an unsupported dimension returns 400. `rbac_group_id` attributes a user to every group they held at any point during each covered UTC day, so grouped rows are not an exclusive partition and can sum above org-level totals. At most 100 entries. maxItems: 100 - `"product"` - `"rbac_group_id"` - `"user_id"` - `limit: Optional[int]` (query parameter) Number of results per page (1-1000, default 100). minimum: 1, maximum: 1000 - `order: Optional[Literal["asc", "desc"]]` (query parameter) Sort direction: `asc` or `desc`. Defaults to `asc` for the endpoint's sort column and to `desc` when `order_by` names a metric (a top-N ranking). Applies to `order_by`, or to the endpoint's default sort field when `order_by` is omitted. - `"asc"` - `"desc"` - `order_by: Optional[str]` (query parameter) Sort field. Restricted to the endpoint's sort column plus its rankable metrics (metrics default to descending; a few metrics rank in date-range mode only, per the endpoint's documented orderable set). - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. - `starting_date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. Start of a date range (inclusive). Enables rollup mode: one row per entity aggregated over the whole range — addable counters are summed across days, and a distinct count is never summed where summing could double-count (a field's range value is recomputed exactly over the window, approximate via HLL with typical error under 2%, null, or — for the creation-event counts, whose per-day values cannot overlap — a per-day sum that is itself exact; each field's own description says which). Use either `date` or `starting_date`, not both. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01. format: date #### Returns - `class BetaAnalyticsConnectorActivity` Per-connector activity data for a given day. - `chat_metrics: BetaAnalyticsConnectorChatMetrics` Claude.ai activity metrics for a single connector on a given day. - `distinct_conversation_connector_used_count: Optional[int]` Number of distinct conversations in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `claude_code_metrics: BetaAnalyticsConnectorClaudeCodeMetrics` Claude Code activity metrics for a single connector on a given day. - `distinct_session_connector_used_count: Optional[int]` Number of distinct Claude Code sessions in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `connector_name: str` Name of the connector. Some rows carry an opaque connector id here instead of a readable name; `connector_display_name` holds the resolved name for those rows. - `cowork_metrics: BetaAnalyticsConnectorCoworkMetrics` Cowork activity metrics for a single connector on a given day. - `distinct_session_connector_used_count: Optional[int]` Number of distinct Cowork sessions in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_user_count: int` Number of distinct users who used the connector on the requested day, or, in date-range mode, over the requested window — recomputed as an exact distinct count over the window's per-member daily rows, never a sum of per-day values. - `office_metrics: BetaAnalyticsConnectorOfficeMetrics` Office Agent activity metrics for a single connector on a given day, broken out by Office product. - `excel: BetaAnalyticsConnectorOfficeProductMetrics` Office Agent activity metrics for a single connector on a given day within one Office product. - `distinct_session_connector_used_count: Optional[int]` Number of distinct Office Agent sessions in which the connector was used. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `outlook: BetaAnalyticsConnectorOfficeProductMetrics` Office Agent activity metrics for a single connector on a given day within one Office product. - `powerpoint: BetaAnalyticsConnectorOfficeProductMetrics` Office Agent activity metrics for a single connector on a given day within one Office product. - `word: BetaAnalyticsConnectorOfficeProductMetrics` Office Agent activity metrics for a single connector on a given day within one Office product. - `chat_cowork_unified_metrics: Optional[ChatCoworkUnifiedMetrics]` Connector use recorded while members had Chat and Cowork unified (Cowork's features inside claude.ai chat) turned on, split into chat conversations and Cowork sessions. A count is null in date-range mode where it cannot be computed. Omitted from the response on deployments that do not offer Chat and Cowork unified. - `chat: BetaAnalyticsConnectorChatCoworkUnifiedChatMetrics` A connector's use in chat conversations recorded while members had Chat and Cowork unified turned on. - `distinct_conversation_connector_used_count: Optional[int]` Same measure as `chat_metrics.distinct_conversation_connector_used_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `sessions: BetaAnalyticsConnectorChatCoworkUnifiedSessionsMetrics` A connector's use in Cowork sessions recorded while members had Chat and Cowork unified turned on. - `distinct_session_connector_used_count: Optional[int]` Same measure as `cowork_metrics.distinct_session_connector_used_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `connector_display_name: Optional[str]` Human-readable display name for rows whose `connector_name` is an opaque connector id rather than a readable name, resolved at request time from the organization's connectors (including connectors that have since been removed). `connector_name` remains the row's stable key for sorting and pagination, and `filter[]=connector_name:{value}` also matches these rows by display name. Display names are not unique, and the same connector's claude.ai usage can appear under a separate row with a readable `connector_name`. Null when `connector_name` is already a readable name, when the id cannot be resolved to one of the organization's connectors, or when display-name resolution is not enabled for this organization. - `individual_auth_distinct_user_count: Optional[int]` Number of distinct users whose use of this connector on the requested day ran on their own individual credential, connected through their own consent flow. Companion bucket to `managed_auth_distinct_user_count`, which carries the measurement, attribution, and null rules. Users whose requests used no stored credential count in neither bucket. - `managed_auth_distinct_user_count: Optional[int]` Number of distinct users whose use of this connector on the requested day ran on Enterprise Managed Auth (an organization-managed credential provisioned through the organization's identity provider), read from the token record each request used. Null, never 0, when managed-auth reporting is not enabled for the organization, the value cannot be attributed to the row, no credentialed requests and no managed-token mint events (a managed credential being provisioned for a user's use of the connector) were observed that day, or the day predates 2026-07-01, the first day the backing data exists (forward-only data, no backfill). When credentialed requests or mint events were observed and attributed, both managed-auth fields populate, reporting 0 for a bucket with no users; the two counts are independent, not a partition — a user whose requests that day used both kinds of credential counts in both. Mint events carry user but not surface attribution, so they count as observed auth activity on `user_id` and `rbac_group_id` cuts — attributed to the user the credential was provisioned for — but never on a cut that references `product` (group or filter). Date-range rollup mode (`starting_date`/`ending_date`) computes both fields exactly over the window — distinct users with at least one qualifying day — when the whole window starts on or after 2026-07-01, with the null-versus-0 and mint-event rules applying with the window in place of the day; a range starting earlier reports every managed-auth field as null, never a partial-window value. - `product: Optional[str]` Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, `office_agent`, or `chat_cowork_unified` (Chat and Cowork unified). These are the canonical Cost & Usage product names; an `office_agent` row's per-surface breakdown is in its `office_metrics`. On `/plugins` only `cowork`, `claude_code` and `chat_cowork_unified` occur (the only surfaces with plugin attribution); on `/artifacts` only `chat`, `claude_code`, `cowork` and `chat_cowork_unified` occur (the surfaces that create artifacts); `/apps/chat/projects` does not support the product dimension (a `product` entry in `group_by[]` or `filter[]` there is rejected). Present only when the request grouped by `product`. - `rbac_group_id: Optional[str]` Tagged RBAC group identifier (`rbac_group_...`), matching the spend-limits API spelling. Present only when the request grouped by `rbac_group_id`. - `rbac_group_name: Optional[str]` Resolved RBAC group display name, alongside `rbac_group_id` when name resolution is available. Null if the group has been deleted or its name could not be resolved; `rbac_group_id` remains the stable key. - `read_call_count: Optional[int]` Number of connector tool calls on the requested day whose trusted read-only annotation marked them read-only. Call count, not distinct users. Every call recorded on a classified surface lands in exactly one of `read_call_count`, `write_call_count`, or `unclassified_call_count`, so the three sum to the day's classified calls. Classification is forward-only per surface: claude.ai from 2026-06-01, Claude Code from 2026-05-30, Claude in Office from 2026-05-29, Cowork from 2026-06-02 (Cowork clients predating annotation forwarding land in `unclassified_call_count`). Null, never 0, when the value cannot be stated: the read/write split is not enabled for this organization, or the day predates 2026-05-29. For a date-range total, sum the per-day values, but treat a window that extends before 2026-05-29 as null rather than summing only its covered days — date-range rollup mode (`starting_date`/`ending_date`) applies both rules server-side. - `unclassified_call_count: Optional[int]` Number of connector tool calls on the requested day with no trusted read-only annotation — the annotation is optional in the MCP spec and is discarded when connector access controls are active, so unclassified calls are common. This field shows how much of the day's classified activity the read/write split actually covers. Call count, not distinct users. One of the three call-classification buckets; see `read_call_count` for the per-surface data-start dates, null conditions, and date-range guidance. - `user_id: Optional[str]` Tagged user identifier (e.g. `user_...`). Present only when the request grouped by `user_id`. - `write_call_count: Optional[int]` Number of connector tool calls on the requested day whose trusted read-only annotation marked them not read-only. Call count, not distinct users. One of the three call-classification buckets; see `read_call_count` for the per-surface data-start dates, null conditions, and date-range guidance. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.analytics.connectors.list() page = page.data[0] print(page.individual_auth_distinct_user_count) ``` ##### Response (200) ```json { "data": [ { "chat_metrics": { "distinct_conversation_connector_used_count": 0 }, "claude_code_metrics": { "distinct_session_connector_used_count": 0 }, "connector_name": "connector_name", "cowork_metrics": { "distinct_session_connector_used_count": 0 }, "distinct_user_count": 0, "office_metrics": { "excel": { "distinct_session_connector_used_count": 0 }, "outlook": { "distinct_session_connector_used_count": 0 }, "powerpoint": { "distinct_session_connector_used_count": 0 }, "word": { "distinct_session_connector_used_count": 0 } }, "chat_cowork_unified_metrics": { "chat": { "distinct_conversation_connector_used_count": 0 }, "sessions": { "distinct_session_connector_used_count": 0 } }, "connector_display_name": "connector_display_name", "individual_auth_distinct_user_count": 0, "managed_auth_distinct_user_count": 0, "product": "product", "rbac_group_id": "rbac_group_id", "rbac_group_name": "rbac_group_name", "read_call_count": 0, "unclassified_call_count": 0, "user_id": "user_id", "write_call_count": 0 } ], "next_page": "next_page" } ``` ## Beta › Organization › Analytics › Plugins ### Get Plugin Usage `beta.organization.analytics.plugins.list(**kwargs) -> SyncPageCursor[BetaAnalyticsPluginActivity]` **GET** `/v1/organizations/analytics/plugins` Get per-plugin install + invocation usage for a given day, with pagination. Returns plugin usage metrics for the organization across Cowork and Claude Code, sorted by plugin name. The `plugin_name` value `third-party` is an aggregate bucket, not a plugin: it collects plugin activity, from either surface, for which the reporting client did not provide a plugin name — so an organization's own plugins can contribute both to their own named rows and to this bucket. Use `group_by[]` to break usage out per member, per RBAC group, or per product surface (Cowork / Claude Code), and `filter[]` to scope results; the parameter descriptions list the supported dimensions. Requires an API key with the `read:analytics` scope. `starting_date` / `ending_date` select range-rollup mode like `/skills`. #### Parameters - `date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. The day to get plugin usage for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01. format: date - `ending_date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. End of the date range (exclusive); only valid with `starting_date`. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day), so this can be at most today — which is also the default when omitted, resolved once when the first page is served and reused for the rest of the pagination sequence. At most 366 days after `starting_date`. format: date - `filter: Optional[Sequence[str]]` (query parameter) Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: `plugin_name`, `product`, `rbac_group_id`, `user_id`. Value forms: `plugin_name` matches case-insensitively; `product` is `chat_cowork_unified`, `claude_code`, or `cowork` (the only surfaces with plugin attribution); `rbac_group_id` takes the tagged id (`rbac_group_...`, as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); `user_id` takes a tagged user id (`user_...`), as emitted in responses. An unsupported dimension returns 400. At most 100 entries. `chat_cowork_unified` is accepted as a `product` value only on deployments that offer Chat and Cowork unified. maxItems: 100 - `group_by: Optional[List[Literal["product", "rbac_group_id", "user_id"]]]` (query parameter) Dimensions to break results out by (e.g. `group_by[]=user_id`). Supported on this endpoint: `product`, `rbac_group_id`, `user_id`. On this endpoint `product` takes the values `chat_cowork_unified`, `claude_code`, or `cowork` only (the surfaces with plugin attribution). Grouped rows carry the requested dimension values as additional fields and paginate like ungrouped responses via `next_page`; an unsupported dimension returns 400. `rbac_group_id` attributes a user to every group they held at any point during each covered UTC day, so grouped rows are not an exclusive partition and can sum above org-level totals. At most 100 entries. maxItems: 100 - `"product"` - `"rbac_group_id"` - `"user_id"` - `limit: Optional[int]` (query parameter) Number of results per page (1-1000, default 100). minimum: 1, maximum: 1000 - `order: Optional[Literal["asc", "desc"]]` (query parameter) Sort direction: `asc` or `desc`. Defaults to `asc` for the endpoint's sort column and to `desc` when `order_by` names a metric (a top-N ranking). Applies to `order_by`, or to the endpoint's default sort field when `order_by` is omitted. - `"asc"` - `"desc"` - `order_by: Optional[str]` (query parameter) Sort field. Restricted to the endpoint's sort column plus its rankable metrics (metrics default to descending; a few metrics rank in date-range mode only, per the endpoint's documented orderable set). - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. - `starting_date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. Start of a date range (inclusive). Enables rollup mode: one row per entity aggregated over the whole range — addable counters are summed across days, and a distinct count is never summed where summing could double-count (a field's range value is recomputed exactly over the window, approximate via HLL with typical error under 2%, null, or — for the creation-event counts, whose per-day values cannot overlap — a per-day sum that is itself exact; each field's own description says which). Use either `date` or `starting_date`, not both. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01. format: date #### Returns - `class BetaAnalyticsPluginActivity` Per-plugin install + invocation activity for a given day. With `group_by[]=user_id` / `rbac_group_id` / `product` (`cowork`, `claude_code` and `chat_cowork_unified` only on this endpoint) each row is one (plugin, user), (plugin, group), or (plugin, product) cut: the flat `user_id` / `rbac_group_id` / `product` keys carry the cut and the counts are scoped to it. - `claude_code_metrics: BetaAnalyticsPluginClaudeCodeMetrics` Claude Code activity metrics for a single plugin on a given day. - `distinct_session_plugin_used_count: Optional[int]` Number of distinct Claude Code sessions in which the plugin was invoked. Null on aggregated rows where a distinct count cannot be computed. - `cowork_metrics: BetaAnalyticsPluginCoworkMetrics` Cowork activity metrics for a single plugin on a given day. - `distinct_session_plugin_used_count: Optional[int]` Number of distinct Cowork sessions in which the plugin was invoked. Null on aggregated rows where a distinct count cannot be computed. - `distinct_user_count: int` Number of distinct users with recorded install or invocation activity for the plugin on the requested day (install-only users count), or, in date-range mode, over the requested window — recomputed as an exact distinct count over the window's per-member daily rows, never a sum of per-day values. - `install_count: Optional[int]` Number of distinct users who installed the plugin on the requested day, or, in date-range mode, over the requested window — recomputed as an exact distinct count over the window's per-member daily rows, never a sum of per-day values. - `invocation_count: int` Number of plugin invocations on the requested day - `plugin_name: str` Name of the plugin - `chat_cowork_unified_metrics: Optional[ChatCoworkUnifiedMetrics]` Plugin use recorded while members had Chat and Cowork unified (Cowork's features inside claude.ai chat) turned on. A count is null in date-range mode where it cannot be computed. Omitted from the response on deployments that do not offer Chat and Cowork unified. - `distinct_session_plugin_used_count: Optional[int]` Same measure as `cowork_metrics.distinct_session_plugin_used_count`, for activity recorded while members had Chat and Cowork unified turned on. Null on aggregated rows where a distinct count cannot be computed. - `plugin_id: Optional[str]` Stable plugin identifier when available (e.g. `serena@claude-plugins-official`). Null for third-party Claude Code plugins (redacted at the source) and Cowork slash commands that carry only a hashed id. - `product: Optional[str]` Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, `office_agent`, or `chat_cowork_unified` (Chat and Cowork unified). These are the canonical Cost & Usage product names; an `office_agent` row's per-surface breakdown is in its `office_metrics`. On `/plugins` only `cowork`, `claude_code` and `chat_cowork_unified` occur (the only surfaces with plugin attribution); on `/artifacts` only `chat`, `claude_code`, `cowork` and `chat_cowork_unified` occur (the surfaces that create artifacts); `/apps/chat/projects` does not support the product dimension (a `product` entry in `group_by[]` or `filter[]` there is rejected). Present only when the request grouped by `product`. - `rbac_group_id: Optional[str]` Tagged RBAC group identifier (`rbac_group_...`), matching the spend-limits API spelling. Present only when the request grouped by `rbac_group_id`. - `rbac_group_name: Optional[str]` Resolved RBAC group display name, alongside `rbac_group_id` when name resolution is available. Null if the group has been deleted or its name could not be resolved; `rbac_group_id` remains the stable key. - `user_id: Optional[str]` Tagged user identifier (e.g. `user_...`). Present only when the request grouped by `user_id`. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.analytics.plugins.list() page = page.data[0] print(page.plugin_id) ``` ##### Response (200) ```json { "data": [ { "claude_code_metrics": { "distinct_session_plugin_used_count": 0 }, "cowork_metrics": { "distinct_session_plugin_used_count": 0 }, "distinct_user_count": 0, "install_count": 0, "invocation_count": 0, "plugin_name": "plugin_name", "chat_cowork_unified_metrics": { "distinct_session_plugin_used_count": 0 }, "plugin_id": "plugin_id", "product": "product", "rbac_group_id": "rbac_group_id", "rbac_group_name": "rbac_group_name", "user_id": "user_id" } ], "next_page": "next_page" } ``` ## Beta › Organization › Analytics › Skills ### Get Skill Usage `beta.organization.analytics.skills.list(**kwargs) -> SyncPageCursor[BetaAnalyticsSkillActivity]` **GET** `/v1/organizations/analytics/skills` Get per-skill usage for a given day, with cursor-based pagination. Returns skill usage metrics for the organization, sorted by skill name. Use `group_by[]` to break usage out per member, per RBAC group, or per product surface, and `filter[]` to scope results; the parameter descriptions list the supported dimensions. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope. #### Parameters - `date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. The day to get skill usage for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01. format: date - `ending_date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. End of the date range (exclusive); only valid with `starting_date`. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day), so this can be at most today — which is also the default when omitted, resolved once when the first page is served and reused for the rest of the pagination sequence. At most 366 days after `starting_date`. format: date - `filter: Optional[Sequence[str]]` (query parameter) Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: `product`, `rbac_group_id`, `share_status`, `skill_name`, `user_id`. Value forms: `product` is one of `chat_cowork_unified`, `chat`, `claude_code`, `cowork`, or `office_agent`; `rbac_group_id` takes the tagged id (`rbac_group_...`, as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); `share_status` is one of `organization`, `private`, or `public`; `skill_name` matches case-insensitively; `user_id` takes a tagged user id (`user_...`), as emitted in responses. An unsupported dimension returns 400. At most 100 entries. `chat_cowork_unified` is accepted as a `product` value only on deployments that offer Chat and Cowork unified. maxItems: 100 - `group_by: Optional[List[Literal["product", "rbac_group_id", "user_id"]]]` (query parameter) Dimensions to break results out by (e.g. `group_by[]=user_id`). Supported on this endpoint: `product`, `rbac_group_id`, `user_id`. Grouped rows carry the requested dimension values as additional fields and paginate like ungrouped responses via `next_page`; an unsupported dimension returns 400. `rbac_group_id` attributes a user to every group they held at any point during each covered UTC day, so grouped rows are not an exclusive partition and can sum above org-level totals. At most 100 entries. maxItems: 100 - `"product"` - `"rbac_group_id"` - `"user_id"` - `limit: Optional[int]` (query parameter) Number of results per page (1-1000, default 100). minimum: 1, maximum: 1000 - `order: Optional[Literal["asc", "desc"]]` (query parameter) Sort direction: `asc` or `desc`. Defaults to `asc` for the endpoint's sort column and to `desc` when `order_by` names a metric (a top-N ranking). Applies to `order_by`, or to the endpoint's default sort field when `order_by` is omitted. - `"asc"` - `"desc"` - `order_by: Optional[str]` (query parameter) Sort field. Restricted to the endpoint's sort column plus its rankable metrics (metrics default to descending; a few metrics rank in date-range mode only, per the endpoint's documented orderable set). - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. - `starting_date: Optional[Union[null, null, null]]` (query parameter) UTC date in YYYY-MM-DD format. Start of a date range (inclusive). Enables rollup mode: one row per entity aggregated over the whole range — addable counters are summed across days, and a distinct count is never summed where summing could double-count (a field's range value is recomputed exactly over the window, approximate via HLL with typical error under 2%, null, or — for the creation-event counts, whose per-day values cannot overlap — a per-day sum that is itself exact; each field's own description says which). Use either `date` or `starting_date`, not both. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01. format: date #### Returns - `class BetaAnalyticsSkillActivity` Per-skill activity data for a given day. - `chat_metrics: BetaAnalyticsSkillChatMetrics` Claude.ai activity metrics for a single skill on a given day. - `distinct_conversation_skill_used_count: Optional[int]` Number of distinct conversations in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `claude_code_metrics: BetaAnalyticsSkillClaudeCodeMetrics` Claude Code activity metrics for a single skill on a given day. - `distinct_session_skill_used_count: Optional[int]` Number of distinct Claude Code sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `cowork_metrics: BetaAnalyticsSkillCoworkMetrics` Cowork activity metrics for a single skill on a given day. - `distinct_session_skill_used_count: Optional[int]` Number of distinct Cowork sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `distinct_user_count: int` Number of distinct users who used the skill on the requested day, or, in date-range mode, over the requested window — recomputed as an exact distinct count over the window's per-member daily rows, never a sum of per-day values. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. - `office_metrics: BetaAnalyticsSkillOfficeMetrics` Office Agent activity metrics for a single skill on a given day, broken out by Office product. - `excel: BetaAnalyticsSkillOfficeProductMetrics` Office Agent activity metrics for a single skill on a given day within one Office product. - `distinct_session_skill_used_count: Optional[int]` Number of distinct Office Agent sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `outlook: BetaAnalyticsSkillOfficeProductMetrics` Office Agent activity metrics for a single skill on a given day within one Office product. - `powerpoint: BetaAnalyticsSkillOfficeProductMetrics` Office Agent activity metrics for a single skill on a given day within one Office product. - `word: BetaAnalyticsSkillOfficeProductMetrics` Office Agent activity metrics for a single skill on a given day within one Office product. - `skill_name: str` Name of the skill - `attributed_list_price: Optional[str]` List-price (rate-card) value of the member requests attributed to this skill, as a decimal string in the minor unit of `currency` (cents for USD), from Claude Code, Cowork, and Office Agent request-level attribution — the value of requests that involved the skill, not the skill's incremental cost. Unlike `estimated_overage_spend` this reflects usage value regardless of how it was funded — seat-covered usage counts — but it is undiscounted and does not tie to billed spend or the organization's spend reporting. claude.ai chat usage carries no request-level attribution and contributes nothing: the field is null on `chat` product rows and on `office_agent` product cuts dated before 2026-06-18 (the Office Agent attribution data-start), and on ungrouped rows it covers the Claude Code + Cowork + Office Agent share only (null when no attributable usage exists). Also null under the same conditions as `estimated_overage_spend` (spend reporting not enabled for this organization, `office_agent` product cuts before the 2026-06-18 data-start). "0" means attributable usage existed but none was attributed to this skill. Addable across days: date-range rollup mode returns the window's sum. On `group_by[]` and `filter[]` shapes both amounts can total below the ungrouped value for the same skill over the same date or range: spend attributed to a member–skill pair with no counted usage on that day is excluded from those cuts. - `chat_cowork_unified_metrics: Optional[ChatCoworkUnifiedMetrics]` Skill use recorded while members had Chat and Cowork unified (Cowork's features inside claude.ai chat) turned on, split into chat conversations and Cowork sessions. A count is null in date-range mode where it cannot be computed. Omitted from the response on deployments that do not offer Chat and Cowork unified. - `chat: BetaAnalyticsSkillChatCoworkUnifiedChatMetrics` A skill's use in chat conversations recorded while members had Chat and Cowork unified turned on. - `distinct_conversation_skill_used_count: Optional[int]` Same measure as `chat_metrics.distinct_conversation_skill_used_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `sessions: BetaAnalyticsSkillChatCoworkUnifiedSessionsMetrics` A skill's use in Cowork sessions recorded while members had Chat and Cowork unified turned on. - `distinct_session_skill_used_count: Optional[int]` Same measure as `cowork_metrics.distinct_session_skill_used_count`, for activity recorded while members had Chat and Cowork unified turned on. