--- title: Batches url: https://platform.claude.com/docs/en/api/go/messages/batches --- # Batches ## Create a Message Batch `client.Messages.Batches.New(ctx, params) (*MessageBatch, error)` **POST** `/v1/messages/batches` Send a batch of Message creation requests. The Message Batches API can be used to process multiple Messages API requests at once. Once a Message Batch is created, it begins processing immediately. Batches can take up to 24 hours to complete. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=go) ### Parameters - `params MessageBatchNewParams` - `Requests []MessageBatchNewParamsRequest` List of requests for prompt completion. Each is an individual request to create a Message. minItems: 1, maxItems: 100000 - `CustomID string` Developer-provided ID created for each request in a Message Batch. Useful for matching results to requests, as results may be given out of request order. Must be unique for each request within the Message Batch. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]{1,64}$ - `Params MessageBatchNewParamsRequestParams` Messages API creation parameters for the individual request. See the [Messages API reference](https://platform.claude.com/docs/en/api/messages?sdk_languages=go) for full documentation on available parameters. - `MaxTokens int64` 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=go#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=go) for details. minimum: 0 - `Messages []MessageParam` 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=go#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=go). 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=go#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 []ContentBlockParamUnion` - `[]ContentBlockParamUnion` - `type TextBlockParam` - `Type Text` - `Text string` minLength: 1 - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Type Ephemeral` - `TTL CacheControlEphemeralTTL Optional` 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=go) for details. - `const CacheControlEphemeralTTLTTL5m CacheControlEphemeralTTL = "5m"` - `const CacheControlEphemeralTTLTTL1h CacheControlEphemeralTTL = "1h"` - `Citations []TextCitationParamUnion Optional` - `type CitationCharLocationParam` - `Type CharLocation` - `CitedText string` - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` minLength: 1, maxLength: 500 - `EndCharIndex int64` - `StartCharIndex int64` minimum: 0 - `type CitationPageLocationParam` - `Type PageLocation` - `CitedText string` - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` minLength: 1, maxLength: 500 - `EndPageNumber int64` - `StartPageNumber int64` minimum: 1 - `type CitationContentBlockLocationParam` - `Type ContentBlockLocation` - `CitedText 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. - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` minLength: 1, maxLength: 500 - `EndBlockIndex int64` 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`. - `StartBlockIndex int64` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `type CitationWebSearchResultLocationParam` - `Type WebSearchResultLocation` - `CitedText string` - `EncryptedIndex string` - `Title string` minLength: 1, maxLength: 512 - `URL string` minLength: 1 - `type CitationSearchResultLocationParam` - `Type SearchResultLocation` - `CitedText 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. - `EndBlockIndex int64` 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`. - `SearchResultIndex int64` 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` - `StartBlockIndex int64` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `Title string` - `type ImageBlockParam` - `Type Image` - `Source ImageBlockParamSourceUnion` - `type Base64ImageSourceParam` - `Type Base64` - `Data string` format: byte - `MediaType Base64ImageSourceMediaType` - `const Base64ImageSourceMediaTypeImageJPEG Base64ImageSourceMediaType = "image/jpeg"` - `const Base64ImageSourceMediaTypeImagePNG Base64ImageSourceMediaType = "image/png"` - `const Base64ImageSourceMediaTypeImageGIF Base64ImageSourceMediaType = "image/gif"` - `const Base64ImageSourceMediaTypeImageWebP Base64ImageSourceMediaType = "image/webp"` - `type URLImageSourceParam` - `Type URL` - `URL string` - `type FileImageSourceParam` - `Type File` - `FileID string` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Transformations ImageTransformationsParam Optional` 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. - `OversizedImage ImageTransformationsParamOversizedImage Optional` 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. - `const ImageTransformationsParamOversizedImageDownsize ImageTransformationsParamOversizedImage = "downsize"` - `const ImageTransformationsParamOversizedImageError ImageTransformationsParamOversizedImage = "error"` - `type DocumentBlockParam` - `Type Document` - `Source DocumentBlockParamSourceUnion` - `type Base64PDFSource` - `Type Base64` - `Data string` format: byte - `MediaType ApplicationPDF` - `type PlainTextSource` - `Type Text` - `Data string` - `MediaType TextPlain` - `type ContentBlockSourceParam` - `Type Content` - `Content ContentBlockSourceContentUnionParam` - `string` - `[]ContentBlockSourceContentItemUnionParam` - `type TextBlockParam` - `type ImageBlockParam` - `type URLPDFSourceParam` - `Type URL` - `URL string` - `type FileDocumentSourceParam` - `Type File` - `FileID string` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Citations CitationsConfigParam Optional` - `Enabled bool Optional` - `Context string Optional` minLength: 1 - `Title string Optional` minLength: 1, maxLength: 500 - `type SearchResultBlockParam` - `Type SearchResult` - `Content []TextBlockParam` - `Type Text` - `Text string` minLength: 1 - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Citations []TextCitationParamUnion Optional` - `Source string` - `Title string` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Citations CitationsConfigParam Optional` - `type 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. - `type RedactedThinkingBlockParam` - `Type RedactedThinking` - `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. - `type ToolUseBlockParam` - `Type ToolUse` - `ID string` pattern: ^[a-zA-Z0-9_-]+$ - `Input map[string, any]` - `Name string` minLength: 1, maxLength: 200 - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Caller ToolUseBlockParamCallerUnion Optional` - `type DirectCaller` Tool invocation directly from the model. - `Type Direct` - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `Type CodeExecution20250825` - `ToolID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ServerToolCaller20260120` - `Type CodeExecution20260120` - `ToolID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `ToolsetName string Optional` For a toolset member tool_use, the toolset family this member belongs to. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `type ToolResultBlockParam` - `Type ToolResult` - `ToolUseID string` pattern: ^[a-zA-Z0-9_-]+$ - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Content []ToolResultBlockParamContentUnion Optional` - `[]ToolResultBlockParamContentUnion` - `type TextBlockParam` - `type ImageBlockParam` - `type SearchResultBlockParam` - `type DocumentBlockParam` - `type ToolReferenceBlockParam` Tool reference block that can be included in tool_result content. - `Type ToolReference` - `ToolName string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `type 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 BrowserState` - `Tabs []BrowserStateTabEntryParam` 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 - `TabID 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 bool Optional` Whether this tab is the active tab after this call. Whenever `tabs` is non-empty, exactly one entry is marked `active: true`. - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `StateChanges []BrowserStateChangeUnionParam Optional` 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 - `type BrowserStateChangeTabOpenedParam` 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 TabOpened` - `TabID string` The `tab_id` of the opened tab, present in `tabs`. minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `type BrowserStateChangeDownloadStartedParam` A file download that started during this call. - `Type DownloadStarted` - `DownloadID 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]*$ - `type BrowserStateChangeDownloadCompletedParam` 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 DownloadCompleted` - `DownloadID 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 Optional` 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]*$ - `SizeBytes int64 Optional` The completed download's size. minimum: 0 - `type BrowserStateChangeDownloadFailedParam` A file download that failed — or was cancelled — during this call. - `Type DownloadFailed` - `DownloadID 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 Optional` The failure or cancellation detail, when known. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `IsError bool Optional` - `ToolsetName string Optional` For a toolset member tool_result, the toolset family of the paired tool_use. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `type ServerToolUseBlockParam` - `Type ServerToolUse` - `ID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `Input map[string, any]` - `Name ServerToolUseBlockParamName` - `const ServerToolUseBlockParamNameWebSearch ServerToolUseBlockParamName = "web_search"` - `const ServerToolUseBlockParamNameWebFetch ServerToolUseBlockParamName = "web_fetch"` - `const ServerToolUseBlockParamNameCodeExecution ServerToolUseBlockParamName = "code_execution"` - `const ServerToolUseBlockParamNameBashCodeExecution ServerToolUseBlockParamName = "bash_code_execution"` - `const ServerToolUseBlockParamNameTextEditorCodeExecution ServerToolUseBlockParamName = "text_editor_code_execution"` - `const ServerToolUseBlockParamNameToolSearchToolRegex ServerToolUseBlockParamName = "tool_search_tool_regex"` - `const ServerToolUseBlockParamNameToolSearchToolBm25 ServerToolUseBlockParamName = "tool_search_tool_bm25"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Caller ServerToolUseBlockParamCallerUnion Optional` - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `type WebSearchToolResultBlockParam` - `Type WebSearchToolResult` - `Content WebSearchToolResultBlockParamContentUnion` - `[]WebSearchResultBlockParam` - `Type WebSearchResult` - `EncryptedContent string` - `Title string` - `URL string` - `PageAge string Optional` - `type WebSearchToolRequestErrorParam` - `Type WebSearchToolResultError` - `ErrorCode WebSearchToolResultErrorCode` - `const WebSearchToolResultErrorCodeInvalidToolInput WebSearchToolResultErrorCode = "invalid_tool_input"` - `const WebSearchToolResultErrorCodeUnavailable WebSearchToolResultErrorCode = "unavailable"` - `const WebSearchToolResultErrorCodeMaxUsesExceeded WebSearchToolResultErrorCode = "max_uses_exceeded"` - `const WebSearchToolResultErrorCodeTooManyRequests WebSearchToolResultErrorCode = "too_many_requests"` - `const WebSearchToolResultErrorCodeQueryTooLong WebSearchToolResultErrorCode = "query_too_long"` - `const WebSearchToolResultErrorCodeRequestTooLarge WebSearchToolResultErrorCode = "request_too_large"` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Caller WebSearchToolResultBlockParamCallerUnion Optional` - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `type WebFetchToolResultBlockParam` - `Type WebFetchToolResult` - `Content WebFetchToolResultBlockParamContentUnion` - `type WebFetchToolResultErrorBlockParam` - `Type WebFetchToolResultError` - `ErrorCode WebFetchToolResultErrorCode` - `const WebFetchToolResultErrorCodeInvalidToolInput WebFetchToolResultErrorCode = "invalid_tool_input"` - `const WebFetchToolResultErrorCodeURLTooLong WebFetchToolResultErrorCode = "url_too_long"` - `const WebFetchToolResultErrorCodeURLNotAllowed WebFetchToolResultErrorCode = "url_not_allowed"` - `const WebFetchToolResultErrorCodeURLNotInPriorContext WebFetchToolResultErrorCode = "url_not_in_prior_context"` - `const WebFetchToolResultErrorCodeURLNotAccessible WebFetchToolResultErrorCode = "url_not_accessible"` - `const WebFetchToolResultErrorCodeUnsupportedContentType WebFetchToolResultErrorCode = "unsupported_content_type"` - `const WebFetchToolResultErrorCodeTooManyRequests WebFetchToolResultErrorCode = "too_many_requests"` - `const WebFetchToolResultErrorCodeMaxUsesExceeded WebFetchToolResultErrorCode = "max_uses_exceeded"` - `const WebFetchToolResultErrorCodeUnavailable WebFetchToolResultErrorCode = "unavailable"` - `const WebFetchToolResultErrorCodeContentTooLarge WebFetchToolResultErrorCode = "content_too_large"` - `type WebFetchBlockParam` - `Type WebFetchResult` - `Content DocumentBlockParam` - `URL string` Fetched content URL - `RetrievedAt string Optional` ISO 8601 timestamp when the content was retrieved - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Caller WebFetchToolResultBlockParamCallerUnion Optional` - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `type CodeExecutionToolResultBlockParam` - `Type CodeExecutionToolResult` - `Content CodeExecutionToolResultBlockParamContentUnion` - `type CodeExecutionToolResultErrorParam` - `Type CodeExecutionToolResultError` - `ErrorCode CodeExecutionToolResultErrorCode` - `const CodeExecutionToolResultErrorCodeInvalidToolInput CodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const CodeExecutionToolResultErrorCodeUnavailable CodeExecutionToolResultErrorCode = "unavailable"` - `const CodeExecutionToolResultErrorCodeTooManyRequests CodeExecutionToolResultErrorCode = "too_many_requests"` - `const CodeExecutionToolResultErrorCodeExecutionTimeExceeded CodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `type CodeExecutionResultBlockParam` - `Type CodeExecutionResult` - `Content []CodeExecutionOutputBlockParam` - `Type CodeExecutionOutput` - `FileID string` - `ReturnCode int64` - `Stderr string` - `Stdout string` - `type EncryptedCodeExecutionResultBlockParam` Code execution result with encrypted stdout for PFC + web_search results. - `Type EncryptedCodeExecutionResult` - `Content []CodeExecutionOutputBlockParam` - `Type CodeExecutionOutput` - `FileID string` - `EncryptedStdout string` - `ReturnCode int64` - `Stderr string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `type BashCodeExecutionToolResultBlockParam` - `Type BashCodeExecutionToolResult` - `Content BashCodeExecutionToolResultBlockParamContentUnion` - `type BashCodeExecutionToolResultErrorParam` - `Type BashCodeExecutionToolResultError` - `ErrorCode BashCodeExecutionToolResultErrorCode` - `const BashCodeExecutionToolResultErrorCodeInvalidToolInput BashCodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const BashCodeExecutionToolResultErrorCodeUnavailable BashCodeExecutionToolResultErrorCode = "unavailable"` - `const BashCodeExecutionToolResultErrorCodeTooManyRequests BashCodeExecutionToolResultErrorCode = "too_many_requests"` - `const BashCodeExecutionToolResultErrorCodeExecutionTimeExceeded BashCodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `const BashCodeExecutionToolResultErrorCodeOutputFileTooLarge BashCodeExecutionToolResultErrorCode = "output_file_too_large"` - `type BashCodeExecutionResultBlockParam` - `Type BashCodeExecutionResult` - `Content []BashCodeExecutionOutputBlockParam` - `Type BashCodeExecutionOutput` - `FileID string` - `ReturnCode int64` - `Stderr string` - `Stdout string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `type TextEditorCodeExecutionToolResultBlockParam` - `Type TextEditorCodeExecutionToolResult` - `Content TextEditorCodeExecutionToolResultBlockParamContentUnion` - `type TextEditorCodeExecutionToolResultErrorParam` - `Type TextEditorCodeExecutionToolResultError` - `ErrorCode TextEditorCodeExecutionToolResultErrorCode` - `const TextEditorCodeExecutionToolResultErrorCodeInvalidToolInput TextEditorCodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const TextEditorCodeExecutionToolResultErrorCodeUnavailable TextEditorCodeExecutionToolResultErrorCode = "unavailable"` - `const TextEditorCodeExecutionToolResultErrorCodeTooManyRequests TextEditorCodeExecutionToolResultErrorCode = "too_many_requests"` - `const TextEditorCodeExecutionToolResultErrorCodeExecutionTimeExceeded TextEditorCodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `const TextEditorCodeExecutionToolResultErrorCodeFileNotFound TextEditorCodeExecutionToolResultErrorCode = "file_not_found"` - `ErrorMessage string Optional` - `type TextEditorCodeExecutionViewResultBlockParam` - `Type TextEditorCodeExecutionViewResult` - `Content string` - `FileType TextEditorCodeExecutionViewResultBlockParamFileType` - `const TextEditorCodeExecutionViewResultBlockParamFileTypeText TextEditorCodeExecutionViewResultBlockParamFileType = "text"` - `const TextEditorCodeExecutionViewResultBlockParamFileTypeImage TextEditorCodeExecutionViewResultBlockParamFileType = "image"` - `const TextEditorCodeExecutionViewResultBlockParamFileTypePDF TextEditorCodeExecutionViewResultBlockParamFileType = "pdf"` - `NumLines int64 Optional` - `StartLine int64 Optional` - `TotalLines int64 Optional` - `type TextEditorCodeExecutionCreateResultBlockParam` - `Type TextEditorCodeExecutionCreateResult` - `IsFileUpdate bool` - `type TextEditorCodeExecutionStrReplaceResultBlockParam` - `Type TextEditorCodeExecutionStrReplaceResult` - `Lines []string Optional` - `NewLines int64 Optional` - `NewStart int64 Optional` - `OldLines int64 Optional` - `OldStart int64 Optional` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `type ToolSearchToolResultBlockParam` - `Type ToolSearchToolResult` - `Content ToolSearchToolResultBlockParamContentUnion` - `type ToolSearchToolResultErrorParam` - `Type ToolSearchToolResultError` - `ErrorCode ToolSearchToolResultErrorCode` - `const ToolSearchToolResultErrorCodeInvalidToolInput ToolSearchToolResultErrorCode = "invalid_tool_input"` - `const ToolSearchToolResultErrorCodeUnavailable ToolSearchToolResultErrorCode = "unavailable"` - `const ToolSearchToolResultErrorCodeTooManyRequests ToolSearchToolResultErrorCode = "too_many_requests"` - `const ToolSearchToolResultErrorCodeExecutionTimeExceeded ToolSearchToolResultErrorCode = "execution_time_exceeded"` - `ErrorMessage string Optional` - `type ToolSearchToolSearchResultBlockParam` - `Type ToolSearchToolSearchResult` - `ToolReferences []ToolReferenceBlockParam` - `Type ToolReference` - `ToolName string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `type 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 ContainerUpload` - `FileID string` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Role MessageParamRole` - `const MessageParamRoleUser MessageParamRole = "user"` - `const MessageParamRoleAssistant MessageParamRole = "assistant"` - `const MessageParamRoleSystem MessageParamRole = "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. - `const ModelClaudeHaiku5_5 Model = "claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `const ModelClaudeSonnet5_5 Model = "claude-sonnet-5-5"` Efficient model for coding and agents - `const ModelClaudeFable5_1 Model = "claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `const ModelClaudeOpus5_5 Model = "claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `const ModelClaudeMythos5_1 Model = "claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `const ModelClaudeSonnet5 Model = "claude-sonnet-5"` Efficient model for coding and agents - `const ModelClaudeFable5 Model = "claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `const ModelClaudeMythos5 Model = "claude-mythos-5"` Most capable model for cybersecurity and biology research - `const ModelClaudeOpus5 Model = "claude-opus-5"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_8 Model = "claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_7 Model = "claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_6 Model = "claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `const ModelClaudeSonnet4_6 Model = "claude-sonnet-4-6"` Best combination of speed and intelligence - `const ModelClaudeHaiku4_5 Model = "claude-haiku-4-5"` - `const ModelClaudeHaiku4_5_20251001 Model = "claude-haiku-4-5-20251001"` - `const ModelClaudeOpus4_5 Model = "claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_5_20251101 Model = "claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `const ModelClaudeMythosPreview Model = "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 - `const ModelClaudeSonnet4_5 Model = "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 - `const ModelClaudeSonnet4_5_20250929 Model = "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 - `CacheControl CacheControlEphemeralParam Optional` Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. - `Container MessageCreateParamsContainerUnion Optional` Container identifier for reuse across requests. - `type ContainerParams` Container parameters with skills to be loaded. - `ID string Optional` Container id - `Skills []SkillParams Optional` List of skills to load in the container maxItems: 20 - `Type SkillParamsType` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `const SkillParamsTypeAnthropic SkillParamsType = "anthropic"` - `const SkillParamsTypeCustom SkillParamsType = "custom"` - `SkillID string` Skill ID minLength: 1, maxLength: 64 - `Version string Optional` Skill version or 'latest' for most recent version minLength: 1, maxLength: 64 - `string` - `Diagnostics DiagnosticsParam Optional` 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. - `PreviousMessageID string Optional` 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 - `InferenceGeo string Optional` Specifies the geographic region for inference processing. If not specified, the workspace's `default_inference_geo` is used. - `Metadata MetadataParam Optional` An object describing metadata about the request. - `UserID string Optional` 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 - `OutputConfig OutputConfigParam Optional` Configuration options for the model's output, such as the output format. - `Effort OutputConfigEffort Optional` 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`. - `const OutputConfigEffortLow OutputConfigEffort = "low"` - `const OutputConfigEffortMedium OutputConfigEffort = "medium"` - `const OutputConfigEffortHigh OutputConfigEffort = "high"` - `const OutputConfigEffortXhigh OutputConfigEffort = "xhigh"` - `const OutputConfigEffortMax OutputConfigEffort = "max"` - `Format JSONOutputFormatParam Optional` 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=go) - `Type JSONSchema` - `Schema map[string, any]` The JSON schema of the format - `ServiceTier string Optional` 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=go) for details. - `const MessageBatchNewParamsRequestParamsServiceTierAuto MessageBatchNewParamsRequestParamsServiceTier = "auto"` - `const MessageBatchNewParamsRequestParamsServiceTierStandardOnly MessageBatchNewParamsRequestParamsServiceTier = "standard_only"` - `Speed string Optional` The inference speed mode for this request. `"fast"` enables high output-tokens-per-second inference. Some models require the `fast-mode-2026-02-01` beta header for any `speed` value. See [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode?sdk_languages=go) for which models. - `const MessageBatchNewParamsRequestParamsSpeedStandard MessageBatchNewParamsRequestParamsSpeed = "standard"` - `const MessageBatchNewParamsRequestParamsSpeedFast MessageBatchNewParamsRequestParamsSpeed = "fast"` - `StopSequences []string Optional` 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 bool Optional` 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=go#streaming-with-sdks) for an example in each language. - `System []TextBlockParam Optional` 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=go#give-claude-a-role). - `[]TextBlockParam` - `Type Text` - `Text string` minLength: 1 - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Citations []TextCitationParamUnion Optional` - `Thinking ThinkingConfigParamUnion Optional` 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=go#configuring-thinking) for each model's behavior. - `type ThinkingConfigEnabledParam` - `Type Enabled` - `BudgetTokens int64` 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=go) for details. minimum: 1024 - `Display ThinkingConfigEnabledDisplay Optional` 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=go#controlling-thinking-display). - `const ThinkingConfigEnabledDisplaySummarized ThinkingConfigEnabledDisplay = "summarized"` - `const ThinkingConfigEnabledDisplayOmitted ThinkingConfigEnabledDisplay = "omitted"` - `type ThinkingConfigDisabledParam` - `Type Disabled` - `type ThinkingConfigBetweenToolsParam` - `Type BetweenTools` - `type ThinkingConfigAdaptiveParam` - `Type Adaptive` - `Display ThinkingConfigAdaptiveDisplay Optional` 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=go#controlling-thinking-display). - `const ThinkingConfigAdaptiveDisplaySummarized ThinkingConfigAdaptiveDisplay = "summarized"` - `const ThinkingConfigAdaptiveDisplayOmitted ThinkingConfigAdaptiveDisplay = "omitted"` - `ToolChoice ToolChoiceUnionParam Optional` 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. - `type ToolChoiceAutoParam` The model will automatically decide whether to use tools. - `Type Auto` - `DisableParallelToolUse bool Optional` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. - `type ToolChoiceAnyParam` The model will use any available tools. - `Type Any` - `DisableParallelToolUse bool Optional` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - `type ToolChoiceToolParam` The model will use the specified tool with `tool_choice.name`. - `Type Tool` - `Name string` The name of the tool to use. - `DisableParallelToolUse bool Optional` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - `type ToolChoiceNoneParam` The model will not be allowed to use tools. - `Type None` - `Tools []ToolUnionParam Optional` 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=go), 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=go)). 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=go) for more details. - `type ToolParam` - `Type ToolType Optional` - `InputSchema ToolInputSchemaParam` [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 map[string, any] Optional` - `Required []string Optional` - `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}$ - `AllowedCallers []string Optional` - `const ToolAllowedCallerDirect ToolAllowedCaller = "direct"` - `const ToolAllowedCallerCodeExecution20250825 ToolAllowedCaller = "code_execution_20250825"` - `const ToolAllowedCallerCodeExecution20260120 ToolAllowedCaller = "code_execution_20260120"` - `const ToolAllowedCallerCodeExecution20260521 ToolAllowedCaller = "code_execution_20260521"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Description string Optional` 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. - `EagerInputStreaming bool Optional` 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. - `InputExamples []map[string, any] Optional` - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `type ToolBash20250124Param` - `Type Bash20250124` - `Name Bash` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const ToolBash20250124AllowedCallerDirect ToolBash20250124AllowedCaller = "direct"` - `const ToolBash20250124AllowedCallerCodeExecution20250825 ToolBash20250124AllowedCaller = "code_execution_20250825"` - `const ToolBash20250124AllowedCallerCodeExecution20260120 ToolBash20250124AllowedCaller = "code_execution_20260120"` - `const ToolBash20250124AllowedCallerCodeExecution20260521 ToolBash20250124AllowedCaller = "code_execution_20260521"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `InputExamples []map[string, any] Optional` - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `type CodeExecutionTool20250522Param` - `Type CodeExecution20250522` - `Name CodeExecution` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const CodeExecutionTool20250522AllowedCallerDirect CodeExecutionTool20250522AllowedCaller = "direct"` - `const CodeExecutionTool20250522AllowedCallerCodeExecution20250825 CodeExecutionTool20250522AllowedCaller = "code_execution_20250825"` - `const CodeExecutionTool20250522AllowedCallerCodeExecution20260120 CodeExecutionTool20250522AllowedCaller = "code_execution_20260120"` - `const CodeExecutionTool20250522AllowedCallerCodeExecution20260521 CodeExecutionTool20250522AllowedCaller = "code_execution_20260521"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `type CodeExecutionTool20250825Param` - `Type CodeExecution20250825` - `Name CodeExecution` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const CodeExecutionTool20250825AllowedCallerDirect CodeExecutionTool20250825AllowedCaller = "direct"` - `const CodeExecutionTool20250825AllowedCallerCodeExecution20250825 CodeExecutionTool20250825AllowedCaller = "code_execution_20250825"` - `const CodeExecutionTool20250825AllowedCallerCodeExecution20260120 CodeExecutionTool20250825AllowedCaller = "code_execution_20260120"` - `const CodeExecutionTool20250825AllowedCallerCodeExecution20260521 CodeExecutionTool20250825AllowedCaller = "code_execution_20260521"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `type CodeExecutionTool20260120Param` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `Type CodeExecution20260120` - `Name CodeExecution` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const CodeExecutionTool20260120AllowedCallerDirect CodeExecutionTool20260120AllowedCaller = "direct"` - `const CodeExecutionTool20260120AllowedCallerCodeExecution20250825 CodeExecutionTool20260120AllowedCaller = "code_execution_20250825"` - `const CodeExecutionTool20260120AllowedCallerCodeExecution20260120 CodeExecutionTool20260120AllowedCaller = "code_execution_20260120"` - `const CodeExecutionTool20260120AllowedCallerCodeExecution20260521 CodeExecutionTool20260120AllowedCaller = "code_execution_20260521"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `type CodeExecutionTool20260521Param` Code execution tool with REPL state persistence. - `Type CodeExecution20260521` - `Name CodeExecution` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const CodeExecutionTool20260521AllowedCallerDirect CodeExecutionTool20260521AllowedCaller = "direct"` - `const CodeExecutionTool20260521AllowedCallerCodeExecution20250825 CodeExecutionTool20260521AllowedCaller = "code_execution_20250825"` - `const CodeExecutionTool20260521AllowedCallerCodeExecution20260120 CodeExecutionTool20260521AllowedCaller = "code_execution_20260120"` - `const CodeExecutionTool20260521AllowedCallerCodeExecution20260521 CodeExecutionTool20260521AllowedCaller = "code_execution_20260521"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `type BrowserToolset20260801Param` 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 BrowserToolset20260801` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Configs BrowserToolsetConfigsParam Optional` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `Type BrowserTypeConfigParam Optional` `type`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `CloseTab BrowserCloseTabConfigParam Optional` `close_tab`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `DoubleClick BrowserDoubleClickConfigParam Optional` `double_click`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `FileUpload BrowserFileUploadConfigParam Optional` `file_upload`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 BrowserFindConfigParam Optional` `find`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `FormInput BrowserFormInputConfigParam Optional` `form_input`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `GetPageText BrowserGetPageTextConfigParam Optional` `get_page_text`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `HoldKey BrowserHoldKeyConfigParam Optional` `hold_key`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 BrowserHoverConfigParam Optional` `hover`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `JavascriptExec BrowserJavascriptExecConfigParam Optional` `javascript_exec`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 BrowserKeyConfigParam Optional` `key`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `LeftClick BrowserLeftClickConfigParam Optional` `left_click`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `LeftClickDrag BrowserLeftClickDragConfigParam Optional` `left_click_drag`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `LeftMouseDown BrowserLeftMouseDownConfigParam Optional` `left_mouse_down`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `LeftMouseUp BrowserLeftMouseUpConfigParam Optional` `left_mouse_up`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `ListTabs BrowserListTabsConfigParam Optional` `list_tabs`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `MiddleClick BrowserMiddleClickConfigParam Optional` `middle_click`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `MouseMove BrowserMouseMoveConfigParam Optional` `mouse_move`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 BrowserNavigateConfigParam Optional` `navigate`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `NewTab BrowserNewTabConfigParam Optional` `new_tab`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `ReadConsole BrowserReadConsoleConfigParam Optional` `read_console`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `ReadNetwork BrowserReadNetworkConfigParam Optional` `read_network`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `ReadPage BrowserReadPageConfigParam Optional` `read_page`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `RightClick BrowserRightClickConfigParam Optional` `right_click`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 BrowserScreenshotConfigParam Optional` `screenshot`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 BrowserScrollConfigParam Optional` `scroll`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `ScrollTo BrowserScrollToConfigParam Optional` `scroll_to`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `SwitchTab BrowserSwitchTabConfigParam Optional` `switch_tab`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `TripleClick BrowserTripleClickConfigParam Optional` `triple_click`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 BrowserWaitConfigParam Optional` `wait`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 BrowserZoomConfigParam Optional` `zoom`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `type MemoryTool20250818Param` - `Type Memory20250818` - `Name Memory` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const MemoryTool20250818AllowedCallerDirect MemoryTool20250818AllowedCaller = "direct"` - `const MemoryTool20250818AllowedCallerCodeExecution20250825 MemoryTool20250818AllowedCaller = "code_execution_20250825"` - `const MemoryTool20250818AllowedCallerCodeExecution20260120 MemoryTool20250818AllowedCaller = "code_execution_20260120"` - `const MemoryTool20250818AllowedCallerCodeExecution20260521 MemoryTool20250818AllowedCaller = "code_execution_20260521"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `InputExamples []map[string, any] Optional` - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `type ComputerToolset20260801Param` 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 ComputerToolset20260801` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Configs ComputerToolsetConfigsParam Optional` Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent. - `Type ComputerTypeConfigParam Optional` `type`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `CursorPosition ComputerCursorPositionConfigParam Optional` `cursor_position`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `DoubleClick ComputerDoubleClickConfigParam Optional` `double_click`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `HoldKey ComputerHoldKeyConfigParam Optional` `hold_key`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 ComputerKeyConfigParam Optional` `key`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `LeftClick ComputerLeftClickConfigParam Optional` `left_click`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `LeftClickDrag ComputerLeftClickDragConfigParam Optional` `left_click_drag`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `LeftMouseDown ComputerLeftMouseDownConfigParam Optional` `left_mouse_down`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `LeftMouseUp ComputerLeftMouseUpConfigParam Optional` `left_mouse_up`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `MiddleClick ComputerMiddleClickConfigParam Optional` `middle_click`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `MouseMove ComputerMouseMoveConfigParam Optional` `mouse_move`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `RightClick ComputerRightClickConfigParam Optional` `right_click`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 ComputerScreenshotConfigParam Optional` `screenshot`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 ComputerScrollConfigParam Optional` `scroll`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `TripleClick ComputerTripleClickConfigParam Optional` `triple_click`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 ComputerWaitConfigParam Optional` `wait`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered 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 ComputerZoomConfigParam Optional` `zoom`'s config overrides. - `DeferLoading bool Optional` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `Enabled bool Optional` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `type ToolTextEditor20250124Param` - `Type TextEditor20250124` - `Name StrReplaceEditor` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const ToolTextEditor20250124AllowedCallerDirect ToolTextEditor20250124AllowedCaller = "direct"` - `const ToolTextEditor20250124AllowedCallerCodeExecution20250825 ToolTextEditor20250124AllowedCaller = "code_execution_20250825"` - `const ToolTextEditor20250124AllowedCallerCodeExecution20260120 ToolTextEditor20250124AllowedCaller = "code_execution_20260120"` - `const ToolTextEditor20250124AllowedCallerCodeExecution20260521 ToolTextEditor20250124AllowedCaller = "code_execution_20260521"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `InputExamples []map[string, any] Optional` - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `type ToolTextEditor20250429Param` - `Type TextEditor20250429` - `Name StrReplaceBasedEditTool` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const ToolTextEditor20250429AllowedCallerDirect ToolTextEditor20250429AllowedCaller = "direct"` - `const ToolTextEditor20250429AllowedCallerCodeExecution20250825 ToolTextEditor20250429AllowedCaller = "code_execution_20250825"` - `const ToolTextEditor20250429AllowedCallerCodeExecution20260120 ToolTextEditor20250429AllowedCaller = "code_execution_20260120"` - `const ToolTextEditor20250429AllowedCallerCodeExecution20260521 ToolTextEditor20250429AllowedCaller = "code_execution_20260521"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `InputExamples []map[string, any] Optional` - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `type ToolTextEditor20250728Param` - `Type TextEditor20250728` - `Name StrReplaceBasedEditTool` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const ToolTextEditor20250728AllowedCallerDirect ToolTextEditor20250728AllowedCaller = "direct"` - `const ToolTextEditor20250728AllowedCallerCodeExecution20250825 ToolTextEditor20250728AllowedCaller = "code_execution_20250825"` - `const ToolTextEditor20250728AllowedCallerCodeExecution20260120 ToolTextEditor20250728AllowedCaller = "code_execution_20260120"` - `const ToolTextEditor20250728AllowedCallerCodeExecution20260521 ToolTextEditor20250728AllowedCaller = "code_execution_20260521"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `InputExamples []map[string, any] Optional` - `MaxCharacters int64 Optional` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. minimum: 1 - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `type WebSearchTool20250305Param` - `Type WebSearch20250305` - `Name WebSearch` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const WebSearchTool20250305AllowedCallerDirect WebSearchTool20250305AllowedCaller = "direct"` - `const WebSearchTool20250305AllowedCallerCodeExecution20250825 WebSearchTool20250305AllowedCaller = "code_execution_20250825"` - `const WebSearchTool20250305AllowedCallerCodeExecution20260120 WebSearchTool20250305AllowedCaller = "code_execution_20260120"` - `const WebSearchTool20250305AllowedCallerCodeExecution20260521 WebSearchTool20250305AllowedCaller = "code_execution_20260521"` - `AllowedDomains []string Optional` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `BlockedDomains []string Optional` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `MaxUses int64 Optional` Maximum number of times the tool can be used in the API request. minimum: 1 - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `UserLocation UserLocationParam Optional` Parameters for the user's location. Used to provide more relevant search results. - `Type Approximate` - `City string Optional` The city of the user. minLength: 1, maxLength: 255 - `Country string Optional` 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 Optional` The region of the user. minLength: 1, maxLength: 255 - `Timezone string Optional` The [IANA timezone](https://nodatime.org/TimeZones) of the user. minLength: 1, maxLength: 255 - `type WebFetchTool20250910Param` - `Type WebFetch20250910` - `Name WebFetch` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const WebFetchTool20250910AllowedCallerDirect WebFetchTool20250910AllowedCaller = "direct"` - `const WebFetchTool20250910AllowedCallerCodeExecution20250825 WebFetchTool20250910AllowedCaller = "code_execution_20250825"` - `const WebFetchTool20250910AllowedCallerCodeExecution20260120 WebFetchTool20250910AllowedCaller = "code_execution_20260120"` - `const WebFetchTool20250910AllowedCallerCodeExecution20260521 WebFetchTool20250910AllowedCaller = "code_execution_20260521"` - `AllowedDomains []string Optional` List of domains to allow fetching from - `BlockedDomains []string Optional` List of domains to block fetching from - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Citations CitationsConfigParam Optional` Citations configuration for fetched documents. Citations are disabled by default. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `MaxContentTokens int64 Optional` 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 - `MaxUses int64 Optional` Maximum number of times the tool can be used in the API request. minimum: 1 - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `URLSources WebFetchURLSourcesParam Optional` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `ClientToolResults WebFetchURLSourcesClientToolResultsUnionParam Optional` Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[]. - `type WebFetchURLSourceAllParam` 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` - `type WebFetchURLSourceNoneParam` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `Type None` - `type WebFetchURLSourceOnlyParam` The tool filter variant under which only the named tools' results contribute. - `Type Only` - `Tools []WebFetchURLSourceToolReferenceParam` - `Type ToolReference` - `Name string` - `type WebFetchURLSourceExceptParam` The tool filter variant under which every result but the named tools' contributes. - `Type Except` - `Tools []WebFetchURLSourceToolReferenceParam` - `Type ToolReference` - `Name string` - `ServerToolResults WebFetchURLSourcesServerToolResultsUnionParam Optional` 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. - `type WebFetchURLSourceAllParam` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type WebFetchURLSourceNoneParam` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type WebFetchURLSourceOnlyParam` The tool filter variant under which only the named tools' results contribute. - `type WebFetchURLSourceExceptParam` The tool filter variant under which every result but the named tools' contributes. - `UserInput WebFetchURLSourcesUserInputUnionParam Optional` Whether URLs in user messages are fetchable: "all" or "none". - `type WebFetchURLSourceAllParam` The `url_sources` variant under which a source contributes in full: every result of the tool filter's source, or all user input. - `type WebFetchURLSourceNoneParam` The `url_sources` variant under which a source contributes nothing: no result of the tool filter's source, or no user input. - `type WebSearchTool20260209Param` - `Type WebSearch20260209` - `Name WebSearch` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const WebSearchTool20260209AllowedCallerDirect WebSearchTool20260209AllowedCaller = "direct"` - `const WebSearchTool20260209AllowedCallerCodeExecution20250825 WebSearchTool20260209AllowedCaller = "code_execution_20250825"` - `const WebSearchTool20260209AllowedCallerCodeExecution20260120 WebSearchTool20260209AllowedCaller = "code_execution_20260120"` - `const WebSearchTool20260209AllowedCallerCodeExecution20260521 WebSearchTool20260209AllowedCaller = "code_execution_20260521"` - `AllowedDomains []string Optional` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `BlockedDomains []string Optional` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `MaxUses int64 Optional` Maximum number of times the tool can be used in the API request. minimum: 1 - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `UserLocation UserLocationParam Optional` Parameters for the user's location. Used to provide more relevant search results. - `type WebFetchTool20260209Param` - `Type WebFetch20260209` - `Name WebFetch` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const WebFetchTool20260209AllowedCallerDirect WebFetchTool20260209AllowedCaller = "direct"` - `const WebFetchTool20260209AllowedCallerCodeExecution20250825 WebFetchTool20260209AllowedCaller = "code_execution_20250825"` - `const WebFetchTool20260209AllowedCallerCodeExecution20260120 WebFetchTool20260209AllowedCaller = "code_execution_20260120"` - `const WebFetchTool20260209AllowedCallerCodeExecution20260521 WebFetchTool20260209AllowedCaller = "code_execution_20260521"` - `AllowedDomains []string Optional` List of domains to allow fetching from - `BlockedDomains []string Optional` List of domains to block fetching from - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Citations CitationsConfigParam Optional` Citations configuration for fetched documents. Citations are disabled by default. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `MaxContentTokens int64 Optional` 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 - `MaxUses int64 Optional` Maximum number of times the tool can be used in the API request. minimum: 1 - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `URLSources WebFetchURLSourcesParam Optional` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `type WebFetchTool20260309Param` Web fetch tool with use_cache parameter for bypassing cached content. - `Type WebFetch20260309` - `Name WebFetch` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const WebFetchTool20260309AllowedCallerDirect WebFetchTool20260309AllowedCaller = "direct"` - `const WebFetchTool20260309AllowedCallerCodeExecution20250825 WebFetchTool20260309AllowedCaller = "code_execution_20250825"` - `const WebFetchTool20260309AllowedCallerCodeExecution20260120 WebFetchTool20260309AllowedCaller = "code_execution_20260120"` - `const WebFetchTool20260309AllowedCallerCodeExecution20260521 WebFetchTool20260309AllowedCaller = "code_execution_20260521"` - `AllowedDomains []string Optional` List of domains to allow fetching from - `BlockedDomains []string Optional` List of domains to block fetching from - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Citations CitationsConfigParam Optional` Citations configuration for fetched documents. Citations are disabled by default. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `MaxContentTokens int64 Optional` 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 - `MaxUses int64 Optional` Maximum number of times the tool can be used in the API request. minimum: 1 - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `URLSources WebFetchURLSourcesParam Optional` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `UseCache bool Optional` 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. - `type WebSearchTool20260318Param` - `Type WebSearch20260318` - `Name WebSearch` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const WebSearchTool20260318AllowedCallerDirect WebSearchTool20260318AllowedCaller = "direct"` - `const WebSearchTool20260318AllowedCallerCodeExecution20250825 WebSearchTool20260318AllowedCaller = "code_execution_20250825"` - `const WebSearchTool20260318AllowedCallerCodeExecution20260120 WebSearchTool20260318AllowedCaller = "code_execution_20260120"` - `const WebSearchTool20260318AllowedCallerCodeExecution20260521 WebSearchTool20260318AllowedCaller = "code_execution_20260521"` - `AllowedDomains []string Optional` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `BlockedDomains []string Optional` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `MaxUses int64 Optional` Maximum number of times the tool can be used in the API request. minimum: 1 - `ResponseInclusion WebSearchTool20260318ResponseInclusion Optional` 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. - `const WebSearchTool20260318ResponseInclusionFull WebSearchTool20260318ResponseInclusion = "full"` - `const WebSearchTool20260318ResponseInclusionExcluded WebSearchTool20260318ResponseInclusion = "excluded"` - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `UserLocation UserLocationParam Optional` Parameters for the user's location. Used to provide more relevant search results. - `type WebFetchTool20260318Param` - `Type WebFetch20260318` - `Name WebFetch` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const WebFetchTool20260318AllowedCallerDirect WebFetchTool20260318AllowedCaller = "direct"` - `const WebFetchTool20260318AllowedCallerCodeExecution20250825 WebFetchTool20260318AllowedCaller = "code_execution_20250825"` - `const WebFetchTool20260318AllowedCallerCodeExecution20260120 WebFetchTool20260318AllowedCaller = "code_execution_20260120"` - `const WebFetchTool20260318AllowedCallerCodeExecution20260521 WebFetchTool20260318AllowedCaller = "code_execution_20260521"` - `AllowedDomains []string Optional` List of domains to allow fetching from - `BlockedDomains []string Optional` List of domains to block fetching from - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `Citations CitationsConfigParam Optional` Citations configuration for fetched documents. Citations are disabled by default. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `MaxContentTokens int64 Optional` 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 - `MaxUses int64 Optional` Maximum number of times the tool can be used in the API request. minimum: 1 - `ResponseInclusion WebFetchTool20260318ResponseInclusion Optional` 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. - `const WebFetchTool20260318ResponseInclusionFull WebFetchTool20260318ResponseInclusion = "full"` - `const WebFetchTool20260318ResponseInclusionExcluded WebFetchTool20260318ResponseInclusion = "excluded"` - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `URLSources WebFetchURLSourcesParam Optional` Which sources contribute to the set of URLs the tool may fetch. Omitted means every source. - `UseCache bool Optional` 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. - `type ToolSearchToolBm25_20251119Param` - `Type ToolSearchToolBm25_20251119Type` - `const ToolSearchToolBm25_20251119TypeToolSearchToolBm25_20251119 ToolSearchToolBm25_20251119Type = "tool_search_tool_bm25_20251119"` - `const ToolSearchToolBm25_20251119TypeToolSearchToolBm25 ToolSearchToolBm25_20251119Type = "tool_search_tool_bm25"` - `Name ToolSearchToolBm25` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const ToolSearchToolBm25_20251119AllowedCallerDirect ToolSearchToolBm25_20251119AllowedCaller = "direct"` - `const ToolSearchToolBm25_20251119AllowedCallerCodeExecution20250825 ToolSearchToolBm25_20251119AllowedCaller = "code_execution_20250825"` - `const ToolSearchToolBm25_20251119AllowedCallerCodeExecution20260120 ToolSearchToolBm25_20251119AllowedCaller = "code_execution_20260120"` - `const ToolSearchToolBm25_20251119AllowedCallerCodeExecution20260521 ToolSearchToolBm25_20251119AllowedCaller = "code_execution_20260521"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `type ToolSearchToolRegex20251119Param` - `Type ToolSearchToolRegex20251119Type` - `const ToolSearchToolRegex20251119TypeToolSearchToolRegex20251119 ToolSearchToolRegex20251119Type = "tool_search_tool_regex_20251119"` - `const ToolSearchToolRegex20251119TypeToolSearchToolRegex ToolSearchToolRegex20251119Type = "tool_search_tool_regex"` - `Name ToolSearchToolRegex` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `AllowedCallers []string Optional` - `const ToolSearchToolRegex20251119AllowedCallerDirect ToolSearchToolRegex20251119AllowedCaller = "direct"` - `const ToolSearchToolRegex20251119AllowedCallerCodeExecution20250825 ToolSearchToolRegex20251119AllowedCaller = "code_execution_20250825"` - `const ToolSearchToolRegex20251119AllowedCallerCodeExecution20260120 ToolSearchToolRegex20251119AllowedCaller = "code_execution_20260120"` - `const ToolSearchToolRegex20251119AllowedCallerCodeExecution20260521 ToolSearchToolRegex20251119AllowedCaller = "code_execution_20260521"` - `CacheControl CacheControlEphemeralParam Optional` Create a cache control breakpoint at this content block. - `DeferLoading bool Optional` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Strict bool Optional` When true, guarantees schema validation on tool names and inputs - `Temperature float64 Optional` **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 - `TopK int64 Optional` **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 - `TopP float64 Optional` **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 - `UserProfileID param.Opt[string] Optional` (header parameter) The user profile ID to attribute the requests in this batch to. Use when acting on behalf of a party other than your organization. Requires the `user-profiles` beta header. Applies to every request in the batch; an individual request whose `user_profile_id` body field conflicts with this header is errored. - `WorkspaceID param.Opt[string] Optional` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. ### Returns - `type MessageBatch` - `Type MessageBatch` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `ID string` Unique object identifier. The format and length of IDs may change over time. - `ArchivedAt Time` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `CancelInitiatedAt Time` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `CreatedAt Time` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `EndedAt Time` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `ExpiresAt Time` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `ProcessingStatus MessageBatchProcessingStatus` Processing status of the Message Batch. - `const MessageBatchProcessingStatusInProgress MessageBatchProcessingStatus = "in_progress"` - `const MessageBatchProcessingStatusCanceling MessageBatchProcessingStatus = "canceling"` - `const MessageBatchProcessingStatusEnded MessageBatchProcessingStatus = "ended"` - `RequestCounts MessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `Canceled int64` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `Errored int64` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `Expired int64` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `Processing int64` Number of requests in the Message Batch that are processing. default: 0 - `Succeeded int64` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `ResultsURL string` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. ### Example ```go package main import ( "context" "fmt" "github.com/anthropics/anthropic-sdk-go" "github.com/anthropics/anthropic-sdk-go/option" ) func main() { client := anthropic.NewClient( option.WithAPIKey("my-anthropic-api-key"), ) messageBatch, err := client.Messages.Batches.New(context.TODO(), anthropic.MessageBatchNewParams{ Requests: []anthropic.MessageBatchNewParamsRequest{anthropic.MessageBatchNewParamsRequest{ CustomID: "my-custom-id-1", Params: anthropic.MessageBatchNewParamsRequestParams{ MaxTokens: 1024, Messages: []anthropic.MessageParam{anthropic.MessageParam{ Content: []anthropic.ContentBlockParamUnion{anthropic.ContentBlockParamUnion{ OfText: &anthropic.TextBlockParam{ Text: "x", }, }}, Role: anthropic.MessageParamRoleUser, }}, Model: anthropic.ModelClaudeOpus5_5, }, }}, }) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", messageBatch.ID) } ``` #### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ``` ## Retrieve a Message Batch `client.Messages.Batches.Get(ctx, messageBatchID, query) (*MessageBatch, error)` **GET** `/v1/messages/batches/{message_batch_id}` This endpoint is idempotent and can be used to poll for Message Batch completion. To access the results of a Message Batch, make a request to the `results_url` field in the response. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=go) ### Parameters - `messageBatchID string` (path parameter) ID of the Message Batch. - `query MessageBatchGetParams` - `WorkspaceID param.Opt[string] Optional` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. ### Returns - `type MessageBatch` - `Type MessageBatch` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `ID string` Unique object identifier. The format and length of IDs may change over time. - `ArchivedAt Time` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `CancelInitiatedAt Time` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `CreatedAt Time` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `EndedAt Time` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `ExpiresAt Time` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `ProcessingStatus MessageBatchProcessingStatus` Processing status of the Message Batch. - `const MessageBatchProcessingStatusInProgress MessageBatchProcessingStatus = "in_progress"` - `const MessageBatchProcessingStatusCanceling MessageBatchProcessingStatus = "canceling"` - `const MessageBatchProcessingStatusEnded MessageBatchProcessingStatus = "ended"` - `RequestCounts MessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `Canceled int64` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `Errored int64` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `Expired int64` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `Processing int64` Number of requests in the Message Batch that are processing. default: 0 - `Succeeded int64` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `ResultsURL string` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. ### Example ```go package main import ( "context" "fmt" "github.com/anthropics/anthropic-sdk-go" "github.com/anthropics/anthropic-sdk-go/option" ) func main() { client := anthropic.NewClient( option.WithAPIKey("my-anthropic-api-key"), ) messageBatch, err := client.Messages.Batches.Get( context.TODO(), "message_batch_id", anthropic.MessageBatchGetParams{}, ) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", messageBatch.ID) } ``` #### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ``` ## List Message Batches `client.Messages.Batches.List(ctx, params) (*Page[MessageBatch], error)` **GET** `/v1/messages/batches` List all Message Batches within a Workspace. Most recently created batches are returned first. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=go) ### Parameters - `params MessageBatchListParams` - `AfterID param.Opt[string] Optional` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately after this object. - `BeforeID param.Opt[string] Optional` (query parameter) ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately before this object. - `Limit param.Opt[int64] Optional` (query parameter) Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. minimum: 1, maximum: 1000 - `WorkspaceID param.Opt[string] Optional` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. ### Returns - `type MessageBatch` - `Type MessageBatch` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `ID string` Unique object identifier. The format and length of IDs may change over time. - `ArchivedAt Time` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `CancelInitiatedAt Time` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `CreatedAt Time` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `EndedAt Time` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `ExpiresAt Time` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `ProcessingStatus MessageBatchProcessingStatus` Processing status of the Message Batch. - `const MessageBatchProcessingStatusInProgress MessageBatchProcessingStatus = "in_progress"` - `const MessageBatchProcessingStatusCanceling MessageBatchProcessingStatus = "canceling"` - `const MessageBatchProcessingStatusEnded MessageBatchProcessingStatus = "ended"` - `RequestCounts MessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `Canceled int64` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `Errored int64` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `Expired int64` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `Processing int64` Number of requests in the Message Batch that are processing. default: 0 - `Succeeded int64` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `ResultsURL string` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. ### Example ```go package main import ( "context" "fmt" "github.com/anthropics/anthropic-sdk-go" "github.com/anthropics/anthropic-sdk-go/option" ) func main() { client := anthropic.NewClient( option.WithAPIKey("my-anthropic-api-key"), ) page, err := client.Messages.Batches.List(context.TODO(), anthropic.MessageBatchListParams{}) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", page) } ``` #### Response (200) ```json { "data": [ { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ], "first_id": "first_id", "has_more": true, "last_id": "last_id" } ``` ## Cancel a Message Batch `client.Messages.Batches.Cancel(ctx, messageBatchID, body) (*MessageBatch, error)` **POST** `/v1/messages/batches/{message_batch_id}/cancel` Batches may be canceled any time before processing ends. Once cancellation is initiated, the batch enters a `canceling` state, at which time the system may complete any in-progress, non-interruptible requests before finalizing cancellation. The number of canceled requests is specified in `request_counts`. To determine which requests were canceled, check the individual results within the batch. Note that cancellation may not result in any canceled requests if they were non-interruptible. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=go) ### Parameters - `messageBatchID string` (path parameter) ID of the Message Batch. - `body MessageBatchCancelParams` - `WorkspaceID param.Opt[string] Optional` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. ### Returns - `type MessageBatch` - `Type MessageBatch` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `ID string` Unique object identifier. The format and length of IDs may change over time. - `ArchivedAt Time` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `CancelInitiatedAt Time` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `CreatedAt Time` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `EndedAt Time` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `ExpiresAt Time` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `ProcessingStatus MessageBatchProcessingStatus` Processing status of the Message Batch. - `const MessageBatchProcessingStatusInProgress MessageBatchProcessingStatus = "in_progress"` - `const MessageBatchProcessingStatusCanceling MessageBatchProcessingStatus = "canceling"` - `const MessageBatchProcessingStatusEnded MessageBatchProcessingStatus = "ended"` - `RequestCounts MessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `Canceled int64` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `Errored int64` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `Expired int64` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `Processing int64` Number of requests in the Message Batch that are processing. default: 0 - `Succeeded int64` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `ResultsURL string` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. ### Example ```go package main import ( "context" "fmt" "github.com/anthropics/anthropic-sdk-go" "github.com/anthropics/anthropic-sdk-go/option" ) func main() { client := anthropic.NewClient( option.WithAPIKey("my-anthropic-api-key"), ) messageBatch, err := client.Messages.Batches.Cancel( context.TODO(), "message_batch_id", anthropic.MessageBatchCancelParams{}, ) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", messageBatch.ID) } ``` #### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ``` ## Delete a Message Batch `client.Messages.Batches.Delete(ctx, messageBatchID, body) (*DeletedMessageBatch, error)` **DELETE** `/v1/messages/batches/{message_batch_id}` Delete a Message Batch. Message Batches can only be deleted once they've finished processing. If you'd like to delete an in-progress batch, you must first cancel it. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=go) ### Parameters - `messageBatchID string` (path parameter) ID of the Message Batch. - `body MessageBatchDeleteParams` - `WorkspaceID param.Opt[string] Optional` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. ### Returns - `type DeletedMessageBatch` - `Type MessageBatchDeleted` Deleted object type. For Message Batches, this is always `"message_batch_deleted"`. default: message_batch_deleted - `ID string` ID of the Message Batch. ### Example ```go package main import ( "context" "fmt" "github.com/anthropics/anthropic-sdk-go" "github.com/anthropics/anthropic-sdk-go/option" ) func main() { client := anthropic.NewClient( option.WithAPIKey("my-anthropic-api-key"), ) deletedMessageBatch, err := client.Messages.Batches.Delete( context.TODO(), "message_batch_id", anthropic.MessageBatchDeleteParams{}, ) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", deletedMessageBatch.ID) } ``` #### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "type": "message_batch_deleted" } ``` ## Retrieve Message Batch results `client.Messages.Batches.ResultsStreaming(ctx, messageBatchID, query) *jsonl.Stream[MessageBatchIndividualResponse]` **GET** `/v1/messages/batches/{message_batch_id}/results` Streams the results of a Message Batch as a `.jsonl` file. Each line in the file is a JSON object containing the result of a single request in the Message Batch. Results are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing?sdk_languages=go) ### Parameters - `messageBatchID string` (path parameter) ID of the Message Batch. - `query MessageBatchResultsParams` - `WorkspaceID param.Opt[string] Optional` (header parameter) Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace. ### Returns - `type MessageBatchIndividualResponse` This is a single line in the response `.jsonl` file and does not represent the response as a whole. - `CustomID string` Developer-provided ID created for each request in a Message Batch. Useful for matching results to requests, as results may be given out of request order. Must be unique for each request within the Message Batch. - `Result MessageBatchResultUnion` Processing result for this request. Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration. - `type MessageBatchSucceededResult` - `Type Succeeded` default: succeeded - `Message 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` 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 - `ExpiresAt Time` The time at which the container will expire. format: date-time - `Skills []ContainerSkill` Skills loaded in the container - `Type ContainerSkillType` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `const ContainerSkillTypeAnthropic ContainerSkillType = "anthropic"` - `const ContainerSkillTypeCustom ContainerSkillType = "custom"` - `SkillID string` Skill ID minLength: 1, maxLength: 64 - `Version string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `Content []ContentBlockUnion` 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)"}] ``` - `type TextBlock` - `Type Text` default: text - `Citations []TextCitationUnion` 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`. - `type CitationCharLocation` - `Type CharLocation` default: char_location - `CitedText string` - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` - `EndCharIndex int64` - `FileID string` - `StartCharIndex int64` minimum: 0 - `type CitationPageLocation` - `Type PageLocation` default: page_location - `CitedText string` - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` - `EndPageNumber int64` - `FileID string` - `StartPageNumber int64` minimum: 1 - `type CitationContentBlockLocation` - `Type ContentBlockLocation` default: content_block_location - `CitedText 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. - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` - `EndBlockIndex int64` 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`. - `FileID string` - `StartBlockIndex int64` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `type CitationsWebSearchResultLocation` - `Type WebSearchResultLocation` default: web_search_result_location - `CitedText string` - `EncryptedIndex string` - `Title string` maxLength: 512 - `URL string` - `type CitationsSearchResultLocation` - `Type SearchResultLocation` default: search_result_location - `CitedText 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. - `EndBlockIndex int64` 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`. - `SearchResultIndex int64` 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` - `StartBlockIndex int64` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `Title string` - `Text string` - `type 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=go) for details. - `Thinking string` The text of Claude's thinking process for this block. - `type RedactedThinkingBlock` - `Type RedactedThinking` 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=go#redacted-thinking-blocks) for details. - `type ToolUseBlock` - `Type ToolUse` default: tool_use - `ID string` pattern: ^[a-zA-Z0-9_-]+$ - `Caller ToolUseBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `Type Direct` - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `Type CodeExecution20250825` - `ToolID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ServerToolCaller20260120` - `Type CodeExecution20260120` - `ToolID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `Input map[string, any]` - `Name string` minLength: 1 - `ToolsetName string Optional` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `type ServerToolUseBlock` - `Type ServerToolUse` default: server_tool_use - `ID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `Caller ServerToolUseBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `Input map[string, any]` - `Name ServerToolUseBlockName` - `const ServerToolUseBlockNameWebSearch ServerToolUseBlockName = "web_search"` - `const ServerToolUseBlockNameWebFetch ServerToolUseBlockName = "web_fetch"` - `const ServerToolUseBlockNameCodeExecution ServerToolUseBlockName = "code_execution"` - `const ServerToolUseBlockNameBashCodeExecution ServerToolUseBlockName = "bash_code_execution"` - `const ServerToolUseBlockNameTextEditorCodeExecution ServerToolUseBlockName = "text_editor_code_execution"` - `const ServerToolUseBlockNameToolSearchToolRegex ServerToolUseBlockName = "tool_search_tool_regex"` - `const ServerToolUseBlockNameToolSearchToolBm25 ServerToolUseBlockName = "tool_search_tool_bm25"` - `type WebSearchToolResultBlock` - `Type WebSearchToolResult` default: web_search_tool_result - `Caller WebSearchToolResultBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `Content WebSearchToolResultBlockContentUnion` - `type WebSearchToolResultError` - `Type WebSearchToolResultError` default: web_search_tool_result_error - `ErrorCode WebSearchToolResultErrorCode` - `const WebSearchToolResultErrorCodeInvalidToolInput WebSearchToolResultErrorCode = "invalid_tool_input"` - `const WebSearchToolResultErrorCodeUnavailable WebSearchToolResultErrorCode = "unavailable"` - `const WebSearchToolResultErrorCodeMaxUsesExceeded WebSearchToolResultErrorCode = "max_uses_exceeded"` - `const WebSearchToolResultErrorCodeTooManyRequests WebSearchToolResultErrorCode = "too_many_requests"` - `const WebSearchToolResultErrorCodeQueryTooLong WebSearchToolResultErrorCode = "query_too_long"` - `const WebSearchToolResultErrorCodeRequestTooLarge WebSearchToolResultErrorCode = "request_too_large"` - `[]WebSearchResultBlock` - `Type WebSearchResult` default: web_search_result - `EncryptedContent string` - `PageAge string` - `Title string` - `URL string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type WebFetchToolResultBlock` - `Type WebFetchToolResult` default: web_fetch_tool_result - `Caller WebFetchToolResultBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `Content WebFetchToolResultBlockContentUnion` - `type WebFetchToolResultErrorBlock` - `Type WebFetchToolResultError` default: web_fetch_tool_result_error - `ErrorCode WebFetchToolResultErrorCode` - `const WebFetchToolResultErrorCodeInvalidToolInput WebFetchToolResultErrorCode = "invalid_tool_input"` - `const WebFetchToolResultErrorCodeURLTooLong WebFetchToolResultErrorCode = "url_too_long"` - `const WebFetchToolResultErrorCodeURLNotAllowed WebFetchToolResultErrorCode = "url_not_allowed"` - `const WebFetchToolResultErrorCodeURLNotInPriorContext WebFetchToolResultErrorCode = "url_not_in_prior_context"` - `const WebFetchToolResultErrorCodeURLNotAccessible WebFetchToolResultErrorCode = "url_not_accessible"` - `const WebFetchToolResultErrorCodeUnsupportedContentType WebFetchToolResultErrorCode = "unsupported_content_type"` - `const WebFetchToolResultErrorCodeTooManyRequests WebFetchToolResultErrorCode = "too_many_requests"` - `const WebFetchToolResultErrorCodeMaxUsesExceeded WebFetchToolResultErrorCode = "max_uses_exceeded"` - `const WebFetchToolResultErrorCodeUnavailable WebFetchToolResultErrorCode = "unavailable"` - `const WebFetchToolResultErrorCodeContentTooLarge WebFetchToolResultErrorCode = "content_too_large"` - `type WebFetchBlock` - `Type WebFetchResult` default: web_fetch_result - `Content DocumentBlock` - `Type Document` default: document - `Citations CitationsConfig` Citation configuration for the document - `Enabled bool` default: false - `Source DocumentBlockSourceUnion` - `type Base64PDFSource` - `Type Base64` - `Data string` format: byte - `MediaType ApplicationPDF` - `type PlainTextSource` - `Type Text` - `Data string` - `MediaType TextPlain` - `Title string` The title of the document - `RetrievedAt string` ISO 8601 timestamp when the content was retrieved - `URL string` Fetched content URL - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type CodeExecutionToolResultBlock` - `Type CodeExecutionToolResult` default: code_execution_tool_result - `Content CodeExecutionToolResultBlockContentUnion` - `type CodeExecutionToolResultError` - `Type CodeExecutionToolResultError` default: code_execution_tool_result_error - `ErrorCode CodeExecutionToolResultErrorCode` - `const CodeExecutionToolResultErrorCodeInvalidToolInput CodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const CodeExecutionToolResultErrorCodeUnavailable CodeExecutionToolResultErrorCode = "unavailable"` - `const CodeExecutionToolResultErrorCodeTooManyRequests CodeExecutionToolResultErrorCode = "too_many_requests"` - `const CodeExecutionToolResultErrorCodeExecutionTimeExceeded CodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `type CodeExecutionResultBlock` - `Type CodeExecutionResult` default: code_execution_result - `Content []CodeExecutionOutputBlock` - `Type CodeExecutionOutput` default: code_execution_output - `FileID string` - `ReturnCode int64` - `Stderr string` - `Stdout string` - `type EncryptedCodeExecutionResultBlock` Code execution result with encrypted stdout for PFC + web_search results. - `Type EncryptedCodeExecutionResult` default: encrypted_code_execution_result - `Content []CodeExecutionOutputBlock` - `Type CodeExecutionOutput` default: code_execution_output - `FileID string` - `EncryptedStdout string` - `ReturnCode int64` - `Stderr string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type BashCodeExecutionToolResultBlock` - `Type BashCodeExecutionToolResult` default: bash_code_execution_tool_result - `Content BashCodeExecutionToolResultBlockContentUnion` - `type BashCodeExecutionToolResultError` - `Type BashCodeExecutionToolResultError` default: bash_code_execution_tool_result_error - `ErrorCode BashCodeExecutionToolResultErrorCode` - `const BashCodeExecutionToolResultErrorCodeInvalidToolInput BashCodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const BashCodeExecutionToolResultErrorCodeUnavailable