--- title: Create a Message url: https://platform.claude.com/docs/en/api/typescript/messages/create --- # Create a Message `client.messages.create(params, options?): Message | Stream` **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=typescript) ## Parameters - `params: MessageCreateParams` - `max_tokens: number` 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=typescript#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=typescript) for details. minimum: 0 - `messages: Array` 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=typescript#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=typescript). 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=typescript#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: string | Array` - `string` - `Array` - `interface TextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl?: "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=typescript) for details. - `"5m"` - `"1h"` - `citations?: Array | null` - `interface CitationCharLocationParam` - `type: "char_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string | null` minLength: 1, maxLength: 500 - `end_char_index: number` - `start_char_index: number` minimum: 0 - `interface CitationPageLocationParam` - `type: "page_location"` - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string | null` minLength: 1, maxLength: 500 - `end_page_number: number` - `start_page_number: number` minimum: 1 - `interface CitationContentBlockLocationParam` - `type: "content_block_location"` - `cited_text: string` 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: number` minimum: 0 - `document_title: string | null` minLength: 1, maxLength: 500 - `end_block_index: number` 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: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `interface CitationWebSearchResultLocationParam` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string | null` minLength: 1, maxLength: 512 - `url: string` minLength: 1 - `interface CitationSearchResultLocationParam` - `type: "search_result_location"` - `cited_text: string` 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: number` 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: number` 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: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string | null` - `interface ImageBlockParam` - `type: "image"` - `source: Base64ImageSource | URLImageSource | FileImageSource` - `interface Base64ImageSource` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" | "image/png" | "image/gif" | "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `interface URLImageSource` - `type: "url"` - `url: string` - `interface FileImageSource` - `type: "file"` - `file_id: string` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `transformations?: ImageTransformationsParam | null` 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?: "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"` - `interface DocumentBlockParam` - `type: "document"` - `source: Base64PDFSource | PlainTextSource | ContentBlockSource | 2 more` - `interface Base64PDFSource` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `interface PlainTextSource` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `interface ContentBlockSource` - `type: "content"` - `content: string | Array` - `string` - `Array` - `interface TextBlockParam` - `interface ImageBlockParam` - `interface URLPDFSource` - `type: "url"` - `url: string` - `interface FileDocumentSource` - `type: "file"` - `file_id: string` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `citations?: CitationsConfigParam | null` - `enabled?: boolean` - `context?: string | null` minLength: 1 - `title?: string | null` minLength: 1, maxLength: 500 - `interface SearchResultBlockParam` - `type: "search_result"` - `content: Array` - `type: "text"` - `text: string` minLength: 1 - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `citations?: Array | null` - `source: string` - `title: string` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `citations?: CitationsConfigParam` - `interface ThinkingBlockParam` - `type: "thinking"` - `signature: string` 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: string` The `thinking` text of this block as returned by the API. - `interface RedactedThinkingBlockParam` - `type: "redacted_thinking"` - `data: string` 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. - `interface ToolUseBlockParam` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: Record` - `name: string` minLength: 1, maxLength: 200 - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `caller?: DirectCaller | ServerToolCaller | ServerToolCaller20260120` - `interface DirectCaller` Tool invocation directly from the model. - `type: "direct"` - `interface ServerToolCaller` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `interface ServerToolCaller20260120` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name?: string | null` For a toolset member tool_use, the toolset family this member belongs to. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `interface ToolResultBlockParam` - `type: "tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `content?: string | Array` - `string` - `Array` - `interface TextBlockParam` - `interface ImageBlockParam` - `interface SearchResultBlockParam` - `interface DocumentBlockParam` - `interface ToolReferenceBlockParam` Tool reference block that can be included in tool_result content. - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `interface BrowserStateBlockParam` 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: "browser_state"` - `tabs: Array` 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: string` The caller-assigned identifier for this tab, unique within the inventory. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `title: string` The title of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The URL of the page the tab is showing. May be empty. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `active?: boolean` Whether this tab is the active tab after this call. Whenever `tabs` is non-empty, exactly one entry is marked `active: true`. - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `state_changes?: Array | null` 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 - `interface BrowserStateChangeTabOpened` 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: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `interface BrowserStateChangeDownloadStarted` A file download that started during this call. - `type: "download_started"` - `download_id: string` 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: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `interface BrowserStateChangeDownloadCompleted` 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: "download_completed"` - `download_id: string` 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: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path?: string | null` 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?: number | null` The completed download's size. minimum: 0 - `interface BrowserStateChangeDownloadFailed` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` 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: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error?: string | null` The failure or cancellation detail, when known. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `is_error?: boolean` - `toolset_name?: string | null` For a toolset member tool_result, the toolset family of the paired tool_use. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `interface ServerToolUseBlockParam` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: Record` - `name: "web_search" | "web_fetch" | "code_execution" | 4 more` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `caller?: DirectCaller | ServerToolCaller | ServerToolCaller20260120` - `interface DirectCaller` Tool invocation directly from the model. - `interface ServerToolCaller` Tool invocation generated by a server-side tool. - `interface ServerToolCaller20260120` - `interface WebSearchToolResultBlockParam` - `type: "web_search_tool_result"` - `content: WebSearchToolResultBlockParamContent` - `Array` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age?: string | null` - `interface WebSearchToolRequestError` - `type: "web_search_tool_result_error"` - `error_code: WebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `caller?: DirectCaller | ServerToolCaller | ServerToolCaller20260120` - `interface DirectCaller` Tool invocation directly from the model. - `interface ServerToolCaller` Tool invocation generated by a server-side tool. - `interface ServerToolCaller20260120` - `interface WebFetchToolResultBlockParam` - `type: "web_fetch_tool_result"` - `content: WebFetchToolResultErrorBlockParam | WebFetchBlockParam` - `interface WebFetchToolResultErrorBlockParam` - `type: "web_fetch_tool_result_error"` - `error_code: WebFetchToolResultErrorCode` - `"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"` - `interface WebFetchBlockParam` - `type: "web_fetch_result"` - `content: DocumentBlockParam` - `url: string` Fetched content URL - `retrieved_at?: string | null` ISO 8601 timestamp when the content was retrieved - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `caller?: DirectCaller | ServerToolCaller | ServerToolCaller20260120` - `interface DirectCaller` Tool invocation directly from the model. - `interface ServerToolCaller` Tool invocation generated by a server-side tool. - `interface ServerToolCaller20260120` - `interface CodeExecutionToolResultBlockParam` - `type: "code_execution_tool_result"` - `content: CodeExecutionToolResultBlockParamContent` - `interface CodeExecutionToolResultErrorParam` - `type: "code_execution_tool_result_error"` - `error_code: CodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `interface CodeExecutionResultBlockParam` - `type: "code_execution_result"` - `content: Array` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `interface EncryptedCodeExecutionResultBlockParam` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: Array` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `interface BashCodeExecutionToolResultBlockParam` - `type: "bash_code_execution_tool_result"` - `content: BashCodeExecutionToolResultErrorParam | BashCodeExecutionResultBlockParam` - `interface BashCodeExecutionToolResultErrorParam` - `type: "bash_code_execution_tool_result_error"` - `error_code: BashCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `interface BashCodeExecutionResultBlockParam` - `type: "bash_code_execution_result"` - `content: Array` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `interface TextEditorCodeExecutionToolResultBlockParam` - `type: "text_editor_code_execution_tool_result"` - `content: TextEditorCodeExecutionToolResultErrorParam | TextEditorCodeExecutionViewResultBlockParam | TextEditorCodeExecutionCreateResultBlockParam | TextEditorCodeExecutionStrReplaceResultBlockParam` - `interface TextEditorCodeExecutionToolResultErrorParam` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: TextEditorCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message?: string | null` - `interface TextEditorCodeExecutionViewResultBlockParam` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" | "image" | "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines?: number | null` - `start_line?: number | null` - `total_lines?: number | null` - `interface TextEditorCodeExecutionCreateResultBlockParam` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `interface TextEditorCodeExecutionStrReplaceResultBlockParam` - `type: "text_editor_code_execution_str_replace_result"` - `lines?: Array | null` - `new_lines?: number | null` - `new_start?: number | null` - `old_lines?: number | null` - `old_start?: number | null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `interface ToolSearchToolResultBlockParam` - `type: "tool_search_tool_result"` - `content: ToolSearchToolResultErrorParam | ToolSearchToolSearchResultBlockParam` - `interface ToolSearchToolResultErrorParam` - `type: "tool_search_tool_result_error"` - `error_code: ToolSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message?: string | null` - `interface ToolSearchToolSearchResultBlockParam` - `type: "tool_search_tool_search_result"` - `tool_references: Array` - `type: "tool_reference"` - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `interface ContainerUploadBlockParam` 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: "container_upload"` - `file_id: string` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `role: "user" | "assistant" | "system"` - `"user"` - `"assistant"` - `"system"` - `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 - `(string & {})` - `cache_control?: CacheControlEphemeral | null` Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. - `container?: MessageCreateParamsContainer | null` Container identifier for reuse across requests. - `interface ContainerParams` Container parameters with skills to be loaded. - `id?: string | null` Container id - `skills?: Array | null` List of skills to load in the container maxItems: 20 - `type: "anthropic" | "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID minLength: 1, maxLength: 64 - `version?: string` Skill version or 'latest' for most recent version minLength: 1, maxLength: 64 - `string` - `diagnostics?: DiagnosticsParam | null` 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?: string | null` 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 - `inference_geo?: string | null` Specifies the geographic region for inference processing. If not specified, the workspace's `default_inference_geo` is used. - `metadata?: Metadata` An object describing metadata about the request. - `user_id?: string | null` 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?: OutputConfig` Configuration options for the model's output, such as the output format. - `effort?: "low" | "medium" | "high" | 2 more | null` 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?: JSONOutputFormat | null` 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=typescript) - `type: "json_schema"` - `schema: Record` The JSON schema of the format - `service_tier?: "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=typescript) for details. - `"auto"` - `"standard_only"` - `stop_sequences?: Array` 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?: boolean` 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=typescript#streaming-with-sdks) for an example in each language. - `system?: string | Array` 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=typescript#give-claude-a-role). - `string` - `Array` - `type: "text"` - `text: string` minLength: 1 - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `citations?: Array | null` - `thinking?: ThinkingConfigParam` 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=typescript#configuring-thinking) for each model's behavior. - `interface ThinkingConfigEnabled` - `type: "enabled"` - `budget_tokens: number` 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=typescript) for details. minimum: 1024 - `display?: "summarized" | "omitted" | null` 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=typescript#controlling-thinking-display). - `"summarized"` - `"omitted"` - `interface ThinkingConfigDisabled` - `type: "disabled"` - `interface ThinkingConfigBetweenTools` - `type: "between_tools"` - `interface ThinkingConfigAdaptive` - `type: "adaptive"` - `display?: "summarized" | "omitted" | null` 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=typescript#controlling-thinking-display). - `"summarized"` - `"omitted"` - `tool_choice?: ToolChoice` 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. - `interface ToolChoiceAuto` The model will automatically decide whether to use tools. - `type: "auto"` - `disable_parallel_tool_use?: boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. - `interface ToolChoiceAny` The model will use any available tools. - `type: "any"` - `disable_parallel_tool_use?: boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - `interface ToolChoiceTool` The model will use the specified tool with `tool_choice.name`. - `type: "tool"` - `name: string` The name of the tool to use. - `disable_parallel_tool_use?: boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - `interface ToolChoiceNone` The model will not be allowed to use tools. - `type: "none"` - `tools?: Array` 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=typescript), 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=typescript)). 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=typescript) for more details. - `interface Tool` - `type?: "custom" | null` - `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: "object"` - `properties?: Record | null` - `required?: Array | null` - `name: string` 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?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `description?: string` 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?: boolean | null` 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?: Array>` - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `interface ToolBash20250124` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples?: Array>` - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `interface CodeExecutionTool20250522` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `interface CodeExecutionTool20250825` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `interface CodeExecutionTool20260120` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `interface CodeExecutionTool20260521` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `interface BrowserToolset20260801` 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: "browser_toolset_20260801"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `configs?: BrowserToolsetConfigs | null` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type?: BrowserTypeConfig | null` `type`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserCloseTabConfig | null` `close_tab`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserDoubleClickConfig | null` `double_click`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserFileUploadConfig | null` `file_upload`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserFindConfig | null` `find`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserFormInputConfig | null` `form_input`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserGetPageTextConfig | null` `get_page_text`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserHoldKeyConfig | null` `hold_key`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserHoverConfig | null` `hover`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserJavascriptExecConfig | null` `javascript_exec`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserKeyConfig | null` `key`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserLeftClickConfig | null` `left_click`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserLeftClickDragConfig | null` `left_click_drag`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserLeftMouseDownConfig | null` `left_mouse_down`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserLeftMouseUpConfig | null` `left_mouse_up`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserListTabsConfig | null` `list_tabs`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserMiddleClickConfig | null` `middle_click`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserMouseMoveConfig | null` `mouse_move`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserNavigateConfig | null` `navigate`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserNewTabConfig | null` `new_tab`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserReadConsoleConfig | null` `read_console`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserReadNetworkConfig | null` `read_network`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserReadPageConfig | null` `read_page`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserRightClickConfig | null` `right_click`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserScreenshotConfig | null` `screenshot`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserScrollConfig | null` `scroll`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserScrollToConfig | null` `scroll_to`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserSwitchTabConfig | null` `switch_tab`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserTripleClickConfig | null` `triple_click`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserWaitConfig | null` `wait`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: BrowserZoomConfig | null` `zoom`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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. - `interface MemoryTool20250818` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples?: Array>` - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `interface ComputerToolset20260801` 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: "computer_toolset_20260801"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `configs?: ComputerToolsetConfigs | null` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `type?: ComputerTypeConfig | null` `type`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerCursorPositionConfig | null` `cursor_position`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerDoubleClickConfig | null` `double_click`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerHoldKeyConfig | null` `hold_key`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerKeyConfig | null` `key`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerLeftClickConfig | null` `left_click`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerLeftClickDragConfig | null` `left_click_drag`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerLeftMouseDownConfig | null` `left_mouse_down`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerLeftMouseUpConfig | null` `left_mouse_up`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerMiddleClickConfig | null` `middle_click`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerMouseMoveConfig | null` `mouse_move`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerRightClickConfig | null` `right_click`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerScreenshotConfig | null` `screenshot`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerScrollConfig | null` `scroll`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerTripleClickConfig | null` `triple_click`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerWaitConfig | null` `wait`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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?: ComputerZoomConfig | null` `zoom`'s config overrides. - `defer_loading?: boolean | null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled?: boolean | null` 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. - `interface ToolTextEditor20250124` - `type: "text_editor_20250124"` - `name: "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?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples?: Array>` - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `interface ToolTextEditor20250429` - `type: "text_editor_20250429"` - `name: "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?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples?: Array>` - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `interface ToolTextEditor20250728` - `type: "text_editor_20250728"` - `name: "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?