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed. - `currency: Optional[str]` Currency for this row's monetary fields (`estimated_overage_spend` and `attributed_list_price`), as an uppercase ISO-4217 code. Always "USD" when either amount is populated; null whenever both amounts are null. - `enable_count: Optional[int]` Distinct accounts that enabled this skill on the requested day (claude.ai only — the skill analog of plugin `install_count`). The count is org-wide: null when enable reporting is not enabled for this organization, or when the request scopes to `user_id` / `rbac_group_id` / `product` via `group_by[]` or `filter[]` (an org-wide count would be misleading on per-cut rows). A distinct count, not an event count: summing across days double-counts members who enable the skill on more than one day, so it is also null in date-range rollup mode (`starting_date`/`ending_date`). - `estimated_overage_spend: Optional[str]` Estimated overage spend attributed to this skill, as a decimal string in the minor unit of `currency` (cents for USD; "1250" is $12.50, fractional cents possible) — an allocation of each member's daily post-discount, pre-credit metered overage spend (the same cost basis as the organization's spend reporting and the Cost & Usage API, so per-skill figures are directly comparable; spend with no skill attribution — including any member-day without skill invocations — is not represented, so skill rows sum to at most those totals) across the skills the member used. Overage only: usage covered by included seat allowances bills nothing and allocates $0 here — see `attributed_list_price` for the funding-independent usage-value companion. Claude Code, Cowork, and Office Agent spend use request-level skill attribution; claude.ai chat spend is approximated proportionally to skill-invoking messages. An estimate, not a billing number — and the cost of the requests/messages that involved the skill, not the skill's incremental cost (the same request would still have cost something without the skill active). "0" means no overage spend was attributed; null when spend reporting is not enabled for this organization, on `office_agent` product cuts dated before 2026-06-18 (the Office Agent attribution data-start). Addable across days: date-range rollup mode (`starting_date`/`ending_date`) returns the window's sum. With `group_by[]=user_id` each row carries the user's own attributed spend. On `group_by[]` and `filter[]` shapes both amounts can total below the ungrouped value for the same skill over the same date or range: spend attributed to a member–skill pair with no counted usage on that day is excluded from those cuts. - `invocation_count: Optional[int]` Total number of times this skill was invoked on the requested day (the skill analog of plugin `invocation_count`). Unlike `distinct_user_count` — which answers '\# of users' — this is the true '# of uses'. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Null when invocation reporting is not enabled for this organization. Sum across a date range for total uses in the window — date-range rollup mode (`starting_date`/`ending_date`) returns this sum directly. - `product: Optional[str]` Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, `office_agent`, or `chat_cowork_unified` (Chat and Cowork unified). These are the canonical Cost & Usage product names; an `office_agent` row's per-surface breakdown is in its `office_metrics`. On `/plugins` only `cowork`, `claude_code` and `chat_cowork_unified` occur (the only surfaces with plugin attribution); on `/artifacts` only `chat`, `claude_code`, `cowork` and `chat_cowork_unified` occur (the surfaces that create artifacts); `/apps/chat/projects` does not support the product dimension (a `product` entry in `group_by[]` or `filter[]` there is rejected). Present only when the request grouped by `product`. - `rbac_group_id: Optional[str]` Tagged RBAC group identifier (`rbac_group_...`), matching the spend-limits API spelling. Present only when the request grouped by `rbac_group_id`. - `rbac_group_name: Optional[str]` Resolved RBAC group display name, alongside `rbac_group_id` when name resolution is available. Null if the group has been deleted or its name could not be resolved; `rbac_group_id` remains the stable key. - `share_status: Optional[Literal["organization", "private", "public"]]` Skill share status (claude.ai only): one of `private`, `organization`, or `public`. Null for skills used only in Claude Code or Office (no per-skill share-status concept) and when share-status reporting is not yet available for the organization. Filterable via `filter[]=share_status:{value}`. - `"organization"` - `"private"` - `"public"` - `skill_display_name: Optional[str]` Human-readable display name for rows whose `skill_name` is an opaque skill id (user/organization skill types and plugin-delivered skills, whose user-defined names usage reports generally withhold). Organization-shared skills and skills delivered by the organization's own plugins (its plugin marketplaces and its library) resolve; plugin skill names are shown without their 'plugin:' prefix. The literal 'unknown' bucket row gets a fixed 'Unknown skill' label. For a member's own skill (private or personal-plugin) it is null, except when the skill's owner used it from Claude Code or Cowork in the requested period: then it shows the name that client reported at the time. Apart from that, the names of members' own skills are not disclosed to analytics-key holders. Also null for Anthropic-provided plugin skills (not resolved), for an organization skill or plugin whose name can no longer be found (for example, one since deleted), when `skill_name` is already a display name, or when display-name resolution is not enabled for this organization. - `user_id: Optional[str]` Tagged user identifier (e.g. `user_...`). Present only when the request grouped by `user_id`. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.analytics.skills.list() page = page.data[0] print(page.rbac_group_id) ``` ##### Response (200) ```json { "data": [ { "chat_metrics": { "distinct_conversation_skill_used_count": 0 }, "claude_code_metrics": { "distinct_session_skill_used_count": 0 }, "cowork_metrics": { "distinct_session_skill_used_count": 0 }, "distinct_user_count": 0, "office_metrics": { "excel": { "distinct_session_skill_used_count": 0 }, "outlook": { "distinct_session_skill_used_count": 0 }, "powerpoint": { "distinct_session_skill_used_count": 0 }, "word": { "distinct_session_skill_used_count": 0 } }, "skill_name": "skill_name", "attributed_list_price": "attributed_list_price", "chat_cowork_unified_metrics": { "chat": { "distinct_conversation_skill_used_count": 0 }, "sessions": { "distinct_session_skill_used_count": 0 } }, "currency": "currency", "enable_count": 0, "estimated_overage_spend": "estimated_overage_spend", "invocation_count": 0, "product": "product", "rbac_group_id": "rbac_group_id", "rbac_group_name": "rbac_group_name", "share_status": "organization", "skill_display_name": "skill_display_name", "user_id": "user_id" } ], "next_page": "next_page" } ``` ## Beta › Organization › Analytics › Artifacts ### Get Artifact Activity `beta.organization.analytics.artifacts.list(**kwargs) -> SyncPageCursor[BetaAnalyticsArtifactActivity]` **GET** `/v1/organizations/analytics/artifacts` Get artifact-creation activity for a given day, broken out by MIME type. Returns the full (`artifact_type`, `is_shared`) cube for the organization; `next_page` is null except for grouped queries, which paginate. The cube can be broken out per product, per member, or per RBAC group via `group_by[]`, and scoped via `filter[]`. Requires an API key with the `read:analytics` scope. #### Parameters - `date: Union[null, null]` (query parameter) UTC date in YYYY-MM-DD format. The day to get artifact activity for. Data is typically available with a 1-day lag (varies by query; the error for a too-recent date names the latest available day) and may be revised by a few percent over the following days. No earlier than 2026-01-01. format: date - `filter: Optional[Sequence[str]]` (query parameter) Filters as `dimension:value`, e.g. `filter[]=rbac_group_id:{id}`. Repeat the param for OR within a dimension and across dimensions for AND. Supported dimensions on this endpoint: `artifact_type`, `is_shared`, `product`, `rbac_group_id`, `user_id`. Value forms: `artifact_type` is a canonical artifact MIME type (e.g. `text/markdown`) or `other`; `is_shared` is `true` or `false`; `product` is `chat_cowork_unified`, `chat`, `claude_code`, or `cowork` (the surfaces that create artifacts); `rbac_group_id` takes the tagged id (`rbac_group_...`, as emitted in responses and by the spend-limits API) or a bare group UUID, and matches users who held the group at any point during each covered UTC day (time-of-usage attribution); `user_id` takes a tagged user id (`user_...`), as emitted in responses. An unsupported dimension returns 400. At most 100 entries. `chat_cowork_unified` is accepted as a `product` value only on deployments that offer Chat and Cowork unified. maxItems: 100 - `group_by: Optional[List[Literal["product", "rbac_group_id", "user_id"]]]` (query parameter) Dimensions to break results out by: `product`, `user_id` and/or `rbac_group_id`. The ungrouped artifact-type cube is finite and returned in full; grouped queries multiply the cube and paginate via `next_page`. `product` takes the values `chat_cowork_unified`, `chat`, `claude_code`, or `cowork` (the surfaces that create artifacts). `rbac_group_id` attributes a user to every group they held at any point during the requested UTC day, so grouped rows are not an exclusive partition. At most 100 entries. maxItems: 100 - `"product"` - `"rbac_group_id"` - `"user_id"` - `limit: Optional[int]` (query parameter) Maximum rows to return (1-1000, default 100). The ungrouped artifact-type cube is finite and returned in full; `limit` is the page size only when `group_by[]` multiplies the cube. minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. Only valid with `group_by[]` — the ungrouped cube is never paginated. #### Returns - `class BetaAnalyticsArtifactActivity` Artifact-creation activity for one (`artifact_type`, `is_shared`) bucket on a given day. Artifacts form a small finite cube — the canonical MIME type (8 values incl. `other`) crossed with shared-vs-private — so the response is the full set of non-empty buckets, not a ranked/paginated list. Claude Code and Cowork artifacts report under `text/html` and are counted from 2026-08-17 onward; earlier days contain claude.ai chat artifacts only. With `group_by[]=product` / `user_id` / `rbac_group_id` each row is further split by the flat group keys and counts are scoped to that cut. - `artifact_type: str` Canonical artifact MIME type (e.g. `text/markdown`, `application/vnd.ant.react`, `image/svg+xml`), or `other`. Claude Code and Cowork artifacts report as `text/html`. - `artifacts_created_count: int` Number of artifacts created in this bucket on the requested day - `distinct_user_count: int` Number of distinct users who created artifacts in this bucket on the requested day - `is_shared: bool` Whether the artifacts in this bucket have ever been shared (a Claude Code / Cowork artifact is shared once anyone beyond its creator may open it: named members, the whole organization, or anyone with the link). - `published_artifacts_created_count: int` Number of those artifacts that have been published (for Claude Code / Cowork artifacts: open to anyone with the link); never exceeds `artifacts_created_count` - `product: Optional[str]` Product that produced this row's activity: one of `chat`, `claude_code`, `cowork`, `office_agent`, or `chat_cowork_unified` (Chat and Cowork unified). These are the canonical Cost & Usage product names; an `office_agent` row's per-surface breakdown is in its `office_metrics`. On `/plugins` only `cowork`, `claude_code` and `chat_cowork_unified` occur (the only surfaces with plugin attribution); on `/artifacts` only `chat`, `claude_code`, `cowork` and `chat_cowork_unified` occur (the surfaces that create artifacts); `/apps/chat/projects` does not support the product dimension (a `product` entry in `group_by[]` or `filter[]` there is rejected). Present only when the request grouped by `product`. - `rbac_group_id: Optional[str]` Tagged RBAC group identifier (`rbac_group_...`), matching the spend-limits API spelling. Present only when the request grouped by `rbac_group_id`. - `rbac_group_name: Optional[str]` Resolved RBAC group display name, alongside `rbac_group_id` when name resolution is available. Null if the group has been deleted or its name could not be resolved; `rbac_group_id` remains the stable key. - `user_id: Optional[str]` Tagged user identifier (e.g. `user_...`). Present only when the request grouped by `user_id`. #### Example ```python import os from datetime import date from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.analytics.artifacts.list( date=date.fromisoformat("2019-12-27"), ) page = page.data[0] print(page.rbac_group_id) ``` ##### Response (200) ```json { "data": [ { "artifact_type": "artifact_type", "artifacts_created_count": 0, "distinct_user_count": 0, "is_shared": true, "published_artifacts_created_count": 0, "product": "product", "rbac_group_id": "rbac_group_id", "rbac_group_name": "rbac_group_name", "user_id": "user_id" } ], "next_page": "next_page" } ``` ## Beta › Organization › Analytics › Usage Report ### Get Token Usage Over Time `beta.organization.analytics.usage_report.list(**kwargs) -> SyncPageCursor[BetaAnalyticsUsageReportTimeBucket]` **GET** `/v1/organizations/analytics/usage_report` Get token usage over time across a date range. Returns token usage bucketed by minute, hour, or day, optionally broken down by product, model, context window, inference region, or speed. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope. #### Parameters - `starting_at: Union[str, datetime]` (query parameter) Start of range, inclusive. RFC 3339 tz-aware. Must be within the last 365 days and no earlier than 2026-01-01T00:00:00Z. format: date-time - `bucket_width: Optional[Literal["1d", "1h", "1m"]]` (query parameter) Time bucket granularity. default: 1d - `"1d"` - `"1h"` - `"1m"` - `claude_tag_categories: Optional[List[BetaAnalyticsClaudeTagCategory]]` (query parameter) Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `claude-tag`, so combining this filter with `products[]=claude-tag` excludes it. Use `group_by[]=claude_tag_category` to break out per-category values. maxItems: 100 - `"dm"` - `"engaged"` - `"monitoring"` - `"proactive"` - `"scheduled"` - `claude_tag_user_ids: Optional[Sequence[str]]` (query parameter) Filter to Claude Tag (Claude in Slack) usage attributed to specific Slack users, by Slack user ID (for example `U0123ABCDEF`), not claude.ai user ID. Usage that is not Claude Tag, and Claude Tag usage not attributed to a single user, never matches. Use `group_by[]=claude_tag_user_id` to break out per-user values. maxItems: 100 - `context_windows: Optional[List[BetaAnalyticsContextWindow]]` (query parameter) Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values. maxItems: 100 - `"0-200k"` - `"200k-1M"` - `ending_at: Optional[Union[str, datetime, null]]` (query parameter) End of range, exclusive. When omitted, defaults to the earlier of now and `starting_at` + 31 days. The range may span at most 31 days. format: date-time - `group_by: Optional[List[Literal["claude_tag_category", "claude_tag_user_id", "context_window", 6 more]]]` (query parameter) Dimensions to break each time bucket out by. Defaults to no grouping (one total per bucket). Each bucket reports at most its top 100 groups; a group beyond that cap has no row in that bucket (there is no remainder row), so grouped buckets are not exhaustive when a dimension has more than 100 distinct values. maxItems: 100 - `"claude_tag_category"` - `"claude_tag_user_id"` - `"context_window"` - `"inference_geo"` - `"model"` - `"product"` - `"rbac_group_id"` - `"slack_channel_id"` - `"speed"` - `inference_geos: Optional[List[BetaAnalyticsInferenceGeoFilter]]` (query parameter) Filter to specific inference regions. `not_available` matches rows where the region is unset. Use `group_by[]=inference_geo` to break out per-region values. maxItems: 100 - `"global"` - `"not_available"` - `"us"` - `limit: Optional[int]` (query parameter) Maximum number of time buckets per page. Defaults and caps vary by `bucket_width` (`1d`: default 7, max 31; `1h`: default 24, max 168; `1m`: default 60, max 256). minimum: 1 - `models: Optional[Sequence[str]]` (query parameter) Models to include. Defaults to all models. Use `group_by[]=model` to break out per-model values. maxItems: 100 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. - `products: Optional[List[BetaAnalyticsProductFilter]]` (query parameter) Product surfaces to include. Defaults to all products. Use `group_by[]=product` to break out per-product values. maxItems: 100 - `"chat"` - `"chat_cowork_unified"` - `"claude-tag"` - `"claude_code"` - `"claude_design"` - `"claude_in_chrome"` - `"cowork"` - `"office_agent"` - `rbac_group_ids: Optional[Sequence[str]]` (query parameter) Filter to usage attributed to specific RBAC groups. Accepts tagged RBAC group IDs (`rbac_group_...`) or bare group UUIDs. A row matches when the user belonged to any of the listed groups on the (UTC) day the usage occurred; usage with no group attribution never matches. maxItems: 100 - `slack_channel_ids: Optional[Sequence[str]]` (query parameter) Filter to usage originating from specific Slack channels. Use `group_by[]=slack_channel_id` to break out per-channel values. maxItems: 100 - `speeds: Optional[List[Literal["fast", "standard"]]]` (query parameter) Filter to fast or standard inference mode. Use `group_by[]=speed` to break out per-mode values. maxItems: 100 - `"fast"` - `"standard"` - `user_ids: Optional[Sequence[str]]` (query parameter) Filter to specific users by tagged user ID. maxItems: 100 #### Returns - `class BetaAnalyticsUsageReportTimeBucket` - `ending_at: datetime` End of the time bucket (exclusive) in RFC 3339 format. format: date-time - `results: List[BetaAnalyticsUsageBucketedResult]` Rows for this time bucket. Empty when the bucket has no data; otherwise a single combined row when `group_by[]` is omitted, or one row per group (subject to the per-bucket group cap described on the `group_by[]` parameter). - `cache_creation: BetaCacheCreation` The number of input tokens for cache creation. - `ephemeral_1h_input_tokens: int` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: int` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_read_input_tokens: int` The number of input tokens read from the cache. - `claude_tag_category: Optional[BetaAnalyticsClaudeTagCategory]` Claude Tag (Claude in Slack) spend category: `engaged` (a person addressed Claude in a channel or thread), `proactive` (Claude responded without being addressed), `scheduled` (a scheduled routine ran), `monitoring` (Claude watching a channel it was asked to monitor), or `dm` (direct messages with Claude). Populated only when `claude_tag_category` is in `group_by[]`; null for usage that is not Claude Tag. Direct-message usage is billed to the individual user and is reported under that user's product, not under `claude-tag`. New categories may be added over time. - `"dm"` - `"engaged"` - `"monitoring"` - `"proactive"` - `"scheduled"` - `claude_tag_user_id: Optional[str]` Slack user ID (for example `U0123ABCDEF`) of the member the Claude Tag (Claude in Slack) usage is attributed to, not a claude.ai user ID. Populated only when `claude_tag_user_id` is in `group_by[]`; null for usage that is not Claude Tag and for Claude Tag usage that is not attributed to a single user (for example `monitoring`, and `proactive` usage Claude initiated), so per-user rows can sum to less than the Claude Tag total. Cannot be combined with `group_by[]=rbac_group_id` or the `rbac_group_ids[]` filter. - `context_window: Optional[BetaAnalyticsContextWindow]` Context-window pricing tier of the usage or cost. Null unless `context_window` is in `group_by[]`; it can also be null on grouped rows with no context-window tier, such as code execution. - `"0-200k"` - `"200k-1M"` - `inference_geo: Optional[Literal["global", "us"]]` Inference region of the usage or cost. Null unless `inference_geo` is in `group_by[]`; it can also be null on grouped rows where the region is not set (the rows that `inference_geos[]=not_available` matches). - `"global"` - `"us"` - `model: Optional[str]` Model that produced the usage or cost, as a model name in the form the `models[]` filter accepts (for example, `claude-opus-5`). Null unless `model` is in `group_by[]`; it can also be null on grouped rows whose usage or cost is not attributed to a specific model, such as code execution. - `output_tokens: int` The number of output tokens generated. - `product: Optional[str]` Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface. Values include `chat`, `claude_code`, `cowork`, `office_agent`, `claude_in_chrome`, `claude_design`, `claude-tag`, and `chat_cowork_unified`. `claude-tag` is Claude Tag, the Claude product in Slack. `chat_cowork_unified` is Chat and Cowork unified, Cowork's features inside claude.ai chat: chat and Cowork usage by a member who has it turned on is reported under this value instead of `chat` or `cowork`. It is accepted as a filter only on deployments that offer Chat and Cowork unified. Some unattributed usage is reported as "other". - `rbac_group_id: Optional[str]` RBAC group (team) the usage is attributed to, in the public tagged `rbac_group_...` spelling — the same spelling the activity resources use for this key, so the same team has one id across resources and it round-trips as an `rbac_group_ids[]` filter value. Populated only when `rbac_group_id` is in `group_by[]`. Any-membership semantics: a user in several groups contributes their full usage to each of those groups' rows, so the named-group rows overlap and their sum can exceed the org total. A null value is the single unassigned row: users in no group on that (UTC) day. For the true org total, run the same query without `group_by[]`. - `requests: Optional[int]` Number of API requests in this row's scope. For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`). - `server_tool_use: BetaAnalyticsServerToolUse` Server-side tool usage metrics. - `web_search_requests: int` The number of web search requests made. - `slack_channel_id: Optional[str]` Slack channel the usage originated from. Populated only when `slack_channel_id` is in `group_by[]`; null for usage outside Slack (and for rows recorded before channel attribution was enabled). - `speed: Optional[Literal["fast", "standard"]]` Inference speed mode of the usage or cost: `fast` or `standard`. Null unless `speed` is in `group_by[]`. - `"fast"` - `"standard"` - `uncached_input_tokens: int` The number of uncached input tokens processed. - `starting_at: datetime` Start of the time bucket (inclusive) in RFC 3339 format. format: date-time #### Example ```python import os from datetime import datetime from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.analytics.usage_report.list( starting_at=datetime.fromisoformat("2019-12-27T18:11:19.117"), ) page = page.data[0] print(page.ending_at) ``` ##### Response (200) ```json { "data": [ { "ending_at": "2019-12-27T18:11:19.117Z", "results": [ { "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_read_input_tokens": 0, "claude_tag_category": "dm", "claude_tag_user_id": "U0123ABCDEF", "context_window": "0-200k", "inference_geo": "global", "model": "claude-opus-5", "output_tokens": 0, "product": "chat", "rbac_group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "requests": 0, "server_tool_use": { "web_search_requests": 10 }, "slack_channel_id": "C0123ABCDEF", "speed": "fast", "uncached_input_tokens": 0 } ], "starting_at": "2019-12-27T18:11:19.117Z" } ], "data_refreshed_at": "2019-12-27T18:11:19.117Z", "has_more": true, "next_page": "next_page", "organization_id": "org_013FP9SaFPBg7Kw7fetjn6cF" } ``` ## Beta › Organization › Analytics › User Usage Report ### Get Per-User Token Usage `beta.organization.analytics.user_usage_report.list(**kwargs) -> SyncPageCursor[BetaAnalyticsUsageUsersItem]` **GET** `/v1/organizations/analytics/user_usage_report` Get per-user token usage across a date range. Returns one row per user, ranked by the chosen token metric. Use this to see which users consume the most tokens. Only usage attributable to a seat user is included; for organization-wide totals including direct API-key and automation traffic, use the bucketed `/v1/organizations/analytics/usage_report` endpoint. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope. #### Parameters - `starting_at: Union[str, datetime]` (query parameter) Start of range, inclusive. RFC 3339 tz-aware. Must be within the last 365 days and no earlier than 2026-01-01T00:00:00Z. format: date-time - `bucket_width: Optional[Literal["1d", "1h", "1m"]]` (query parameter) Time-bucket granularity. When set, each row's `starting_at` and `ending_at` are populated and one actor may span several rows (one per time bucket with usage). The time bucket counts toward `limit`, so one page can return multiple rows for the same actor. `ending_at` is required when `bucket_width` is set, and with `bucket_width="1m"` the range may span at most 24 hours. When omitted, each row aggregates the full `[starting_at, ending_at)` range. - `"1d"` - `"1h"` - `"1m"` - `claude_tag_categories: Optional[List[BetaAnalyticsClaudeTagCategory]]` (query parameter) Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `claude-tag`, so combining this filter with `products[]=claude-tag` excludes it. Use `group_by[]=claude_tag_category` to break out per-category values. maxItems: 100 - `"dm"` - `"engaged"` - `"monitoring"` - `"proactive"` - `"scheduled"` - `claude_tag_user_ids: Optional[Sequence[str]]` (query parameter) Filter to Claude Tag (Claude in Slack) usage attributed to specific Slack users, by Slack user ID (for example `U0123ABCDEF`), not claude.ai user ID. Usage that is not Claude Tag, and Claude Tag usage not attributed to a single user, never matches. Use `group_by[]=claude_tag_user_id` to break out per-user values. maxItems: 100 - `context_windows: Optional[List[BetaAnalyticsContextWindow]]` (query parameter) Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values. maxItems: 100 - `"0-200k"` - `"200k-1M"` - `ending_at: Optional[Union[str, datetime, null]]` (query parameter) End of range, exclusive. When omitted, defaults to the earlier of now and `starting_at` + 31 days. The range may span at most 31 days. format: date-time - `exclude_deleted_users: Optional[bool]` (query parameter) If true, omit rows for users who are deleted (`deleted: true`). A page may contain fewer than `limit` rows; use `has_more` and `next_page` to paginate as usual. default: false - `group_by: Optional[List[Literal["claude_tag_category", "claude_tag_user_id", "context_window", 6 more]]]` (query parameter) Break each actor's row out by the given dimensions. Accepts the same values as the bucketed `/usage_report` endpoint. `limit` bounds (actor × time bucket × dimension) rows — with dimensions or `bucket_width` present, one actor may span several rows. maxItems: 100 - `"claude_tag_category"` - `"claude_tag_user_id"` - `"context_window"` - `"inference_geo"` - `"model"` - `"product"` - `"rbac_group_id"` - `"slack_channel_id"` - `"speed"` - `inference_geos: Optional[List[BetaAnalyticsInferenceGeoFilter]]` (query parameter) Filter to specific inference regions. `not_available` matches rows where the region is unset. Use `group_by[]=inference_geo` to break out per-region values. maxItems: 100 - `"global"` - `"not_available"` - `"us"` - `limit: Optional[int]` (query parameter) Number of rows per page (1-1000, default 20). One row per actor unless `group_by[]` or `bucket_width` splits an actor across rows; `cost_type`/`token_type` fan-out rows (cost endpoint only) are the exception — they do not count toward this limit, so `data` can exceed it. default: 20, minimum: 1, maximum: 1000 - `models: Optional[Sequence[str]]` (query parameter) Models to include. Defaults to all models. Use `group_by[]=model` to break out per-model values. maxItems: 100 - `order: Optional[Literal["asc", "desc"]]` (query parameter) Sort direction. Defaults to `desc`. default: desc - `"asc"` - `"desc"` - `order_by: Optional[Literal["output_tokens", "requests", "total_tokens", "uncached_input_tokens"]]` (query parameter) Metric to rank actors by. Defaults to `total_tokens`. default: total_tokens - `"output_tokens"` - `"requests"` - `"total_tokens"` - `"uncached_input_tokens"` - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. - `products: Optional[List[BetaAnalyticsProductFilter]]` (query parameter) Product surfaces to include. Defaults to all products. maxItems: 100 - `"chat"` - `"chat_cowork_unified"` - `"claude-tag"` - `"claude_code"` - `"claude_design"` - `"claude_in_chrome"` - `"cowork"` - `"office_agent"` - `rbac_group_ids: Optional[Sequence[str]]` (query parameter) Filter to usage attributed to specific RBAC groups. Accepts tagged RBAC group IDs (`rbac_group_...