One change
Create a Message Batch
api/messages/batches/create
Nearest release: v2.1.245, published an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
api/messages/batches/create Changed · +363 / -394 lines
# Create a Message Batch ## Headers ## Body parameters ## Returns ## Example ### Response (200) ## Create a Message Batch ### Header Parameters ### Body Parameters ### Returns ### Example #### Response
The two sides of this change are too far apart to line up, so this is the differ's own diff of it.
from line 1
---- -title: Create a Message Batch -url: https://platform.claude.com/docs/en/api/messages/batches/create ---- - -## Create a Message Batch - -**post** `/v1/messages/batches` +# Create a Message Batch + +**POST** `/v1/messages/batches` Send a batch of Message creation requests.
from line 8
Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing) -### Header Parameters +## Headers - `"anthropic-user-profile-id": optional string` 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. -### Body Parameters - -- `requests: array of object { custom_id, params }` +## Body parameters + +- `requests: array of object` List of requests for prompt completion. Each is an individual request to create a Message. + maxItems: 100000, minItems: 1 + - `custom_id: 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. - - `params: object { max_tokens, messages, model, 15 more }` + maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,64}$ + + - `params: object` Messages API creation parameters for the individual request.
from line 45
Set to `0` to populate the [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#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) for details. + + minimum: 0 - `messages: array of MessageParam`
from line 105
- `array of ContentBlockParam` - - `TextBlockParam object { text, type, cache_control, citations }` + - `TextBlockParam object` - `text: string` + minLength: 1 + - `type: "text"` - - `"text"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - - - `"ephemeral"` - `ttl: optional "5m" or "1h"`
from line 136
- `citations: optional array of TextCitationParam or null` - - `CitationCharLocationParam object { cited_text, document_index, document_title, 3 more }` + - `CitationCharLocationParam object` - `cited_text: string` - `document_index: number` + minimum: 0 + - `document_title: string or null` + maxLength: 500, minLength: 1 + - `end_char_index: number` - `start_char_index: number` + minimum: 0 + - `type: "char_location"` - - `"char_location"` - - - `CitationPageLocationParam object { cited_text, document_index, document_title, 3 more }` + - `CitationPageLocationParam object` - `cited_text: string` - `document_index: number` + minimum: 0 + - `document_title: string or null` + maxLength: 500, minLength: 1 + - `end_page_number: number` - `start_page_number: number` + minimum: 1 + - `type: "page_location"` - - `"page_location"` - - - `CitationContentBlockLocationParam object { cited_text, document_index, document_title, 3 more }` + - `CitationContentBlockLocationParam object` - `cited_text: string`
from line 186
- `document_index: number` + minimum: 0 + - `document_title: string or null` + maxLength: 500, minLength: 1 + - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array.
from line 202
0-based index of the first cited block in the source's `content` array. + minimum: 0 + - `type: "content_block_location"` - - `"content_block_location"` - - - `CitationWebSearchResultLocationParam object { cited_text, encrypted_index, title, 2 more }` + - `CitationWebSearchResultLocationParam object` - `cited_text: string`
from line 214
- `title: string or null` + maxLength: 512, minLength: 1 + - `type: "web_search_result_location"` - - `"web_search_result_location"` - - `url: string` - - `CitationSearchResultLocationParam object { cited_text, end_block_index, search_result_index, 4 more }` + minLength: 1 + + - `CitationSearchResultLocationParam object` - `cited_text: string`
from line 242
Counted separately from `document_index`; server-side web search results are not included in this count. + minimum: 0 + - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. + minimum: 0 + - `title: string or null` - `type: "search_result_location"` - - `"search_result_location"` - - - `ImageBlockParam object { source, type, cache_control, transformations }` + - `ImageBlockParam object` - `source: Base64ImageSource or URLImageSource or FileImageSource` - - `Base64ImageSource object { data, media_type, type }` + - `Base64ImageSource object` - `data: string` + format: byte + - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"`
from line 278
- `type: "base64"` - - `"base64"` - - - `URLImageSource object { type, url }` + - `URLImageSource object` - `type: "url"` - - `"url"` - - `url: string` - - `FileImageSource object { file_id, type }` + - `FileImageSource object` - `file_id: string` - `type: "file"` - - `"file"` - - `type: "image"` - - `"image"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block.