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `input_examples?: Array>` - `max_characters?: number | null` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `interface WebSearchTool20250305` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains?: Array | null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains?: Array | null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses?: number | null` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `user_location?: UserLocation | null` Parameters for the user's location. Used to provide more relevant search results. - `type: "approximate"` - `city?: string | null` The city of the user. minLength: 1, maxLength: 255 - `country?: string | null` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. minLength: 2, maxLength: 2 - `region?: string | null` The region of the user. minLength: 1, maxLength: 255 - `timezone?: string | null` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `interface WebFetchTool20250910` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains?: Array | null` List of domains to allow fetching from - `blocked_domains?: Array | null` List of domains to block fetching from - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `citations?: CitationsConfigParam | null` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens?: number | null` 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?: number | null` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `url_sources?: WebFetchURLSources | null` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `client_tool_results?: WebFetchURLSourceAll | WebFetchURLSourceNone | WebFetchURLSourceOnly | WebFetchURLSourceExcept` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `interface WebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type: "all"` - `interface WebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type: "none"` - `interface WebFetchURLSourceOnly` The tool filter variant under which only the named tools' results contribute. - `type: "only"` - `tools: Array` - `type: "tool_reference"` - `name: string` - `interface WebFetchURLSourceExcept` The tool filter variant under which every result but the named tools' contributes. - `type: "except"` - `tools: Array` - `type: "tool_reference"` - `name: string` - `server_tool_results?: WebFetchURLSourceAll | WebFetchURLSourceNone | WebFetchURLSourceOnly | WebFetchURLSourceExcept` 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. - `interface WebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `interface WebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `interface WebFetchURLSourceOnly` The tool filter variant under which only the named tools' results contribute. - `interface WebFetchURLSourceExcept` The tool filter variant under which every result but the named tools' contributes. - `user_input?: WebFetchURLSourceAll | WebFetchURLSourceNone` Whether URLs in user messages are fetchable: "all" or "none". - `interface WebFetchURLSourceAll` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `interface WebFetchURLSourceNone` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `interface WebSearchTool20260209` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains?: Array | null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains?: Array | null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses?: number | null` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `user_location?: UserLocation | null` Parameters for the user's location. Used to provide more relevant search results. - `interface WebFetchTool20260209` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains?: Array | null` List of domains to allow fetching from - `blocked_domains?: Array | null` List of domains to block fetching from - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `citations?: CitationsConfigParam | null` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens?: number | null` 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?: number | null` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `url_sources?: WebFetchURLSources | null` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `interface WebFetchTool20260309` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains?: Array | null` List of domains to allow fetching from - `blocked_domains?: Array | null` List of domains to block fetching from - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `citations?: CitationsConfigParam | null` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens?: number | null` 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?: number | null` Maximum number of times the tool can be used in the API request. minimum: 1 - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `url_sources?: WebFetchURLSources | null` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `use_cache?: boolean` 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. - `interface WebSearchTool20260318` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains?: Array | null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains?: Array | null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_uses?: number | null` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion?: "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?: boolean` When true, guarantees schema validation on tool names and inputs - `user_location?: UserLocation | null` Parameters for the user's location. Used to provide more relevant search results. - `interface WebFetchTool20260318` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `allowed_domains?: Array | null` List of domains to allow fetching from - `blocked_domains?: Array | null` List of domains to block fetching from - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `citations?: CitationsConfigParam | null` Citations configuration for fetched documents. Citations are disabled by default. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_content_tokens?: number | null` 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?: number | null` Maximum number of times the tool can be used in the API request. minimum: 1 - `response_inclusion?: "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?: boolean` When true, guarantees schema validation on tool names and inputs - `url_sources?: WebFetchURLSources | null` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `use_cache?: boolean` 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. - `interface ToolSearchToolBm25_20251119` - `type: "tool_search_tool_bm25_20251119" | "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "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?