`) or bare group UUIDs. A row matches when the user belonged to any of the listed groups on the (UTC) day the usage occurred; usage with no group attribution never matches. maxItems: 100 - `slack_channel_ids: Optional[Sequence[str]]` (query parameter) Filter to usage originating from specific Slack channels. Use `group_by[]=slack_channel_id` to break out per-channel values. maxItems: 100 - `speeds: Optional[List[Literal["fast", "standard"]]]` (query parameter) Filter to fast or standard inference mode. Use `group_by[]=speed` to break out per-mode values. maxItems: 100 - `"fast"` - `"standard"` - `user_ids: Optional[Sequence[str]]` (query parameter) Filter to specific users by tagged user ID. maxItems: 100 #### Returns - `class BetaAnalyticsUsageUsersItem` - `actor: BetaAnalyticsUserActor` The user this row's usage or cost is attributed to. Always a `user_actor`. - `type: Literal["user_actor"]` Actor type. Always `"user_actor"`. - `deleted: bool` True when the account has been deleted, or when the user is no longer a member of the organization or its associated organizations (for example, their membership was removed or they were deprovisioned via your identity provider). `email_address` stays populated for removed users and is null when the account has been deleted. `name` follows the rules described on that field. The `user_id` is still populated for reconciliation. - `email_address: Optional[str]` The user's email address, including for users who are no longer members of the organization or its associated organizations. Null when the account has been deleted (check `deleted`) and for system-minted service accounts, which have no person's mailbox behind them (check `name`). - `name: Optional[str]` The user's full name. Null when the user has not set a name. Returns `"Deleted User"` when the account itself has been deleted, or when the user is no longer a member of the organization or its associated organizations and the organization has chosen to hide the names of removed users. Otherwise, the name stays populated for removed users. Rows for system-minted service accounts render the service name (for example, `"Claude Security"` for usage by Anthropic's security-patching service) or null. - `user_id: str` Tagged user ID. - `cache_creation: BetaCacheCreation` The number of input tokens for cache creation. - `ephemeral_1h_input_tokens: int` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: int` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_read_input_tokens: int` The number of input tokens read from the cache. - `claude_tag_category: Optional[BetaAnalyticsClaudeTagCategory]` Claude Tag (Claude in Slack) spend category: `engaged` (a person addressed Claude in a channel or thread), `proactive` (Claude responded without being addressed), `scheduled` (a scheduled routine ran), `monitoring` (Claude watching a channel it was asked to monitor), or `dm` (direct messages with Claude). Populated only when `claude_tag_category` is in `group_by[]`; null for usage that is not Claude Tag. Direct-message usage is billed to the individual user and is reported under that user's product, not under `claude-tag`. New categories may be added over time. - `"dm"` - `"engaged"` - `"monitoring"` - `"proactive"` - `"scheduled"` - `claude_tag_user_id: Optional[str]` Slack user ID (for example `U0123ABCDEF`) of the member the Claude Tag (Claude in Slack) usage is attributed to, not a claude.ai user ID. Populated only when `claude_tag_user_id` is in `group_by[]`; null for usage that is not Claude Tag and for Claude Tag usage that is not attributed to a single user (for example `monitoring`, and `proactive` usage Claude initiated), so per-user rows can sum to less than the Claude Tag total. Cannot be combined with `group_by[]=rbac_group_id` or the `rbac_group_ids[]` filter. - `context_window: Optional[BetaAnalyticsContextWindow]` Context-window pricing tier of the usage or cost. Null unless `context_window` is in `group_by[]`; it can also be null on grouped rows with no context-window tier, such as code execution. - `"0-200k"` - `"200k-1M"` - `ending_at: Optional[datetime]` End of the row's UTC time bucket (exclusive), as an RFC 3339 timestamp; equal to `starting_at` plus one `bucket_width`. Null unless `bucket_width` is set. format: date-time - `inference_geo: Optional[Literal["global", "us"]]` Inference region of the usage or cost. Null unless `inference_geo` is in `group_by[]`; it can also be null on grouped rows where the region is not set (the rows that `inference_geos[]=not_available` matches). - `"global"` - `"us"` - `model: Optional[str]` Model that produced the usage or cost, as a model name in the form the `models[]` filter accepts (for example, `claude-opus-5`). Null unless `model` is in `group_by[]`; it can also be null on grouped rows whose usage or cost is not attributed to a specific model, such as code execution. - `output_tokens: int` The number of output tokens generated. - `product: Optional[str]` Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface. Values include `chat`, `claude_code`, `cowork`, `office_agent`, `claude_in_chrome`, `claude_design`, `claude-tag`, and `chat_cowork_unified`. `claude-tag` is Claude Tag, the Claude product in Slack. `chat_cowork_unified` is Chat and Cowork unified, Cowork's features inside claude.ai chat: chat and Cowork usage by a member who has it turned on is reported under this value instead of `chat` or `cowork`. It is accepted as a filter only on deployments that offer Chat and Cowork unified. Some unattributed usage is reported as "other". - `rbac_group_id: Optional[str]` RBAC group (team) the usage is attributed to, in the public tagged `rbac_group_...` spelling — the same spelling the activity resources use for this key, so the same team has one id across resources and it round-trips as an `rbac_group_ids[]` filter value. Populated only when `rbac_group_id` is in `group_by[]`. Any-membership semantics: a user in several groups contributes their full usage to each of those groups' rows, so the named-group rows overlap and their sum can exceed the org total. A null value is the single unassigned row: users in no group on that (UTC) day. For the true org total, run the same query without `group_by[]`. - `requests: Optional[int]` Number of API requests in this row's scope. For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`). - `server_tool_use: BetaAnalyticsServerToolUse` Server-side tool usage metrics. - `web_search_requests: int` The number of web search requests made. - `slack_channel_id: Optional[str]` Slack channel the usage originated from. Populated only when `slack_channel_id` is in `group_by[]`; null for usage outside Slack (and for rows recorded before channel attribution was enabled). - `speed: Optional[Literal["fast", "standard"]]` Inference speed mode of the usage or cost: `fast` or `standard`. Null unless `speed` is in `group_by[]`. - `"fast"` - `"standard"` - `starting_at: Optional[datetime]` Start of the row's UTC time bucket (inclusive), as an RFC 3339 timestamp. Null unless `bucket_width` is set; without `bucket_width`, each row aggregates the full requested range. format: date-time - `total_tokens: int` Total token count across all token types. This is the value the default `order_by` (`total_tokens`) sorts on. - `uncached_input_tokens: int` The number of uncached input tokens processed. #### Example ```python import os from datetime import datetime from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.analytics.user_usage_report.list( starting_at=datetime.fromisoformat("2019-12-27T18:11:19.117"), ) page = page.data[0] print(page.claude_tag_user_id) ``` ##### Response (200) ```json { "data": [ { "actor": { "deleted": true, "email": "jane@example.com", "email_address": "jane@example.com", "name": "Jane Smith", "type": "user_actor", "user_id": "user_01AbCdEfGhIjKlMnOpQrSt" }, "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_read_input_tokens": 3200000, "claude_tag_category": "dm", "claude_tag_user_id": "U0123ABCDEF", "context_window": "0-200k", "ending_at": "2019-12-27T18:11:19.117Z", "inference_geo": "global", "model": "claude-opus-5", "output_tokens": 891000, "product": "chat", "rbac_group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "requests": 128, "server_tool_use": { "web_search_requests": 10 }, "slack_channel_id": "C0123ABCDEF", "speed": "fast", "starting_at": "2019-12-27T18:11:19.117Z", "total_tokens": 5377000, "uncached_input_tokens": 1284500 } ], "data_refreshed_at": "2019-12-27T18:11:19.117Z", "has_more": true, "next_page": "next_page", "organization_id": "org_013FP9SaFPBg7Kw7fetjn6cF" } ``` ## Beta › Organization › Analytics › Cost Report ### Get Cost Over Time `beta.organization.analytics.cost_report.list(**kwargs) -> SyncPageCursor[BetaAnalyticsCostReportTimeBucket]` **GET** `/v1/organizations/analytics/cost_report` Get cost in USD over time across a date range. Returns cost bucketed by minute, hour, or day, optionally broken down by product, model, context window, inference region, speed, cost type, or token type. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope. #### Parameters - `starting_at: Union[str, datetime]` (query parameter) Start of range, inclusive. RFC 3339 tz-aware. Must be within the last 365 days and no earlier than 2026-01-01T00:00:00Z. format: date-time - `bucket_width: Optional[Literal["1d", "1h", "1m"]]` (query parameter) Time bucket granularity. default: 1d - `"1d"` - `"1h"` - `"1m"` - `claude_tag_categories: Optional[List[BetaAnalyticsClaudeTagCategory]]` (query parameter) Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `claude-tag`, so combining this filter with `products[]=claude-tag` excludes it. Use `group_by[]=claude_tag_category` to break out per-category values. maxItems: 100 - `"dm"` - `"engaged"` - `"monitoring"` - `"proactive"` - `"scheduled"` - `claude_tag_user_ids: Optional[Sequence[str]]` (query parameter) Filter to Claude Tag (Claude in Slack) usage attributed to specific Slack users, by Slack user ID (for example `U0123ABCDEF`), not claude.ai user ID. Usage that is not Claude Tag, and Claude Tag usage not attributed to a single user, never matches. Use `group_by[]=claude_tag_user_id` to break out per-user values. maxItems: 100 - `context_windows: Optional[List[BetaAnalyticsContextWindow]]` (query parameter) Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values. maxItems: 100 - `"0-200k"` - `"200k-1M"` - `ending_at: Optional[Union[str, datetime, null]]` (query parameter) End of range, exclusive. When omitted, defaults to the earlier of now and `starting_at` + 31 days. The range may span at most 31 days. format: date-time - `group_by: Optional[List[Literal["claude_tag_category", "claude_tag_user_id", "context_window", 8 more]]]` (query parameter) Dimensions to break each time bucket out by. Defaults to no grouping (one total per bucket). Each bucket reports at most its top 100 groups; a group beyond that cap has no row in that bucket (there is no remainder row), so grouped buckets are not exhaustive when a dimension has more than 100 distinct values. maxItems: 100 - `"claude_tag_category"` - `"claude_tag_user_id"` - `"context_window"` - `"cost_type"` - `"inference_geo"` - `"model"` - `"product"` - `"rbac_group_id"` - `"slack_channel_id"` - `"speed"` - `"token_type"` - `inference_geos: Optional[List[BetaAnalyticsInferenceGeoFilter]]` (query parameter) Filter to specific inference regions. `not_available` matches rows where the region is unset. Use `group_by[]=inference_geo` to break out per-region values. maxItems: 100 - `"global"` - `"not_available"` - `"us"` - `limit: Optional[int]` (query parameter) Maximum number of time buckets per page. Defaults and caps vary by `bucket_width` (`1d`: default 7, max 31; `1h`: default 24, max 168; `1m`: default 60, max 256). minimum: 1 - `models: Optional[Sequence[str]]` (query parameter) Models to include. Defaults to all models. Use `group_by[]=model` to break out per-model values. maxItems: 100 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. - `products: Optional[List[BetaAnalyticsProductFilter]]` (query parameter) Product surfaces to include. Defaults to all products. Use `group_by[]=product` to break out per-product values. maxItems: 100 - `"chat"` - `"chat_cowork_unified"` - `"claude-tag"` - `"claude_code"` - `"claude_design"` - `"claude_in_chrome"` - `"cowork"` - `"office_agent"` - `rbac_group_ids: Optional[Sequence[str]]` (query parameter) Filter to usage attributed to specific RBAC groups. Accepts tagged RBAC group IDs (`rbac_group_...`) or bare group UUIDs. A row matches when the user belonged to any of the listed groups on the (UTC) day the usage occurred; usage with no group attribution never matches. maxItems: 100 - `slack_channel_ids: Optional[Sequence[str]]` (query parameter) Filter to usage originating from specific Slack channels. Use `group_by[]=slack_channel_id` to break out per-channel values. maxItems: 100 - `speeds: Optional[List[Literal["fast", "standard"]]]` (query parameter) Filter to fast or standard inference mode. Use `group_by[]=speed` to break out per-mode values. maxItems: 100 - `"fast"` - `"standard"` - `user_ids: Optional[Sequence[str]]` (query parameter) Filter to specific users by tagged user ID. maxItems: 100 #### Returns - `class BetaAnalyticsCostReportTimeBucket` - `ending_at: datetime` End of the time bucket (exclusive) in RFC 3339 format. format: date-time - `results: List[BetaAnalyticsCostBucketedResult]` Rows for this time bucket. Empty when the bucket has no data; otherwise a single combined row when `group_by[]` is omitted, or one row per group (subject to the per-bucket group cap described on the `group_by[]` parameter). - `amount: str` Amount (post-discount, pre-credit) in fractional cents. - `claude_tag_category: Optional[BetaAnalyticsClaudeTagCategory]` Claude Tag (Claude in Slack) spend category: `engaged` (a person addressed Claude in a channel or thread), `proactive` (Claude responded without being addressed), `scheduled` (a scheduled routine ran), `monitoring` (Claude watching a channel it was asked to monitor), or `dm` (direct messages with Claude). Populated only when `claude_tag_category` is in `group_by[]`; null for usage that is not Claude Tag. Direct-message usage is billed to the individual user and is reported under that user's product, not under `claude-tag`. New categories may be added over time. - `"dm"` - `"engaged"` - `"monitoring"` - `"proactive"` - `"scheduled"` - `claude_tag_user_id: Optional[str]` Slack user ID (for example `U0123ABCDEF`) of the member the Claude Tag (Claude in Slack) usage is attributed to, not a claude.ai user ID. Populated only when `claude_tag_user_id` is in `group_by[]`; null for usage that is not Claude Tag and for Claude Tag usage that is not attributed to a single user (for example `monitoring`, and `proactive` usage Claude initiated), so per-user rows can sum to less than the Claude Tag total. Cannot be combined with `group_by[]=rbac_group_id` or the `rbac_group_ids[]` filter. - `context_window: Optional[BetaAnalyticsContextWindow]` Context-window pricing tier of the usage or cost. Null unless `context_window` is in `group_by[]`; it can also be null on grouped rows with no context-window tier, such as code execution. - `"0-200k"` - `"200k-1M"` - `cost_type: Optional[BetaAnalyticsCostType]` Cost component when `group_by[]=cost_type`; null otherwise (amount is the combined total). - `"code_execution"` - `"tokens"` - `"web_search"` - `currency: str` Currency code for the cost amount. Currently always `"USD"`. default: USD - `inference_geo: Optional[Literal["global", "us"]]` Inference region of the usage or cost. Null unless `inference_geo` is in `group_by[]`; it can also be null on grouped rows where the region is not set (the rows that `inference_geos[]=not_available` matches). - `"global"` - `"us"` - `list_amount: str` List-price amount (pre-discount) in fractional cents. - `model: Optional[str]` Model that produced the usage or cost, as a model name in the form the `models[]` filter accepts (for example, `claude-opus-5`). Null unless `model` is in `group_by[]`; it can also be null on grouped rows whose usage or cost is not attributed to a specific model, such as code execution. - `product: Optional[str]` Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface. Values include `chat`, `claude_code`, `cowork`, `office_agent`, `claude_in_chrome`, `claude_design`, `claude-tag`, and `chat_cowork_unified`. `claude-tag` is Claude Tag, the Claude product in Slack. `chat_cowork_unified` is Chat and Cowork unified, Cowork's features inside claude.ai chat: chat and Cowork usage by a member who has it turned on is reported under this value instead of `chat` or `cowork`. It is accepted as a filter only on deployments that offer Chat and Cowork unified. Some unattributed usage is reported as "other". - `rbac_group_id: Optional[str]` RBAC group (team) the usage is attributed to, in the public tagged `rbac_group_...` spelling — the same spelling the activity resources use for this key, so the same team has one id across resources and it round-trips as an `rbac_group_ids[]` filter value. Populated only when `rbac_group_id` is in `group_by[]`. Any-membership semantics: a user in several groups contributes their full usage to each of those groups' rows, so the named-group rows overlap and their sum can exceed the org total. A null value is the single unassigned row: users in no group on that (UTC) day. For the true org total, run the same query without `group_by[]`. - `requests: Optional[int]` Number of API requests in this row's scope. Null when `group_by` includes `cost_type` or `token_type` (the count has no per-component attribution; read it from the ungrouped response). For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`). - `slack_channel_id: Optional[str]` Slack channel the usage originated from. Populated only when `slack_channel_id` is in `group_by[]`; null for usage outside Slack (and for rows recorded before channel attribution was enabled). - `speed: Optional[Literal["fast", "standard"]]` Inference speed mode of the usage or cost: `fast` or `standard`. Null unless `speed` is in `group_by[]`. - `"fast"` - `"standard"` - `token_type: Optional[BetaAnalyticsTokenType]` Token type when `group_by[]=token_type` and `cost_type=tokens`; null otherwise. - `"cache_creation.ephemeral_1h_input_tokens"` - `"cache_creation.ephemeral_5m_input_tokens"` - `"cache_read_input_tokens"` - `"output_tokens"` - `"uncached_input_tokens"` - `starting_at: datetime` Start of the time bucket (inclusive) in RFC 3339 format. format: date-time #### Example ```python import os from datetime import datetime from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.analytics.cost_report.list( starting_at=datetime.fromisoformat("2019-12-27T18:11:19.117"), ) page = page.data[0] print(page.ending_at) ``` ##### Response (200) ```json { "data": [ { "ending_at": "2019-12-27T18:11:19.117Z", "results": [ { "amount": "amount", "claude_tag_category": "dm", "claude_tag_user_id": "U0123ABCDEF", "context_window": "0-200k", "cost_type": "code_execution", "currency": "USD", "inference_geo": "global", "list_amount": "list_amount", "model": "claude-opus-5", "product": "chat", "rbac_group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "requests": 0, "slack_channel_id": "C0123ABCDEF", "speed": "fast", "token_type": "cache_creation.ephemeral_1h_input_tokens" } ], "starting_at": "2019-12-27T18:11:19.117Z" } ], "data_refreshed_at": "2019-12-27T18:11:19.117Z", "has_more": true, "next_page": "next_page", "organization_id": "org_013FP9SaFPBg7Kw7fetjn6cF" } ``` ## Beta › Organization › Analytics › User Cost Report ### Get Per-User Cost `beta.organization.analytics.user_cost_report.list(**kwargs) -> SyncPageCursor[BetaAnalyticsCostUsersItem]` **GET** `/v1/organizations/analytics/user_cost_report` Get per-user cost in USD across a date range. Returns one row per user, ranked by spend. Use this to see which users account for the most cost. Only cost attributable to a seat user is included; for organization-wide totals including direct API-key and automation traffic, use the bucketed `/v1/organizations/analytics/cost_report` endpoint. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope. #### Parameters - `starting_at: Union[str, datetime]` (query parameter) Start of range, inclusive. RFC 3339 tz-aware. Must be within the last 365 days and no earlier than 2026-01-01T00:00:00Z. format: date-time - `bucket_width: Optional[Literal["1d", "1h", "1m"]]` (query parameter) Time-bucket granularity. When set, each row's `starting_at` and `ending_at` are populated and one actor may span several rows (one per time bucket with usage). The time bucket counts toward `limit`, so one page can return multiple rows for the same actor. `ending_at` is required when `bucket_width` is set, and with `bucket_width="1m"` the range may span at most 24 hours. When omitted, each row aggregates the full `[starting_at, ending_at)` range. - `"1d"` - `"1h"` - `"1m"` - `claude_tag_categories: Optional[List[BetaAnalyticsClaudeTagCategory]]` (query parameter) Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `claude-tag`, so combining this filter with `products[]=claude-tag` excludes it. Use `group_by[]=claude_tag_category` to break out per-category values. maxItems: 100 - `"dm"` - `"engaged"` - `"monitoring"` - `"proactive"` - `"scheduled"` - `claude_tag_user_ids: Optional[Sequence[str]]` (query parameter) Filter to Claude Tag (Claude in Slack) usage attributed to specific Slack users, by Slack user ID (for example `U0123ABCDEF`), not claude.ai user ID. Usage that is not Claude Tag, and Claude Tag usage not attributed to a single user, never matches. Use `group_by[]=claude_tag_user_id` to break out per-user values. maxItems: 100 - `context_windows: Optional[List[BetaAnalyticsContextWindow]]` (query parameter) Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values. maxItems: 100 - `"0-200k"` - `"200k-1M"` - `ending_at: Optional[Union[str, datetime, null]]` (query parameter) End of range, exclusive. When omitted, defaults to the earlier of now and `starting_at` + 31 days. The range may span at most 31 days. format: date-time - `exclude_deleted_users: Optional[bool]` (query parameter) If true, omit rows for users who are deleted (`deleted: true`). A page may contain fewer than `limit` rows; use `has_more` and `next_page` to paginate as usual. default: false - `group_by: Optional[List[Literal["claude_tag_category", "claude_tag_user_id", "context_window", 8 more]]]` (query parameter) Break each actor's row out by the given dimensions. Accepts the same values as the bucketed `/cost_report` endpoint. The `product`, `model`, `context_window`, `inference_geo`, and `speed` dimensions — and the time bucket, when `bucket_width` is set — count toward `limit`. `cost_type` and `token_type` do not: `cost_type` returns one row per cost component (tokens, web search, code execution); `token_type` returns one row per token type, each with `cost_type: "tokens"`; combining both returns the per-token-type rows plus the web-search and code-execution rows. A page can therefore contain more rows than `limit` when `cost_type` or `token_type` is requested. maxItems: 100 - `"claude_tag_category"` - `"claude_tag_user_id"` - `"context_window"` - `"cost_type"` - `"inference_geo"` - `"model"` - `"product"` - `"rbac_group_id"` - `"slack_channel_id"` - `"speed"` - `"token_type"` - `inference_geos: Optional[List[BetaAnalyticsInferenceGeoFilter]]` (query parameter) Filter to specific inference regions. `not_available` matches rows where the region is unset. Use `group_by[]=inference_geo` to break out per-region values. maxItems: 100 - `"global"` - `"not_available"` - `"us"` - `limit: Optional[int]` (query parameter) Number of rows per page (1-1000, default 20). One row per actor unless `group_by[]` or `bucket_width` splits an actor across rows; `cost_type`/`token_type` fan-out rows (cost endpoint only) are the exception — they do not count toward this limit, so `data` can exceed it. default: 20, minimum: 1, maximum: 1000 - `models: Optional[Sequence[str]]` (query parameter) Models to include. Defaults to all models. Use `group_by[]=model` to break out per-model values. maxItems: 100 - `order: Optional[Literal["asc", "desc"]]` (query parameter) Sort direction. Defaults to `desc`. default: desc - `"asc"` - `"desc"` - `order_by: Optional[Literal["amount", "list_amount"]]` (query parameter) Metric to rank actors by. Defaults to `amount`. default: amount - `"amount"` - `"list_amount"` - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. - `products: Optional[List[BetaAnalyticsProductFilter]]` (query parameter) Product surfaces to include. Defaults to all products. maxItems: 100 - `"chat"` - `"chat_cowork_unified"` - `"claude-tag"` - `"claude_code"` - `"claude_design"` - `"claude_in_chrome"` - `"cowork"` - `"office_agent"` - `rbac_group_ids: Optional[Sequence[str]]` (query parameter) Filter to usage attributed to specific RBAC groups. Accepts tagged RBAC group IDs (`rbac_group_...`) or bare group UUIDs. A row matches when the user belonged to any of the listed groups on the (UTC) day the usage occurred; usage with no group attribution never matches. maxItems: 100 - `slack_channel_ids: Optional[Sequence[str]]` (query parameter) Filter to usage originating from specific Slack channels. Use `group_by[]=slack_channel_id` to break out per-channel values. maxItems: 100 - `speeds: Optional[List[Literal["fast", "standard"]]]` (query parameter) Filter to fast or standard inference mode. Use `group_by[]=speed` to break out per-mode values. maxItems: 100 - `"fast"` - `"standard"` - `user_ids: Optional[Sequence[str]]` (query parameter) Filter to specific users by tagged user ID. maxItems: 100 #### Returns - `class BetaAnalyticsCostUsersItem` - `actor: BetaAnalyticsUserActor` The user this row's usage or cost is attributed to. Always a `user_actor`. - `type: Literal["user_actor"]` Actor type. Always `"user_actor"`. - `deleted: bool` True when the account has been deleted, or when the user is no longer a member of the organization or its associated organizations (for example, their membership was removed or they were deprovisioned via your identity provider). `email_address` stays populated for removed users and is null when the account has been deleted. `name` follows the rules described on that field. The `user_id` is still populated for reconciliation. - `email_address: Optional[str]` The user's email address, including for users who are no longer members of the organization or its associated organizations. Null when the account has been deleted (check `deleted`) and for system-minted service accounts, which have no person's mailbox behind them (check `name`). - `name: Optional[str]` The user's full name. Null when the user has not set a name. Returns `"Deleted User"` when the account itself has been deleted, or when the user is no longer a member of the organization or its associated organizations and the organization has chosen to hide the names of removed users. Otherwise, the name stays populated for removed users. Rows for system-minted service accounts render the service name (for example, `"Claude Security"` for usage by Anthropic's security-patching service) or null. - `user_id: str` Tagged user ID. - `amount: str` Amount (post-discount, pre-credit) in fractional cents (minor units). - `claude_tag_category: Optional[BetaAnalyticsClaudeTagCategory]` Claude Tag (Claude in Slack) spend category: `engaged` (a person addressed Claude in a channel or thread), `proactive` (Claude responded without being addressed), `scheduled` (a scheduled routine ran), `monitoring` (Claude watching a channel it was asked to monitor), or `dm` (direct messages with Claude). Populated only when `claude_tag_category` is in `group_by[]`; null for usage that is not Claude Tag. Direct-message usage is billed to the individual user and is reported under that user's product, not under `claude-tag`. New categories may be added over time. - `"dm"` - `"engaged"` - `"monitoring"` - `"proactive"` - `"scheduled"` - `claude_tag_user_id: Optional[str]` Slack user ID (for example `U0123ABCDEF`) of the member the Claude Tag (Claude in Slack) usage is attributed to, not a claude.ai user ID. Populated only when `claude_tag_user_id` is in `group_by[]`; null for usage that is not Claude Tag and for Claude Tag usage that is not attributed to a single user (for example `monitoring`, and `proactive` usage Claude initiated), so per-user rows can sum to less than the Claude Tag total. Cannot be combined with `group_by[]=rbac_group_id` or the `rbac_group_ids[]` filter. - `context_window: Optional[BetaAnalyticsContextWindow]` Context-window pricing tier of the usage or cost. Null unless `context_window` is in `group_by[]`; it can also be null on grouped rows with no context-window tier, such as code execution. - `"0-200k"` - `"200k-1M"` - `cost_type: Optional[BetaAnalyticsCostType]` Cost component breakdown; null when returning the combined total. - `"code_execution"` - `"tokens"` - `"web_search"` - `currency: str` Currency code for the cost amount. Currently always `"USD"`. default: USD - `ending_at: Optional[datetime]` End of the row's UTC time bucket (exclusive), as an RFC 3339 timestamp; equal to `starting_at` plus one `bucket_width`. Null unless `bucket_width` is set. format: date-time - `inference_geo: Optional[Literal["global", "us"]]` Inference region of the usage or cost. Null unless `inference_geo` is in `group_by[]`; it can also be null on grouped rows where the region is not set (the rows that `inference_geos[]=not_available` matches). - `"global"` - `"us"` - `list_amount: str` List-price amount (pre-discount) in fractional cents. - `model: Optional[str]` Model that produced the usage or cost, as a model name in the form the `models[]` filter accepts (for example, `claude-opus-5`). Null unless `model` is in `group_by[]`; it can also be null on grouped rows whose usage or cost is not attributed to a specific model, such as code execution. - `product: Optional[str]` Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface. Values include `chat`, `claude_code`, `cowork`, `office_agent`, `claude_in_chrome`, `claude_design`, `claude-tag`, and `chat_cowork_unified`. `claude-tag` is Claude Tag, the Claude product in Slack. `chat_cowork_unified` is Chat and Cowork unified, Cowork's features inside claude.ai chat: chat and Cowork usage by a member who has it turned on is reported under this value instead of `chat` or `cowork`. It is accepted as a filter only on deployments that offer Chat and Cowork unified. Some unattributed usage is reported as "other". - `rbac_group_id: Optional[str]` RBAC group (team) the usage is attributed to, in the public tagged `rbac_group_...