BashCodeExecutionToolResultErrorCode = "unavailable"` - `const BashCodeExecutionToolResultErrorCodeTooManyRequests BashCodeExecutionToolResultErrorCode = "too_many_requests"` - `const BashCodeExecutionToolResultErrorCodeExecutionTimeExceeded BashCodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `const BashCodeExecutionToolResultErrorCodeOutputFileTooLarge BashCodeExecutionToolResultErrorCode = "output_file_too_large"` - `type BashCodeExecutionResultBlock` - `Type BashCodeExecutionResult` default: bash_code_execution_result - `Content []BashCodeExecutionOutputBlock` - `Type BashCodeExecutionOutput` default: bash_code_execution_output - `FileID string` - `ReturnCode int64` - `Stderr string` - `Stdout string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type TextEditorCodeExecutionToolResultBlock` - `Type TextEditorCodeExecutionToolResult` default: text_editor_code_execution_tool_result - `Content TextEditorCodeExecutionToolResultBlockContentUnion` - `type TextEditorCodeExecutionToolResultError` - `Type TextEditorCodeExecutionToolResultError` default: text_editor_code_execution_tool_result_error - `ErrorCode TextEditorCodeExecutionToolResultErrorCode` - `const TextEditorCodeExecutionToolResultErrorCodeInvalidToolInput TextEditorCodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const TextEditorCodeExecutionToolResultErrorCodeUnavailable TextEditorCodeExecutionToolResultErrorCode = "unavailable"` - `const TextEditorCodeExecutionToolResultErrorCodeTooManyRequests TextEditorCodeExecutionToolResultErrorCode = "too_many_requests"` - `const TextEditorCodeExecutionToolResultErrorCodeExecutionTimeExceeded TextEditorCodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `const TextEditorCodeExecutionToolResultErrorCodeFileNotFound TextEditorCodeExecutionToolResultErrorCode = "file_not_found"` - `ErrorMessage string` - `type TextEditorCodeExecutionViewResultBlock` - `Type TextEditorCodeExecutionViewResult` default: text_editor_code_execution_view_result - `Content string` - `FileType TextEditorCodeExecutionViewResultBlockFileType` - `const TextEditorCodeExecutionViewResultBlockFileTypeText TextEditorCodeExecutionViewResultBlockFileType = "text"` - `const TextEditorCodeExecutionViewResultBlockFileTypeImage TextEditorCodeExecutionViewResultBlockFileType = "image"` - `const TextEditorCodeExecutionViewResultBlockFileTypePDF TextEditorCodeExecutionViewResultBlockFileType = "pdf"` - `NumLines int64` - `StartLine int64` - `TotalLines int64` - `type TextEditorCodeExecutionCreateResultBlock` - `Type TextEditorCodeExecutionCreateResult` default: text_editor_code_execution_create_result - `IsFileUpdate bool` - `type TextEditorCodeExecutionStrReplaceResultBlock` - `Type TextEditorCodeExecutionStrReplaceResult` default: text_editor_code_execution_str_replace_result - `Lines []string` - `NewLines int64` - `NewStart int64` - `OldLines int64` - `OldStart int64` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ToolSearchToolResultBlock` - `Type ToolSearchToolResult` default: tool_search_tool_result - `Content ToolSearchToolResultBlockContentUnion` - `type ToolSearchToolResultError` - `Type ToolSearchToolResultError` default: tool_search_tool_result_error - `ErrorCode ToolSearchToolResultErrorCode` - `const ToolSearchToolResultErrorCodeInvalidToolInput ToolSearchToolResultErrorCode = "invalid_tool_input"` - `const ToolSearchToolResultErrorCodeUnavailable ToolSearchToolResultErrorCode = "unavailable"` - `const ToolSearchToolResultErrorCodeTooManyRequests ToolSearchToolResultErrorCode = "too_many_requests"` - `const ToolSearchToolResultErrorCodeExecutionTimeExceeded ToolSearchToolResultErrorCode = "execution_time_exceeded"` - `ErrorMessage string` - `type ToolSearchToolSearchResultBlock` - `Type ToolSearchToolSearchResult` default: tool_search_tool_search_result - `ToolReferences []ToolReferenceBlock` - `Type ToolReference` default: tool_reference - `ToolName string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ContainerUploadBlock` Response model for a file uploaded to the container. - `Type ContainerUpload` default: container_upload - `FileID string` - `Diagnostics Diagnostics` Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected. - `CacheMissReason CacheMissReasonUnion` 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. - `type CacheMissModelChanged` - `Type ModelChanged` default: model_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissSystemChanged` - `Type SystemChanged` default: system_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissToolsChanged` - `Type ToolsChanged` default: tools_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissMessagesChanged` - `Type MessagesChanged` default: messages_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissPreviousMessageNotFound` - `Type PreviousMessageNotFound` default: previous_message_not_found - `type 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. - `const ModelClaudeHaiku5_5 Model = "claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `const ModelClaudeSonnet5_5 Model = "claude-sonnet-5-5"` Efficient model for coding and agents - `const ModelClaudeFable5_1 Model = "claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `const ModelClaudeOpus5_5 Model = "claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `const ModelClaudeMythos5_1 Model = "claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `const ModelClaudeSonnet5 Model = "claude-sonnet-5"` Efficient model for coding and agents - `const ModelClaudeFable5 Model = "claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `const ModelClaudeMythos5 Model = "claude-mythos-5"` Most capable model for cybersecurity and biology research - `const ModelClaudeOpus5 Model = "claude-opus-5"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_8 Model = "claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_7 Model = "claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_6 Model = "claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `const ModelClaudeSonnet4_6 Model = "claude-sonnet-4-6"` Best combination of speed and intelligence - `const ModelClaudeHaiku4_5 Model = "claude-haiku-4-5"` - `const ModelClaudeHaiku4_5_20251001 Model = "claude-haiku-4-5-20251001"` - `const ModelClaudeOpus4_5 Model = "claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_5_20251101 Model = "claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `const ModelClaudeMythosPreview Model = "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 - `const ModelClaudeSonnet4_5 Model = "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 - `const ModelClaudeSonnet4_5_20250929 Model = "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 - `Role Assistant` Conversational role of the generated message. This will always be `"assistant"`. default: assistant - `StopDetails RefusalStopDetails` 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 RefusalStopDetailsCategory` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `const RefusalStopDetailsCategoryCyber RefusalStopDetailsCategory = "cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `const RefusalStopDetailsCategoryBio RefusalStopDetailsCategory = "bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `const RefusalStopDetailsCategoryFrontierLLM RefusalStopDetailsCategory = "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. - `const RefusalStopDetailsCategoryReasoningExtraction RefusalStopDetailsCategory = "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=go). - `const RefusalStopDetailsCategoryGeneralHarms RefusalStopDetailsCategory = "general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `Explanation string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `StopReason StopReason` 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. - `const StopReasonEndTurn StopReason = "end_turn"` - `const StopReasonMaxTokens StopReason = "max_tokens"` - `const StopReasonStopSequence StopReason = "stop_sequence"` - `const StopReasonToolUse StopReason = "tool_use"` - `const StopReasonPauseTurn StopReason = "pause_turn"` - `const StopReasonRefusal StopReason = "refusal"` - `const StopReasonModelContextWindowExceeded StopReason = "model_context_window_exceeded"` - `StopSequence string` 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`. - `CacheCreation CacheCreation` Breakdown of cached tokens by TTL - `Ephemeral1hInputTokens int64` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `Ephemeral5mInputTokens int64` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `CacheCreationInputTokens int64` The number of input tokens used to create the cache entry. minimum: 0 - `CacheReadInputTokens int64` The number of input tokens read from the cache. minimum: 0 - `InferenceGeo string` The geographic region where inference was performed for this request. - `InputTokens int64` The number of input tokens which were used. minimum: 0 - `OutputTokens int64` The number of output tokens which were used. minimum: 0 - `OutputTokensDetails OutputTokensDetails` 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. - `ThinkingTokens int64` 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 - `ServerToolUse ServerToolUsage` The number of server tool requests. - `WebFetchRequests int64` The number of web fetch tool requests. default: 0, minimum: 0 - `WebSearchRequests int64` The number of web search tool requests. default: 0, minimum: 0 - `ServiceTier UsageServiceTier` If the request used the priority, standard, or batch tier. - `const UsageServiceTierStandard UsageServiceTier = "standard"` - `const UsageServiceTierPriority UsageServiceTier = "priority"` - `const UsageServiceTierBatch UsageServiceTier = "batch"` - `Speed UsageSpeed` The inference speed mode used for this request. - `const UsageSpeedStandard UsageSpeed = "standard"` - `const UsageSpeedFast UsageSpeed = "fast"` - `type MessageBatchErroredResult` - `Type Errored` default: errored - `Error ErrorResponse` - `Type Error` default: error - `Error ErrorObjectUnion` - `type InvalidRequestError` - `Type InvalidRequestError` default: invalid_request_error - `Message string` default: Invalid request - `type AuthenticationError` - `Type AuthenticationError` default: authentication_error - `Message string` default: Authentication error - `type BillingError` - `Type BillingError` default: billing_error - `Message string` default: Billing error - `type PermissionError` - `Type PermissionError` default: permission_error - `Message string` default: Permission denied - `type NotFoundError` - `Type NotFoundError` default: not_found_error - `Message string` default: Not found - `type RateLimitError` - `Type RateLimitError` default: rate_limit_error - `Message string` default: Rate limited - `type GatewayTimeoutError` - `Type TimeoutError` default: timeout_error - `Message string` default: Request timeout - `type APIErrorObject` - `Type APIError` default: api_error - `Message string` default: Internal server error - `type OverloadedError` - `Type OverloadedError` default: overloaded_error - `Message string` default: Overloaded - `RequestID string` - `type MessageBatchCanceledResult` - `Type Canceled` default: canceled - `type MessageBatchExpiredResult` - `Type Expired` default: expired ### Example ```go package main import ( "context" "fmt" "github.com/anthropics/anthropic-sdk-go" "github.com/anthropics/anthropic-sdk-go/option" ) func main() { client := anthropic.NewClient( option.WithAPIKey("my-anthropic-api-key"), ) stream := client.Messages.Batches.ResultsStreaming( context.TODO(), "message_batch_id", anthropic.MessageBatchResultsParams{}, ) for stream.Next() { fmt.Printf("%+v\n", stream.Current()) } err := stream.Err() if err != nil { panic(err.Error()) } } ``` ## Domain types ### Deleted Message Batch - `type DeletedMessageBatch` - `Type MessageBatchDeleted` Deleted object type. For Message Batches, this is always `"message_batch_deleted"`. default: message_batch_deleted - `ID string` ID of the Message Batch. ### Message Batch - `type MessageBatch` - `Type MessageBatch` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `ID string` Unique object identifier. The format and length of IDs may change over time. - `ArchivedAt Time` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `CancelInitiatedAt Time` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `CreatedAt Time` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `EndedAt Time` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `ExpiresAt Time` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `ProcessingStatus MessageBatchProcessingStatus` Processing status of the Message Batch. - `const MessageBatchProcessingStatusInProgress MessageBatchProcessingStatus = "in_progress"` - `const MessageBatchProcessingStatusCanceling MessageBatchProcessingStatus = "canceling"` - `const MessageBatchProcessingStatusEnded MessageBatchProcessingStatus = "ended"` - `RequestCounts MessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `Canceled int64` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `Errored int64` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `Expired int64` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `Processing int64` Number of requests in the Message Batch that are processing. default: 0 - `Succeeded int64` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `ResultsURL string` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. ### Message Batch Canceled Result - `type MessageBatchCanceledResult` - `Type Canceled` default: canceled ### Message Batch Errored Result - `type MessageBatchErroredResult` - `Type Errored` default: errored - `Error ErrorResponse` - `Type Error` default: error - `Error ErrorObjectUnion` - `type InvalidRequestError` - `Type InvalidRequestError` default: invalid_request_error - `Message string` default: Invalid request - `type AuthenticationError` - `Type AuthenticationError` default: authentication_error - `Message string` default: Authentication error - `type BillingError` - `Type BillingError` default: billing_error - `Message string` default: Billing error - `type PermissionError` - `Type PermissionError` default: permission_error - `Message string` default: Permission denied - `type NotFoundError` - `Type NotFoundError` default: not_found_error - `Message string` default: Not found - `type RateLimitError` - `Type RateLimitError` default: rate_limit_error - `Message string` default: Rate limited - `type GatewayTimeoutError` - `Type TimeoutError` default: timeout_error - `Message string` default: Request timeout - `type APIErrorObject` - `Type APIError` default: api_error - `Message string` default: Internal server error - `type OverloadedError` - `Type OverloadedError` default: overloaded_error - `Message string` default: Overloaded - `RequestID string` ### Message Batch Expired Result - `type MessageBatchExpiredResult` - `Type Expired` default: expired ### Message Batch Individual Response - `type MessageBatchIndividualResponse` This is a single line in the response `.jsonl` file and does not represent the response as a whole. - `CustomID string` Developer-provided ID created for each request in a Message Batch. Useful for matching results to requests, as results may be given out of request order. Must be unique for each request within the Message Batch. - `Result MessageBatchResultUnion` Processing result for this request. Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration. - `type MessageBatchSucceededResult` - `Type Succeeded` default: succeeded - `Message 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` 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 - `ExpiresAt Time` The time at which the container will expire. format: date-time - `Skills []ContainerSkill` Skills loaded in the container - `Type ContainerSkillType` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `const ContainerSkillTypeAnthropic ContainerSkillType = "anthropic"` - `const ContainerSkillTypeCustom ContainerSkillType = "custom"` - `SkillID string` Skill ID minLength: 1, maxLength: 64 - `Version string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `Content []ContentBlockUnion` 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)"}] ``` - `type TextBlock` - `Type Text` default: text - `Citations []TextCitationUnion` 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`. - `type CitationCharLocation` - `Type CharLocation` default: char_location - `CitedText string` - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` - `EndCharIndex int64` - `FileID string` - `StartCharIndex int64` minimum: 0 - `type CitationPageLocation` - `Type PageLocation` default: page_location - `CitedText string` - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` - `EndPageNumber int64` - `FileID string` - `StartPageNumber int64` minimum: 1 - `type CitationContentBlockLocation` - `Type ContentBlockLocation` default: content_block_location - `CitedText 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. - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` - `EndBlockIndex int64` 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`. - `FileID string` - `StartBlockIndex int64` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `type CitationsWebSearchResultLocation` - `Type WebSearchResultLocation` default: web_search_result_location - `CitedText string` - `EncryptedIndex string` - `Title string` maxLength: 512 - `URL string` - `type CitationsSearchResultLocation` - `Type SearchResultLocation` default: search_result_location - `CitedText 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. - `EndBlockIndex int64` 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`. - `SearchResultIndex int64` 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` - `StartBlockIndex int64` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `Title string` - `Text string` - `type 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=go) for details. - `Thinking string` The text of Claude's thinking process for this block. - `type RedactedThinkingBlock` - `Type RedactedThinking` 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=go#redacted-thinking-blocks) for details. - `type ToolUseBlock` - `Type ToolUse` default: tool_use - `ID string` pattern: ^[a-zA-Z0-9_-]+$ - `Caller ToolUseBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `Type Direct` - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `Type CodeExecution20250825` - `ToolID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ServerToolCaller20260120` - `Type CodeExecution20260120` - `ToolID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `Input map[string, any]` - `Name string` minLength: 1 - `ToolsetName string Optional` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `type ServerToolUseBlock` - `Type ServerToolUse` default: server_tool_use - `ID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `Caller ServerToolUseBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `Input map[string, any]` - `Name ServerToolUseBlockName` - `const ServerToolUseBlockNameWebSearch ServerToolUseBlockName = "web_search"` - `const ServerToolUseBlockNameWebFetch ServerToolUseBlockName = "web_fetch"` - `const ServerToolUseBlockNameCodeExecution ServerToolUseBlockName = "code_execution"` - `const ServerToolUseBlockNameBashCodeExecution ServerToolUseBlockName = "bash_code_execution"` - `const ServerToolUseBlockNameTextEditorCodeExecution ServerToolUseBlockName = "text_editor_code_execution"` - `const ServerToolUseBlockNameToolSearchToolRegex ServerToolUseBlockName = "tool_search_tool_regex"` - `const ServerToolUseBlockNameToolSearchToolBm25 ServerToolUseBlockName = "tool_search_tool_bm25"` - `type WebSearchToolResultBlock` - `Type WebSearchToolResult` default: web_search_tool_result - `Caller WebSearchToolResultBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `Content WebSearchToolResultBlockContentUnion` - `type WebSearchToolResultError` - `Type WebSearchToolResultError` default: web_search_tool_result_error - `ErrorCode WebSearchToolResultErrorCode` - `const WebSearchToolResultErrorCodeInvalidToolInput WebSearchToolResultErrorCode = "invalid_tool_input"` - `const WebSearchToolResultErrorCodeUnavailable WebSearchToolResultErrorCode = "unavailable"` - `const WebSearchToolResultErrorCodeMaxUsesExceeded WebSearchToolResultErrorCode = "max_uses_exceeded"` - `const WebSearchToolResultErrorCodeTooManyRequests WebSearchToolResultErrorCode = "too_many_requests"` - `const WebSearchToolResultErrorCodeQueryTooLong WebSearchToolResultErrorCode = "query_too_long"` - `const WebSearchToolResultErrorCodeRequestTooLarge WebSearchToolResultErrorCode = "request_too_large"` - `[]WebSearchResultBlock` - `Type WebSearchResult` default: web_search_result - `EncryptedContent string` - `PageAge string` - `Title string` - `URL string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type WebFetchToolResultBlock` - `Type WebFetchToolResult` default: web_fetch_tool_result - `Caller WebFetchToolResultBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `Content WebFetchToolResultBlockContentUnion` - `type WebFetchToolResultErrorBlock` - `Type WebFetchToolResultError` default: web_fetch_tool_result_error - `ErrorCode WebFetchToolResultErrorCode` - `const WebFetchToolResultErrorCodeInvalidToolInput WebFetchToolResultErrorCode = "invalid_tool_input"` - `const WebFetchToolResultErrorCodeURLTooLong WebFetchToolResultErrorCode = "url_too_long"` - `const WebFetchToolResultErrorCodeURLNotAllowed WebFetchToolResultErrorCode = "url_not_allowed"` - `const WebFetchToolResultErrorCodeURLNotInPriorContext WebFetchToolResultErrorCode = "url_not_in_prior_context"` - `const WebFetchToolResultErrorCodeURLNotAccessible WebFetchToolResultErrorCode = "url_not_accessible"` - `const WebFetchToolResultErrorCodeUnsupportedContentType WebFetchToolResultErrorCode = "unsupported_content_type"` - `const WebFetchToolResultErrorCodeTooManyRequests WebFetchToolResultErrorCode = "too_many_requests"` - `const WebFetchToolResultErrorCodeMaxUsesExceeded WebFetchToolResultErrorCode = "max_uses_exceeded"` - `const WebFetchToolResultErrorCodeUnavailable WebFetchToolResultErrorCode = "unavailable"` - `const WebFetchToolResultErrorCodeContentTooLarge WebFetchToolResultErrorCode = "content_too_large"` - `type WebFetchBlock` - `Type WebFetchResult` default: web_fetch_result - `Content DocumentBlock` - `Type Document` default: document - `Citations CitationsConfig` Citation configuration for the document - `Enabled bool` default: false - `Source DocumentBlockSourceUnion` - `type Base64PDFSource` - `Type Base64` - `Data string` format: byte - `MediaType ApplicationPDF` - `type PlainTextSource` - `Type Text` - `Data string` - `MediaType TextPlain` - `Title string` The title of the document - `RetrievedAt string` ISO 8601 timestamp when the content was retrieved - `URL string` Fetched content URL - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type CodeExecutionToolResultBlock` - `Type CodeExecutionToolResult` default: code_execution_tool_result - `Content CodeExecutionToolResultBlockContentUnion` - `type CodeExecutionToolResultError` - `Type CodeExecutionToolResultError` default: code_execution_tool_result_error - `ErrorCode CodeExecutionToolResultErrorCode` - `const CodeExecutionToolResultErrorCodeInvalidToolInput CodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const CodeExecutionToolResultErrorCodeUnavailable CodeExecutionToolResultErrorCode = "unavailable"` - `const CodeExecutionToolResultErrorCodeTooManyRequests CodeExecutionToolResultErrorCode = "too_many_requests"` - `const CodeExecutionToolResultErrorCodeExecutionTimeExceeded CodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `type CodeExecutionResultBlock` - `Type CodeExecutionResult` default: code_execution_result - `Content []CodeExecutionOutputBlock` - `Type CodeExecutionOutput` default: code_execution_output - `FileID string` - `ReturnCode int64` - `Stderr string` - `Stdout string` - `type EncryptedCodeExecutionResultBlock` Code execution result with encrypted stdout for PFC + web_search results. - `Type EncryptedCodeExecutionResult` default: encrypted_code_execution_result - `Content []CodeExecutionOutputBlock` - `Type CodeExecutionOutput` default: code_execution_output - `FileID string` - `EncryptedStdout string` - `ReturnCode int64` - `Stderr string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type BashCodeExecutionToolResultBlock` - `Type BashCodeExecutionToolResult` default: bash_code_execution_tool_result - `Content BashCodeExecutionToolResultBlockContentUnion` - `type BashCodeExecutionToolResultError` - `Type BashCodeExecutionToolResultError` default: bash_code_execution_tool_result_error - `ErrorCode BashCodeExecutionToolResultErrorCode` - `const BashCodeExecutionToolResultErrorCodeInvalidToolInput BashCodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const BashCodeExecutionToolResultErrorCodeUnavailable BashCodeExecutionToolResultErrorCode = "unavailable"` - `const BashCodeExecutionToolResultErrorCodeTooManyRequests BashCodeExecutionToolResultErrorCode = "too_many_requests"` - `const BashCodeExecutionToolResultErrorCodeExecutionTimeExceeded BashCodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `const BashCodeExecutionToolResultErrorCodeOutputFileTooLarge BashCodeExecutionToolResultErrorCode = "output_file_too_large"` - `type BashCodeExecutionResultBlock` - `Type BashCodeExecutionResult` default: bash_code_execution_result - `Content []BashCodeExecutionOutputBlock` - `Type BashCodeExecutionOutput` default: bash_code_execution_output - `FileID string` - `ReturnCode int64` - `Stderr string` - `Stdout string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type TextEditorCodeExecutionToolResultBlock` - `Type TextEditorCodeExecutionToolResult` default: text_editor_code_execution_tool_result - `Content TextEditorCodeExecutionToolResultBlockContentUnion` - `type TextEditorCodeExecutionToolResultError` - `Type TextEditorCodeExecutionToolResultError` default: text_editor_code_execution_tool_result_error - `ErrorCode TextEditorCodeExecutionToolResultErrorCode` - `const TextEditorCodeExecutionToolResultErrorCodeInvalidToolInput TextEditorCodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const TextEditorCodeExecutionToolResultErrorCodeUnavailable TextEditorCodeExecutionToolResultErrorCode = "unavailable"` - `const TextEditorCodeExecutionToolResultErrorCodeTooManyRequests TextEditorCodeExecutionToolResultErrorCode = "too_many_requests"` - `const TextEditorCodeExecutionToolResultErrorCodeExecutionTimeExceeded TextEditorCodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `const TextEditorCodeExecutionToolResultErrorCodeFileNotFound TextEditorCodeExecutionToolResultErrorCode = "file_not_found"` - `ErrorMessage string` - `type TextEditorCodeExecutionViewResultBlock` - `Type TextEditorCodeExecutionViewResult` default: text_editor_code_execution_view_result - `Content string` - `FileType TextEditorCodeExecutionViewResultBlockFileType` - `const TextEditorCodeExecutionViewResultBlockFileTypeText TextEditorCodeExecutionViewResultBlockFileType = "text"` - `const TextEditorCodeExecutionViewResultBlockFileTypeImage TextEditorCodeExecutionViewResultBlockFileType = "image"` - `const TextEditorCodeExecutionViewResultBlockFileTypePDF TextEditorCodeExecutionViewResultBlockFileType = "pdf"` - `NumLines int64` - `StartLine int64` - `TotalLines int64` - `type TextEditorCodeExecutionCreateResultBlock` - `Type TextEditorCodeExecutionCreateResult` default: text_editor_code_execution_create_result - `IsFileUpdate bool` - `type TextEditorCodeExecutionStrReplaceResultBlock` - `Type TextEditorCodeExecutionStrReplaceResult` default: text_editor_code_execution_str_replace_result - `Lines []string` - `NewLines int64` - `NewStart int64` - `OldLines int64` - `OldStart int64` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ToolSearchToolResultBlock` - `Type ToolSearchToolResult` default: tool_search_tool_result - `Content ToolSearchToolResultBlockContentUnion` - `type ToolSearchToolResultError` - `Type ToolSearchToolResultError` default: tool_search_tool_result_error - `ErrorCode ToolSearchToolResultErrorCode` - `const ToolSearchToolResultErrorCodeInvalidToolInput ToolSearchToolResultErrorCode = "invalid_tool_input"` - `const ToolSearchToolResultErrorCodeUnavailable ToolSearchToolResultErrorCode = "unavailable"` - `const ToolSearchToolResultErrorCodeTooManyRequests ToolSearchToolResultErrorCode = "too_many_requests"` - `const ToolSearchToolResultErrorCodeExecutionTimeExceeded ToolSearchToolResultErrorCode = "execution_time_exceeded"` - `ErrorMessage string` - `type ToolSearchToolSearchResultBlock` - `Type ToolSearchToolSearchResult` default: tool_search_tool_search_result - `ToolReferences []ToolReferenceBlock` - `Type ToolReference` default: tool_reference - `ToolName string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ContainerUploadBlock` Response model for a file uploaded to the container. - `Type ContainerUpload` default: container_upload - `FileID string` - `Diagnostics Diagnostics` Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected. - `CacheMissReason CacheMissReasonUnion` 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. - `type CacheMissModelChanged` - `Type ModelChanged` default: model_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissSystemChanged` - `Type SystemChanged` default: system_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissToolsChanged` - `Type ToolsChanged` default: tools_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissMessagesChanged` - `Type MessagesChanged` default: messages_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissPreviousMessageNotFound` - `Type PreviousMessageNotFound` default: previous_message_not_found - `type 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. - `const ModelClaudeHaiku5_5 Model = "claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `const ModelClaudeSonnet5_5 Model = "claude-sonnet-5-5"` Efficient model for coding and agents - `const ModelClaudeFable5_1 Model = "claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `const ModelClaudeOpus5_5 Model = "claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `const ModelClaudeMythos5_1 Model = "claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `const ModelClaudeSonnet5 Model = "claude-sonnet-5"` Efficient model for coding and agents - `const ModelClaudeFable5 Model = "claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `const ModelClaudeMythos5 Model = "claude-mythos-5"` Most capable model for cybersecurity and biology research - `const ModelClaudeOpus5 Model = "claude-opus-5"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_8 Model = "claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_7 Model = "claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_6 Model = "claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `const ModelClaudeSonnet4_6 Model = "claude-sonnet-4-6"` Best combination of speed and intelligence - `const ModelClaudeHaiku4_5 Model = "claude-haiku-4-5"` - `const ModelClaudeHaiku4_5_20251001 Model = "claude-haiku-4-5-20251001"` - `const ModelClaudeOpus4_5 Model = "claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_5_20251101 Model = "claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `const ModelClaudeMythosPreview Model = "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 - `const ModelClaudeSonnet4_5 Model = "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 - `const ModelClaudeSonnet4_5_20250929 Model = "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 - `Role Assistant` Conversational role of the generated message. This will always be `"assistant"`. default: assistant - `StopDetails RefusalStopDetails` 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 RefusalStopDetailsCategory` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `const RefusalStopDetailsCategoryCyber RefusalStopDetailsCategory = "cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `const RefusalStopDetailsCategoryBio RefusalStopDetailsCategory = "bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `const RefusalStopDetailsCategoryFrontierLLM RefusalStopDetailsCategory = "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. - `const RefusalStopDetailsCategoryReasoningExtraction RefusalStopDetailsCategory = "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=go). - `const RefusalStopDetailsCategoryGeneralHarms RefusalStopDetailsCategory = "general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `Explanation string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `StopReason StopReason` 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. - `const StopReasonEndTurn StopReason = "end_turn"` - `const StopReasonMaxTokens StopReason = "max_tokens"` - `const StopReasonStopSequence StopReason = "stop_sequence"` - `const StopReasonToolUse StopReason = "tool_use"` - `const StopReasonPauseTurn StopReason = "pause_turn"` - `const StopReasonRefusal StopReason = "refusal"` - `const StopReasonModelContextWindowExceeded StopReason = "model_context_window_exceeded"` - `StopSequence string` 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`. - `CacheCreation CacheCreation` Breakdown of cached tokens by TTL - `Ephemeral1hInputTokens int64` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `Ephemeral5mInputTokens int64` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `CacheCreationInputTokens int64` The number of input tokens used to create the cache entry. minimum: 0 - `CacheReadInputTokens int64` The number of input tokens read from the cache. minimum: 0 - `InferenceGeo string` The geographic region where inference was performed for this request. - `InputTokens int64` The number of input tokens which were used. minimum: 0 - `OutputTokens int64` The number of output tokens which were used. minimum: 0 - `OutputTokensDetails OutputTokensDetails` 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. - `ThinkingTokens int64` 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 - `ServerToolUse ServerToolUsage` The number of server tool requests. - `WebFetchRequests int64` The number of web fetch tool requests. default: 0, minimum: 0 - `WebSearchRequests int64` The number of web search tool requests. default: 0, minimum: 0 - `ServiceTier UsageServiceTier` If the request used the priority, standard, or batch tier. - `const UsageServiceTierStandard UsageServiceTier = "standard"` - `const UsageServiceTierPriority UsageServiceTier = "priority"` - `const UsageServiceTierBatch UsageServiceTier = "batch"` - `Speed UsageSpeed` The inference speed mode used for this request. - `const UsageSpeedStandard UsageSpeed = "standard"` - `const UsageSpeedFast UsageSpeed = "fast"` - `type MessageBatchErroredResult` - `Type Errored` default: errored - `Error ErrorResponse` - `Type Error` default: error - `Error ErrorObjectUnion` - `type InvalidRequestError` - `Type InvalidRequestError` default: invalid_request_error - `Message string` default: Invalid request - `type AuthenticationError` - `Type AuthenticationError` default: authentication_error - `Message string` default: Authentication error - `type BillingError` - `Type BillingError` default: billing_error - `Message string` default: Billing error - `type PermissionError` - `Type PermissionError` default: permission_error - `Message string` default: Permission denied - `type NotFoundError` - `Type NotFoundError` default: not_found_error - `Message string` default: Not found - `type RateLimitError` - `Type RateLimitError` default: rate_limit_error - `Message string` default: Rate limited - `type GatewayTimeoutError` - `Type TimeoutError` default: timeout_error - `Message string` default: Request timeout - `type APIErrorObject` - `Type APIError` default: api_error - `Message string` default: Internal server error - `type OverloadedError` - `Type OverloadedError` default: overloaded_error - `Message string` default: Overloaded - `RequestID string` - `type MessageBatchCanceledResult` - `Type Canceled` default: canceled - `type MessageBatchExpiredResult` - `Type Expired` default: expired ### Message Batch Request Counts - `type MessageBatchRequestCounts` - `Canceled int64` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `Errored int64` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `Expired int64` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `Processing int64` Number of requests in the Message Batch that are processing. default: 0 - `Succeeded int64` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 ### Message Batch Result - `type MessageBatchResultUnion interface{…}` Processing result for this request. Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration. - `type MessageBatchSucceededResult` - `Type Succeeded` default: succeeded - `Message 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` 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 - `ExpiresAt Time` The time at which the container will expire. format: date-time - `Skills []ContainerSkill` Skills loaded in the container - `Type ContainerSkillType` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `const ContainerSkillTypeAnthropic ContainerSkillType = "anthropic"` - `const ContainerSkillTypeCustom ContainerSkillType = "custom"` - `SkillID string` Skill ID minLength: 1, maxLength: 64 - `Version string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `Content []ContentBlockUnion` 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)"}] ``` - `type TextBlock` - `Type Text` default: text - `Citations []TextCitationUnion` 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`. - `type CitationCharLocation` - `Type CharLocation` default: char_location - `CitedText string` - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` - `EndCharIndex int64` - `FileID string` - `StartCharIndex int64` minimum: 0 - `type CitationPageLocation` - `Type PageLocation` default: page_location - `CitedText string` - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` - `EndPageNumber int64` - `FileID string` - `StartPageNumber int64` minimum: 1 - `type CitationContentBlockLocation` - `Type ContentBlockLocation` default: content_block_location - `CitedText 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. - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` - `EndBlockIndex int64` 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`. - `FileID string` - `StartBlockIndex int64` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `type CitationsWebSearchResultLocation` - `Type WebSearchResultLocation` default: web_search_result_location - `CitedText string` - `EncryptedIndex string` - `Title string` maxLength: 512 - `URL string` - `type CitationsSearchResultLocation` - `Type SearchResultLocation` default: search_result_location - `CitedText 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. - `EndBlockIndex int64` 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`. - `SearchResultIndex int64` 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` - `StartBlockIndex int64` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `Title string` - `Text string` - `type 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=go) for details. - `Thinking string` The text of Claude's thinking process for this block. - `type RedactedThinkingBlock` - `Type RedactedThinking` 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=go#redacted-thinking-blocks) for details. - `type ToolUseBlock` - `Type ToolUse` default: tool_use - `ID string` pattern: ^[a-zA-Z0-9_-]+$ - `Caller ToolUseBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `Type Direct` - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `Type CodeExecution20250825` - `ToolID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ServerToolCaller20260120` - `Type CodeExecution20260120` - `ToolID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `Input map[string, any]` - `Name string` minLength: 1 - `ToolsetName string Optional` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `type ServerToolUseBlock` - `Type ServerToolUse` default: server_tool_use - `ID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `Caller ServerToolUseBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `Input map[string, any]` - `Name ServerToolUseBlockName` - `const ServerToolUseBlockNameWebSearch ServerToolUseBlockName = "web_search"` - `const ServerToolUseBlockNameWebFetch ServerToolUseBlockName = "web_fetch"` - `const ServerToolUseBlockNameCodeExecution ServerToolUseBlockName = "code_execution"` - `const ServerToolUseBlockNameBashCodeExecution ServerToolUseBlockName = "bash_code_execution"` - `const ServerToolUseBlockNameTextEditorCodeExecution ServerToolUseBlockName = "text_editor_code_execution"` - `const ServerToolUseBlockNameToolSearchToolRegex ServerToolUseBlockName = "tool_search_tool_regex"` - `const ServerToolUseBlockNameToolSearchToolBm25 ServerToolUseBlockName = "tool_search_tool_bm25"` - `type WebSearchToolResultBlock` - `Type WebSearchToolResult` default: web_search_tool_result - `Caller WebSearchToolResultBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `Content WebSearchToolResultBlockContentUnion` - `type WebSearchToolResultError` - `Type WebSearchToolResultError` default: web_search_tool_result_error - `ErrorCode WebSearchToolResultErrorCode` - `const WebSearchToolResultErrorCodeInvalidToolInput WebSearchToolResultErrorCode = "invalid_tool_input"` - `const WebSearchToolResultErrorCodeUnavailable WebSearchToolResultErrorCode = "unavailable"` - `const WebSearchToolResultErrorCodeMaxUsesExceeded WebSearchToolResultErrorCode = "max_uses_exceeded"` - `const WebSearchToolResultErrorCodeTooManyRequests WebSearchToolResultErrorCode = "too_many_requests"` - `const WebSearchToolResultErrorCodeQueryTooLong WebSearchToolResultErrorCode = "query_too_long"` - `const WebSearchToolResultErrorCodeRequestTooLarge WebSearchToolResultErrorCode = "request_too_large"` - `[]WebSearchResultBlock` - `Type WebSearchResult` default: web_search_result - `EncryptedContent string` - `PageAge string` - `Title string` - `URL string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type WebFetchToolResultBlock` - `Type WebFetchToolResult` default: web_fetch_tool_result - `Caller WebFetchToolResultBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `Content WebFetchToolResultBlockContentUnion` - `type WebFetchToolResultErrorBlock` - `Type WebFetchToolResultError` default: web_fetch_tool_result_error - `ErrorCode WebFetchToolResultErrorCode` - `const WebFetchToolResultErrorCodeInvalidToolInput WebFetchToolResultErrorCode = "invalid_tool_input"` - `const WebFetchToolResultErrorCodeURLTooLong WebFetchToolResultErrorCode = "url_too_long"` - `const WebFetchToolResultErrorCodeURLNotAllowed WebFetchToolResultErrorCode = "url_not_allowed"` - `const WebFetchToolResultErrorCodeURLNotInPriorContext WebFetchToolResultErrorCode = "url_not_in_prior_context"` - `const WebFetchToolResultErrorCodeURLNotAccessible WebFetchToolResultErrorCode = "url_not_accessible"` - `const WebFetchToolResultErrorCodeUnsupportedContentType WebFetchToolResultErrorCode = "unsupported_content_type"` - `const WebFetchToolResultErrorCodeTooManyRequests WebFetchToolResultErrorCode = "too_many_requests"` - `const WebFetchToolResultErrorCodeMaxUsesExceeded WebFetchToolResultErrorCode = "max_uses_exceeded"` - `const WebFetchToolResultErrorCodeUnavailable WebFetchToolResultErrorCode = "unavailable"` - `const WebFetchToolResultErrorCodeContentTooLarge WebFetchToolResultErrorCode = "content_too_large"` - `type WebFetchBlock` - `Type WebFetchResult` default: web_fetch_result - `Content DocumentBlock` - `Type Document` default: document - `Citations CitationsConfig` Citation configuration for the document - `Enabled bool` default: false - `Source DocumentBlockSourceUnion` - `type Base64PDFSource` - `Type Base64` - `Data string` format: byte - `MediaType ApplicationPDF` - `type PlainTextSource` - `Type Text` - `Data string` - `MediaType TextPlain` - `Title string` The title of the document - `RetrievedAt string` ISO 8601 timestamp when the content was retrieved - `URL string` Fetched content URL - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type CodeExecutionToolResultBlock` - `Type CodeExecutionToolResult` default: code_execution_tool_result - `Content CodeExecutionToolResultBlockContentUnion` - `type CodeExecutionToolResultError` - `Type CodeExecutionToolResultError` default: code_execution_tool_result_error - `ErrorCode CodeExecutionToolResultErrorCode` - `const CodeExecutionToolResultErrorCodeInvalidToolInput CodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const CodeExecutionToolResultErrorCodeUnavailable CodeExecutionToolResultErrorCode = "unavailable"` - `const CodeExecutionToolResultErrorCodeTooManyRequests CodeExecutionToolResultErrorCode = "too_many_requests"` - `const CodeExecutionToolResultErrorCodeExecutionTimeExceeded CodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `type CodeExecutionResultBlock` - `Type CodeExecutionResult` default: code_execution_result - `Content []CodeExecutionOutputBlock` - `Type CodeExecutionOutput` default: code_execution_output - `FileID string` - `ReturnCode int64` - `Stderr string` - `Stdout string` - `type EncryptedCodeExecutionResultBlock` Code execution result with encrypted stdout for PFC + web_search results. - `Type EncryptedCodeExecutionResult` default: encrypted_code_execution_result - `Content []CodeExecutionOutputBlock` - `Type CodeExecutionOutput` default: code_execution_output - `FileID string` - `EncryptedStdout string` - `ReturnCode int64` - `Stderr string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type BashCodeExecutionToolResultBlock` - `Type BashCodeExecutionToolResult` default: bash_code_execution_tool_result - `Content BashCodeExecutionToolResultBlockContentUnion` - `type BashCodeExecutionToolResultError` - `Type BashCodeExecutionToolResultError` default: bash_code_execution_tool_result_error - `ErrorCode BashCodeExecutionToolResultErrorCode` - `const BashCodeExecutionToolResultErrorCodeInvalidToolInput BashCodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const BashCodeExecutionToolResultErrorCodeUnavailable BashCodeExecutionToolResultErrorCode = "unavailable"` - `const BashCodeExecutionToolResultErrorCodeTooManyRequests BashCodeExecutionToolResultErrorCode = "too_many_requests"` - `const BashCodeExecutionToolResultErrorCodeExecutionTimeExceeded BashCodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `const BashCodeExecutionToolResultErrorCodeOutputFileTooLarge BashCodeExecutionToolResultErrorCode = "output_file_too_large"` - `type BashCodeExecutionResultBlock` - `Type BashCodeExecutionResult` default: bash_code_execution_result - `Content []BashCodeExecutionOutputBlock` - `Type BashCodeExecutionOutput` default: bash_code_execution_output - `FileID string` - `ReturnCode int64` - `Stderr string` - `Stdout string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type TextEditorCodeExecutionToolResultBlock` - `Type TextEditorCodeExecutionToolResult` default: text_editor_code_execution_tool_result - `Content TextEditorCodeExecutionToolResultBlockContentUnion` - `type TextEditorCodeExecutionToolResultError` - `Type TextEditorCodeExecutionToolResultError` default: text_editor_code_execution_tool_result_error - `ErrorCode TextEditorCodeExecutionToolResultErrorCode` - `const TextEditorCodeExecutionToolResultErrorCodeInvalidToolInput TextEditorCodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const TextEditorCodeExecutionToolResultErrorCodeUnavailable TextEditorCodeExecutionToolResultErrorCode = "unavailable"` - `const TextEditorCodeExecutionToolResultErrorCodeTooManyRequests TextEditorCodeExecutionToolResultErrorCode = "too_many_requests"` - `const TextEditorCodeExecutionToolResultErrorCodeExecutionTimeExceeded TextEditorCodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `const TextEditorCodeExecutionToolResultErrorCodeFileNotFound TextEditorCodeExecutionToolResultErrorCode = "file_not_found"` - `ErrorMessage string` - `type TextEditorCodeExecutionViewResultBlock` - `Type TextEditorCodeExecutionViewResult` default: text_editor_code_execution_view_result - `Content string` - `FileType TextEditorCodeExecutionViewResultBlockFileType` - `const TextEditorCodeExecutionViewResultBlockFileTypeText TextEditorCodeExecutionViewResultBlockFileType = "text"` - `const TextEditorCodeExecutionViewResultBlockFileTypeImage TextEditorCodeExecutionViewResultBlockFileType = "image"` - `const TextEditorCodeExecutionViewResultBlockFileTypePDF TextEditorCodeExecutionViewResultBlockFileType = "pdf"` - `NumLines int64` - `StartLine int64` - `TotalLines int64` - `type TextEditorCodeExecutionCreateResultBlock` - `Type TextEditorCodeExecutionCreateResult` default: text_editor_code_execution_create_result - `IsFileUpdate bool` - `type TextEditorCodeExecutionStrReplaceResultBlock` - `Type TextEditorCodeExecutionStrReplaceResult` default: text_editor_code_execution_str_replace_result - `Lines []string` - `NewLines int64` - `NewStart int64` - `OldLines int64` - `OldStart int64` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ToolSearchToolResultBlock` - `Type ToolSearchToolResult` default: tool_search_tool_result - `Content ToolSearchToolResultBlockContentUnion` - `type ToolSearchToolResultError` - `Type ToolSearchToolResultError` default: tool_search_tool_result_error - `ErrorCode ToolSearchToolResultErrorCode` - `const ToolSearchToolResultErrorCodeInvalidToolInput ToolSearchToolResultErrorCode = "invalid_tool_input"` - `const ToolSearchToolResultErrorCodeUnavailable ToolSearchToolResultErrorCode = "unavailable"` - `const ToolSearchToolResultErrorCodeTooManyRequests ToolSearchToolResultErrorCode = "too_many_requests"` - `const ToolSearchToolResultErrorCodeExecutionTimeExceeded ToolSearchToolResultErrorCode = "execution_time_exceeded"` - `ErrorMessage string` - `type ToolSearchToolSearchResultBlock` - `Type ToolSearchToolSearchResult` default: tool_search_tool_search_result - `ToolReferences []ToolReferenceBlock` - `Type ToolReference` default: tool_reference - `ToolName string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ContainerUploadBlock` Response model for a file uploaded to the container. - `Type ContainerUpload` default: container_upload - `FileID string` - `Diagnostics Diagnostics` Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected. - `CacheMissReason CacheMissReasonUnion` 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. - `type CacheMissModelChanged` - `Type ModelChanged` default: model_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissSystemChanged` - `Type SystemChanged` default: system_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissToolsChanged` - `Type ToolsChanged` default: tools_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissMessagesChanged` - `Type MessagesChanged` default: messages_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissPreviousMessageNotFound` - `Type PreviousMessageNotFound` default: previous_message_not_found - `type 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. - `const ModelClaudeHaiku5_5 Model = "claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `const ModelClaudeSonnet5_5 Model = "claude-sonnet-5-5"` Efficient model for coding and agents - `const ModelClaudeFable5_1 Model = "claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `const ModelClaudeOpus5_5 Model = "claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `const ModelClaudeMythos5_1 Model = "claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `const ModelClaudeSonnet5 Model = "claude-sonnet-5"` Efficient model for coding and agents - `const ModelClaudeFable5 Model = "claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `const ModelClaudeMythos5 Model = "claude-mythos-5"` Most capable model for cybersecurity and biology research - `const ModelClaudeOpus5 Model = "claude-opus-5"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_8 Model = "claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_7 Model = "claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_6 Model = "claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `const ModelClaudeSonnet4_6 Model = "claude-sonnet-4-6"` Best combination of speed and intelligence - `const ModelClaudeHaiku4_5 Model = "claude-haiku-4-5"` - `const ModelClaudeHaiku4_5_20251001 Model = "claude-haiku-4-5-20251001"` - `const ModelClaudeOpus4_5 Model = "claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_5_20251101 Model = "claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `const ModelClaudeMythosPreview Model = "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 - `const ModelClaudeSonnet4_5 Model = "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 - `const ModelClaudeSonnet4_5_20250929 Model = "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 - `Role Assistant` Conversational role of the generated message. This will always be `"assistant"`. default: assistant - `StopDetails RefusalStopDetails` 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 RefusalStopDetailsCategory` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `const RefusalStopDetailsCategoryCyber RefusalStopDetailsCategory = "cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `const RefusalStopDetailsCategoryBio RefusalStopDetailsCategory = "bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `const RefusalStopDetailsCategoryFrontierLLM RefusalStopDetailsCategory = "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. - `const RefusalStopDetailsCategoryReasoningExtraction RefusalStopDetailsCategory = "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=go). - `const RefusalStopDetailsCategoryGeneralHarms RefusalStopDetailsCategory = "general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `Explanation string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `StopReason StopReason` 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. - `const StopReasonEndTurn StopReason = "end_turn"` - `const StopReasonMaxTokens StopReason = "max_tokens"` - `const StopReasonStopSequence StopReason = "stop_sequence"` - `const StopReasonToolUse StopReason = "tool_use"` - `const StopReasonPauseTurn StopReason = "pause_turn"` - `const StopReasonRefusal StopReason = "refusal"` - `const StopReasonModelContextWindowExceeded StopReason = "model_context_window_exceeded"` - `StopSequence string` 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`. - `CacheCreation CacheCreation` Breakdown of cached tokens by TTL - `Ephemeral1hInputTokens int64` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `Ephemeral5mInputTokens int64` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `CacheCreationInputTokens int64` The number of input tokens used to create the cache entry. minimum: 0 - `CacheReadInputTokens int64` The number of input tokens read from the cache. minimum: 0 - `InferenceGeo string` The geographic region where inference was performed for this request. - `InputTokens int64` The number of input tokens which were used. minimum: 0 - `OutputTokens int64` The number of output tokens which were used. minimum: 0 - `OutputTokensDetails OutputTokensDetails` 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. - `ThinkingTokens int64` 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 - `ServerToolUse ServerToolUsage` The number of server tool requests. - `WebFetchRequests int64` The number of web fetch tool requests. default: 0, minimum: 0 - `WebSearchRequests int64` The number of web search tool requests. default: 0, minimum: 0 - `ServiceTier UsageServiceTier` If the request used the priority, standard, or batch tier. - `const UsageServiceTierStandard UsageServiceTier = "standard"` - `const UsageServiceTierPriority UsageServiceTier = "priority"` - `const UsageServiceTierBatch UsageServiceTier = "batch"` - `Speed UsageSpeed` The inference speed mode used for this request. - `const UsageSpeedStandard UsageSpeed = "standard"` - `const UsageSpeedFast UsageSpeed = "fast"` - `type MessageBatchErroredResult` - `Type Errored` default: errored - `Error ErrorResponse` - `Type Error` default: error - `Error ErrorObjectUnion` - `type InvalidRequestError` - `Type InvalidRequestError` default: invalid_request_error - `Message string` default: Invalid request - `type AuthenticationError` - `Type AuthenticationError` default: authentication_error - `Message string` default: Authentication error - `type BillingError` - `Type BillingError` default: billing_error - `Message string` default: Billing error - `type PermissionError` - `Type PermissionError` default: permission_error - `Message string` default: Permission denied - `type NotFoundError` - `Type NotFoundError` default: not_found_error - `Message string` default: Not found - `type RateLimitError` - `Type RateLimitError` default: rate_limit_error - `Message string` default: Rate limited - `type GatewayTimeoutError` - `Type TimeoutError` default: timeout_error - `Message string` default: Request timeout - `type APIErrorObject` - `Type APIError` default: api_error - `Message string` default: Internal server error - `type OverloadedError` - `Type OverloadedError` default: overloaded_error - `Message string` default: Overloaded - `RequestID string` - `type MessageBatchCanceledResult` - `Type Canceled` default: canceled - `type MessageBatchExpiredResult` - `Type Expired` default: expired ### Message Batch Succeeded Result - `type MessageBatchSucceededResult` - `Type Succeeded` default: succeeded - `Message 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` 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 - `ExpiresAt Time` The time at which the container will expire. format: date-time - `Skills []ContainerSkill` Skills loaded in the container - `Type ContainerSkillType` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `const ContainerSkillTypeAnthropic ContainerSkillType = "anthropic"` - `const