from line 308
- `"error"` - - `DocumentBlockParam object { source, type, cache_control, 3 more }` + - `DocumentBlockParam object` - `source: Base64PDFSource or PlainTextSource or ContentBlockSource or 2 more` - - `Base64PDFSource object { data, media_type, type }` + - `Base64PDFSource object` - `data: string` + format: byte + - `media_type: "application/pdf"` - - `"application/pdf"` - - `type: "base64"` - - `"base64"` - - - `PlainTextSource object { data, media_type, type }` + - `PlainTextSource object` - `data: string` - `media_type: "text/plain"` - - `"text/plain"` - - `type: "text"` - - `"text"` - - - `ContentBlockSource object { content, type }` + - `ContentBlockSource object` - `content: string or array of ContentBlockSourceContent`
from line 338
- `ContentBlockSourceContent = array of ContentBlockSourceContent` - - `TextBlockParam object { text, type, cache_control, citations }` - - - `ImageBlockParam object { source, type, cache_control, transformations }` + - `TextBlockParam object` + + - `ImageBlockParam object` - `type: "content"` - - `"content"` - - - `URLPDFSource object { type, url }` + - `URLPDFSource object` - `type: "url"` - - `"url"` - - `url: string` - - `FileDocumentSource object { file_id, type }` + - `FileDocumentSource object` - `file_id: string` - `type: "file"` - - `"file"` - - `type: "document"` - - `"document"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block.
from line 368
- `context: optional string or null` + minLength: 1 + - `title: optional string or null` - - `SearchResultBlockParam object { content, source, title, 3 more }` + maxLength: 500, minLength: 1 + + - `SearchResultBlockParam object` - `content: array of TextBlockParam` - `text: string` + minLength: 1 + - `type: "text"` - `cache_control: optional CacheControlEphemeral or null`
from line 396
- `type: "search_result"` - - `"search_result"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional CitationsConfigParam` - - `ThinkingBlockParam object { signature, thinking, type }` + - `ThinkingBlockParam object` - `signature: string`
from line 416
- `type: "thinking"` - - `"thinking"` - - - `RedactedThinkingBlockParam object { data, type }` + - `RedactedThinkingBlockParam object` - `data: string`
from line 424
- `type: "redacted_thinking"` - - `"redacted_thinking"` - - - `ToolUseBlockParam object { id, input, name, 4 more }` + - `ToolUseBlockParam object` - `id: string` + pattern: ^[a-zA-Z0-9_-]+$ + - `input: map[unknown]` - `name: string` + maxLength: 200, minLength: 1 + - `type: "tool_use"` - - `"tool_use"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block.
from line 446
Tool invocation directly from the model. - - `DirectCaller object { type }` + - `DirectCaller object` Tool invocation directly from the model. - `type: "direct"` - - `"direct"` - - - `ServerToolCaller object { tool_id, type }` + - `ServerToolCaller object` Tool invocation generated by a server-side tool. - `tool_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "code_execution_20250825"` - - `"code_execution_20250825"` - - - `ServerToolCaller20260120 object { tool_id, type }` + - `ServerToolCaller20260120 object` - `tool_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "code_execution_20260120"` - - `"code_execution_20260120"` - - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family this member belongs to. - - `ToolResultBlockParam object { tool_use_id, type, cache_control, 3 more }` + maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ + + - `ToolResultBlockParam object` - `tool_use_id: string` + pattern: ^[a-zA-Z0-9_-]+$ + - `type: "tool_result"` - - `"tool_result"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block.