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `interface ToolSearchToolRegex20251119` - `type: "tool_search_tool_regex_20251119" | "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "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?: Array<"direct" | "code_execution_20250825" | "code_execution_20260120" | "code_execution_20260521">` - `"direct"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control?: CacheControlEphemeral | null` Create a cache control breakpoint at this content block. - `defer_loading?: boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `strict?: boolean` When true, guarantees schema validation on tool names and inputs - `user_profile_id?: string` (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?: string` (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. - `temperature?: number` **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not support setting temperature. A value of 1.0 will be accepted for backwards compatibility, all other values will be rejected with a 400 error. Amount of randomness injected into the response. Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0` for analytical / multiple choice, and closer to `1.0` for creative and generative tasks. Note that even with `temperature` of `0.0`, the results will not be fully deterministic. minimum: 0, maximum: 1 - `top_k?: number` **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not accept top_k; any value will be rejected with a 400 error. Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277). Recommended for advanced use cases only. minimum: 0 - `top_p?: number` **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not support setting top_p. A value >= 0.99 will be accepted for backwards compatibility, all other values will be rejected with a 400 error. Use nucleus sampling. In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`. Recommended for advanced use cases only. minimum: 0, maximum: 1 ## Returns - When `stream` is `false` or omitted: `interface Message` - `type: "message"` Object type. For Messages, this is always `"message"`. default: message - `id: string` Unique object identifier. The format and length of IDs may change over time. - `container: Container | null` Information about the container used in this request. This will be non-null if a container tool (e.g. code execution) was used. - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: Array | null` Skills loaded in the container - `type: "anthropic" | "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID minLength: 1, maxLength: 64 - `version: string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `content: Array` 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)"}] ``` - `interface TextBlock` - `type: "text"` default: text - `citations: Array | null` 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`. - `interface CitationCharLocation` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string | null` - `end_char_index: number` - `file_id: string | null` - `start_char_index: number` minimum: 0 - `interface CitationPageLocation` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string | null` - `end_page_number: number` - `file_id: string | null` - `start_page_number: number` minimum: 1 - `interface CitationContentBlockLocation` - `type: "content_block_location"` default: content_block_location - `cited_text: string` 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: number` minimum: 0 - `document_title: string | null` - `end_block_index: number` 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: string | null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `interface CitationsWebSearchResultLocation` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string | null` maxLength: 512 - `url: string` - `interface CitationsSearchResultLocation` - `type: "search_result_location"` default: search_result_location - `cited_text: string` 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: number` 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: number` 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: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string | null` - `text: string` - `interface ThinkingBlock` - `type: "thinking"` default: thinking - `signature: string` 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=typescript) for details. - `thinking: string` The text of Claude's thinking process for this block. - `interface RedactedThinkingBlock` - `type: "redacted_thinking"` default: redacted_thinking - `data: string` 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=typescript#redacted-thinking-blocks) for details. - `interface ToolUseBlock` - `type: "tool_use"` default: tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `caller: DirectCaller | ServerToolCaller | ServerToolCaller20260120` default: {"type":"direct"} - `interface DirectCaller` Tool invocation directly from the model. - `type: "direct"` - `interface ServerToolCaller` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `interface ServerToolCaller20260120` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: Record` - `name: string` minLength: 1 - `toolset_name?: string | null` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `interface ServerToolUseBlock` - `type: "server_tool_use"` default: server_tool_use - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: DirectCaller | ServerToolCaller | ServerToolCaller20260120` default: {"type":"direct"} - `interface DirectCaller` Tool invocation directly from the model. - `interface ServerToolCaller` Tool invocation generated by a server-side tool. - `interface ServerToolCaller20260120` - `input: Record` - `name: "web_search" | "web_fetch" | "code_execution" | 4 more` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `interface WebSearchToolResultBlock` - `type: "web_search_tool_result"` default: web_search_tool_result - `caller: DirectCaller | ServerToolCaller | ServerToolCaller20260120` default: {"type":"direct"} - `interface