` spelling — the same spelling the activity resources use for this key, so the same team has one id across resources and it round-trips as an `rbac_group_ids[]` filter value. Populated only when `rbac_group_id` is in `group_by[]`. Any-membership semantics: a user in several groups contributes their full usage to each of those groups' rows, so the named-group rows overlap and their sum can exceed the org total. A null value is the single unassigned row: users in no group on that (UTC) day. For the true org total, run the same query without `group_by[]`. - `requests: Optional[int]` Number of API requests in this row's scope. Null when `group_by` includes `cost_type` or `token_type` (the count has no per-component attribution; read it from the ungrouped response). For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`). - `slack_channel_id: Optional[str]` Slack channel the usage originated from. Populated only when `slack_channel_id` is in `group_by[]`; null for usage outside Slack (and for rows recorded before channel attribution was enabled). - `speed: Optional[Literal["fast", "standard"]]` Inference speed mode of the usage or cost: `fast` or `standard`. Null unless `speed` is in `group_by[]`. - `"fast"` - `"standard"` - `starting_at: Optional[datetime]` Start of the row's UTC time bucket (inclusive), as an RFC 3339 timestamp. Null unless `bucket_width` is set; without `bucket_width`, each row aggregates the full requested range. format: date-time - `token_type: Optional[BetaAnalyticsTokenType]` Token type when `cost_type` is `tokens`; null otherwise. - `"cache_creation.ephemeral_1h_input_tokens"` - `"cache_creation.ephemeral_5m_input_tokens"` - `"cache_read_input_tokens"` - `"output_tokens"` - `"uncached_input_tokens"` #### Example ```python import os from datetime import datetime from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.analytics.user_cost_report.list( starting_at=datetime.fromisoformat("2019-12-27T18:11:19.117"), ) page = page.data[0] print(page.claude_tag_user_id) ``` ##### Response (200) ```json { "data": [ { "actor": { "deleted": true, "email": "jane@example.com", "email_address": "jane@example.com", "name": "Jane Smith", "type": "user_actor", "user_id": "user_01AbCdEfGhIjKlMnOpQrSt" }, "amount": "41280.000000", "claude_tag_category": "dm", "claude_tag_user_id": "U0123ABCDEF", "context_window": "0-200k", "cost_type": "code_execution", "currency": "USD", "ending_at": "2019-12-27T18:11:19.117Z", "inference_geo": "global", "list_amount": "51600.000000", "model": "claude-opus-5", "product": "chat", "rbac_group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "requests": 128, "slack_channel_id": "C0123ABCDEF", "speed": "fast", "starting_at": "2019-12-27T18:11:19.117Z", "token_type": "cache_creation.ephemeral_1h_input_tokens" } ], "data_refreshed_at": "2019-12-27T18:11:19.117Z", "has_more": true, "next_page": "next_page", "organization_id": "org_013FP9SaFPBg7Kw7fetjn6cF" } ``` ## Beta › Organization › Spend Limits ### Set Spend Limit `beta.organization.spend_limits.set(**kwargs) -> BetaSpendLimit` **POST** `/v1/organizations/spend_limits` Set a spend limit. Upsert keyed on (scope, period): setting a limit that already exists overwrites it in place. A Claude Enterprise organization sets `user` limits. Its seat-tier, group, and organization-level defaults are configured in claude.ai. A Claude Console organization sets `organization` and `workspace` limits, which are monthly and always carry an amount. Setting those limits is in an early access preview. To request access, contact your Anthropic account team. #### Parameters - `amount: Optional[str]` Limit amount as a non-negative integer decimal string in the minor unit of the organization's billing currency (cents for USD): "50000" is $500.00. `null` sets an explicit no-limit override for this scope and `period` only — each period resolves independently, so caps for other periods still apply. - `scope: Scope` What the limit applies to. Claude Enterprise organizations set `user` limits. Claude Console organizations set `organization` and `workspace` limits. Any other combination returns 400. Setting `organization` and `workspace` limits through the API is in an early access preview. To request access, contact your Anthropic account team. - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `type: Literal["user"]` Scope type. Always `user` for this scope. default: user - `user_id: str` Tagged ID of the member the spend limit applies to. - `class BetaSpendLimitOrganizationScope` - `type: Literal["organization"]` default: organization - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `type: Literal["workspace"]` Scope type. Always `workspace` for this scope. default: workspace - `workspace_id: str` Tagged ID of the workspace the spend limit applies to. - `period: Optional[BetaSpendLimitPeriod]` - `"daily"` - `"monthly"` - `"weekly"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) Optional header to specify the beta version(s) you want to use. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaSpendLimit` A configured spend limit: a cap on metered spend for one scope and period. - `type: Literal["spend_limit"]` Object type. Always `spend_limit`. default: spend_limit - `id: str` Unique tagged ID of the spend limit (`spl_...`). - `amount: Optional[str]` Limit amount as a non-negative integer decimal string in the minor unit of `currency` (cents for USD): "50000" is $500.00. `null` means no numeric cap is configured at this scope — see the effective report for whether a limit applies. - `created_at: datetime` RFC 3339 datetime at which the spend limit was created. format: date-time - `currency: str` ISO 4217 code of the organization's billing currency; the unit for `amount`. - `is_enabled: bool` Read-only. `false` when extra usage is switched off for this organization (`organization` limit) or for this member (`user` limit); `amount` is kept and applies again when it's switched back on. Always `true` for other limits. - `period: BetaSpendLimitPeriod` Length of the window the limit resets over. `amount` caps spend within each period. - `"daily"` - `"monthly"` - `"weekly"` - `scope: Scope` What the limit applies to. A tagged union on `type`; each variant carries the identifier for its scope. - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `type: Literal["user"]` Scope type. Always `user` for this scope. default: user - `user_id: str` Tagged ID of the member the spend limit applies to. - `class BetaSpendLimitSeatTierScope` - `type: Literal["seat_tier"]` default: seat_tier - `seat_tier: str` - `class BetaSpendLimitRBACGroupScope` - `type: Literal["rbac_group"]` default: rbac_group - `rbac_group_id: str` - `class BetaSpendLimitOrganizationServiceScope` - `type: Literal["organization_service"]` default: organization_service - `service: str` - `class BetaSpendLimitOrganizationScope` - `type: Literal["organization"]` default: organization - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `type: Literal["workspace"]` Scope type. Always `workspace` for this scope. default: workspace - `workspace_id: str` Tagged ID of the workspace the spend limit applies to. - `updated_at: datetime` RFC 3339 datetime at which the spend limit was last modified. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_spend_limit = client.beta.organization.spend_limits.set( amount="50000", scope={ "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q", }, ) print(beta_spend_limit.id) ``` ##### Response (200) ```json { "id": "id", "amount": "50000", "created_at": "2019-12-27T18:11:19.117Z", "currency": "USD", "is_enabled": true, "period": "daily", "scope": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "type": "spend_limit", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ### Get Spend Limit `beta.organization.spend_limits.retrieve(spend_limit_id) -> BetaSpendLimit` **GET** `/v1/organizations/spend_limits/{spend_limit_id}` Retrieve a spend limit by ID. #### Parameters - `spend_limit_id: str` (path parameter) ID of the Spend Limit. #### Returns - `class BetaSpendLimit` A configured spend limit: a cap on metered spend for one scope and period. - `type: Literal["spend_limit"]` Object type. Always `spend_limit`. default: spend_limit - `id: str` Unique tagged ID of the spend limit (`spl_...`). - `amount: Optional[str]` Limit amount as a non-negative integer decimal string in the minor unit of `currency` (cents for USD): "50000" is $500.00. `null` means no numeric cap is configured at this scope — see the effective report for whether a limit applies. - `created_at: datetime` RFC 3339 datetime at which the spend limit was created. format: date-time - `currency: str` ISO 4217 code of the organization's billing currency; the unit for `amount`. - `is_enabled: bool` Read-only. `false` when extra usage is switched off for this organization (`organization` limit) or for this member (`user` limit); `amount` is kept and applies again when it's switched back on. Always `true` for other limits. - `period: BetaSpendLimitPeriod` Length of the window the limit resets over. `amount` caps spend within each period. - `"daily"` - `"monthly"` - `"weekly"` - `scope: Scope` What the limit applies to. A tagged union on `type`; each variant carries the identifier for its scope. - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `type: Literal["user"]` Scope type. Always `user` for this scope. default: user - `user_id: str` Tagged ID of the member the spend limit applies to. - `class BetaSpendLimitSeatTierScope` - `type: Literal["seat_tier"]` default: seat_tier - `seat_tier: str` - `class BetaSpendLimitRBACGroupScope` - `type: Literal["rbac_group"]` default: rbac_group - `rbac_group_id: str` - `class BetaSpendLimitOrganizationServiceScope` - `type: Literal["organization_service"]` default: organization_service - `service: str` - `class BetaSpendLimitOrganizationScope` - `type: Literal["organization"]` default: organization - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `type: Literal["workspace"]` Scope type. Always `workspace` for this scope. default: workspace - `workspace_id: str` Tagged ID of the workspace the spend limit applies to. - `updated_at: datetime` RFC 3339 datetime at which the spend limit was last modified. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_spend_limit = client.beta.organization.spend_limits.retrieve( "spend_limit_id", ) print(beta_spend_limit.id) ``` ##### Response (200) ```json { "id": "id", "amount": "50000", "created_at": "2019-12-27T18:11:19.117Z", "currency": "USD", "is_enabled": true, "period": "daily", "scope": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "type": "spend_limit", "updated_at": "2019-12-27T18:11:19.117Z" } ``` ### Delete Spend Limit `beta.organization.spend_limits.delete(spend_limit_id) -> SpendLimitDeleteResponse` **DELETE** `/v1/organizations/spend_limits/{spend_limit_id}` Delete a spend limit. For a Claude Enterprise organization, this deletes a per-user override, and the member falls back to any inherited spend limit at that period. Its seat-tier, group, and organization-level rows cannot be deleted via this endpoint. A Claude Console organization deletes its organization and workspace limits. Deleting them through the API is in an early access preview. #### Parameters - `spend_limit_id: str` (path parameter) ID of the Spend Limit. #### Returns - `class SpendLimitDeleteResponse` - `type: Literal["spend_limit_deleted"]` default: spend_limit_deleted - `id: str` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) spend_limit = client.beta.organization.spend_limits.delete( "spend_limit_id", ) print(spend_limit.id) ``` ##### Response (200) ```json { "id": "id", "type": "spend_limit_deleted" } ``` ### List Spend Limits `beta.organization.spend_limits.list(**kwargs) -> SyncPageCursor[BetaSpendLimit]` **GET** `/v1/organizations/spend_limits` List the organization's spend limits. A Claude Console organization's limits come in an order that is stable across pages. A Claude Enterprise organization's are grouped by scope type, in the order `organization`, `seat_tier`, `rbac_group`, `organization_service`, `user`; within a type they come in a fixed order that is not creation order. Listing Claude Console limits is in an early access preview. To request access, contact your Anthropic account team. #### Parameters - `limit: Optional[int]` (query parameter) Maximum number of limits per page. Defaults to `20`. default: 20, minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. - `scope_type: Optional[List[Literal["organization", "organization_service", "rbac_group", 3 more]]]` (query parameter) Return only limits with these scope types. A Claude Console organization has `organization` and `workspace` limits; a Claude Enterprise organization has `organization`, `seat_tier`, `rbac_group`, `organization_service` and `user` limits. Omit for all. maxItems: 100 - `"organization"` - `"organization_service"` - `"rbac_group"` - `"seat_tier"` - `"user"` - `"workspace"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `spend-limit-reads-2026-09-26` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaSpendLimit` A configured spend limit: a cap on metered spend for one scope and period. - `type: Literal["spend_limit"]` Object type. Always `spend_limit`. default: spend_limit - `id: str` Unique tagged ID of the spend limit (`spl_...`). - `amount: Optional[str]` Limit amount as a non-negative integer decimal string in the minor unit of `currency` (cents for USD): "50000" is $500.00. `null` means no numeric cap is configured at this scope — see the effective report for whether a limit applies. - `created_at: datetime` RFC 3339 datetime at which the spend limit was created. format: date-time - `currency: str` ISO 4217 code of the organization's billing currency; the unit for `amount`. - `is_enabled: bool` Read-only. `false` when extra usage is switched off for this organization (`organization` limit) or for this member (`user` limit); `amount` is kept and applies again when it's switched back on. Always `true` for other limits. - `period: BetaSpendLimitPeriod` Length of the window the limit resets over. `amount` caps spend within each period. - `"daily"` - `"monthly"` - `"weekly"` - `scope: Scope` What the limit applies to. A tagged union on `type`; each variant carries the identifier for its scope. - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `type: Literal["user"]` Scope type. Always `user` for this scope. default: user - `user_id: str` Tagged ID of the member the spend limit applies to. - `class BetaSpendLimitSeatTierScope` - `type: Literal["seat_tier"]` default: seat_tier - `seat_tier: str` - `class BetaSpendLimitRBACGroupScope` - `type: Literal["rbac_group"]` default: rbac_group - `rbac_group_id: str` - `class BetaSpendLimitOrganizationServiceScope` - `type: Literal["organization_service"]` default: organization_service - `service: str` - `class BetaSpendLimitOrganizationScope` - `type: Literal["organization"]` default: organization - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `type: Literal["workspace"]` Scope type. Always `workspace` for this scope. default: workspace - `workspace_id: str` Tagged ID of the workspace the spend limit applies to. - `updated_at: datetime` RFC 3339 datetime at which the spend limit was last modified. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.spend_limits.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "id", "amount": "50000", "created_at": "2019-12-27T18:11:19.117Z", "currency": "USD", "is_enabled": true, "period": "daily", "scope": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "type": "spend_limit", "updated_at": "2019-12-27T18:11:19.117Z" } ], "next_page": "next_page" } ``` ## Beta › Organization › Spend Limits › Effective ### List Effective Spend Limits `beta.organization.spend_limits.effective.list(**kwargs) -> SyncPageCursor[BetaSpendSummary]` **GET** `/v1/organizations/spend_limits/effective` List each member's effective spend limit and period-to-date spend. Returns one row per (member, period) the member resolves a spend limit for, with the `source` scope the spend limit was inherited from. Paginates by member, so a member's periods never split across pages. Listing Claude Console limits is in an early access preview. To request access, contact your Anthropic account team. #### Parameters - `limit: Optional[int]` (query parameter) Maximum number of members per page. A member's period rows never split across pages, so a page may carry more rows than this. Defaults to `20`. default: 20, minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page` field. - `period: Optional[List[Literal["daily", "monthly", "weekly"]]]` (query parameter) Restrict the report to these limit periods. Omit to return one row per period each member resolves a spend limit for. maxItems: 3 - `"daily"` - `"monthly"` - `"weekly"` - `user_ids: Optional[Sequence[str]]` (query parameter) Restrict the report to these members, by tagged user ID (`user_...`). At most 100 entries. maxItems: 100 #### Returns - `class BetaSpendSummary` Per-member effective-limit report row (`GET /spend_limits/effective`). - `actor: Actor` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `type: Literal["user_actor"]` Actor type. Always `user_actor`. default: user_actor - `deleted: bool` True only when the underlying account has been deleted. default: false - `email_address: Optional[str]` The user's email address. Null when the account is unavailable or has been deleted. - `name: Optional[str]` The user's current display name. Null when the account is unavailable, has been deleted, or has no name set. - `user_id: str` Tagged ID of the user. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `type: Literal["scoped_api_key_actor"]` default: scoped_api_key_actor - `scoped_api_key_id: str` - `amount: Optional[str]` Effective limit amount as a non-negative integer decimal string in the minor unit of `currency` (cents for USD). `null` means no limit applies for this row's `period` — each period resolves independently, so another period may still cap this member. - `currency: str` ISO 4217 code of the organization's billing currency; the unit for `amount` and `period_to_date_spend`. - `period: BetaSpendLimitPeriod` Period this row's effective limit and spend are reported for. - `"daily"` - `"monthly"` - `"weekly"` - `period_to_date_spend: str` The member's spend so far in the current period, as a non-negative decimal string in the minor unit of `currency` (cents for USD). May carry fractional minor units up to three decimal places (e.g. `"12050.5"`) — metered usage is not rounded to whole cents. Reads as `"0"` when the spend reading is temporarily unavailable. - `scope: Scope` - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `type: Literal["user"]` Scope type. Always `user` for this scope. default: user - `user_id: str` Tagged ID of the member the spend limit applies to. - `class BetaSpendLimitSeatTierScope` - `type: Literal["seat_tier"]` default: seat_tier - `seat_tier: str` - `class BetaSpendLimitRBACGroupScope` - `type: Literal["rbac_group"]` default: rbac_group - `rbac_group_id: str` - `class BetaSpendLimitOrganizationServiceScope` - `type: Literal["organization_service"]` default: organization_service - `service: str` - `class BetaSpendLimitOrganizationScope` - `type: Literal["organization"]` default: organization - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `type: Literal["workspace"]` Scope type. Always `workspace` for this scope. default: workspace - `workspace_id: str` Tagged ID of the workspace the spend limit applies to. - `source: Source` - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `class BetaSpendLimitSeatTierScope` - `class BetaSpendLimitRBACGroupScope` - `class BetaSpendLimitOrganizationServiceScope` - `class BetaSpendLimitOrganizationScope` - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `spend_limit_id: str` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.spend_limits.effective.list() page = page.data[0] print(page.spend_limit_id) ``` ##### Response (200) ```json { "data": [ { "actor": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "amount": "50000", "currency": "USD", "period": "daily", "period_to_date_spend": "12050.5", "scope": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "source": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "spend_limit_id": "spend_limit_id" } ], "next_page": "next_page" } ``` ## Beta › Organization › Spend Limits › Increase Requests ### List Spend Limit Increase Requests `beta.organization.spend_limits.increase_requests.list(**kwargs) -> SyncPageCursor[BetaSpendLimitIncreaseRequest]` **GET** `/v1/organizations/spend_limit_increase_requests` List spend limit increase requests, most recent first. Pending requests include a live `spend_summary` for the requester. Requests whose requester is no longer a member are excluded. #### Parameters - `actor_ids: Optional[Sequence[str]]` (query parameter) Filter by requester, as `user_...` tagged IDs. - `limit: Optional[int]` (query parameter) default: 20, minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Opaque cursor from a previous response's `next_page`. - `status: Optional[List[BetaSpendLimitIncreaseRequestStatus]]` (query parameter) Filter by status. Omit to return all. - `"approved"` - `"denied"` - `"pending"` #### Returns - `class BetaSpendLimitIncreaseRequest` - `type: Literal["spend_limit_increase_request"]` default: spend_limit_increase_request - `id: str` - `actor: Actor` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `type: Literal["user_actor"]` Actor type. Always `user_actor`. default: user_actor - `deleted: bool` True only when the underlying account has been deleted. default: false - `email_address: Optional[str]` The user's email address. Null when the account is unavailable or has been deleted. - `name: Optional[str]` The user's current display name. Null when the account is unavailable, has been deleted, or has no name set. - `user_id: str` Tagged ID of the user. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `type: Literal["scoped_api_key_actor"]` default: scoped_api_key_actor - `scoped_api_key_id: str` - `created_at: datetime` format: date-time - `period: BetaSpendLimitPeriod` - `"daily"` - `"monthly"` - `"weekly"` - `resolved_at: Optional[datetime]` format: date-time - `resolved_by: Optional[ResolvedBy]` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `spend_summary: Optional[BetaSpendSummary]` Per-member effective-limit report row (`GET /spend_limits/effective`). - `actor: Actor` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `amount: Optional[str]` Effective limit amount as a non-negative integer decimal string in the minor unit of `currency` (cents for USD). `null` means no limit applies for this row's `period` — each period resolves independently, so another period may still cap this member. - `currency: str` ISO 4217 code of the organization's billing currency; the unit for `amount` and `period_to_date_spend`. - `period: BetaSpendLimitPeriod` Period this row's effective limit and spend are reported for. - `period_to_date_spend: str` The member's spend so far in the current period, as a non-negative decimal string in the minor unit of `currency` (cents for USD). May carry fractional minor units up to three decimal places (e.g. `"12050.5"`) — metered usage is not rounded to whole cents. Reads as `"0"` when the spend reading is temporarily unavailable. - `scope: Scope` - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `type: Literal["user"]` Scope type. Always `user` for this scope. default: user - `user_id: str` Tagged ID of the member the spend limit applies to. - `class BetaSpendLimitSeatTierScope` - `type: Literal["seat_tier"]` default: seat_tier - `seat_tier: str` - `class BetaSpendLimitRBACGroupScope` - `type: Literal["rbac_group"]` default: rbac_group - `rbac_group_id: str` - `class BetaSpendLimitOrganizationServiceScope` - `type: Literal["organization_service"]` default: organization_service - `service: str` - `class BetaSpendLimitOrganizationScope` - `type: Literal["organization"]` default: organization - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `type: Literal["workspace"]` Scope type. Always `workspace` for this scope. default: workspace - `workspace_id: str` Tagged ID of the workspace the spend limit applies to. - `source: Source` - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `class BetaSpendLimitSeatTierScope` - `class BetaSpendLimitRBACGroupScope` - `class BetaSpendLimitOrganizationServiceScope` - `class BetaSpendLimitOrganizationScope` - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `spend_limit_id: str` - `status: BetaSpendLimitIncreaseRequestStatus` - `"approved"` - `"denied"` - `"pending"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.spend_limits.increase_requests.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "id", "actor": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "created_at": "2019-12-27T18:11:19.117Z", "period": "daily", "resolved_at": "2019-12-27T18:11:19.117Z", "resolved_by": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "spend_summary": { "actor": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "amount": "50000", "currency": "USD", "period": "daily", "period_to_date_spend": "12050.5", "scope": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "source": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "spend_limit_id": "spend_limit_id" }, "status": "approved", "type": "spend_limit_increase_request" } ], "next_page": "next_page" } ``` ### Get Spend Limit Increase Request `beta.organization.spend_limits.increase_requests.retrieve(spend_limit_increase_request_id) -> BetaSpendLimitIncreaseRequest` **GET** `/v1/organizations/spend_limit_increase_requests/{spend_limit_increase_request_id}` Retrieve a spend limit increase request. While `pending`, the response includes a live `spend_summary` for the requester at the request's period. #### Parameters - `spend_limit_increase_request_id: str` (path parameter) ID of the spend limit increase request. #### Returns - `class BetaSpendLimitIncreaseRequest` - `type: Literal["spend_limit_increase_request"]` default: spend_limit_increase_request - `id: str` - `actor: Actor` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `type: Literal["user_actor"]` Actor type. Always `user_actor`. default: user_actor - `deleted: bool` True only when the underlying account has been deleted. default: false - `email_address: Optional[str]` The user's email address. Null when the account is unavailable or has been deleted. - `name: Optional[str]` The user's current display name. Null when the account is unavailable, has been deleted, or has no name set. - `user_id: str` Tagged ID of the user. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `type: Literal["scoped_api_key_actor"]` default: scoped_api_key_actor - `scoped_api_key_id: str` - `created_at: datetime` format: date-time - `period: BetaSpendLimitPeriod` - `"daily"` - `"monthly"` - `"weekly"` - `resolved_at: Optional[datetime]` format: date-time - `resolved_by: Optional[ResolvedBy]` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `spend_summary: Optional[BetaSpendSummary]` Per-member effective-limit report row (`GET /spend_limits/effective`). - `actor: Actor` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `amount: Optional[str]` Effective limit amount as a non-negative integer decimal string in the minor unit of `currency` (cents for USD). `null` means no limit applies for this row's `period` — each period resolves independently, so another period may still cap this member. - `currency: str` ISO 4217 code of the organization's billing currency; the unit for `amount` and `period_to_date_spend`. - `period: BetaSpendLimitPeriod` Period this row's effective limit and spend are reported for. - `period_to_date_spend: str` The member's spend so far in the current period, as a non-negative decimal string in the minor unit of `currency` (cents for USD). May carry fractional minor units up to three decimal places (e.g. `"12050.5"`) — metered usage is not rounded to whole cents. Reads as `"0"` when the spend reading is temporarily unavailable. - `scope: Scope` - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `type: Literal["user"]` Scope type. Always `user` for this scope. default: user - `user_id: str` Tagged ID of the member the spend limit applies to. - `class BetaSpendLimitSeatTierScope` - `type: Literal["seat_tier"]` default: seat_tier - `seat_tier: str` - `class BetaSpendLimitRBACGroupScope` - `type: Literal["rbac_group"]` default: rbac_group - `rbac_group_id: str` - `class BetaSpendLimitOrganizationServiceScope` - `type: Literal["organization_service"]` default: organization_service - `service: str` - `class BetaSpendLimitOrganizationScope` - `type: Literal["organization"]` default: organization - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `type: Literal["workspace"]` Scope type. Always `workspace` for this scope. default: workspace - `workspace_id: str` Tagged ID of the workspace the spend limit applies to. - `source: Source` - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `class BetaSpendLimitSeatTierScope` - `class BetaSpendLimitRBACGroupScope` - `class BetaSpendLimitOrganizationServiceScope` - `class BetaSpendLimitOrganizationScope` - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `spend_limit_id: str` - `status: BetaSpendLimitIncreaseRequestStatus` - `"approved"` - `"denied"` - `"pending"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_spend_limit_increase_request = ( client.beta.organization.spend_limits.increase_requests.retrieve( "spend_limit_increase_request_id", ) ) print(beta_spend_limit_increase_request.id) ``` ##### Response (200) ```json { "id": "id", "actor": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "created_at": "2019-12-27T18:11:19.117Z", "period": "daily", "resolved_at": "2019-12-27T18:11:19.117Z", "resolved_by": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "spend_summary": { "actor": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "amount": "50000", "currency": "USD", "period": "daily", "period_to_date_spend": "12050.5", "scope": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "source": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "spend_limit_id": "spend_limit_id" }, "status": "approved", "type": "spend_limit_increase_request" } ``` ### Approve Spend Limit Increase Request `beta.organization.spend_limits.increase_requests.approve(spend_limit_increase_request_id, **kwargs) -> IncreaseRequestApproveResponse` **POST** `/v1/organizations/spend_limit_increase_requests/{spend_limit_increase_request_id}/approve` Approve a pending spend limit increase request. Writes a per-user spend limit at `amount` for the requester and transitions the request to `approved`. `period` defaults to the period the member was blocked on. Anthropic emails the requester unless `suppress_notification` is set. #### Parameters - `spend_limit_increase_request_id: str` (path parameter) ID of the spend limit increase request. - `amount: str` New per-user spend limit as a non-negative integer decimal string (minor units). - `period: Optional[BetaSpendLimitPeriod]` - `"daily"` - `"monthly"` - `"weekly"` - `suppress_notification: Optional[bool]` #### Returns - `class IncreaseRequestApproveResponse` - `type: Literal["spend_limit_increase_request"]` default: spend_limit_increase_request - `id: str` - `actor: Actor` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `type: Literal["user_actor"]` Actor type. Always `user_actor`. default: user_actor - `deleted: bool` True only when the underlying account has been deleted. default: false - `email_address: Optional[str]` The user's email address. Null when the account is unavailable or has been deleted. - `name: Optional[str]` The user's current display name. Null when the account is unavailable, has been deleted, or has no name set. - `user_id: str` Tagged ID of the user. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `type: Literal["scoped_api_key_actor"]` default: scoped_api_key_actor - `scoped_api_key_id: str` - `created_at: datetime` format: date-time - `period: BetaSpendLimitPeriod` - `"daily"` - `"monthly"` - `"weekly"` - `resolved_at: Optional[datetime]` format: date-time - `resolved_by: Optional[ResolvedBy]` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `spend_limit: BetaSpendLimit` A configured spend limit: a cap on metered spend for one scope and period. - `type: Literal["spend_limit"]` Object type. Always `spend_limit`. default: spend_limit - `id: str` Unique tagged ID of the spend limit (`spl_...