from line 494
- `array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more` - - `TextBlockParam object { text, type, cache_control, citations }` - - - `ImageBlockParam object { source, type, cache_control, transformations }` - - - `SearchResultBlockParam object { content, source, title, 3 more }` - - - `DocumentBlockParam object { source, type, cache_control, 3 more }` - - - `ToolReferenceBlockParam object { tool_name, type, cache_control }` + - `TextBlockParam object` + + - `ImageBlockParam object` + + - `SearchResultBlockParam object` + + - `DocumentBlockParam object` + + - `ToolReferenceBlockParam object` Tool reference block that can be included in tool_result content. - `tool_name: string` + maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ + - `type: "tool_reference"` - - `"tool_reference"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `BrowserStateBlockParam object { tabs, type, cache_control, state_changes }` + - `BrowserStateBlockParam object` The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side
from line 530
All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. + maxItems: 100 + - `tab_id: string` The caller-assigned identifier for this tab, unique within the inventory. + maxLength: 4096, minLength: 1, 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: optional boolean` Whether this tab is the active tab after this call. Whenever `tabs` is non-empty, exactly one entry is marked `active: true`. - `type: "browser_state"` - - `"browser_state"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block.
from line 564
Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. - - `BrowserStateChangeTabOpened object { tab_id, type }` + maxItems: 200, minItems: 1 + + - `BrowserStateChangeTabOpened object` A tab this call's execution opened that remains open at its end — the creation delta of the `tabs` inventory, not an event log.
from line 580
The `tab_id` of the opened tab, present in `tabs`. + maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ + - `type: "tab_opened"` - - `"tab_opened"` - - - `BrowserStateChangeDownloadStarted object { download_id, type, url }` + - `BrowserStateChangeDownloadStarted object` A file download that started during this call.
from line 592
The caller-assigned identifier for this download, stable across the state changes reporting it. + maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ + - `type: "download_started"` - - `"download_started"` - - `url: string` The final post-redirect URL the download was served from. - - `BrowserStateChangeDownloadCompleted object { download_id, type, url, 2 more }` + maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ + + - `BrowserStateChangeDownloadCompleted object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior
from line 613
The caller-assigned identifier for this download, stable across the state changes reporting it. + maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ + - `type: "download_completed"` - - `"download_completed"` - - `url: string` The final post-redirect URL the download was served from. + maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ + - `path: optional string or null` Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path. + pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096 + - `size_bytes: optional number or null` The completed download's size. - - `BrowserStateChangeDownloadFailed object { download_id, type, url, error }` + minimum: 0 + + - `BrowserStateChangeDownloadFailed object` A file download that failed — or was cancelled — during this call.
from line 643
The caller-assigned identifier for this download, stable across the state changes reporting it. + maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ + - `type: "download_failed"` - - `"download_failed"` - - `url: string` The final post-redirect URL the download was served from. + maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ + - `error: optional string or null` The failure or cancellation detail, when known. + pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096 + - `is_error: optional boolean` - `toolset_name: optional string or null` For a toolset member tool_result, the toolset family of the paired tool_use. - - `ServerToolUseBlockParam object { id, input, name, 3 more }` + maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ + + - `ServerToolUseBlockParam object` - `id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `input: map[unknown]` - `name: "web_search" or "web_fetch" or "code_execution" or 4 more`
from line 693
- `type: "server_tool_use"` - - `"server_tool_use"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block.
from line 701
Tool invocation directly from the model. - - `DirectCaller object { type }` + - `DirectCaller object` Tool invocation directly from the model. - - `ServerToolCaller object { tool_id, type }` + - `ServerToolCaller object` Tool invocation generated by a server-side tool. - - `ServerToolCaller20260120 object { tool_id, type }` - - - `WebSearchToolResultBlockParam object { content, tool_use_id, type, 2 more }` + - `ServerToolCaller20260120 object` + + - `WebSearchToolResultBlockParam object` - `content: WebSearchToolResultBlockParamContent`
from line 723
- `type: "web_search_result"` - - `"web_search_result"` - - `url: string` - `page_age: optional string or null` - - `WebSearchToolRequestError object { error_code, type }` + - `WebSearchToolRequestError object` - `error_code: WebSearchToolResultErrorCode`
from line 745
- `type: "web_search_tool_result_error"` - - `"web_search_tool_result_error"` - - `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "web_search_tool_result"` - - `"web_search_tool_result"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block.