DirectCaller` Tool invocation directly from the model. - `interface ServerToolCaller` Tool invocation generated by a server-side tool. - `interface ServerToolCaller20260120` - `content: WebSearchToolResultBlockContent` - `interface WebSearchToolResultError` - `type: "web_search_tool_result_error"` default: web_search_tool_result_error - `error_code: WebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `Array` - `type: "web_search_result"` default: web_search_result - `encrypted_content: string` - `page_age: string | null` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `interface WebFetchToolResultBlock` - `type: "web_fetch_tool_result"` default: web_fetch_tool_result - `caller: DirectCaller | ServerToolCaller | ServerToolCaller20260120` default: {"type":"direct"} - `interface DirectCaller` Tool invocation directly from the model. - `interface ServerToolCaller` Tool invocation generated by a server-side tool. - `interface ServerToolCaller20260120` - `content: WebFetchToolResultErrorBlock | WebFetchBlock` - `interface WebFetchToolResultErrorBlock` - `type: "web_fetch_tool_result_error"` default: web_fetch_tool_result_error - `error_code: WebFetchToolResultErrorCode` - `"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"` - `interface WebFetchBlock` - `type: "web_fetch_result"` default: web_fetch_result - `content: DocumentBlock` - `type: "document"` default: document - `citations: CitationsConfig | null` Citation configuration for the document - `enabled: boolean` default: false - `source: Base64PDFSource | PlainTextSource` - `interface Base64PDFSource` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `interface PlainTextSource` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string | null` The title of the document - `retrieved_at: string | null` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `interface CodeExecutionToolResultBlock` - `type: "code_execution_tool_result"` default: code_execution_tool_result - `content: CodeExecutionToolResultBlockContent` - `interface CodeExecutionToolResultError` - `type: "code_execution_tool_result_error"` default: code_execution_tool_result_error - `error_code: CodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `interface CodeExecutionResultBlock` - `type: "code_execution_result"` default: code_execution_result - `content: Array` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `interface EncryptedCodeExecutionResultBlock` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` default: encrypted_code_execution_result - `content: Array` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `interface BashCodeExecutionToolResultBlock` - `type: "bash_code_execution_tool_result"` default: bash_code_execution_tool_result - `content: BashCodeExecutionToolResultError | BashCodeExecutionResultBlock` - `interface BashCodeExecutionToolResultError` - `type: "bash_code_execution_tool_result_error"` default: bash_code_execution_tool_result_error - `error_code: BashCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `interface BashCodeExecutionResultBlock` - `type: "bash_code_execution_result"` default: bash_code_execution_result - `content: Array` - `type: "bash_code_execution_output"` default: bash_code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `interface TextEditorCodeExecutionToolResultBlock` - `type: "text_editor_code_execution_tool_result"` default: text_editor_code_execution_tool_result - `content: TextEditorCodeExecutionToolResultError | TextEditorCodeExecutionViewResultBlock | TextEditorCodeExecutionCreateResultBlock | TextEditorCodeExecutionStrReplaceResultBlock` - `interface TextEditorCodeExecutionToolResultError` - `type: "text_editor_code_execution_tool_result_error"` default: text_editor_code_execution_tool_result_error - `error_code: TextEditorCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string | null` - `interface TextEditorCodeExecutionViewResultBlock` - `type: "text_editor_code_execution_view_result"` default: text_editor_code_execution_view_result - `content: string` - `file_type: "text" | "image" | "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number | null` - `start_line: number | null` - `total_lines: number | null` - `interface TextEditorCodeExecutionCreateResultBlock` - `type: "text_editor_code_execution_create_result"` default: text_editor_code_execution_create_result - `is_file_update: boolean` - `interface TextEditorCodeExecutionStrReplaceResultBlock` - `type: "text_editor_code_execution_str_replace_result"` default: text_editor_code_execution_str_replace_result - `lines: Array | null` - `new_lines: number | null` - `new_start: number | null` - `old_lines: number | null` - `old_start: number | null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `interface ToolSearchToolResultBlock` - `type: "tool_search_tool_result"` default: tool_search_tool_result - `content: ToolSearchToolResultError | ToolSearchToolSearchResultBlock` - `interface ToolSearchToolResultError` - `type: "tool_search_tool_result_error"` default: tool_search_tool_result_error - `error_code: ToolSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string | null` - `interface ToolSearchToolSearchResultBlock` - `type: "tool_search_tool_search_result"` default: tool_search_tool_search_result - `tool_references: Array` - `type: "tool_reference"` default: tool_reference - `tool_name: string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `interface ContainerUploadBlock` Response model for a file uploaded to the container. - `type: "container_upload"` default: container_upload - `file_id: string` - `diagnostics: Diagnostics | null` 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: CacheMissReason | null` 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. - `interface CacheMissModelChanged` - `type: "model_changed"` default: model_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `interface CacheMissSystemChanged` - `type: "system_changed"` default: system_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `interface CacheMissToolsChanged` - `type: "tools_changed"` default: tools_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `interface CacheMissMessagesChanged` - `type: "messages_changed"` default: messages_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `interface CacheMissPreviousMessageNotFound` - `type: "previous_message_not_found"` default: previous_message_not_found - `interface CacheMissUnavailable` - `type: "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. - `"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 - `(string & {})` - `role: "assistant"` Conversational role of the generated message. This will always be `"assistant"`. default: assistant - `stop_details: RefusalStopDetails | null` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `type: "refusal"` default: refusal - `category: "cyber" | "bio" | "frontier_llm" | 2 more | null` 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=typescript). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string | null` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `stop_reason: StopReason | null` 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"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string | null` 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: Usage` 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: CacheCreation | null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number | null` The number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number | null` The number of input tokens read from the cache. minimum: 0 - `inference_geo: string | null` The geographic region where inference was performed for this request. - `input_tokens: number` The number of input tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens_details: OutputTokensDetails | null` 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: number` 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: ServerToolUsage | null` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. default: 0, minimum: 0 - `web_search_requests: number` The number of web search tool requests. default: 0, minimum: 0 - `service_tier: "standard" | "priority" | "batch" | null` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - When `stream` is `true`: `Stream` - `interface RawMessageStartEvent` - `type: "message_start"` default: message_start - `message: Message` - `interface RawMessageDeltaEvent` - `type: "message_delta"` default: message_delta - `delta: Delta` - `container: Container | null` 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: RefusalStopDetails | null` Structured information about why model output stopped. This is `null` when the `stop_reason` has no additional detail to report. - `stop_reason: StopReason | null` - `stop_sequence: string | null` - `usage: MessageDeltaUsage` 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: number | null` The cumulative number of input tokens used to create the cache entry. minimum: 0 - `cache_read_input_tokens: number | null` The cumulative number of input tokens read from the cache. minimum: 0 - `input_tokens: number | null` The cumulative number of input tokens which were used. minimum: 0 - `output_tokens: number` The cumulative number of output tokens which were used. - `output_tokens_details: OutputTokensDetails | null` 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: ServerToolUsage | null` The number of server tool requests. - `interface RawMessageStopEvent` - `type: "message_stop"` default: message_stop - `interface RawContentBlockStartEvent` - `type: "content_block_start"` default: content_block_start - `content_block: TextBlock | ThinkingBlock | RedactedThinkingBlock | 9 more` - `interface TextBlock` - `interface ThinkingBlock` - `interface RedactedThinkingBlock` - `interface ToolUseBlock` - `interface ServerToolUseBlock` - `interface WebSearchToolResultBlock` - `interface WebFetchToolResultBlock` - `interface CodeExecutionToolResultBlock` - `interface BashCodeExecutionToolResultBlock` - `interface TextEditorCodeExecutionToolResultBlock` - `interface ToolSearchToolResultBlock` - `interface ContainerUploadBlock` Response model for a file uploaded to the container. - `index: number` - `interface RawContentBlockDeltaEvent` - `type: "content_block_delta"` default: content_block_delta - `delta: RawContentBlockDelta` - `interface TextDelta` - `type: "text_delta"` default: text_delta - `text: string` - `interface InputJSONDelta` - `type: "input_json_delta"` default: input_json_delta - `partial_json: string` - `interface CitationsDelta` - `type: "citations_delta"` default: citations_delta - `citation: CitationCharLocation | CitationPageLocation | CitationContentBlockLocation | 2 more` - `interface CitationCharLocation` - `interface CitationPageLocation` - `interface CitationContentBlockLocation` - `interface CitationsWebSearchResultLocation` - `interface CitationsSearchResultLocation` - `interface ThinkingDelta` - `type: "thinking_delta"` default: thinking_delta - `thinking: string` 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. - `interface SignatureDelta` - `type: "signature_delta"` default: signature_delta - `signature: string` 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. - `index: number` - `interface RawContentBlockStopEvent` - `type: "content_block_stop"` default: content_block_stop - `index: number` ## Example ```typescript import Anthropic from "@anthropic-ai/sdk"; const client = new Anthropic({ apiKey: process.env["ANTHROPIC_API_KEY"] // This is the default and can be omitted }); const message = await client.messages.create({ max_tokens: 1024, messages: [{ content: "Hello, world", role: "user" }], model: "claude-opus-5" }); console.log(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" } ], "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.", "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, "inference_geo": "global", "input_tokens": 2095, "output_tokens": 503, "output_tokens_details": { "thinking_tokens": 0 }, "server_tool_use": { "web_fetch_requests": 2, "web_search_requests": 0 }, "service_tier": "standard" } } ```