`). - `amount: Optional[str]` Limit amount as a non-negative integer decimal string in the minor unit of `currency` (cents for USD): "50000" is $500.00. `null` means no numeric cap is configured at this scope — see the effective report for whether a limit applies. - `created_at: datetime` RFC 3339 datetime at which the spend limit was created. format: date-time - `currency: str` ISO 4217 code of the organization's billing currency; the unit for `amount`. - `is_enabled: bool` Read-only. `false` when extra usage is switched off for this organization (`organization` limit) or for this member (`user` limit); `amount` is kept and applies again when it's switched back on. Always `true` for other limits. - `period: BetaSpendLimitPeriod` Length of the window the limit resets over. `amount` caps spend within each period. - `scope: Scope` What the limit applies to. A tagged union on `type`; each variant carries the identifier for its scope. - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `type: Literal["user"]` Scope type. Always `user` for this scope. default: user - `user_id: str` Tagged ID of the member the spend limit applies to. - `class BetaSpendLimitSeatTierScope` - `type: Literal["seat_tier"]` default: seat_tier - `seat_tier: str` - `class BetaSpendLimitRBACGroupScope` - `type: Literal["rbac_group"]` default: rbac_group - `rbac_group_id: str` - `class BetaSpendLimitOrganizationServiceScope` - `type: Literal["organization_service"]` default: organization_service - `service: str` - `class BetaSpendLimitOrganizationScope` - `type: Literal["organization"]` default: organization - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `type: Literal["workspace"]` Scope type. Always `workspace` for this scope. default: workspace - `workspace_id: str` Tagged ID of the workspace the spend limit applies to. - `updated_at: datetime` RFC 3339 datetime at which the spend limit was last modified. format: date-time - `spend_summary: Optional[BetaSpendSummary]` Per-member effective-limit report row (`GET /spend_limits/effective`). - `actor: Actor` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `amount: Optional[str]` Effective limit amount as a non-negative integer decimal string in the minor unit of `currency` (cents for USD). `null` means no limit applies for this row's `period` — each period resolves independently, so another period may still cap this member. - `currency: str` ISO 4217 code of the organization's billing currency; the unit for `amount` and `period_to_date_spend`. - `period: BetaSpendLimitPeriod` Period this row's effective limit and spend are reported for. - `period_to_date_spend: str` The member's spend so far in the current period, as a non-negative decimal string in the minor unit of `currency` (cents for USD). May carry fractional minor units up to three decimal places (e.g. `"12050.5"`) — metered usage is not rounded to whole cents. Reads as `"0"` when the spend reading is temporarily unavailable. - `scope: Scope` - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `class BetaSpendLimitSeatTierScope` - `class BetaSpendLimitRBACGroupScope` - `class BetaSpendLimitOrganizationServiceScope` - `class BetaSpendLimitOrganizationScope` - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `source: Source` - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `class BetaSpendLimitSeatTierScope` - `class BetaSpendLimitRBACGroupScope` - `class BetaSpendLimitOrganizationServiceScope` - `class BetaSpendLimitOrganizationScope` - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `spend_limit_id: str` - `status: BetaSpendLimitIncreaseRequestStatus` - `"approved"` - `"denied"` - `"pending"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) response = client.beta.organization.spend_limits.increase_requests.approve( spend_limit_increase_request_id="spend_limit_increase_request_id", amount="50000", ) print(response.id) ``` ##### Response (200) ```json { "id": "id", "actor": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "created_at": "2019-12-27T18:11:19.117Z", "period": "daily", "resolved_at": "2019-12-27T18:11:19.117Z", "resolved_by": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "spend_limit": { "id": "id", "amount": "50000", "created_at": "2019-12-27T18:11:19.117Z", "currency": "USD", "is_enabled": true, "period": "daily", "scope": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "type": "spend_limit", "updated_at": "2019-12-27T18:11:19.117Z" }, "spend_summary": { "actor": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "amount": "50000", "currency": "USD", "period": "daily", "period_to_date_spend": "12050.5", "scope": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "source": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "spend_limit_id": "spend_limit_id" }, "status": "approved", "type": "spend_limit_increase_request" } ``` ### Deny Spend Limit Increase Request `beta.organization.spend_limits.increase_requests.deny(spend_limit_increase_request_id, **kwargs) -> BetaSpendLimitIncreaseRequest` **POST** `/v1/organizations/spend_limit_increase_requests/{spend_limit_increase_request_id}/deny` Deny a pending spend limit increase request. Idempotent on `denied`; denying an already-`approved` request returns 400. Anthropic emails the requester unless `suppress_notification` is set. #### Parameters - `spend_limit_increase_request_id: str` (path parameter) ID of the spend limit increase request. - `suppress_notification: Optional[bool]` #### Returns - `class BetaSpendLimitIncreaseRequest` - `type: Literal["spend_limit_increase_request"]` default: spend_limit_increase_request - `id: str` - `actor: Actor` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `type: Literal["user_actor"]` Actor type. Always `user_actor`. default: user_actor - `deleted: bool` True only when the underlying account has been deleted. default: false - `email_address: Optional[str]` The user's email address. Null when the account is unavailable or has been deleted. - `name: Optional[str]` The user's current display name. Null when the account is unavailable, has been deleted, or has no name set. - `user_id: str` Tagged ID of the user. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `type: Literal["scoped_api_key_actor"]` default: scoped_api_key_actor - `scoped_api_key_id: str` - `created_at: datetime` format: date-time - `period: BetaSpendLimitPeriod` - `"daily"` - `"monthly"` - `"weekly"` - `resolved_at: Optional[datetime]` format: date-time - `resolved_by: Optional[ResolvedBy]` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `spend_summary: Optional[BetaSpendSummary]` Per-member effective-limit report row (`GET /spend_limits/effective`). - `actor: Actor` - `class BetaSpendLimitUserActor` A user within the organization. `name` and `email_address` are null when the underlying account is unavailable or has been deleted; `deleted` is true only for deleted accounts. - `class BetaSpendLimitScopedAPIKeyActor` A scoped Admin API key acting on behalf of the organization. - `amount: Optional[str]` Effective limit amount as a non-negative integer decimal string in the minor unit of `currency` (cents for USD). `null` means no limit applies for this row's `period` — each period resolves independently, so another period may still cap this member. - `currency: str` ISO 4217 code of the organization's billing currency; the unit for `amount` and `period_to_date_spend`. - `period: BetaSpendLimitPeriod` Period this row's effective limit and spend are reported for. - `period_to_date_spend: str` The member's spend so far in the current period, as a non-negative decimal string in the minor unit of `currency` (cents for USD). May carry fractional minor units up to three decimal places (e.g. `"12050.5"`) — metered usage is not rounded to whole cents. Reads as `"0"` when the spend reading is temporarily unavailable. - `scope: Scope` - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `type: Literal["user"]` Scope type. Always `user` for this scope. default: user - `user_id: str` Tagged ID of the member the spend limit applies to. - `class BetaSpendLimitSeatTierScope` - `type: Literal["seat_tier"]` default: seat_tier - `seat_tier: str` - `class BetaSpendLimitRBACGroupScope` - `type: Literal["rbac_group"]` default: rbac_group - `rbac_group_id: str` - `class BetaSpendLimitOrganizationServiceScope` - `type: Literal["organization_service"]` default: organization_service - `service: str` - `class BetaSpendLimitOrganizationScope` - `type: Literal["organization"]` default: organization - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `type: Literal["workspace"]` Scope type. Always `workspace` for this scope. default: workspace - `workspace_id: str` Tagged ID of the workspace the spend limit applies to. - `source: Source` - `class BetaSpendLimitUserScope` Scope selecting a single member of the organization. - `class BetaSpendLimitSeatTierScope` - `class BetaSpendLimitRBACGroupScope` - `class BetaSpendLimitOrganizationServiceScope` - `class BetaSpendLimitOrganizationScope` - `class BetaSpendLimitWorkspaceScope` Scope selecting one workspace of a Claude Console organization. - `spend_limit_id: str` - `status: BetaSpendLimitIncreaseRequestStatus` - `"approved"` - `"denied"` - `"pending"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_spend_limit_increase_request = ( client.beta.organization.spend_limits.increase_requests.deny( spend_limit_increase_request_id="spend_limit_increase_request_id", ) ) print(beta_spend_limit_increase_request.id) ``` ##### Response (200) ```json { "id": "id", "actor": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "created_at": "2019-12-27T18:11:19.117Z", "period": "daily", "resolved_at": "2019-12-27T18:11:19.117Z", "resolved_by": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "spend_summary": { "actor": { "deleted": true, "email_address": "email_address", "name": "name", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "amount": "50000", "currency": "USD", "period": "daily", "period_to_date_spend": "12050.5", "scope": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "source": { "type": "user", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "spend_limit_id": "spend_limit_id" }, "status": "approved", "type": "spend_limit_increase_request" } ``` ## Beta › Organization › RBAC Groups ### Create RBAC Group `beta.organization.rbac_groups.create(**kwargs) -> BetaRBACGroup` **POST** `/v1/organizations/rbac_groups` Create an RBAC Group in the Claude Enterprise tenant. Groups created via the API have source type `"direct"`. The RBAC Groups API is available to Claude Enterprise organizations only. #### Parameters - `name: str` Name of the RBAC Group. Not uniqueness-enforced. minLength: 1, maxLength: 255 #### Returns - `class BetaRBACGroup` - `type: Literal["rbac_group"]` Object type. For RBAC Groups, this is always `"rbac_group"`. default: rbac_group - `id: str` ID of the RBAC Group. - `created_at: datetime` RFC 3339 timestamp of when the RBAC Group was created. format: date-time - `name: str` Name of the RBAC Group. Not uniqueness-enforced. - `role_ids: Optional[List[str]]` RBAC Role IDs attached to this RBAC Group. Role attachment is managed in the admin settings and is read-only on this API. `null` means role data was temporarily unavailable — retry to distinguish from an empty list. - `source_type: Literal["direct", "scim"]` How the RBAC Group was created: `"direct"` for groups created directly (for example, in the organization's admin settings), `"scim"` for groups provisioned by the identity provider. - `"direct"` - `"scim"` - `updated_at: datetime` RFC 3339 timestamp of when the RBAC Group was last updated. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_rbac_group = client.beta.organization.rbac_groups.create( name="Engineering", ) print(beta_rbac_group.id) ``` ##### Response (200) ```json { "id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "created_at": "2024-10-30T23:58:27.427722Z", "name": "Engineering", "role_ids": [ "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s" ], "roles": [ "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s" ], "source_type": "direct", "type": "rbac_group", "updated_at": "2024-10-30T23:58:27.427722Z" } ``` ### List RBAC Groups `beta.organization.rbac_groups.list(**kwargs) -> SyncPageCursor[BetaRBACGroup]` **GET** `/v1/organizations/rbac_groups` List RBAC Groups in the Claude Enterprise tenant. The RBAC Groups API is available to Claude Enterprise organizations only. #### Parameters - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Optionally set to the `next_page` token from the previous response. #### Returns - `class BetaRBACGroup` - `type: Literal["rbac_group"]` Object type. For RBAC Groups, this is always `"rbac_group"`. default: rbac_group - `id: str` ID of the RBAC Group. - `created_at: datetime` RFC 3339 timestamp of when the RBAC Group was created. format: date-time - `name: str` Name of the RBAC Group. Not uniqueness-enforced. - `role_ids: Optional[List[str]]` RBAC Role IDs attached to this RBAC Group. Role attachment is managed in the admin settings and is read-only on this API. `null` means role data was temporarily unavailable — retry to distinguish from an empty list. - `source_type: Literal["direct", "scim"]` How the RBAC Group was created: `"direct"` for groups created directly (for example, in the organization's admin settings), `"scim"` for groups provisioned by the identity provider. - `"direct"` - `"scim"` - `updated_at: datetime` RFC 3339 timestamp of when the RBAC Group was last updated. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.rbac_groups.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "created_at": "2024-10-30T23:58:27.427722Z", "name": "Engineering", "role_ids": [ "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s" ], "roles": [ "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s" ], "source_type": "direct", "type": "rbac_group", "updated_at": "2024-10-30T23:58:27.427722Z" } ], "has_more": false, "next_page": "eyJjdXJzb3IiOiAicmJhY19ncm91cF8wMSJ9" } ``` ### Get RBAC Group `beta.organization.rbac_groups.retrieve(rbac_group_id) -> BetaRBACGroup` **GET** `/v1/organizations/rbac_groups/{rbac_group_id}` Retrieve an RBAC Group by ID. The RBAC Groups API is available to Claude Enterprise organizations only. #### Parameters - `rbac_group_id: str` (path parameter) ID of the RBAC Group. #### Returns - `class BetaRBACGroup` - `type: Literal["rbac_group"]` Object type. For RBAC Groups, this is always `"rbac_group"`. default: rbac_group - `id: str` ID of the RBAC Group. - `created_at: datetime` RFC 3339 timestamp of when the RBAC Group was created. format: date-time - `name: str` Name of the RBAC Group. Not uniqueness-enforced. - `role_ids: Optional[List[str]]` RBAC Role IDs attached to this RBAC Group. Role attachment is managed in the admin settings and is read-only on this API. `null` means role data was temporarily unavailable — retry to distinguish from an empty list. - `source_type: Literal["direct", "scim"]` How the RBAC Group was created: `"direct"` for groups created directly (for example, in the organization's admin settings), `"scim"` for groups provisioned by the identity provider. - `"direct"` - `"scim"` - `updated_at: datetime` RFC 3339 timestamp of when the RBAC Group was last updated. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_rbac_group = client.beta.organization.rbac_groups.retrieve( "rbac_group_id", ) print(beta_rbac_group.id) ``` ##### Response (200) ```json { "id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "created_at": "2024-10-30T23:58:27.427722Z", "name": "Engineering", "role_ids": [ "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s" ], "roles": [ "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s" ], "source_type": "direct", "type": "rbac_group", "updated_at": "2024-10-30T23:58:27.427722Z" } ``` ### Update RBAC Group `beta.organization.rbac_groups.update(rbac_group_id, **kwargs) -> BetaRBACGroup` **POST** `/v1/organizations/rbac_groups/{rbac_group_id}` Update an RBAC Group's name. Groups provisioned by an identity provider (source type `"scim"`) cannot be modified via the API while an organization in the tenant uses SCIM provisioning. The RBAC Groups API is available to Claude Enterprise organizations only. #### Parameters - `rbac_group_id: str` (path parameter) ID of the RBAC Group. - `name: Optional[str]` Name of the RBAC Group. Not uniqueness-enforced. minLength: 1, maxLength: 255 #### Returns - `class BetaRBACGroup` - `type: Literal["rbac_group"]` Object type. For RBAC Groups, this is always `"rbac_group"`. default: rbac_group - `id: str` ID of the RBAC Group. - `created_at: datetime` RFC 3339 timestamp of when the RBAC Group was created. format: date-time - `name: str` Name of the RBAC Group. Not uniqueness-enforced. - `role_ids: Optional[List[str]]` RBAC Role IDs attached to this RBAC Group. Role attachment is managed in the admin settings and is read-only on this API. `null` means role data was temporarily unavailable — retry to distinguish from an empty list. - `source_type: Literal["direct", "scim"]` How the RBAC Group was created: `"direct"` for groups created directly (for example, in the organization's admin settings), `"scim"` for groups provisioned by the identity provider. - `"direct"` - `"scim"` - `updated_at: datetime` RFC 3339 timestamp of when the RBAC Group was last updated. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_rbac_group = client.beta.organization.rbac_groups.update( rbac_group_id="rbac_group_id", ) print(beta_rbac_group.id) ``` ##### Response (200) ```json { "id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "created_at": "2024-10-30T23:58:27.427722Z", "name": "Engineering", "role_ids": [ "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s" ], "roles": [ "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s" ], "source_type": "direct", "type": "rbac_group", "updated_at": "2024-10-30T23:58:27.427722Z" } ``` ### Delete RBAC Group `beta.organization.rbac_groups.delete(rbac_group_id) -> RBACGroupDeleteResponse` **DELETE** `/v1/organizations/rbac_groups/{rbac_group_id}` Delete an RBAC Group. Groups provisioned by an identity provider (source type `"scim"`) cannot be deleted via the API while an organization in the tenant uses SCIM provisioning. The RBAC Groups API is available to Claude Enterprise organizations only. #### Parameters - `rbac_group_id: str` (path parameter) ID of the RBAC Group. #### Returns - `class RBACGroupDeleteResponse` - `type: Literal["rbac_group_deleted"]` Deleted object type. For RBAC Groups, this is always `"rbac_group_deleted"`. default: rbac_group_deleted - `id: str` ID of the RBAC Group. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) rbac_group = client.beta.organization.rbac_groups.delete( "rbac_group_id", ) print(rbac_group.id) ``` ##### Response (200) ```json { "id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "type": "rbac_group_deleted" } ``` ## Beta › Organization › RBAC Groups › Members ### List RBAC Group Members `beta.organization.rbac_groups.members.list(rbac_group_id, **kwargs) -> SyncPageCursor[BetaRBACGroupMember]` **GET** `/v1/organizations/rbac_groups/{rbac_group_id}/members` List members of an RBAC Group. The RBAC Groups API is available to Claude Enterprise organizations only. #### Parameters - `rbac_group_id: str` (path parameter) ID of the RBAC Group. - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Optionally set to the `next_page` token from the previous response. #### Returns - `class BetaRBACGroupMember` - `type: Literal["rbac_group_member"]` Object type. For RBAC Group Members, this is always `"rbac_group_member"`. default: rbac_group_member - `created_at: datetime` RFC 3339 timestamp of when the User was added to the RBAC Group. format: date-time - `email: str` Email of the User. - `rbac_group_id: str` ID of the RBAC Group. - `user_id: str` ID of the User. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.rbac_groups.members.list( rbac_group_id="rbac_group_id", ) page = page.data[0] print(page.rbac_group_id) ``` ##### Response (200) ```json { "data": [ { "created_at": "2024-10-30T23:58:27.427722Z", "email": "user@emaildomain.com", "group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "rbac_group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "type": "rbac_group_member", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" } ], "has_more": false, "next_page": "eyJjdXJzb3IiOiAicmJhY19ncm91cF8wMSJ9" } ``` ### Add RBAC Group Member `beta.organization.rbac_groups.members.add(rbac_group_id, **kwargs) -> BetaRBACGroupMember` **POST** `/v1/organizations/rbac_groups/{rbac_group_id}/members` Add a User to an RBAC Group. Membership of groups provisioned by an identity provider (source type `"scim"`) cannot be modified via the API while an organization in the tenant uses SCIM provisioning. The RBAC Groups API is available to Claude Enterprise organizations only. #### Parameters - `rbac_group_id: str` (path parameter) ID of the RBAC Group. - `user_id: str` ID of the User. #### Returns - `class BetaRBACGroupMember` - `type: Literal["rbac_group_member"]` Object type. For RBAC Group Members, this is always `"rbac_group_member"`. default: rbac_group_member - `created_at: datetime` RFC 3339 timestamp of when the User was added to the RBAC Group. format: date-time - `email: str` Email of the User. - `rbac_group_id: str` ID of the RBAC Group. - `user_id: str` ID of the User. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_rbac_group_member = client.beta.organization.rbac_groups.members.add( rbac_group_id="rbac_group_id", user_id="user_01WCz1FkmYMm4gnmykNKUu3Q", ) print(beta_rbac_group_member.rbac_group_id) ``` ##### Response (200) ```json { "created_at": "2024-10-30T23:58:27.427722Z", "email": "user@emaildomain.com", "group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "rbac_group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "type": "rbac_group_member", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" } ``` ### Remove RBAC Group Member `beta.organization.rbac_groups.members.remove(user_id, **kwargs) -> MemberRemoveResponse` **DELETE** `/v1/organizations/rbac_groups/{rbac_group_id}/members/{user_id}` Remove a User from an RBAC Group. Membership of groups provisioned by an identity provider (source type `"scim"`) cannot be modified via the API while an organization in the tenant uses SCIM provisioning. The RBAC Groups API is available to Claude Enterprise organizations only. #### Parameters - `rbac_group_id: str` (path parameter) ID of the RBAC Group. - `user_id: str` (path parameter) ID of the User. #### Returns - `class MemberRemoveResponse` - `type: Literal["rbac_group_member_deleted"]` Deleted object type. For RBAC Group Members, this is always `"rbac_group_member_deleted"`. default: rbac_group_member_deleted - `rbac_group_id: str` ID of the RBAC Group. - `user_id: str` ID of the User. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) member = client.beta.organization.rbac_groups.members.remove( user_id="user_id", rbac_group_id="rbac_group_id", ) print(member.rbac_group_id) ``` ##### Response (200) ```json { "group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "rbac_group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "type": "rbac_group_member_deleted", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" } ``` ## Beta › Organization › RBAC Roles ### List RBAC Roles `beta.organization.rbac_roles.list(**kwargs) -> SyncPageCursor[BetaRBACRole]` **GET** `/v1/organizations/rbac_roles` List RBAC Roles in the organization. The RBAC Roles API is available to Claude Enterprise organizations only. #### Parameters - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Optionally set to the `next_page` token from the previous response. #### Returns - `class BetaRBACRole` - `type: Literal["rbac_role"]` Object type. For RBAC Roles, this is always `"rbac_role"`. default: rbac_role - `id: str` ID of the RBAC Role. - `created_at: datetime` RFC 3339 datetime string indicating when the RBAC Role was created. format: date-time - `display_name: str` Name of the RBAC Role. For a role created by Anthropic, this name can differ from the label claude.ai shows, and Anthropic may change the name. To keep a lasting reference to a role, store its `id`. - `updated_at: datetime` RFC 3339 datetime string indicating when the RBAC Role was last updated. format: date-time - `name: str` **Deprecated**: Use `display_name` instead; `name` always has the same value. Deprecated: use `display_name` instead. Name of the RBAC Role; always the same value as `display_name`. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.rbac_roles.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s", "created_at": "2024-10-30T23:58:27.427722Z", "display_name": "Project Editor", "name": "Project Editor", "type": "rbac_role", "updated_at": "2024-10-30T23:58:27.427722Z" } ], "has_more": true, "next_page": "eyJjdXJzb3IiOiAicmJhY19yb2xlXzAxIn0" } ``` ### Get RBAC Role `beta.organization.rbac_roles.retrieve(rbac_role_id) -> BetaRBACRole` **GET** `/v1/organizations/rbac_roles/{rbac_role_id}` Retrieve an RBAC Role by ID. The RBAC Roles API is available to Claude Enterprise organizations only. #### Parameters - `rbac_role_id: str` (path parameter) ID of the RBAC Role. #### Returns - `class BetaRBACRole` - `type: Literal["rbac_role"]` Object type. For RBAC Roles, this is always `"rbac_role"`. default: rbac_role - `id: str` ID of the RBAC Role. - `created_at: datetime` RFC 3339 datetime string indicating when the RBAC Role was created. format: date-time - `display_name: str` Name of the RBAC Role. For a role created by Anthropic, this name can differ from the label claude.ai shows, and Anthropic may change the name. To keep a lasting reference to a role, store its `id`. - `updated_at: datetime` RFC 3339 datetime string indicating when the RBAC Role was last updated. format: date-time - `name: str` **Deprecated**: Use `display_name` instead; `name` always has the same value. Deprecated: use `display_name` instead. Name of the RBAC Role; always the same value as `display_name`. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_rbac_role = client.beta.organization.rbac_roles.retrieve( "rbac_role_id", ) print(beta_rbac_role.id) ``` ##### Response (200) ```json { "id": "rbac_role_016J8xVtKpDq3Wy9ZmN2hR4s", "created_at": "2024-10-30T23:58:27.427722Z", "display_name": "Project Editor", "name": "Project Editor", "type": "rbac_role", "updated_at": "2024-10-30T23:58:27.427722Z" } ``` ## Beta › Organization › RBAC Roles › Permissions ### List RBAC Role Permissions `beta.organization.rbac_roles.permissions.list(rbac_role_id, **kwargs) -> SyncPageCursor[BetaRBACRolePermission]` **GET** `/v1/organizations/rbac_roles/{rbac_role_id}/permissions` List the permissions an RBAC Role grants. The RBAC Roles API is available to Claude Enterprise organizations only. #### Parameters - `rbac_role_id: str` (path parameter) ID of the RBAC Role. - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 - `page: Optional[str]` (query parameter) Optionally set to the `next_page` token from the previous response. #### Returns - `class BetaRBACRolePermission` - `type: Literal["rbac_role_permission"]` Object type. For RBAC Role Permissions, this is always `"rbac_role_permission"`. default: rbac_role_permission - `action: str` Action the permission grants on the resource. The vocabulary follows the resource: an `organization` grant carries a product-feature entitlement (for example `chat`), an admin-panel permission entitlement (`permission_*`), or a blanket capability-access mode — `capability_access_all` grants every product-feature entitlement, and `capability_access_all_ga` grants the generally-available subset as it stands at permission-check time; neither mode grants model-access entitlements. A consumer enumerating a role's per-feature grants should treat a blanket row as granting every product-feature entitlement it covers, or it will under-report the role's effective access. A `connector_tool` grant carries a tool-access action (`use` or `always_allow`); a `connector_scope` grant carries the scope action `grant` (the role may receive the named OAuth scope when tokens are minted for the connector); `connector` and `all_connectors` grants carry a tool-access action, the scope action, or an authentication-method action (`interactive` or `managed`). - `resource: Resource` What the permission applies to. A tagged union: `type` names the kind of resource and determines which identifier fields are present. - `class BetaRBACOrganizationPermissionResource` - `type: Literal["organization"]` Kind of resource the permission applies to. default: organization - `organization_id: str` UUID of the organization the permission applies to. - `class BetaRBACConnectorToolPermissionResource` - `type: Literal["connector_tool"]` Kind of resource the permission applies to. default: connector_tool - `connector_id: str` ID of the connector the permission applies to. - `tool_name: str` Published name of the connector tool the permission applies to. When the published name contains characters outside `[a-zA-Z0-9_-]` (or collides with a reserved form), it is server-encoded into a stable `{prefix}_{32-hex}` form — a shortened readable prefix of the name plus a hash — from which the published name is not recoverable. - `class BetaRBACConnectorScopePermissionResource` - `type: Literal["connector_scope"]` Kind of resource the permission applies to. default: connector_scope - `connector_id: str` ID of the connector the permission applies to. - `scope: str` OAuth scope the permission names — the role may receive this scope when tokens are minted for the connector. Subject to the same encoding rule as `tool_name`: a scope containing characters outside `[a-zA-Z0-9_-]` (or colliding with a reserved form) appears server-encoded in a stable `{prefix}_{32-hex}` form. OAuth scopes routinely contain `:` and `/`, so most appear encoded. - `class BetaRBACConnectorPermissionResource` - `type: Literal["connector"]` Kind of resource the permission applies to. default: connector - `connector_id: str` ID of the connector the permission applies to. - `class BetaRBACAllConnectorsPermissionResource` - `type: Literal["all_connectors"]` Kind of resource the permission applies to. default: all_connectors #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.rbac_roles.permissions.list( rbac_role_id="rbac_role_id", ) page = page.data[0] print(page.action) ``` ##### Response (200) ```json { "data": [ { "action": "use", "resource": { "organization_id": "3c4f5e6d-7a8b-49c0-9d1e-2f3a4b5c6d7e", "type": "organization" }, "type": "rbac_role_permission" } ], "has_more": true, "next_page": "eyJjdXJzb3IiOiAicmJhY19yb2xlXzAxIn0" } ``` ## Beta › Organization › Plugins ### Create Plugin `beta.organization.plugins.create(**kwargs) -> BetaPlugin` **POST** `/v1/organizations/plugins` Create an organization-owned Plugin and its first version by uploading the version's files. The upload is `multipart/form-data`: the version's files (`files`, each part sent as `files[]`), with an optional `marketplace_id` and `release_notes`. The manifest's `name` becomes the Plugin's `name`, and `display_name`, `description` and `manifest_version` come