from line 759
Tool invocation directly from the model. - - `DirectCaller object { type }` + - `DirectCaller object` Tool invocation directly from the model. - - `ServerToolCaller object { tool_id, type }` + - `ServerToolCaller object` Tool invocation generated by a server-side tool. - - `ServerToolCaller20260120 object { tool_id, type }` - - - `WebFetchToolResultBlockParam object { content, tool_use_id, type, 2 more }` + - `ServerToolCaller20260120 object` + + - `WebFetchToolResultBlockParam object` - `content: WebFetchToolResultErrorBlockParam or WebFetchBlockParam` - - `WebFetchToolResultErrorBlockParam object { error_code, type }` + - `WebFetchToolResultErrorBlockParam object` - `error_code: WebFetchToolResultErrorCode`
from line 797
- `type: "web_fetch_tool_result_error"` - - `"web_fetch_tool_result_error"` - - - `WebFetchBlockParam object { content, type, url, retrieved_at }` + - `WebFetchBlockParam object` - `content: DocumentBlockParam` - `type: "web_fetch_result"` - - `"web_fetch_result"` - - `url: string` Fetched content URL
from line 813
- `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "web_fetch_tool_result"` - - `"web_fetch_tool_result"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block.
from line 825
Tool invocation directly from the model. - - `DirectCaller object { type }` + - `DirectCaller object` Tool invocation directly from the model. - - `ServerToolCaller object { tool_id, type }` + - `ServerToolCaller object` Tool invocation generated by a server-side tool. - - `ServerToolCaller20260120 object { tool_id, type }` - - - `CodeExecutionToolResultBlockParam object { content, tool_use_id, type, cache_control }` + - `ServerToolCaller20260120 object` + + - `CodeExecutionToolResultBlockParam object` - `content: CodeExecutionToolResultBlockParamContent` Code execution result with encrypted stdout for PFC + web_search results. - - `CodeExecutionToolResultErrorParam object { error_code, type }` + - `CodeExecutionToolResultErrorParam object` - `error_code: CodeExecutionToolResultErrorCode`
from line 855
- `type: "code_execution_tool_result_error"` - - `"code_execution_tool_result_error"` - - - `CodeExecutionResultBlockParam object { content, return_code, stderr, 2 more }` + - `CodeExecutionResultBlockParam object` - `content: array of CodeExecutionOutputBlockParam`
from line 863
- `type: "code_execution_output"` - - `"code_execution_output"` - - `return_code: number` - `stderr: string`
from line 871
- `type: "code_execution_result"` - - `"code_execution_result"` - - - `EncryptedCodeExecutionResultBlockParam object { content, encrypted_stdout, return_code, 2 more }` + - `EncryptedCodeExecutionResultBlockParam object` Code execution result with encrypted stdout for PFC + web_search results.