ContainerSkillTypeCustom ContainerSkillType = "custom"` - `SkillID string` Skill ID minLength: 1, maxLength: 64 - `Version string` The resolved version: a skill version ID for custom skills. minLength: 1, maxLength: 64 - `Content []ContentBlockUnion` 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)"}] ``` - `type TextBlock` - `Type Text` default: text - `Citations []TextCitationUnion` 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`. - `type CitationCharLocation` - `Type CharLocation` default: char_location - `CitedText string` - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` - `EndCharIndex int64` - `FileID string` - `StartCharIndex int64` minimum: 0 - `type CitationPageLocation` - `Type PageLocation` default: page_location - `CitedText string` - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` - `EndPageNumber int64` - `FileID string` - `StartPageNumber int64` minimum: 1 - `type CitationContentBlockLocation` - `Type ContentBlockLocation` default: content_block_location - `CitedText 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. - `DocumentIndex int64` minimum: 0 - `DocumentTitle string` - `EndBlockIndex int64` 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`. - `FileID string` - `StartBlockIndex int64` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `type CitationsWebSearchResultLocation` - `Type WebSearchResultLocation` default: web_search_result_location - `CitedText string` - `EncryptedIndex string` - `Title string` maxLength: 512 - `URL string` - `type CitationsSearchResultLocation` - `Type SearchResultLocation` default: search_result_location - `CitedText 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. - `EndBlockIndex int64` 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`. - `SearchResultIndex int64` 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` - `StartBlockIndex int64` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `Title string` - `Text string` - `type 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=go) for details. - `Thinking string` The text of Claude's thinking process for this block. - `type RedactedThinkingBlock` - `Type RedactedThinking` 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=go#redacted-thinking-blocks) for details. - `type ToolUseBlock` - `Type ToolUse` default: tool_use - `ID string` pattern: ^[a-zA-Z0-9_-]+$ - `Caller ToolUseBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `Type Direct` - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `Type CodeExecution20250825` - `ToolID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ServerToolCaller20260120` - `Type CodeExecution20260120` - `ToolID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `Input map[string, any]` - `Name string` minLength: 1 - `ToolsetName string Optional` For a toolset member tool_use, the toolset family. minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$ - `type ServerToolUseBlock` - `Type ServerToolUse` default: server_tool_use - `ID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `Caller ServerToolUseBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `Input map[string, any]` - `Name ServerToolUseBlockName` - `const ServerToolUseBlockNameWebSearch ServerToolUseBlockName = "web_search"` - `const ServerToolUseBlockNameWebFetch ServerToolUseBlockName = "web_fetch"` - `const ServerToolUseBlockNameCodeExecution ServerToolUseBlockName = "code_execution"` - `const ServerToolUseBlockNameBashCodeExecution ServerToolUseBlockName = "bash_code_execution"` - `const ServerToolUseBlockNameTextEditorCodeExecution ServerToolUseBlockName = "text_editor_code_execution"` - `const ServerToolUseBlockNameToolSearchToolRegex ServerToolUseBlockName = "tool_search_tool_regex"` - `const ServerToolUseBlockNameToolSearchToolBm25 ServerToolUseBlockName = "tool_search_tool_bm25"` - `type WebSearchToolResultBlock` - `Type WebSearchToolResult` default: web_search_tool_result - `Caller WebSearchToolResultBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `Content WebSearchToolResultBlockContentUnion` - `type WebSearchToolResultError` - `Type WebSearchToolResultError` default: web_search_tool_result_error - `ErrorCode WebSearchToolResultErrorCode` - `const WebSearchToolResultErrorCodeInvalidToolInput WebSearchToolResultErrorCode = "invalid_tool_input"` - `const WebSearchToolResultErrorCodeUnavailable WebSearchToolResultErrorCode = "unavailable"` - `const WebSearchToolResultErrorCodeMaxUsesExceeded WebSearchToolResultErrorCode = "max_uses_exceeded"` - `const WebSearchToolResultErrorCodeTooManyRequests WebSearchToolResultErrorCode = "too_many_requests"` - `const WebSearchToolResultErrorCodeQueryTooLong WebSearchToolResultErrorCode = "query_too_long"` - `const WebSearchToolResultErrorCodeRequestTooLarge WebSearchToolResultErrorCode = "request_too_large"` - `[]WebSearchResultBlock` - `Type WebSearchResult` default: web_search_result - `EncryptedContent string` - `PageAge string` - `Title string` - `URL string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type WebFetchToolResultBlock` - `Type WebFetchToolResult` default: web_fetch_tool_result - `Caller WebFetchToolResultBlockCallerUnion` default: {"type":"direct"} - `type DirectCaller` Tool invocation directly from the model. - `type ServerToolCaller` Tool invocation generated by a server-side tool. - `type ServerToolCaller20260120` - `Content WebFetchToolResultBlockContentUnion` - `type WebFetchToolResultErrorBlock` - `Type WebFetchToolResultError` default: web_fetch_tool_result_error - `ErrorCode WebFetchToolResultErrorCode` - `const WebFetchToolResultErrorCodeInvalidToolInput WebFetchToolResultErrorCode = "invalid_tool_input"` - `const WebFetchToolResultErrorCodeURLTooLong WebFetchToolResultErrorCode = "url_too_long"` - `const WebFetchToolResultErrorCodeURLNotAllowed WebFetchToolResultErrorCode = "url_not_allowed"` - `const WebFetchToolResultErrorCodeURLNotInPriorContext WebFetchToolResultErrorCode = "url_not_in_prior_context"` - `const WebFetchToolResultErrorCodeURLNotAccessible WebFetchToolResultErrorCode = "url_not_accessible"` - `const WebFetchToolResultErrorCodeUnsupportedContentType WebFetchToolResultErrorCode = "unsupported_content_type"` - `const WebFetchToolResultErrorCodeTooManyRequests WebFetchToolResultErrorCode = "too_many_requests"` - `const WebFetchToolResultErrorCodeMaxUsesExceeded WebFetchToolResultErrorCode = "max_uses_exceeded"` - `const WebFetchToolResultErrorCodeUnavailable WebFetchToolResultErrorCode = "unavailable"` - `const WebFetchToolResultErrorCodeContentTooLarge WebFetchToolResultErrorCode = "content_too_large"` - `type WebFetchBlock` - `Type WebFetchResult` default: web_fetch_result - `Content DocumentBlock` - `Type Document` default: document - `Citations CitationsConfig` Citation configuration for the document - `Enabled bool` default: false - `Source DocumentBlockSourceUnion` - `type Base64PDFSource` - `Type Base64` - `Data string` format: byte - `MediaType ApplicationPDF` - `type PlainTextSource` - `Type Text` - `Data string` - `MediaType TextPlain` - `Title string` The title of the document - `RetrievedAt string` ISO 8601 timestamp when the content was retrieved - `URL string` Fetched content URL - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type CodeExecutionToolResultBlock` - `Type CodeExecutionToolResult` default: code_execution_tool_result - `Content CodeExecutionToolResultBlockContentUnion` - `type CodeExecutionToolResultError` - `Type CodeExecutionToolResultError` default: code_execution_tool_result_error - `ErrorCode CodeExecutionToolResultErrorCode` - `const CodeExecutionToolResultErrorCodeInvalidToolInput CodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const CodeExecutionToolResultErrorCodeUnavailable CodeExecutionToolResultErrorCode = "unavailable"` - `const CodeExecutionToolResultErrorCodeTooManyRequests CodeExecutionToolResultErrorCode = "too_many_requests"` - `const CodeExecutionToolResultErrorCodeExecutionTimeExceeded CodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `type CodeExecutionResultBlock` - `Type CodeExecutionResult` default: code_execution_result - `Content []CodeExecutionOutputBlock` - `Type CodeExecutionOutput` default: code_execution_output - `FileID string` - `ReturnCode int64` - `Stderr string` - `Stdout string` - `type EncryptedCodeExecutionResultBlock` Code execution result with encrypted stdout for PFC + web_search results. - `Type EncryptedCodeExecutionResult` default: encrypted_code_execution_result - `Content []CodeExecutionOutputBlock` - `Type CodeExecutionOutput` default: code_execution_output - `FileID string` - `EncryptedStdout string` - `ReturnCode int64` - `Stderr string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type BashCodeExecutionToolResultBlock` - `Type BashCodeExecutionToolResult` default: bash_code_execution_tool_result - `Content BashCodeExecutionToolResultBlockContentUnion` - `type BashCodeExecutionToolResultError` - `Type BashCodeExecutionToolResultError` default: bash_code_execution_tool_result_error - `ErrorCode BashCodeExecutionToolResultErrorCode` - `const BashCodeExecutionToolResultErrorCodeInvalidToolInput BashCodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const BashCodeExecutionToolResultErrorCodeUnavailable BashCodeExecutionToolResultErrorCode = "unavailable"` - `const BashCodeExecutionToolResultErrorCodeTooManyRequests BashCodeExecutionToolResultErrorCode = "too_many_requests"` - `const BashCodeExecutionToolResultErrorCodeExecutionTimeExceeded BashCodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `const BashCodeExecutionToolResultErrorCodeOutputFileTooLarge BashCodeExecutionToolResultErrorCode = "output_file_too_large"` - `type BashCodeExecutionResultBlock` - `Type BashCodeExecutionResult` default: bash_code_execution_result - `Content []BashCodeExecutionOutputBlock` - `Type BashCodeExecutionOutput` default: bash_code_execution_output - `FileID string` - `ReturnCode int64` - `Stderr string` - `Stdout string` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type TextEditorCodeExecutionToolResultBlock` - `Type TextEditorCodeExecutionToolResult` default: text_editor_code_execution_tool_result - `Content TextEditorCodeExecutionToolResultBlockContentUnion` - `type TextEditorCodeExecutionToolResultError` - `Type TextEditorCodeExecutionToolResultError` default: text_editor_code_execution_tool_result_error - `ErrorCode TextEditorCodeExecutionToolResultErrorCode` - `const TextEditorCodeExecutionToolResultErrorCodeInvalidToolInput TextEditorCodeExecutionToolResultErrorCode = "invalid_tool_input"` - `const TextEditorCodeExecutionToolResultErrorCodeUnavailable TextEditorCodeExecutionToolResultErrorCode = "unavailable"` - `const TextEditorCodeExecutionToolResultErrorCodeTooManyRequests TextEditorCodeExecutionToolResultErrorCode = "too_many_requests"` - `const TextEditorCodeExecutionToolResultErrorCodeExecutionTimeExceeded TextEditorCodeExecutionToolResultErrorCode = "execution_time_exceeded"` - `const TextEditorCodeExecutionToolResultErrorCodeFileNotFound TextEditorCodeExecutionToolResultErrorCode = "file_not_found"` - `ErrorMessage string` - `type TextEditorCodeExecutionViewResultBlock` - `Type TextEditorCodeExecutionViewResult` default: text_editor_code_execution_view_result - `Content string` - `FileType TextEditorCodeExecutionViewResultBlockFileType` - `const TextEditorCodeExecutionViewResultBlockFileTypeText TextEditorCodeExecutionViewResultBlockFileType = "text"` - `const TextEditorCodeExecutionViewResultBlockFileTypeImage TextEditorCodeExecutionViewResultBlockFileType = "image"` - `const TextEditorCodeExecutionViewResultBlockFileTypePDF TextEditorCodeExecutionViewResultBlockFileType = "pdf"` - `NumLines int64` - `StartLine int64` - `TotalLines int64` - `type TextEditorCodeExecutionCreateResultBlock` - `Type TextEditorCodeExecutionCreateResult` default: text_editor_code_execution_create_result - `IsFileUpdate bool` - `type TextEditorCodeExecutionStrReplaceResultBlock` - `Type TextEditorCodeExecutionStrReplaceResult` default: text_editor_code_execution_str_replace_result - `Lines []string` - `NewLines int64` - `NewStart int64` - `OldLines int64` - `OldStart int64` - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ToolSearchToolResultBlock` - `Type ToolSearchToolResult` default: tool_search_tool_result - `Content ToolSearchToolResultBlockContentUnion` - `type ToolSearchToolResultError` - `Type ToolSearchToolResultError` default: tool_search_tool_result_error - `ErrorCode ToolSearchToolResultErrorCode` - `const ToolSearchToolResultErrorCodeInvalidToolInput ToolSearchToolResultErrorCode = "invalid_tool_input"` - `const ToolSearchToolResultErrorCodeUnavailable ToolSearchToolResultErrorCode = "unavailable"` - `const ToolSearchToolResultErrorCodeTooManyRequests ToolSearchToolResultErrorCode = "too_many_requests"` - `const ToolSearchToolResultErrorCodeExecutionTimeExceeded ToolSearchToolResultErrorCode = "execution_time_exceeded"` - `ErrorMessage string` - `type ToolSearchToolSearchResultBlock` - `Type ToolSearchToolSearchResult` default: tool_search_tool_search_result - `ToolReferences []ToolReferenceBlock` - `Type ToolReference` default: tool_reference - `ToolName string` minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `ToolUseID string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `type ContainerUploadBlock` Response model for a file uploaded to the container. - `Type ContainerUpload` default: container_upload - `FileID string` - `Diagnostics Diagnostics` Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected. - `CacheMissReason CacheMissReasonUnion` 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. - `type CacheMissModelChanged` - `Type ModelChanged` default: model_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissSystemChanged` - `Type SystemChanged` default: system_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissToolsChanged` - `Type ToolsChanged` default: tools_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissMessagesChanged` - `Type MessagesChanged` default: messages_changed - `CacheMissedInputTokens int64` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `type CacheMissPreviousMessageNotFound` - `Type PreviousMessageNotFound` default: previous_message_not_found - `type 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. - `const ModelClaudeHaiku5_5 Model = "claude-haiku-5-5"` Fastest model for high-volume, real-time tasks - `const ModelClaudeSonnet5_5 Model = "claude-sonnet-5-5"` Efficient model for coding and agents - `const ModelClaudeFable5_1 Model = "claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `const ModelClaudeOpus5_5 Model = "claude-opus-5-5"` Powerful intelligence for coding, knowledge work, and long-running agents - `const ModelClaudeMythos5_1 Model = "claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `const ModelClaudeSonnet5 Model = "claude-sonnet-5"` Efficient model for coding and agents - `const ModelClaudeFable5 Model = "claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `const ModelClaudeMythos5 Model = "claude-mythos-5"` Most capable model for cybersecurity and biology research - `const ModelClaudeOpus5 Model = "claude-opus-5"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_8 Model = "claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_7 Model = "claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_6 Model = "claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `const ModelClaudeSonnet4_6 Model = "claude-sonnet-4-6"` Best combination of speed and intelligence - `const ModelClaudeHaiku4_5 Model = "claude-haiku-4-5"` - `const ModelClaudeHaiku4_5_20251001 Model = "claude-haiku-4-5-20251001"` - `const ModelClaudeOpus4_5 Model = "claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `const ModelClaudeOpus4_5_20251101 Model = "claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `const ModelClaudeMythosPreview Model = "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 - `const ModelClaudeSonnet4_5 Model = "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 - `const ModelClaudeSonnet4_5_20250929 Model = "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 - `Role Assistant` Conversational role of the generated message. This will always be `"assistant"`. default: assistant - `StopDetails RefusalStopDetails` 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 RefusalStopDetailsCategory` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `const RefusalStopDetailsCategoryCyber RefusalStopDetailsCategory = "cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `const RefusalStopDetailsCategoryBio RefusalStopDetailsCategory = "bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `const RefusalStopDetailsCategoryFrontierLLM RefusalStopDetailsCategory = "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. - `const RefusalStopDetailsCategoryReasoningExtraction RefusalStopDetailsCategory = "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=go). - `const RefusalStopDetailsCategoryGeneralHarms RefusalStopDetailsCategory = "general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `Explanation string` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `StopReason StopReason` 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. - `const StopReasonEndTurn StopReason = "end_turn"` - `const StopReasonMaxTokens StopReason = "max_tokens"` - `const StopReasonStopSequence StopReason = "stop_sequence"` - `const StopReasonToolUse StopReason = "tool_use"` - `const StopReasonPauseTurn StopReason = "pause_turn"` - `const StopReasonRefusal StopReason = "refusal"` - `const StopReasonModelContextWindowExceeded StopReason = "model_context_window_exceeded"` - `StopSequence string` 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`. - `CacheCreation CacheCreation` Breakdown of cached tokens by TTL - `Ephemeral1hInputTokens int64` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `Ephemeral5mInputTokens int64` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `CacheCreationInputTokens int64` The number of input tokens used to create the cache entry. minimum: 0 - `CacheReadInputTokens int64` The number of input tokens read from the cache. minimum: 0 - `InferenceGeo string` The geographic region where inference was performed for this request. - `InputTokens int64` The number of input tokens which were used. minimum: 0 - `OutputTokens int64` The number of output tokens which were used. minimum: 0 - `OutputTokensDetails OutputTokensDetails` 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. - `ThinkingTokens int64` 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 - `ServerToolUse ServerToolUsage` The number of server tool requests. - `WebFetchRequests int64` The number of web fetch tool requests. default: 0, minimum: 0 - `WebSearchRequests int64` The number of web search tool requests. default: 0, minimum: 0 - `ServiceTier UsageServiceTier` If the request used the priority, standard, or batch tier. - `const UsageServiceTierStandard UsageServiceTier = "standard"` - `const UsageServiceTierPriority UsageServiceTier = "priority"` - `const UsageServiceTierBatch UsageServiceTier = "batch"` - `Speed UsageSpeed` The inference speed mode used for this request. - `const UsageSpeedStandard UsageSpeed = "standard"` - `const UsageSpeedFast UsageSpeed = "fast"`