from the manifest too. `name` may contain lowercase letters (from any alphabet), digits, and hyphens, up to 64 characters. Uppercase letters, spaces, underscores, and other punctuation are rejected. The `name` must be unique within the marketplace: a name already taken returns a 409 with `error_code` `plugin_name_taken` and, when a Plugin holds it, that Plugin's ID in `details.plugin_id`. A Plugin going into the organization's library marketplace is also refused with a 409 when one of its skills has the name of an organization skill (a skill an administrator uploaded for the whole organization in claude.ai): `error_code` `skill_name_taken`, with that name in `details.skill_name`; rename the skill, or remove the organization skill in claude.ai. A 503 with `error_code` `registration_pending` means the Plugin and its version were stored (their IDs are in `details`) but are not yet usable in claude.ai: do not retry the create (the retry would return `plugin_name_taken`); create a version on the stored Plugin instead, which completes it. For a worked example, see [Create a plugin](https://platform.claude.com/docs/en/manage-claude/plugins-api?sdk_languages=python#create-a-plugin) in the Plugins API guide. **Accepted credentials:** an Admin API key with the `write:plugins` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `files: Sequence[FileTypes]` The version's files: one part per file, the part's filename being the file's path within the Plugin (for example `skills/review-pr/SKILL.md`), or a single `.zip` or `.plugin` archive holding them all. On the wire each part is named `files[]`, and a part named plain `files` is not read; with cURL, `-F 'files[]=@SKILL.md;filename=skills/review-pr/SKILL.md'`. The files must include the manifest, `.claude-plugin/plugin.json`. - `marketplace_id: Optional[str]` ID of the organization-owned plugin marketplace to create the Plugin in (prefixed `marketplace_`). It must be a `manual` marketplace, one whose Plugins are uploaded rather than synchronized from a repository. When omitted, the Plugin is created in the organization's library marketplace, an organization-owned `manual` marketplace created on first use. - `release_notes: Optional[str]` Release notes stored with the version and shown in its version history in claude.ai; up to 5,000 characters. maxLength: 5000 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPlugin` - `type: Literal["plugin"]` Always `plugin`. default: plugin - `id: str` The Plugin's ID. - `components: Optional[List[BetaPluginComponent]]` What the served version contains; null when not enumerated. - `type: Literal["agent", "cli", "command", 3 more]` The kind of component. - `"agent"` - `"cli"` - `"command"` - `"hook"` - `"mcp_server"` - `"skill"` - `description: Optional[str]` What the component declares about itself; always null for MCP servers, hooks, and CLIs. - `name: str` The component's name: a skill's, command's or agent's name, an MCP server's key in the manifest, the event a hook runs on, or a CLI's executable. - `content_scan: Optional[BetaPluginContentScan]` The served version's content scan; null when it has not been scanned. - `assessment: Optional[Literal["fail", "pass", "unknown", "warn"]]` The scan's verdict; set only when `status` is `completed`. - `"fail"` - `"pass"` - `"unknown"` - `"warn"` - `reason: Optional[str]` The primary mechanism behind a `warn` or `fail`, such as `credential-exposure` or `guardrail-tampering`; a mechanism this API does not yet name reads as `other`. Null on a `pass`, whenever `assessment` is null, and when no mechanism is reported for the verdict. - `status: Literal["completed", "errored", "processing"]` `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run or its outcome cannot be read. - `"completed"` - `"errored"` - `"processing"` - `created_at: datetime` RFC 3339. format: date-time - `created_by: Optional[CreatedBy]` Who created the Plugin; null when no creator is recorded. - `class BetaPluginUserActor` - `type: Literal["user_actor"]` A member of the organization. default: user_actor - `email_address: Optional[str]` The member's email address; may be null, for example when they are no longer a member of the organization. - `user_id: str` The member's User ID. - `class BetaPluginAPIActor` - `type: Literal["api_actor"]` An Admin API key, in the same form the Compliance API activity feed uses for it. default: api_actor - `api_key_id: str` The key's ID. - `description: Optional[str]` The served version's description. - `display_name: Optional[str]` The served version's display name. - `latest_version_id: str` The newest version. - `manifest_version: Optional[str]` The version string the served version's manifest declares. - `marketplace_id: str` The ID of the plugin marketplace the Plugin lives in. - `name: str` Lowercase identifier, unique within its plugin marketplace. Fixed for an organization-owned Plugin's lifetime; a member-owned Plugin's changes when its owner renames it in claude.ai, while its `id` stays the same. - `organization_installation_preference: Optional[Literal["auto_install", "available", "not_available", "required"]]` Organization-owned Plugin: the organization-wide installation setting every member gets unless an RBAC Group they belong to holds its own — the Plugin's own setting, or its plugin marketplace's default. Null for a member-owned Plugin, which has shares instead. One of `required`, `auto_install`, `available`, `not_available`; a value this API does not yet name is returned as stored. - `"auto_install"` - `"available"` - `"not_available"` - `"required"` - `organization_installation_preference_inherited: Optional[bool]` Organization-owned Plugin: true while it has no organization-wide setting of its own and `organization_installation_preference` is its plugin marketplace's default. Null for a member-owned Plugin. - `owner: Owner` Who owns the Plugin: the organization, or the member whose personal plugin marketplace it lives in. - `class BetaPluginOwnerOrganization` - `type: Literal["organization"]` The Plugin lives in a plugin marketplace the organization owns. default: organization - `class BetaPluginOwnerUser` - `type: Literal["user"]` The Plugin lives in one member's personal plugin marketplace. default: user - `user_id: str` The member's User ID. - `reach: Optional[Literal["contained", "privileged", "remote"]]` How far the served version reaches: `remote` when it declares an MCP server or a CLI, `privileged` when it declares a hook, monitor, language server or settings but nothing remote, `contained` otherwise; null when not classifiable. - `"contained"` - `"privileged"` - `"remote"` - `served_version_id: str` The version claude.ai serves to members. - `served_version_pinned: bool` False while the served version follows each new version; true once it has been pinned to one. - `updated_at: datetime` RFC 3339. Moves on a new version and on a served-version change; a change to the Plugin's installation settings or shares does not move it. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_plugin = client.beta.organization.plugins.create( files=[b"Example data"], ) print(beta_plugin.id) ``` ##### Response (200) ```json { "id": "plugin_01JyHfbRkZvD1gW7oTqXc3Ne", "components": [ { "description": "description", "name": "review-pr", "type": "skill" } ], "content_scan": { "assessment": "warn", "reason": "credential-exposure", "status": "completed" }, "created_at": "2026-03-14T09:26:53.589793Z", "created_by": { "email_address": "user@example.com", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "description": "Reviews pull requests against your team's conventions.", "display_name": "Code Review Helper", "latest_version_id": "pluginver_01KaZmQpRsTuVwXyZ2b4c6d8", "manifest_version": "1.2.0", "marketplace_id": "marketplace_01HxQ3v9KpZ2mTn8RwLc4Ys7", "name": "code-review-helper", "organization_installation_preference": "available", "organization_installation_preference_inherited": true, "owner": { "type": "organization" }, "reach": "contained", "served_version_id": "pluginver_01K9wPcHd4Rm2Tx8Vq6Ln3Sb", "served_version_pinned": true, "type": "plugin", "updated_at": "2026-03-14T09:26:53.589793Z" } ``` ### Get Plugin `beta.organization.plugins.retrieve(plugin_id, **kwargs) -> BetaPlugin` **GET** `/v1/organizations/plugins/{plugin_id}` Retrieve a Plugin by ID. **Accepted credentials:** an Admin API key with the `read:plugins` or `read:org_audit` scope, or a Compliance Access Key with the `read:compliance_org_data` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `plugin_id: str` (path parameter) ID of the Plugin (prefixed `plugin_`). - `organization_id: Optional[str]` (query parameter) For a `read:org_audit` or `read:compliance_org_data` key created for all of a parent organization's linked organizations: a child organization of that parent to read instead of the organization the key was created in, given as the organization's UUID or its `org_`-prefixed ID. A value that is neither returns a 400; an organization that is not a child of the key's parent, or where the Plugins API is not available, returns a 404. Any other key may pass only its own organization's ID here; another organization returns a 404. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPlugin` - `type: Literal["plugin"]` Always `plugin`. default: plugin - `id: str` The Plugin's ID. - `components: Optional[List[BetaPluginComponent]]` What the served version contains; null when not enumerated. - `type: Literal["agent", "cli", "command", 3 more]` The kind of component. - `"agent"` - `"cli"` - `"command"` - `"hook"` - `"mcp_server"` - `"skill"` - `description: Optional[str]` What the component declares about itself; always null for MCP servers, hooks, and CLIs. - `name: str` The component's name: a skill's, command's or agent's name, an MCP server's key in the manifest, the event a hook runs on, or a CLI's executable. - `content_scan: Optional[BetaPluginContentScan]` The served version's content scan; null when it has not been scanned. - `assessment: Optional[Literal["fail", "pass", "unknown", "warn"]]` The scan's verdict; set only when `status` is `completed`. - `"fail"` - `"pass"` - `"unknown"` - `"warn"` - `reason: Optional[str]` The primary mechanism behind a `warn` or `fail`, such as `credential-exposure` or `guardrail-tampering`; a mechanism this API does not yet name reads as `other`. Null on a `pass`, whenever `assessment` is null, and when no mechanism is reported for the verdict. - `status: Literal["completed", "errored", "processing"]` `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run or its outcome cannot be read. - `"completed"` - `"errored"` - `"processing"` - `created_at: datetime` RFC 3339. format: date-time - `created_by: Optional[CreatedBy]` Who created the Plugin; null when no creator is recorded. - `class BetaPluginUserActor` - `type: Literal["user_actor"]` A member of the organization. default: user_actor - `email_address: Optional[str]` The member's email address; may be null, for example when they are no longer a member of the organization. - `user_id: str` The member's User ID. - `class BetaPluginAPIActor` - `type: Literal["api_actor"]` An Admin API key, in the same form the Compliance API activity feed uses for it. default: api_actor - `api_key_id: str` The key's ID. - `description: Optional[str]` The served version's description. - `display_name: Optional[str]` The served version's display name. - `latest_version_id: str` The newest version. - `manifest_version: Optional[str]` The version string the served version's manifest declares. - `marketplace_id: str` The ID of the plugin marketplace the Plugin lives in. - `name: str` Lowercase identifier, unique within its plugin marketplace. Fixed for an organization-owned Plugin's lifetime; a member-owned Plugin's changes when its owner renames it in claude.ai, while its `id` stays the same. - `organization_installation_preference: Optional[Literal["auto_install", "available", "not_available", "required"]]` Organization-owned Plugin: the organization-wide installation setting every member gets unless an RBAC Group they belong to holds its own — the Plugin's own setting, or its plugin marketplace's default. Null for a member-owned Plugin, which has shares instead. One of `required`, `auto_install`, `available`, `not_available`; a value this API does not yet name is returned as stored. - `"auto_install"` - `"available"` - `"not_available"` - `"required"` - `organization_installation_preference_inherited: Optional[bool]` Organization-owned Plugin: true while it has no organization-wide setting of its own and `organization_installation_preference` is its plugin marketplace's default. Null for a member-owned Plugin. - `owner: Owner` Who owns the Plugin: the organization, or the member whose personal plugin marketplace it lives in. - `class BetaPluginOwnerOrganization` - `type: Literal["organization"]` The Plugin lives in a plugin marketplace the organization owns. default: organization - `class BetaPluginOwnerUser` - `type: Literal["user"]` The Plugin lives in one member's personal plugin marketplace. default: user - `user_id: str` The member's User ID. - `reach: Optional[Literal["contained", "privileged", "remote"]]` How far the served version reaches: `remote` when it declares an MCP server or a CLI, `privileged` when it declares a hook, monitor, language server or settings but nothing remote, `contained` otherwise; null when not classifiable. - `"contained"` - `"privileged"` - `"remote"` - `served_version_id: str` The version claude.ai serves to members. - `served_version_pinned: bool` False while the served version follows each new version; true once it has been pinned to one. - `updated_at: datetime` RFC 3339. Moves on a new version and on a served-version change; a change to the Plugin's installation settings or shares does not move it. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_plugin = client.beta.organization.plugins.retrieve( plugin_id="plugin_id", ) print(beta_plugin.id) ``` ##### Response (200) ```json { "id": "plugin_01JyHfbRkZvD1gW7oTqXc3Ne", "components": [ { "description": "description", "name": "review-pr", "type": "skill" } ], "content_scan": { "assessment": "warn", "reason": "credential-exposure", "status": "completed" }, "created_at": "2026-03-14T09:26:53.589793Z", "created_by": { "email_address": "user@example.com", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "description": "Reviews pull requests against your team's conventions.", "display_name": "Code Review Helper", "latest_version_id": "pluginver_01KaZmQpRsTuVwXyZ2b4c6d8", "manifest_version": "1.2.0", "marketplace_id": "marketplace_01HxQ3v9KpZ2mTn8RwLc4Ys7", "name": "code-review-helper", "organization_installation_preference": "available", "organization_installation_preference_inherited": true, "owner": { "type": "organization" }, "reach": "contained", "served_version_id": "pluginver_01K9wPcHd4Rm2Tx8Vq6Ln3Sb", "served_version_pinned": true, "type": "plugin", "updated_at": "2026-03-14T09:26:53.589793Z" } ``` ### Update Plugin `beta.organization.plugins.update(plugin_id, **kwargs) -> BetaPlugin` **POST** `/v1/organizations/plugins/{plugin_id}` Change which stored version of an organization-owned Plugin is served to members, for example to roll back to an earlier one. This pins the served version: later uploads are stored but no longer change what is served, and pinning cannot currently be undone, here or in claude.ai. Pass the version as `served_version_id`: an earlier one to roll back, a later one to start serving a version that was stored without being served, or the one already served to pin it without changing what is served. No new version is created. When the organization has content scanning enabled, a version whose scan is still running is refused with a 409 (`error_code` `scan_pending`; retry once the scan finishes) and one whose scan failed, errored or reached no verdict with a 400 (`scan_failed`; a `warn` is accepted). When the Plugin is in the organization's library marketplace, a version other than the one served is also refused with a 409 when one of its skills has a name that an organization skill (one an administrator uploaded for the whole organization in claude.ai) has since taken: `error_code` `skill_name_taken`, with that name in `details.skill_name`. A member-owned Plugin cannot be updated here (403). This endpoint does not write installation settings; they are written at `/v1/organizations/plugins/{plugin_id}/installation_settings/{target}`. **Accepted credentials:** an Admin API key with the `write:plugins` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `plugin_id: str` (path parameter) ID of the Plugin (prefixed `plugin_`). - `served_version_id: str` Serve this version of the Plugin (prefixed `pluginver_`) and pin the served version to it; `latest` is not accepted. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPlugin` - `type: Literal["plugin"]` Always `plugin`. default: plugin - `id: str` The Plugin's ID. - `components: Optional[List[BetaPluginComponent]]` What the served version contains; null when not enumerated. - `type: Literal["agent", "cli", "command", 3 more]` The kind of component. - `"agent"` - `"cli"` - `"command"` - `"hook"` - `"mcp_server"` - `"skill"` - `description: Optional[str]` What the component declares about itself; always null for MCP servers, hooks, and CLIs. - `name: str` The component's name: a skill's, command's or agent's name, an MCP server's key in the manifest, the event a hook runs on, or a CLI's executable. - `content_scan: Optional[BetaPluginContentScan]` The served version's content scan; null when it has not been scanned. - `assessment: Optional[Literal["fail", "pass", "unknown", "warn"]]` The scan's verdict; set only when `status` is `completed`. - `"fail"` - `"pass"` - `"unknown"` - `"warn"` - `reason: Optional[str]` The primary mechanism behind a `warn` or `fail`, such as `credential-exposure` or `guardrail-tampering`; a mechanism this API does not yet name reads as `other`. Null on a `pass`, whenever `assessment` is null, and when no mechanism is reported for the verdict. - `status: Literal["completed", "errored", "processing"]` `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run or its outcome cannot be read. - `"completed"` - `"errored"` - `"processing"` - `created_at: datetime` RFC 3339. format: date-time - `created_by: Optional[CreatedBy]` Who created the Plugin; null when no creator is recorded. - `class BetaPluginUserActor` - `type: Literal["user_actor"]` A member of the organization. default: user_actor - `email_address: Optional[str]` The member's email address; may be null, for example when they are no longer a member of the organization. - `user_id: str` The member's User ID. - `class BetaPluginAPIActor` - `type: Literal["api_actor"]` An Admin API key, in the same form the Compliance API activity feed uses for it. default: api_actor - `api_key_id: str` The key's ID. - `description: Optional[str]` The served version's description. - `display_name: Optional[str]` The served version's display name. - `latest_version_id: str` The newest version. - `manifest_version: Optional[str]` The version string the served version's manifest declares. - `marketplace_id: str` The ID of the plugin marketplace the Plugin lives in. - `name: str` Lowercase identifier, unique within its plugin marketplace. Fixed for an organization-owned Plugin's lifetime; a member-owned Plugin's changes when its owner renames it in claude.ai, while its `id` stays the same. - `organization_installation_preference: Optional[Literal["auto_install", "available", "not_available", "required"]]` Organization-owned Plugin: the organization-wide installation setting every member gets unless an RBAC Group they belong to holds its own — the Plugin's own setting, or its plugin marketplace's default. Null for a member-owned Plugin, which has shares instead. One of `required`, `auto_install`, `available`, `not_available`; a value this API does not yet name is returned as stored. - `"auto_install"` - `"available"` - `"not_available"` - `"required"` - `organization_installation_preference_inherited: Optional[bool]` Organization-owned Plugin: true while it has no organization-wide setting of its own and `organization_installation_preference` is its plugin marketplace's default. Null for a member-owned Plugin. - `owner: Owner` Who owns the Plugin: the organization, or the member whose personal plugin marketplace it lives in. - `class BetaPluginOwnerOrganization` - `type: Literal["organization"]` The Plugin lives in a plugin marketplace the organization owns. default: organization - `class BetaPluginOwnerUser` - `type: Literal["user"]` The Plugin lives in one member's personal plugin marketplace. default: user - `user_id: str` The member's User ID. - `reach: Optional[Literal["contained", "privileged", "remote"]]` How far the served version reaches: `remote` when it declares an MCP server or a CLI, `privileged` when it declares a hook, monitor, language server or settings but nothing remote, `contained` otherwise; null when not classifiable. - `"contained"` - `"privileged"` - `"remote"` - `served_version_id: str` The version claude.ai serves to members. - `served_version_pinned: bool` False while the served version follows each new version; true once it has been pinned to one. - `updated_at: datetime` RFC 3339. Moves on a new version and on a served-version change; a change to the Plugin's installation settings or shares does not move it. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_plugin = client.beta.organization.plugins.update( plugin_id="plugin_id", served_version_id="pluginver_01KaZmQpRsTuVwXyZ2b4c6d8", ) print(beta_plugin.id) ``` ##### Response (200) ```json { "id": "plugin_01JyHfbRkZvD1gW7oTqXc3Ne", "components": [ { "description": "description", "name": "review-pr", "type": "skill" } ], "content_scan": { "assessment": "warn", "reason": "credential-exposure", "status": "completed" }, "created_at": "2026-03-14T09:26:53.589793Z", "created_by": { "email_address": "user@example.com", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "description": "Reviews pull requests against your team's conventions.", "display_name": "Code Review Helper", "latest_version_id": "pluginver_01KaZmQpRsTuVwXyZ2b4c6d8", "manifest_version": "1.2.0", "marketplace_id": "marketplace_01HxQ3v9KpZ2mTn8RwLc4Ys7", "name": "code-review-helper", "organization_installation_preference": "available", "organization_installation_preference_inherited": true, "owner": { "type": "organization" }, "reach": "contained", "served_version_id": "pluginver_01K9wPcHd4Rm2Tx8Vq6Ln3Sb", "served_version_pinned": true, "type": "plugin", "updated_at": "2026-03-14T09:26:53.589793Z" } ``` ### List Plugins `beta.organization.plugins.list(**kwargs) -> SyncPageCursor[BetaPlugin]` **GET** `/v1/organizations/plugins` List the Plugins created under the organization, newest first: those in the organization's own plugin marketplaces and those in members' personal plugin marketplaces. Plugins in members' personal marketplaces are listed with the same detail as the organization's own, and their files can be downloaded through the version archive endpoint, which records each such download on the Compliance API activity feed. **Accepted credentials:** an Admin API key with the `read:plugins` or `read:org_audit` scope, or a Compliance Access Key with the `read:compliance_org_data` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `created_at_gt: Optional[Union[str, datetime, null]]` (query parameter) RFC 3339 timestamp bound; combine [gte], [gt], [lte], [lt]. format: date-time - `created_at_gte: Optional[Union[str, datetime, null]]` (query parameter) RFC 3339 timestamp bound; combine [gte], [gt], [lte], [lt]. format: date-time - `created_at_lt: Optional[Union[str, datetime, null]]` (query parameter) RFC 3339 timestamp bound; combine [gte], [gt], [lte], [lt]. format: date-time - `created_at_lte: Optional[Union[str, datetime, null]]` (query parameter) RFC 3339 timestamp bound; combine [gte], [gt], [lte], [lt]. format: date-time - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `100`. default: 20, minimum: 1, maximum: 100 - `marketplace_id: Optional[str]` (query parameter) Only Plugins in this plugin marketplace (prefixed `marketplace_`). - `organization_id: Optional[str]` (query parameter) For a `read:org_audit` or `read:compliance_org_data` key created for all of a parent organization's linked organizations: a child organization of that parent to read instead of the organization the key was created in, given as the organization's UUID or its `org_`-prefixed ID. A value that is neither returns a 400; an organization that is not a child of the key's parent, or where the Plugins API is not available, returns a 404. Any other key may pass only its own organization's ID here; another organization returns a 404. - `owner_type: Optional[Literal["organization", "user"]]` (query parameter) `organization` for Plugins in the organization's plugin marketplaces, `user` for Plugins in members' personal plugin marketplaces. - `"organization"` - `"user"` - `owner_user_id: Optional[str]` (query parameter) Only Plugins in this member's personal plugin marketplaces (prefixed `user_`); a removed member's ID is accepted. - `page: Optional[str]` (query parameter) Optionally set to the `next_page` token from the previous response. maxLength: 2048 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPlugin` - `type: Literal["plugin"]` Always `plugin`. default: plugin - `id: str` The Plugin's ID. - `components: Optional[List[BetaPluginComponent]]` What the served version contains; null when not enumerated. - `type: Literal["agent", "cli", "command", 3 more]` The kind of component. - `"agent"` - `"cli"` - `"command"` - `"hook"` - `"mcp_server"` - `"skill"` - `description: Optional[str]` What the component declares about itself; always null for MCP servers, hooks, and CLIs. - `name: str` The component's name: a skill's, command's or agent's name, an MCP server's key in the manifest, the event a hook runs on, or a CLI's executable. - `content_scan: Optional[BetaPluginContentScan]` The served version's content scan; null when it has not been scanned. - `assessment: Optional[Literal["fail", "pass", "unknown", "warn"]]` The scan's verdict; set only when `status` is `completed`. - `"fail"` - `"pass"` - `"unknown"` - `"warn"` - `reason: Optional[str]` The primary mechanism behind a `warn` or `fail`, such as `credential-exposure` or `guardrail-tampering`; a mechanism this API does not yet name reads as `other`. Null on a `pass`, whenever `assessment` is null, and when no mechanism is reported for the verdict. - `status: Literal["completed", "errored", "processing"]` `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run or its outcome cannot be read. - `"completed"` - `"errored"` - `"processing"` - `created_at: datetime` RFC 3339. format: date-time - `created_by: Optional[CreatedBy]` Who created the Plugin; null when no creator is recorded. - `class BetaPluginUserActor` - `type: Literal["user_actor"]` A member of the organization. default: user_actor - `email_address: Optional[str]` The member's email address; may be null, for example when they are no longer a member of the organization. - `user_id: str` The member's User ID. - `class BetaPluginAPIActor` - `type: Literal["api_actor"]` An Admin API key, in the same form the Compliance API activity feed uses for it. default: api_actor - `api_key_id: str` The key's ID. - `description: Optional[str]` The served version's description. - `display_name: Optional[str]` The served version's display name. - `latest_version_id: str` The newest version. - `manifest_version: Optional[str]` The version string the served version's manifest declares. - `marketplace_id: str` The ID of the plugin marketplace the Plugin lives in. - `name: str` Lowercase identifier, unique within its plugin marketplace. Fixed for an organization-owned Plugin's lifetime; a member-owned Plugin's changes when its owner renames it in claude.ai, while its `id` stays the same. - `organization_installation_preference: Optional[Literal["auto_install", "available", "not_available", "required"]]` Organization-owned Plugin: the organization-wide installation setting every member gets unless an RBAC Group they belong to holds its own — the Plugin's own setting, or its plugin marketplace's default. Null for a member-owned Plugin, which has shares instead. One of `required`, `auto_install`, `available`, `not_available`; a value this API does not yet name is returned as stored. - `"auto_install"` - `"available"` - `"not_available"` - `"required"` - `organization_installation_preference_inherited: Optional[bool]` Organization-owned Plugin: true while it has no organization-wide setting of its own and `organization_installation_preference` is its plugin marketplace's default. Null for a member-owned Plugin. - `owner: Owner` Who owns the Plugin: the organization, or the member whose personal plugin marketplace it lives in. - `class BetaPluginOwnerOrganization` - `type: Literal["organization"]` The Plugin lives in a plugin marketplace the organization owns. default: organization - `class BetaPluginOwnerUser` - `type: Literal["user"]` The Plugin lives in one member's personal plugin marketplace. default: user - `user_id: str` The member's User ID. - `reach: Optional[Literal["contained", "privileged", "remote"]]` How far the served version reaches: `remote` when it declares an MCP server or a CLI, `privileged` when it declares a hook, monitor, language server or settings but nothing remote, `contained` otherwise; null when not classifiable. - `"contained"` - `"privileged"` - `"remote"` - `served_version_id: str` The version claude.ai serves to members. - `served_version_pinned: bool` False while the served version follows each new version; true once it has been pinned to one. - `updated_at: datetime` RFC 3339. Moves on a new version and on a served-version change; a change to the Plugin's installation settings or shares does not move it. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.plugins.