from line 889
- `type: "encrypted_code_execution_result"` - - `"encrypted_code_execution_result"` - - `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "code_execution_tool_result"` - - `"code_execution_tool_result"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `BashCodeExecutionToolResultBlockParam object { content, tool_use_id, type, cache_control }` + - `BashCodeExecutionToolResultBlockParam object` - `content: BashCodeExecutionToolResultErrorParam or BashCodeExecutionResultBlockParam` - - `BashCodeExecutionToolResultErrorParam object { error_code, type }` + - `BashCodeExecutionToolResultErrorParam object` - `error_code: BashCodeExecutionToolResultErrorCode`
from line 919
- `type: "bash_code_execution_tool_result_error"` - - `"bash_code_execution_tool_result_error"` - - - `BashCodeExecutionResultBlockParam object { content, return_code, stderr, 2 more }` + - `BashCodeExecutionResultBlockParam object` - `content: array of BashCodeExecutionOutputBlockParam`
from line 927
- `type: "bash_code_execution_output"` - - `"bash_code_execution_output"` - - `return_code: number` - `stderr: string`
from line 935
- `type: "bash_code_execution_result"` - - `"bash_code_execution_result"` - - `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "bash_code_execution_tool_result"` - - `"bash_code_execution_tool_result"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `TextEditorCodeExecutionToolResultBlockParam object { content, tool_use_id, type, cache_control }` + - `TextEditorCodeExecutionToolResultBlockParam object` - `content: TextEditorCodeExecutionToolResultErrorParam or TextEditorCodeExecutionViewResultBlockParam or TextEditorCodeExecutionCreateResultBlockParam or TextEditorCodeExecutionStrReplaceResultBlockParam` - - `TextEditorCodeExecutionToolResultErrorParam object { error_code, type, error_message }` + - `TextEditorCodeExecutionToolResultErrorParam object` - `error_code: TextEditorCodeExecutionToolResultErrorCode`
from line 965
- `type: "text_editor_code_execution_tool_result_error"` - - `"text_editor_code_execution_tool_result_error"` - - `error_message: optional string or null` - - `TextEditorCodeExecutionViewResultBlockParam object { content, file_type, type, 3 more }` + - `TextEditorCodeExecutionViewResultBlockParam object` - `content: string`
from line 981
- `type: "text_editor_code_execution_view_result"` - - `"text_editor_code_execution_view_result"` - - `num_lines: optional number or null` - `start_line: optional number or null` - `total_lines: optional number or null` - - `TextEditorCodeExecutionCreateResultBlockParam object { is_file_update, type }` + - `TextEditorCodeExecutionCreateResultBlockParam object` - `is_file_update: boolean` - `type: "text_editor_code_execution_create_result"` - - `"text_editor_code_execution_create_result"` - - - `TextEditorCodeExecutionStrReplaceResultBlockParam object { type, lines, new_lines, 3 more }` + - `TextEditorCodeExecutionStrReplaceResultBlockParam object` - `type: "text_editor_code_execution_str_replace_result"` - - `"text_editor_code_execution_str_replace_result"` - - `lines: optional array of string or null` - `new_lines: optional number or null`
from line 1009
- `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "text_editor_code_execution_tool_result"` - - `"text_editor_code_execution_tool_result"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `ToolSearchToolResultBlockParam object { content, tool_use_id, type, cache_control }` + - `ToolSearchToolResultBlockParam object` - `content: ToolSearchToolResultErrorParam or ToolSearchToolSearchResultBlockParam` - - `ToolSearchToolResultErrorParam object { error_code, type, error_message }` + - `ToolSearchToolResultErrorParam object` - `error_code: ToolSearchToolResultErrorCode`
from line 1035
- `type: "tool_search_tool_result_error"` - - `"tool_search_tool_result_error"` - - `error_message: optional string or null` - - `ToolSearchToolSearchResultBlockParam object { tool_references, type }` + - `ToolSearchToolSearchResultBlockParam object` - `tool_references: array of ToolReferenceBlockParam` - `tool_name: string` + maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ + - `type: "tool_reference"` - `cache_control: optional CacheControlEphemeral or null`
from line 1053
- `type: "tool_search_tool_search_result"` - - `"tool_search_tool_search_result"` - - `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "tool_search_tool_result"` - - `"tool_search_tool_result"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `ContainerUploadBlockParam object { file_id, type, cache_control }` + - `ContainerUploadBlockParam object` 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.
from line 1072
- `type: "container_upload"` - - `"container_upload"` - - `cache_control: optional CacheControlEphemeral or null` Create a cache control breakpoint at this content block.
from line 1166
Container identifier for reuse across requests. - - `ContainerParams object { id, skills }` + - `ContainerParams object` Container parameters with skills to be loaded.