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "plugin_01JyHfbRkZvD1gW7oTqXc3Ne", "components": [ { "description": "description", "name": "review-pr", "type": "skill" } ], "content_scan": { "assessment": "warn", "reason": "credential-exposure", "status": "completed" }, "created_at": "2026-03-14T09:26:53.589793Z", "created_by": { "email_address": "user@example.com", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "description": "Reviews pull requests against your team's conventions.", "display_name": "Code Review Helper", "latest_version_id": "pluginver_01KaZmQpRsTuVwXyZ2b4c6d8", "manifest_version": "1.2.0", "marketplace_id": "marketplace_01HxQ3v9KpZ2mTn8RwLc4Ys7", "name": "code-review-helper", "organization_installation_preference": "available", "organization_installation_preference_inherited": true, "owner": { "type": "organization" }, "reach": "contained", "served_version_id": "pluginver_01K9wPcHd4Rm2Tx8Vq6Ln3Sb", "served_version_pinned": true, "type": "plugin", "updated_at": "2026-03-14T09:26:53.589793Z" } ], "next_page": "page_MjAyNi0wOS0xNlQxNDowNTowOVo" } ``` ### Delete Plugin `beta.organization.plugins.delete(plugin_id, **kwargs) -> BetaDeletedPlugin` **DELETE** `/v1/organizations/plugins/{plugin_id}` Permanently delete a Plugin and every version it holds, exactly as when an administrator deletes it in claude.ai. The Plugin may belong to the organization or to a member, including a member who has since left the organization. An organization-owned Plugin's installation settings go with it; a member-owned Plugin's shares are withdrawn and its owner no longer has it. To take an organization-owned Plugin out of use reversibly, set its organization-wide installation setting to `not_available` instead (and remove or change any group settings, which override it for their members). Only a Plugin in a `manual` marketplace can be deleted here; one synchronized from a repository is removed by removing it from the repository (400). **Accepted credentials:** an Admin API key with the `write:plugins` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `plugin_id: str` (path parameter) ID of the Plugin (prefixed `plugin_`). - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaDeletedPlugin` - `type: Literal["plugin_deleted"]` Always `plugin_deleted`. default: plugin_deleted - `id: str` The deleted Plugin's ID. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_deleted_plugin = client.beta.organization.plugins.delete( plugin_id="plugin_id", ) print(beta_deleted_plugin.id) ``` ##### Response (200) ```json { "id": "plugin_01JyHfbRkZvD1gW7oTqXc3Ne", "type": "plugin_deleted" } ``` ## Beta › Organization › Plugins › Versions ### Create Plugin Version `beta.organization.plugins.versions.create(plugin_id, **kwargs) -> BetaPluginVersion` **POST** `/v1/organizations/plugins/{plugin_id}/versions` Add a version to an organization-owned Plugin by uploading the new version's files; it becomes the version served to members unless the Plugin's served version has been pinned. The upload is the same `multipart/form-data` as creating a Plugin: the version's files (`files`, each part sent as `files[]`) and optional `release_notes`. The uploaded manifest's `name` must equal the Plugin's `name`. Returns the stored version; read the Plugin back to see which version it serves. Only a Plugin in a `manual` marketplace takes uploads; a Plugin synchronized from a repository gets its versions from the repository. When the Plugin is in the organization's library marketplace, a version that adds a skill with the name of an organization skill (a skill an administrator uploaded for the whole organization in claude.ai) is refused with a 409: `error_code` `skill_name_taken`, with that name in `details.skill_name`. A 503 with `error_code` `registration_pending` means the version was stored but is not yet usable; a later version create on the Plugin completes it. For a worked example, see [Create a version](https://platform.claude.com/docs/en/manage-claude/plugins-api?sdk_languages=python#create-a-version) in the Plugins API guide. **Accepted credentials:** an Admin API key with the `write:plugins` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `plugin_id: str` (path parameter) ID of the Plugin (prefixed `plugin_`). - `files: Sequence[FileTypes]` The version's files: one part per file, the part's filename being the file's path within the Plugin (for example `skills/review-pr/SKILL.md`), or a single `.zip` or `.plugin` archive holding them all. On the wire each part is named `files[]`, and a part named plain `files` is not read; with cURL, `-F 'files[]=@SKILL.md;filename=skills/review-pr/SKILL.md'`. The files must include the manifest, `.claude-plugin/plugin.json`. - `release_notes: Optional[str]` Release notes stored with the version and shown in its version history in claude.ai; up to 5,000 characters. maxLength: 5000 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPluginVersion` - `type: Literal["plugin_version"]` Always `plugin_version`. default: plugin_version - `id: str` The version's ID. - `components: Optional[List[BetaPluginComponent]]` What the version contains; null when not enumerated. - `type: Literal["agent", "cli", "command", 3 more]` The kind of component. - `"agent"` - `"cli"` - `"command"` - `"hook"` - `"mcp_server"` - `"skill"` - `description: Optional[str]` What the component declares about itself; always null for MCP servers, hooks, and CLIs. - `name: str` The component's name: a skill's, command's or agent's name, an MCP server's key in the manifest, the event a hook runs on, or a CLI's executable. - `content_scan: Optional[BetaPluginContentScan]` This version's content scan; null when it has not been scanned. - `assessment: Optional[Literal["fail", "pass", "unknown", "warn"]]` The scan's verdict; set only when `status` is `completed`. - `"fail"` - `"pass"` - `"unknown"` - `"warn"` - `reason: Optional[str]` The primary mechanism behind a `warn` or `fail`, such as `credential-exposure` or `guardrail-tampering`; a mechanism this API does not yet name reads as `other`. Null on a `pass`, whenever `assessment` is null, and when no mechanism is reported for the verdict. - `status: Literal["completed", "errored", "processing"]` `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run or its outcome cannot be read. - `"completed"` - `"errored"` - `"processing"` - `created_at: datetime` RFC 3339. format: date-time - `created_by: Optional[CreatedBy]` Who uploaded this version; null when not recorded. - `class BetaPluginUserActor` - `type: Literal["user_actor"]` A member of the organization. default: user_actor - `email_address: Optional[str]` The member's email address; may be null, for example when they are no longer a member of the organization. - `user_id: str` The member's User ID. - `class BetaPluginAPIActor` - `type: Literal["api_actor"]` An Admin API key, in the same form the Compliance API activity feed uses for it. default: api_actor - `api_key_id: str` The key's ID. - `description: Optional[str]` The manifest's description; null when it declares none. - `display_name: Optional[str]` The manifest's display name; null when it declares none. - `manifest_version: Optional[str]` The version string the manifest declares; null when it declares none. - `plugin_id: str` The Plugin's ID. - `reach: Optional[Literal["contained", "privileged", "remote"]]` How far the version reaches: `remote`, `privileged` or `contained`, as on the Plugin; null when not classifiable. - `"contained"` - `"privileged"` - `"remote"` - `release_notes: Optional[str]` As supplied with the upload; null when none were supplied. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_plugin_version = client.beta.organization.plugins.versions.create( plugin_id="plugin_id", files=[b"Example data"], ) print(beta_plugin_version.id) ``` ##### Response (200) ```json { "id": "pluginver_01KaZmQpRsTuVwXyZ2b4c6d8", "components": [ { "description": "description", "name": "review-pr", "type": "skill" } ], "content_scan": { "assessment": "warn", "reason": "credential-exposure", "status": "completed" }, "created_at": "2026-03-14T09:26:53.589793Z", "created_by": { "email_address": "user@example.com", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "description": "Reviews pull requests against your team's conventions.", "display_name": "Code Review Helper", "manifest_version": "1.2.0", "plugin_id": "plugin_01JyHfbRkZvD1gW7oTqXc3Ne", "reach": "contained", "release_notes": "Adds a review checklist for database migrations.", "type": "plugin_version" } ``` ### List Plugin Versions `beta.organization.plugins.versions.list(plugin_id, **kwargs) -> SyncPageCursor[BetaPluginVersion]` **GET** `/v1/organizations/plugins/{plugin_id}/versions` List a Plugin's versions, newest first. The first item of the first page is the version the Plugin's `latest_version_id` refers to. **Accepted credentials:** an Admin API key with the `read:plugins` or `read:org_audit` scope, or a Compliance Access Key with the `read:compliance_org_data` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `plugin_id: str` (path parameter) ID of the Plugin (prefixed `plugin_`). - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 - `organization_id: Optional[str]` (query parameter) For a `read:org_audit` or `read:compliance_org_data` key created for all of a parent organization's linked organizations: a child organization of that parent to read instead of the organization the key was created in, given as the organization's UUID or its `org_`-prefixed ID. A value that is neither returns a 400; an organization that is not a child of the key's parent, or where the Plugins API is not available, returns a 404. Any other key may pass only its own organization's ID here; another organization returns a 404. - `page: Optional[str]` (query parameter) Optionally set to the `next_page` token from the previous response. maxLength: 2048 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPluginVersion` - `type: Literal["plugin_version"]` Always `plugin_version`. default: plugin_version - `id: str` The version's ID. - `components: Optional[List[BetaPluginComponent]]` What the version contains; null when not enumerated. - `type: Literal["agent", "cli", "command", 3 more]` The kind of component. - `"agent"` - `"cli"` - `"command"` - `"hook"` - `"mcp_server"` - `"skill"` - `description: Optional[str]` What the component declares about itself; always null for MCP servers, hooks, and CLIs. - `name: str` The component's name: a skill's, command's or agent's name, an MCP server's key in the manifest, the event a hook runs on, or a CLI's executable. - `content_scan: Optional[BetaPluginContentScan]` This version's content scan; null when it has not been scanned. - `assessment: Optional[Literal["fail", "pass", "unknown", "warn"]]` The scan's verdict; set only when `status` is `completed`. - `"fail"` - `"pass"` - `"unknown"` - `"warn"` - `reason: Optional[str]` The primary mechanism behind a `warn` or `fail`, such as `credential-exposure` or `guardrail-tampering`; a mechanism this API does not yet name reads as `other`. Null on a `pass`, whenever `assessment` is null, and when no mechanism is reported for the verdict. - `status: Literal["completed", "errored", "processing"]` `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run or its outcome cannot be read. - `"completed"` - `"errored"` - `"processing"` - `created_at: datetime` RFC 3339. format: date-time - `created_by: Optional[CreatedBy]` Who uploaded this version; null when not recorded. - `class BetaPluginUserActor` - `type: Literal["user_actor"]` A member of the organization. default: user_actor - `email_address: Optional[str]` The member's email address; may be null, for example when they are no longer a member of the organization. - `user_id: str` The member's User ID. - `class BetaPluginAPIActor` - `type: Literal["api_actor"]` An Admin API key, in the same form the Compliance API activity feed uses for it. default: api_actor - `api_key_id: str` The key's ID. - `description: Optional[str]` The manifest's description; null when it declares none. - `display_name: Optional[str]` The manifest's display name; null when it declares none. - `manifest_version: Optional[str]` The version string the manifest declares; null when it declares none. - `plugin_id: str` The Plugin's ID. - `reach: Optional[Literal["contained", "privileged", "remote"]]` How far the version reaches: `remote`, `privileged` or `contained`, as on the Plugin; null when not classifiable. - `"contained"` - `"privileged"` - `"remote"` - `release_notes: Optional[str]` As supplied with the upload; null when none were supplied. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.plugins.versions.list( plugin_id="plugin_id", ) page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "pluginver_01KaZmQpRsTuVwXyZ2b4c6d8", "components": [ { "description": "description", "name": "review-pr", "type": "skill" } ], "content_scan": { "assessment": "warn", "reason": "credential-exposure", "status": "completed" }, "created_at": "2026-03-14T09:26:53.589793Z", "created_by": { "email_address": "user@example.com", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "description": "Reviews pull requests against your team's conventions.", "display_name": "Code Review Helper", "manifest_version": "1.2.0", "plugin_id": "plugin_01JyHfbRkZvD1gW7oTqXc3Ne", "reach": "contained", "release_notes": "Adds a review checklist for database migrations.", "type": "plugin_version" } ], "next_page": "page_MjAyNi0wOS0xNlQxNDowNTowOVo" } ``` ### Get Plugin Version `beta.organization.plugins.versions.retrieve(version, **kwargs) -> BetaPluginVersion` **GET** `/v1/organizations/plugins/{plugin_id}/versions/{version}` Retrieve one version of a Plugin by its ID, or the Plugin's newest version. **Accepted credentials:** an Admin API key with the `read:plugins` or `read:org_audit` scope, or a Compliance Access Key with the `read:compliance_org_data` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `plugin_id: str` (path parameter) ID of the Plugin (prefixed `plugin_`). - `version: str` (path parameter) ID of the Plugin Version (prefixed `pluginver_`), or `latest` for the newest one. - `organization_id: Optional[str]` (query parameter) For a `read:org_audit` or `read:compliance_org_data` key created for all of a parent organization's linked organizations: a child organization of that parent to read instead of the organization the key was created in, given as the organization's UUID or its `org_`-prefixed ID. A value that is neither returns a 400; an organization that is not a child of the key's parent, or where the Plugins API is not available, returns a 404. Any other key may pass only its own organization's ID here; another organization returns a 404. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPluginVersion` - `type: Literal["plugin_version"]` Always `plugin_version`. default: plugin_version - `id: str` The version's ID. - `components: Optional[List[BetaPluginComponent]]` What the version contains; null when not enumerated. - `type: Literal["agent", "cli", "command", 3 more]` The kind of component. - `"agent"` - `"cli"` - `"command"` - `"hook"` - `"mcp_server"` - `"skill"` - `description: Optional[str]` What the component declares about itself; always null for MCP servers, hooks, and CLIs. - `name: str` The component's name: a skill's, command's or agent's name, an MCP server's key in the manifest, the event a hook runs on, or a CLI's executable. - `content_scan: Optional[BetaPluginContentScan]` This version's content scan; null when it has not been scanned. - `assessment: Optional[Literal["fail", "pass", "unknown", "warn"]]` The scan's verdict; set only when `status` is `completed`. - `"fail"` - `"pass"` - `"unknown"` - `"warn"` - `reason: Optional[str]` The primary mechanism behind a `warn` or `fail`, such as `credential-exposure` or `guardrail-tampering`; a mechanism this API does not yet name reads as `other`. Null on a `pass`, whenever `assessment` is null, and when no mechanism is reported for the verdict. - `status: Literal["completed", "errored", "processing"]` `processing` while a scan runs, `completed` when it ran to completion, `errored` when it could not run or its outcome cannot be read. - `"completed"` - `"errored"` - `"processing"` - `created_at: datetime` RFC 3339. format: date-time - `created_by: Optional[CreatedBy]` Who uploaded this version; null when not recorded. - `class BetaPluginUserActor` - `type: Literal["user_actor"]` A member of the organization. default: user_actor - `email_address: Optional[str]` The member's email address; may be null, for example when they are no longer a member of the organization. - `user_id: str` The member's User ID. - `class BetaPluginAPIActor` - `type: Literal["api_actor"]` An Admin API key, in the same form the Compliance API activity feed uses for it. default: api_actor - `api_key_id: str` The key's ID. - `description: Optional[str]` The manifest's description; null when it declares none. - `display_name: Optional[str]` The manifest's display name; null when it declares none. - `manifest_version: Optional[str]` The version string the manifest declares; null when it declares none. - `plugin_id: str` The Plugin's ID. - `reach: Optional[Literal["contained", "privileged", "remote"]]` How far the version reaches: `remote`, `privileged` or `contained`, as on the Plugin; null when not classifiable. - `"contained"` - `"privileged"` - `"remote"` - `release_notes: Optional[str]` As supplied with the upload; null when none were supplied. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_plugin_version = client.beta.organization.plugins.versions.retrieve( version="version", plugin_id="plugin_id", ) print(beta_plugin_version.id) ``` ##### Response (200) ```json { "id": "pluginver_01KaZmQpRsTuVwXyZ2b4c6d8", "components": [ { "description": "description", "name": "review-pr", "type": "skill" } ], "content_scan": { "assessment": "warn", "reason": "credential-exposure", "status": "completed" }, "created_at": "2026-03-14T09:26:53.589793Z", "created_by": { "email_address": "user@example.com", "type": "user_actor", "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q" }, "description": "Reviews pull requests against your team's conventions.", "display_name": "Code Review Helper", "manifest_version": "1.2.0", "plugin_id": "plugin_01JyHfbRkZvD1gW7oTqXc3Ne", "reach": "contained", "release_notes": "Adds a review checklist for database migrations.", "type": "plugin_version" } ``` ### Download Plugin Version Archive `beta.organization.plugins.versions.download(version, **kwargs) -> BinaryResponseContent` **GET** `/v1/organizations/plugins/{plugin_id}/versions/{version}/content` Download one version's `.zip` archive, exactly as stored. Each download of a Plugin from a member's personal plugin marketplace is recorded on the Compliance API activity feed. The response body is the archive (`Content-Type: application/zip`), sent as an attachment whose filename is derived from the Plugin's name; name saved files from the IDs in the request path, since that filename is not unique. **Accepted credentials:** an Admin API key with the `read:plugins` or `read:org_audit` scope, or a Compliance Access Key with the `read:compliance_org_data` scope. Every read scope above (`read:plugins`, `read:org_audit`, and `read:compliance_org_data`) can download the files of plugins in members' personal marketplaces, including files that claude.ai's admin settings do not show, and a `read:org_audit` or `read:compliance_org_data` key created for all of your parent organization's linked organizations can do this in any organization under it that has access to this API, by passing `organization_id`. Each such download records a `claude_plugin_archive_accessed` event on the Compliance API activity feed, identifying the key, the plugin, the version, and the member. Downloads of organization-owned plugins are not recorded. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `plugin_id: str` (path parameter) ID of the Plugin (prefixed `plugin_`). - `version: str` (path parameter) ID of the Plugin Version (prefixed `pluginver_`). `latest` is not accepted here. - `organization_id: Optional[str]` (query parameter) For a `read:org_audit` or `read:compliance_org_data` key created for all of a parent organization's linked organizations: a child organization of that parent to read instead of the organization the key was created in, given as the organization's UUID or its `org_`-prefixed ID. A value that is neither returns a 400; an organization that is not a child of the key's parent, or where the Plugins API is not available, returns a 404. Any other key may pass only its own organization's ID here; another organization returns a 404. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `BinaryResponseContent` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) response = client.beta.organization.plugins.versions.download( version="version", plugin_id="plugin_id", ) print(response) content = response.read() print(content) ``` ## Beta › Organization › Plugins › Installation Settings ### List Plugin Installation Settings `beta.organization.plugins.installation_settings.list(plugin_id, **kwargs) -> SyncPageCursor[BetaPluginInstallationSetting]` **GET** `/v1/organizations/plugins/{plugin_id}/installation_settings` List an organization-owned Plugin's installation settings, which say which members it is for, most recently created first. The list holds the Plugin's own organization-wide setting (absent while the Plugin inherits its marketplace's default) and each RBAC Group's own setting. A member-owned Plugin has shares instead, so this path returns 404 for one. **Accepted credentials:** an Admin API key with the `read:plugins` or `read:org_audit` scope, or a Compliance Access Key with the `read:compliance_org_data` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `plugin_id: str` (path parameter) ID of the Plugin (prefixed `plugin_`). - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `100`. default: 20, minimum: 1, maximum: 100 - `organization_id: Optional[str]` (query parameter) For a `read:org_audit` or `read:compliance_org_data` key created for all of a parent organization's linked organizations: a child organization of that parent to read instead of the organization the key was created in, given as the organization's UUID or its `org_`-prefixed ID. A value that is neither returns a 400; an organization that is not a child of the key's parent, or where the Plugins API is not available, returns a 404. Any other key may pass only its own organization's ID here; another organization returns a 404. - `page: Optional[str]` (query parameter) Optionally set to the `next_page` token from the previous response. maxLength: 2048 - `target_type: Optional[Literal["organization", "rbac_group"]]` (query parameter) Only settings for this kind of target: `organization` (the organization-wide setting) or `rbac_group` (an RBAC Group's). - `"organization"` - `"rbac_group"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPluginInstallationSetting` The installation setting an organization-owned Plugin holds for one target. It has no ID of its own: it is addressed by the Plugin's ID and the target. - `type: Literal["plugin_installation_setting"]` Always `plugin_installation_setting`. default: plugin_installation_setting - `created_at: datetime` When the target was first given a setting for this Plugin. format: date-time - `installation_preference: Literal["auto_install", "available", "not_available", "required"]` The setting the target holds for this Plugin. One of `required`, `auto_install`, `available`, `not_available`; a value this API does not yet name is returned as stored. - `"auto_install"` - `"available"` - `"not_available"` - `"required"` - `plugin_id: str` The Plugin's ID. - `target: Target` Whose setting this is: `organization` (the Plugin's own organization-wide setting) or `rbac_group` (one RBAC Group's own setting); `organization_member` does not occur here. - `class BetaPluginTargetOrganization` - `type: Literal["organization"]` Every member of the organization. default: organization - `class BetaPluginTargetRBACGroup` - `type: Literal["rbac_group"]` An RBAC Group. default: rbac_group - `rbac_group_id: str` The RBAC Group's ID. - `class BetaPluginTargetOrganizationMember` - `type: Literal["organization_member"]` One member of the organization. default: organization_member - `user_id: str` The member's User ID. - `updated_at: datetime` When its setting last changed. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.plugins.installation_settings.list( plugin_id="plugin_id", ) page = page.data[0] print(page.plugin_id) ``` ##### Response (200) ```json { "data": [ { "created_at": "2026-03-14T09:26:53.589793Z", "installation_preference": "required", "plugin_id": "plugin_01JyHfbRkZvD1gW7oTqXc3Ne", "target": { "type": "organization" }, "type": "plugin_installation_setting", "updated_at": "2026-03-14T09:26:53.589793Z" } ], "next_page": "page_MjAyNi0wOS0xNlQxNDowNTowOVo" } ``` ### Set Plugin Installation Setting `beta.organization.plugins.installation_settings.set(target, **kwargs) -> BetaPluginInstallationSetting` **POST** `/v1/organizations/plugins/{plugin_id}/installation_settings/{target}` Set or change an organization-owned Plugin's installation setting for the whole organization or for one RBAC Group. Writing the value a target already holds of its own changes nothing. A member-owned Plugin has shares instead of installation settings, so this path returns 404 for one. Send a Plugin's installation-setting writes one at a time. If several writes for the same Plugin arrive at the same time, the server handles them one after another and can answer some of them with `503` instead of applying them. That `503` carries `x-should-retry: true`, and the write is safe to repeat: wait a second or two, then send it again. **Accepted credentials:** an Admin API key with the `write:plugins` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `plugin_id: str` (path parameter) ID of the Plugin (prefixed `plugin_`). - `target: str` (path parameter) The target whose setting is written: the literal `organization` for the Plugin's organization-wide setting, or an RBAC Group's ID (prefixed `rbac_group_`) for that group's own setting. Writing the `organization` target stops the Plugin from inheriting its marketplace's default, even when the value written equals that default. - `installation_preference: Literal["auto_install", "available", "not_available", "required"]` The installation setting the target is to hold for this Plugin: one of `required`, `auto_install`, `available`, `not_available`. - `"auto_install"` - `"available"` - `"not_available"` - `"required"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPluginInstallationSetting` The installation setting an organization-owned Plugin holds for one target. It has no ID of its own: it is addressed by the Plugin's ID and the target. - `type: Literal["plugin_installation_setting"]` Always `plugin_installation_setting`. default: plugin_installation_setting - `created_at: datetime` When the target was first given a setting for this Plugin. format: date-time - `installation_preference: Literal["auto_install", "available", "not_available", "required"]` The setting the target holds for this Plugin. One of `required`, `auto_install`, `available`, `not_available`; a value this API does not yet name is returned as stored. - `"auto_install"` - `"available"` - `"not_available"` - `"required"` - `plugin_id: str` The Plugin's ID. - `target: Target` Whose setting this is: `organization` (the Plugin's own organization-wide setting) or `rbac_group` (one RBAC Group's own setting); `organization_member` does not occur here. - `class BetaPluginTargetOrganization` - `type: Literal["organization"]` Every member of the organization. default: organization - `class BetaPluginTargetRBACGroup` - `type: Literal["rbac_group"]` An RBAC Group. default: rbac_group - `rbac_group_id: str` The RBAC Group's ID. - `class BetaPluginTargetOrganizationMember` - `type: Literal["organization_member"]` One member of the organization. default: organization_member - `user_id: str` The member's User ID. - `updated_at: datetime` When its setting last changed. format: date-time #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_plugin_installation_setting = ( client.beta.organization.plugins.installation_settings.set( target="target", plugin_id="plugin_id", installation_preference="required", ) ) print(beta_plugin_installation_setting.plugin_id) ``` ##### Response (200) ```json { "created_at": "2026-03-14T09:26:53.589793Z", "installation_preference": "required", "plugin_id": "plugin_01JyHfbRkZvD1gW7oTqXc3Ne", "target": { "type": "organization" }, "type": "plugin_installation_setting", "updated_at": "2026-03-14T09:26:53.589793Z" } ``` ### Remove Plugin Installation Setting `beta.organization.plugins.installation_settings.remove(target, **kwargs) -> BetaDeletedPluginInstallationSetting` **DELETE** `/v1/organizations/plugins/{plugin_id}/installation_settings/{target}` Remove an organization-owned Plugin's own installation setting for the whole organization or for one RBAC Group. Removing the `organization` target returns the Plugin to its marketplace's default installation setting and leaves the groups' settings in place. Removing a group's setting makes the group's members fall back to the Plugin's organization-wide setting or to the settings of their other groups. A target that holds no setting of its own returns 404 (a Plugin that already inherits its marketplace's default holds no `organization` setting), and so does a member-owned Plugin. A removal counts as one of the Plugin's installation-setting writes: send all of those writes one at a time. If several arrive for the same Plugin at the same time, the server handles them one after another and can answer some of them with `503` and `x-should-retry: true` instead of applying them; wait a second or two and send the removal again. A `404` on the repeat means the setting is already gone. **Accepted credentials:** an Admin API key with the `write:plugins` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `plugin_id: str` (path parameter) ID of the Plugin (prefixed `plugin_`). - `target: str` (path parameter) The target whose own setting is removed: the literal `organization` for the Plugin's organization-wide setting, or an RBAC Group's ID (prefixed `rbac_group_`) for that group's own setting. Removing the `organization` setting returns the Plugin to its marketplace's default. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaDeletedPluginInstallationSetting` Confirmation that one target's installation setting was removed, naming the Plugin and the target in place of an ID. - `type: Literal["plugin_installation_setting_deleted"]` Always `plugin_installation_setting_deleted`. default: plugin_installation_setting_deleted - `plugin_id: str` The Plugin's ID. - `target: Target` Whose setting was removed. - `class BetaPluginTargetOrganization` - `type: Literal["organization"]` Every member of the organization. default: organization - `class BetaPluginTargetRBACGroup` - `type: Literal["rbac_group"]` An RBAC Group. default: rbac_group - `rbac_group_id: str` The RBAC Group's ID. - `class BetaPluginTargetOrganizationMember` - `type: Literal["organization_member"]` One member of the organization. default: organization_member - `user_id: str` The member's User ID. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_deleted_plugin_installation_setting = ( client.beta.organization.plugins.installation_settings.remove( target="target", plugin_id="plugin_id", ) ) print(beta_deleted_plugin_installation_setting.plugin_id) ``` ##### Response (200) ```json { "plugin_id": "plugin_01JyHfbRkZvD1gW7oTqXc3Ne", "target": { "rbac_group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF", "type": "rbac_group" }, "type": "plugin_installation_setting_deleted" } ``` ## Beta › Organization › Plugins › Shares ### List Plugin Shares `beta.organization.plugins.shares.list(plugin_id, **kwargs) -> SyncPageCursor[BetaPluginShare]` **GET** `/v1/organizations/plugins/{plugin_id}/shares` List the shares the owner of a member-owned Plugin has given — to every member of the organization, to an RBAC Group, or to one member — most recently granted first. Shares are read-only in this API: members give and withdraw them in claude.ai, and who gave a share is recorded on the Compliance API activity feed rather than on the share. An organization-owned Plugin has installation settings instead, so this path returns 404 for one. **Accepted credentials:** an Admin API key with the `read:plugins` or `read:org_audit` scope, or a Compliance Access Key with the `read:compliance_org_data` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `plugin_id: str` (path parameter) ID of the Plugin (prefixed `plugin_`). - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `100`. default: 20, minimum: 1, maximum: 100 - `organization_id: Optional[str]` (query parameter) For a `read:org_audit` or `read:compliance_org_data` key created for all of a parent organization's linked organizations: a child organization of that parent to read instead of the organization the key was created in, given as the organization's UUID or its `org_`-prefixed ID. A value that is neither returns a 400; an organization that is not a child of the key's parent, or where the Plugins API is not available, returns a 404. Any other key may pass only its own organization's ID here; another organization returns a 404. - `page: Optional[str]` (query parameter) Optionally set to the `next_page` token from the previous response. maxLength: 2048 - `target_type: Optional[Literal["organization", "organization_member", "rbac_group"]]` (query parameter) Only shares with this kind of target: `organization` (every member), `rbac_group` (one RBAC Group), or `organization_member` (one member). - `"organization"` - `"organization_member"` - `"rbac_group"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPluginShare` One share the owner of a member-owned Plugin has given. Shares are read-only in this API and have no ID of their own; who gave a share is recorded on the Compliance API activity feed, not here. - `type: Literal["plugin_share"]` Always `plugin_share`. default: plugin_share - `granted_at: datetime` When the share was given; a share whose role is later changed in claude.ai is re-granted and carries the time of that change. format: date-time - `plugin_id: str` The Plugin's ID. - `target: Target` Who the Plugin is shared with: `organization` (every member), `rbac_group` (one RBAC Group), or `organization_member` (one member). - `class BetaPluginTargetOrganization` - `type: Literal["organization"]` Every member of the organization. default: organization - `class BetaPluginTargetRBACGroup` - `type: Literal["rbac_group"]` An RBAC Group. default: rbac_group - `rbac_group_id: str` The RBAC Group's ID. - `class BetaPluginTargetOrganizationMember` - `type: Literal["organization_member"]` One member of the organization. default: organization_member - `user_id: str` The member's User ID. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.plugins.shares.list( plugin_id="plugin_id", ) page = page.data[0] print(page.plugin_id) ``` ##### Response (200) ```json { "data": [ { "granted_at": "2026-03-14T09:26:53.589793Z", "plugin_id": "plugin_01JyHfbRkZvD1gW7oTqXc3Ne", "target": { "type": "organization" }, "type": "plugin_share" } ], "next_page": "page_MjAyNi0wOS0xNlQxNDowNTowOVo" } ``` ## Beta › Organization › Plugin Marketplaces ### List Plugin Marketplaces `beta.organization.plugin_marketplaces.list(**kwargs) -> SyncPageCursor[BetaPluginMarketplace]` **GET** `/v1/organizations/plugin_marketplaces` List the plugin marketplaces Plugins live in, newest first: the organization's own and its members' personal ones. Plugin marketplaces are created, connected to a repository and deleted in claude.ai, not through this API. The organization's library marketplace, the organization-owned `manual` marketplace that uploads go to when no marketplace is named, is created the first time something is put in it and is listed from then on. **Accepted credentials:** an Admin API key with the `read:plugins` or `read:org_audit` scope, or a Compliance Access Key with the `read:compliance_org_data` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `limit: Optional[int]` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, minimum: 1, maximum: 1000 - `organization_id: Optional[str]` (query parameter) For a `read:org_audit` or `read:compliance_org_data` key created for all of a parent organization's linked organizations: a child organization of that parent to read instead of the organization the key was created in, given as the organization's UUID or its `org_`-prefixed ID. A value that is neither returns a 400; an organization that is not a child of the key's parent, or where the Plugins API is not available, returns a 404. Any other key may pass only its own organization's ID here; another organization returns a 404. - `owner_type: Optional[Literal["organization", "user"]]` (query parameter) `organization` for the organization's plugin marketplaces, `user` for members' personal plugin marketplaces. - `"organization"` - `"user"` - `page: Optional[str]` (query parameter) Optionally set to the `next_page` token from the previous response. maxLength: 2048 - `source: Optional[Literal["directory", "github", "gitlab", 2 more]]` (query parameter) Only plugin marketplaces with this `source`: `manual` for those whose Plugins are uploaded; `github`, `gitlab` or `public_git` for those synchronized from a Git repository. `directory` (Anthropic's catalog) is never listed here. - `"directory"` - `"github"` - `"gitlab"` - `"manual"` - `"public_git"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPluginMarketplace` - `type: Literal["plugin_marketplace"]` Always `plugin_marketplace`. default: plugin_marketplace - `id: str` The plugin marketplace's ID, prefixed `marketplace_`. - `created_at: datetime` RFC 3339. format: date-time - `default_installation_preference: Optional[Literal["auto_install", "available", "not_available", "required"]]` Organization plugin marketplace: the organization-wide setting every Plugin in it with no setting of its own gets. Null for a member's personal plugin marketplace. One of `required`, `auto_install`, `available`, `not_available`; a value this API does not yet name is returned as stored. - `"auto_install"` - `"available"` - `"not_available"` - `"required"` - `last_sync_ended_at: Optional[datetime]` RFC 3339. When the most recent synchronization attempt to finish did so, whatever its outcome; for a repository plugin marketplace no synchronization has run on yet, when it was created. Null for a plugin marketplace that is not synchronized from a repository. format: date-time - `last_sync_read_sha: Optional[str]` The commit the last synchronization attempt that reached the repository read, whether or not its content was then accepted (see `sync_status`); an attempt that ends `failed_auth` or `failed_transient` leaves it unchanged. Null until an attempt has first read the repository, and for a plugin marketplace that is not synchronized from a repository. - `name: str` Fixed for the plugin marketplace's lifetime. - `owner: Owner` The organization, or the member whose personal plugin marketplace it is. - `class BetaPluginOwnerOrganization` - `type: Literal["organization"]` The Plugin lives in a plugin marketplace the organization owns. default: organization - `class BetaPluginOwnerUser` - `type: Literal["user"]` The Plugin lives in one member's personal plugin marketplace. default: user - `user_id: str` The member's User ID. - `source: Literal["directory", "github", "gitlab", 2 more]` Where the plugin marketplace's Plugins come from: `manual` when they are uploaded; `github`, `gitlab` or `public_git` when they are synchronized from the Git repository the owner connected, into which nothing can be uploaded; `directory` is Anthropic's own catalog, which this API does not list. A value this API does not yet name is returned as stored. - `"directory"` - `"github"` - `"gitlab"` - `"manual"` - `"public_git"` - `sync_status: Optional[Literal["failed_auth", "failed_content", "failed_limits", 3 more]]` Outcome of the plugin marketplace's most recent synchronization: one of `success`, `in_progress`, `failed_content`, `failed_transient`, `failed_auth`, `failed_limits`; a value this API does not yet name is returned as stored. Null until a synchronization is first attempted — so always for a `manual` plugin marketplace. - `"failed_auth"` - `"failed_content"` - `"failed_limits"` - `"failed_transient"` - `"in_progress"` - `"success"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) page = client.beta.organization.plugin_marketplaces.list() page = page.data[0] print(page.id) ``` ##### Response (200) ```json { "data": [ { "id": "marketplace_01HxQ3v9KpZ2mTn8RwLc4Ys7", "created_at": "2026-03-14T09:26:53.589793Z", "default_installation_preference": "available", "last_sync_ended_at": "2026-03-14T09:26:53.589793Z", "last_sync_read_sha": "9fceb02d0ae598e95dc970b74767f19372d61af8", "name": "engineering-tools", "owner": { "type": "organization" }, "source": "github", "sync_status": "success", "type": "plugin_marketplace" } ], "next_page": "page_MjAyNi0wOS0xNlQxNDowNTowOVo" } ``` ### Get Plugin Marketplace `beta.organization.plugin_marketplaces.retrieve(marketplace_id, **kwargs) -> BetaPluginMarketplace` **GET** `/v1/organizations/plugin_marketplaces/{marketplace_id}` Retrieve a plugin marketplace by ID. **Accepted credentials:** an Admin API key with the `read:plugins` or `read:org_audit` scope, or a Compliance Access Key with the `read:compliance_org_data` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `marketplace_id: str` (path parameter) ID of the plugin marketplace (prefixed `marketplace_`). - `organization_id: Optional[str]` (query parameter) For a `read:org_audit` or `read:compliance_org_data` key created for all of a parent organization's linked organizations: a child organization of that parent to read instead of the organization the key was created in, given as the organization's UUID or its `org_`-prefixed ID. A value that is neither returns a 400; an organization that is not a child of the key's parent, or where the Plugins API is not available, returns a 404. Any other key may pass only its own organization's ID here; another organization returns a 404. - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPluginMarketplace` - `type: Literal["plugin_marketplace"]` Always `plugin_marketplace`. default: plugin_marketplace - `id: str` The plugin marketplace's ID, prefixed `marketplace_`. - `created_at: datetime` RFC 3339. format: date-time - `default_installation_preference: Optional[Literal["auto_install", "available", "not_available", "required"]]` Organization plugin marketplace: the organization-wide setting every Plugin in it with no setting of its own gets. Null for a member's personal plugin marketplace. One of `required`, `auto_install`, `available`, `not_available`; a value this API does not yet name is returned as stored. - `"auto_install"` - `"available"` - `"not_available"` - `"required"` - `last_sync_ended_at: Optional[datetime]` RFC 3339. When the most recent synchronization attempt to finish did so, whatever its outcome; for a repository plugin marketplace no synchronization has run on yet, when it was created. Null for a plugin marketplace that is not synchronized from a repository. format: date-time - `last_sync_read_sha: Optional[str]` The commit the last synchronization attempt that reached the repository read, whether or not its content was then accepted (see `sync_status`); an attempt that ends `failed_auth` or `failed_transient` leaves it unchanged. Null until an attempt has first read the repository, and for a plugin marketplace that is not synchronized from a repository. - `name: str` Fixed for the plugin marketplace's lifetime. - `owner: Owner` The organization, or the member whose personal plugin marketplace it is. - `class BetaPluginOwnerOrganization` - `type: Literal["organization"]` The Plugin lives in a plugin marketplace the organization owns. default: organization - `class BetaPluginOwnerUser` - `type: Literal["user"]` The Plugin lives in one member's personal plugin marketplace. default: user - `user_id: str` The member's User ID. - `source: Literal["directory", "github", "gitlab", 2 more]` Where the plugin marketplace's Plugins come from: `manual` when they are uploaded; `github`, `gitlab` or `public_git` when they are synchronized from the Git repository the owner connected, into which nothing can be uploaded; `directory` is Anthropic's own catalog, which this API does not list. A value this API does not yet name is returned as stored. - `"directory"` - `"github"` - `"gitlab"` - `"manual"` - `"public_git"` - `sync_status: Optional[Literal["failed_auth", "failed_content", "failed_limits", 3 more]]` Outcome of the plugin marketplace's most recent synchronization: one of `success`, `in_progress`, `failed_content`, `failed_transient`, `failed_auth`, `failed_limits`; a value this API does not yet name is returned as stored. Null until a synchronization is first attempted — so always for a `manual` plugin marketplace. - `"failed_auth"` - `"failed_content"` - `"failed_limits"` - `"failed_transient"` - `"in_progress"` - `"success"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_plugin_marketplace = client.beta.organization.plugin_marketplaces.retrieve( marketplace_id="marketplace_id", ) print(beta_plugin_marketplace.id) ``` ##### Response (200) ```json { "id": "marketplace_01HxQ3v9KpZ2mTn8RwLc4Ys7", "created_at": "2026-03-14T09:26:53.589793Z", "default_installation_preference": "available", "last_sync_ended_at": "2026-03-14T09:26:53.589793Z", "last_sync_read_sha": "9fceb02d0ae598e95dc970b74767f19372d61af8", "name": "engineering-tools", "owner": { "type": "organization" }, "source": "github", "sync_status": "success", "type": "plugin_marketplace" } ``` ### Update Plugin Marketplace `beta.organization.plugin_marketplaces.update(marketplace_id, **kwargs) -> BetaPluginMarketplace` **POST** `/v1/organizations/plugin_marketplaces/{marketplace_id}` Set the default installation setting of one of the organization's own plugin marketplaces. Every Plugin in it without a setting of its own gets this default as its organization-wide setting, including Plugins added later. Pass it as `default_installation_preference`. A member's personal marketplace cannot be updated here (403). **Accepted credentials:** an Admin API key with the `write:plugins` scope. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `marketplace_id: str` (path parameter) ID of the plugin marketplace (prefixed `marketplace_`). - `default_installation_preference: Literal["auto_install", "available", "not_available", "required"]` The organization-wide installation setting every Plugin in the marketplace without one of its own gets: one of `required`, `auto_install`, `available`, `not_available`. Once set it can be changed but not removed. - `"auto_install"` - `"available"` - `"not_available"` - `"required"` - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPluginMarketplace` - `type: Literal["plugin_marketplace"]` Always `plugin_marketplace`. default: plugin_marketplace - `id: str` The plugin marketplace's ID, prefixed `marketplace_`. - `created_at: datetime` RFC 3339. format: date-time - `default_installation_preference: Optional[Literal["auto_install", "available", "not_available", "required"]]` Organization plugin marketplace: the organization-wide setting every Plugin in it with no setting of its own gets. Null for a member's personal plugin marketplace. One of `required`, `auto_install`, `available`, `not_available`; a value this API does not yet name is returned as stored. - `"auto_install"` - `"available"` - `"not_available"` - `"required"` - `last_sync_ended_at: Optional[datetime]` RFC 3339. When the most recent synchronization attempt to finish did so, whatever its outcome; for a repository plugin marketplace no synchronization has run on yet, when it was created. Null for a plugin marketplace that is not synchronized from a repository. format: date-time - `last_sync_read_sha: Optional[str]` The commit the last synchronization attempt that reached the repository read, whether or not its content was then accepted (see `sync_status`); an attempt that ends `failed_auth` or `failed_transient` leaves it unchanged. Null until an attempt has first read the repository, and for a plugin marketplace that is not synchronized from a repository. - `name: str` Fixed for the plugin marketplace's lifetime. - `owner: Owner` The organization, or the member whose personal plugin marketplace it is. - `class BetaPluginOwnerOrganization` - `type: Literal["organization"]` The Plugin lives in a plugin marketplace the organization owns. default: organization - `class BetaPluginOwnerUser` - `type: Literal["user"]` The Plugin lives in one member's personal plugin marketplace. default: user - `user_id: str` The member's User ID. - `source: Literal["directory", "github", "gitlab", 2 more]` Where the plugin marketplace's Plugins come from: `manual` when they are uploaded; `github`, `gitlab` or `public_git` when they are synchronized from the Git repository the owner connected, into which nothing can be uploaded; `directory` is Anthropic's own catalog, which this API does not list. A value this API does not yet name is returned as stored. - `"directory"` - `"github"` - `"gitlab"` - `"manual"` - `"public_git"` - `sync_status: Optional[Literal["failed_auth", "failed_content", "failed_limits", 3 more]]` Outcome of the plugin marketplace's most recent synchronization: one of `success`, `in_progress`, `failed_content`, `failed_transient`, `failed_auth`, `failed_limits`; a value this API does not yet name is returned as stored. Null until a synchronization is first attempted — so always for a `manual` plugin marketplace. - `"failed_auth"` - `"failed_content"` - `"failed_limits"` - `"failed_transient"` - `"in_progress"` - `"success"` #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_plugin_marketplace = client.beta.organization.plugin_marketplaces.update( marketplace_id="marketplace_id", default_installation_preference="available", ) print(beta_plugin_marketplace.id) ``` ##### Response (200) ```json { "id": "marketplace_01HxQ3v9KpZ2mTn8RwLc4Ys7", "created_at": "2026-03-14T09:26:53.589793Z", "default_installation_preference": "available", "last_sync_ended_at": "2026-03-14T09:26:53.589793Z", "last_sync_read_sha": "9fceb02d0ae598e95dc970b74767f19372d61af8", "name": "engineering-tools", "owner": { "type": "organization" }, "source": "github", "sync_status": "success", "type": "plugin_marketplace" } ``` ### Validate Plugin Marketplace Repository `beta.organization.plugin_marketplaces.validate_repository(**kwargs) -> BetaPluginMarketplaceValidationReport` **POST** `/v1/organizations/plugin_marketplaces/validate_repository` Check whether a plugin marketplace held in a public GitHub repository would synchronize into claude.ai, without connecting or storing it. To check a `.zip` of the marketplace directory instead, use Validate Plugin Marketplace Archive. The report says whether `marketplace.json` is well-formed, which plugins a synchronization would skip and why, and which plugins would synchronize only in part, with some files left out. A repository that is missing, private, or has no such branch or commit is reported, not refused: the response is a report with `valid: false`. Plugin sources outside the marketplace are fetched anonymously from GitHub, so a private one is reported as not found; a source on any other host is not fetched here, and the report notes that it will be checked when the marketplace actually synchronizes. Nothing is recorded on the Compliance API activity feed. For a worked example, see [Validate marketplace content](https://platform.claude.com/docs/en/manage-claude/plugins-api?sdk_languages=python#validate-marketplace-content) in the Plugins API guide. **Accepted credentials:** an Admin API key with the `read:plugins` or `write:plugins` scope; `read:org_audit` and `read:compliance_org_data` do not grant it. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `repository_url: str` The `https://` URL of a public repository on github.com that holds the marketplace. Any other host, a URL with credentials in it, or one that does not name a repository is a 400. minLength: 1 - `ref: Optional[str]` The branch to validate the tip of, or the full 40-character SHA of the commit to validate. When omitted, the branch a synchronization would read (usually the repository's default branch); if that is not the default branch, the report's `ref` says which branch was read. An empty string, or a value that is neither a branch name nor a 40-character SHA, is a 400. minLength: 1 - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPluginMarketplaceValidationReport` The outcome of validating plugin marketplace content: a report, not a stored object, so nothing in it can be retrieved afterwards. - `type: Literal["plugin_marketplace_validation_report"]` Always `plugin_marketplace_validation_report`. default: plugin_marketplace_validation_report - `commit_sha: Optional[str]` The full SHA of the commit that was validated: for a repository, the commit that was read; for an uploaded archive, the commit recorded in the archive's comment (as a Git host's download writes it; not verified), else null. - `manifest_error: Optional[str]` Set when nothing could be validated: the repository or archive could not be read, or marketplace.json is missing, malformed or over a limit. Null otherwise. - `manifest_error_code: Optional[str]` A stable identifier for `manifest_error`; null when that is. - `plugin_errors: List[BetaPluginMarketplaceValidationPluginError]` One entry per plugin a synchronization would skip entirely, keyed by the plugin's name in marketplace.json. - `error: str` Why the plugin would be skipped by a synchronization. - `error_code: str` A stable identifier for the reason — the value to branch on. - `name: str` The plugin's name, as its entry in marketplace.json declares it. - `plugin_warnings: List[BetaPluginMarketplaceValidationPluginWarnings]` One entry per plugin that would synchronize with some of its contents left out, keyed by the plugin's name in marketplace.json. - `name: str` The plugin's name, as its entry in marketplace.json declares it. - `warnings: List[BetaPluginMarketplaceValidationPluginWarning]` The parts of the plugin a synchronization would leave out. - `error_code: str` A stable identifier for the kind of warning. - `message: str` What would be left out, and why. - `ref: Optional[str]` For a repository, the branch that was read by name: the one requested, or else the branch a synchronization of this repository is set to read. Null when no branch is named or set and the repository's default branch was read, for a request by commit SHA, and for an uploaded archive. - `total_plugin_count: int` How many plugins marketplace.json declares; 0 when it could not be read. - `valid: bool` True when marketplace.json is well-formed and no plugin would be skipped; warnings never make it false. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_plugin_marketplace_validation_report = ( client.beta.organization.plugin_marketplaces.validate_repository( repository_url="https://github.com/example-org/example-marketplace", ) ) print(beta_plugin_marketplace_validation_report.valid) ``` ##### Response (200) ```json { "commit_sha": "9fceb02d0ae598e95dc970b74767f19372d61af8", "manifest_error": "manifest_error", "manifest_error_code": "marketplace_sync_manifest_not_found", "plugin_errors": [ { "error": "error", "error_code": "marketplace_sync_plugin_missing_manifest", "name": "name" } ], "plugin_warnings": [ { "name": "name", "warnings": [ { "error_code": "marketplace_sync_zipball_symlink_dangling", "message": "message" } ] } ], "ref": "main", "total_plugin_count": 0, "type": "plugin_marketplace_validation_report", "valid": false } ``` ### Validate Plugin Marketplace Archive `beta.organization.plugin_marketplaces.validate_archive(**kwargs) -> BetaPluginMarketplaceValidationReport` **POST** `/v1/organizations/plugin_marketplaces/validate_archive` Check whether a plugin marketplace, uploaded as a `.zip` of the marketplace directory, would synchronize into claude.ai, without connecting or storing it. To check a public GitHub repository instead, use Validate Plugin Marketplace Repository. The report says whether `marketplace.json` is well-formed, which plugins a synchronization would skip and why, and which plugins would synchronize only in part, with some files left out. An archive that cannot be read as a marketplace is reported, not refused: the response is a report with `valid: false`. Plugin sources outside the marketplace are fetched anonymously from GitHub, so a private one is reported as not found; a source on any other host is not fetched here, and the report notes that it will be checked when the marketplace actually synchronizes. Nothing is recorded on the Compliance API activity feed. For a worked example, see [Validate marketplace content](https://platform.claude.com/docs/en/manage-claude/plugins-api?sdk_languages=python#validate-marketplace-content) in the Plugins API guide. **Accepted credentials:** an Admin API key with the `read:plugins` or `write:plugins` scope; `read:org_audit` and `read:compliance_org_data` do not grant it. Every request must include the beta header `anthropic-beta: ce-plugins-2026-09-01`. A request without it returns `404`, exactly as if the endpoint did not exist. The Plugins API is in beta and is available to Claude Enterprise organizations only. It is not available to Claude Platform (Claude Console) organizations, or to organizations with HIPAA readiness enabled. #### Parameters - `archive: FileTypes` A .zip of the marketplace directory (its contents at the root, or wrapped in one folder as a Git host's download produces), sent as a file part with a filename; DEFLATE- or STORE-compressed, at most 32 MB. A part sent without a filename, a second archive part, or any other form field is a 400; a larger archive is a 413. format: binary - `betas: Optional[List[AnthropicBetaParam]]` (header parameter) This endpoint is in beta: requests must send `ce-plugins-2026-09-01` in this header. - `str` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"compact-2026-09-04"` - `"inline-tools-2026-09-15"` - `"mcp-client-2026-09-15"` - `"ce-plugins-2026-09-01"` - `"spend-limit-reads-2026-09-26"` #### Returns - `class BetaPluginMarketplaceValidationReport` The outcome of validating plugin marketplace content: a report, not a stored object, so nothing in it can be retrieved afterwards. - `type: Literal["plugin_marketplace_validation_report"]` Always `plugin_marketplace_validation_report`. default: plugin_marketplace_validation_report - `commit_sha: Optional[str]` The full SHA of the commit that was validated: for a repository, the commit that was read; for an uploaded archive, the commit recorded in the archive's comment (as a Git host's download writes it; not verified), else null. - `manifest_error: Optional[str]` Set when nothing could be validated: the repository or archive could not be read, or marketplace.json is missing, malformed or over a limit. Null otherwise. - `manifest_error_code: Optional[str]` A stable identifier for `manifest_error`; null when that is. - `plugin_errors: List[BetaPluginMarketplaceValidationPluginError]` One entry per plugin a synchronization would skip entirely, keyed by the plugin's name in marketplace.json. - `error: str` Why the plugin would be skipped by a synchronization. - `error_code: str` A stable identifier for the reason — the value to branch on. - `name: str` The plugin's name, as its entry in marketplace.json declares it. - `plugin_warnings: List[BetaPluginMarketplaceValidationPluginWarnings]` One entry per plugin that would synchronize with some of its contents left out, keyed by the plugin's name in marketplace.json. - `name: str` The plugin's name, as its entry in marketplace.json declares it. - `warnings: List[BetaPluginMarketplaceValidationPluginWarning]` The parts of the plugin a synchronization would leave out. - `error_code: str` A stable identifier for the kind of warning. - `message: str` What would be left out, and why. - `ref: Optional[str]` For a repository, the branch that was read by name: the one requested, or else the branch a synchronization of this repository is set to read. Null when no branch is named or set and the repository's default branch was read, for a request by commit SHA, and for an uploaded archive. - `total_plugin_count: int` How many plugins marketplace.json declares; 0 when it could not be read. - `valid: bool` True when marketplace.json is well-formed and no plugin would be skipped; warnings never make it false. #### Example ```python import os from anthropic import Anthropic client = Anthropic( api_key=os.environ.get( "ANTHROPIC_API_KEY" ), # This is the default and can be omitted ) beta_plugin_marketplace_validation_report = ( client.beta.organization.plugin_marketplaces.validate_archive( archive=b"Example data", ) ) print(beta_plugin_marketplace_validation_report.valid) ``` ##### Response (200) ```json { "commit_sha": "9fceb02d0ae598e95dc970b74767f19372d61af8", "manifest_error": "manifest_error", "manifest_error_code": "marketplace_sync_manifest_not_found", "plugin_errors": [ { "error": "error", "error_code": "marketplace_sync_plugin_missing_manifest", "name": "name" } ], "plugin_warnings": [ { "name": "name", "warnings": [ { "error_code": "marketplace_sync_zipball_symlink_dangling", "message": "message" } ] } ], "ref": "main", "total_plugin_count": 0, "type": "plugin_marketplace_validation_report", "valid": false } ```