from line 1178
List of skills to load in the container + maxItems: 20 + - `skill_id: string` Skill ID + maxLength: 64, minLength: 1 + - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
from line 1198
Skill version or 'latest' for most recent version + maxLength: 64, minLength: 1 + - `string` - `inference_geo: optional string or null`
from line 1216
This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number. + maxLength: 512 + - `output_config: optional OutputConfig` Configuration options for the model's output, such as the output format.
from line 1246
- `type: "json_schema"` - - `"json_schema"` - - `service_tier: optional "auto" or "standard_only"` Determines whether to use priority capacity (if available) or standard capacity for this request.
from line 1282
- `text: string` + minLength: 1 + - `type: "text"` - `cache_control: optional CacheControlEphemeral or null`
from line 1292
- `citations: optional array of TextCitationParam or null` - - `temperature: optional number` - - 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. - - `thinking: optional ThinkingConfigParam` Configuration for enabling Claude's extended thinking.
from line 1300
See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - - `ThinkingConfigEnabled object { budget_tokens, type, display }` + - `ThinkingConfigEnabled object` - `budget_tokens: number`
from line 1310
See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. + minimum: 1024 + - `type: "enabled"` - - `"enabled"` - - `display: optional "summarized" or "omitted" or null` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to `summarized`.
from line 1322
- `"omitted"` - - `ThinkingConfigDisabled object { type }` + - `ThinkingConfigDisabled object` - `type: "disabled"` - - `"disabled"` - - - `ThinkingConfigAdaptive object { type, display }` + - `ThinkingConfigAdaptive object` - `type: "adaptive"` - - `"adaptive"` - - `display: optional "summarized" or "omitted" or null` Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to `summarized`.
from line 1342
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. - - `ToolChoiceAuto object { type, disable_parallel_tool_use }` + - `ToolChoiceAuto object` The model will automatically decide whether to use tools. - `type: "auto"` - - `"auto"` - - `disable_parallel_tool_use: optional boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. - - `ToolChoiceAny object { type, disable_parallel_tool_use }` + - `ToolChoiceAny object` The model will use any available tools. - `type: "any"` - - `"any"` - - `disable_parallel_tool_use: optional boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - - `ToolChoiceTool object { name, type, disable_parallel_tool_use }` + - `ToolChoiceTool object` The model will use the specified tool with `tool_choice.name`.
from line 1376
- `type: "tool"` - - `"tool"` - - `disable_parallel_tool_use: optional boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. - - `ToolChoiceNone object { type }` + - `ToolChoiceNone object` The model will not be allowed to use tools. - `type: "none"` - - - `"none"` - `tools: optional array of ToolUnion`
from line 1452
See our [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) for more details. - - `Tool object { input_schema, name, allowed_callers, 7 more }` - - - `input_schema: object { type, properties, required }` + - `Tool object` + + - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input.
from line 1462
- `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 1472
This is how the tool will be called by the model and in `tool_use` blocks. + maxLength: 128, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,128}$ + - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 1510
- `type: optional "custom" or null` - - `"custom"` - - - `ToolBash20250124 object { name, type, allowed_callers, 4 more }` + - `ToolBash20250124 object` - `name: "bash"`
from line 1518
This is how the tool will be called by the model and in `tool_use` blocks. - - `"bash"` - - `type: "bash_20250124"` - - `"bash_20250124"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 1544
When true, guarantees schema validation on tool names and inputs - - `CodeExecutionTool20250522 object { name, type, allowed_callers, 3 more }` + - `CodeExecutionTool20250522 object` - `name: "code_execution"`
from line 1552
This is how the tool will be called by the model and in `tool_use` blocks. - - `"code_execution"` - - `type: "code_execution_20250522"` - - `"code_execution_20250522"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 1576
When true, guarantees schema validation on tool names and inputs - - `CodeExecutionTool20250825 object { name, type, allowed_callers, 3 more }` + - `CodeExecutionTool20250825 object` - `name: "code_execution"`
from line 1584
This is how the tool will be called by the model and in `tool_use` blocks. - - `"code_execution"` - - `type: "code_execution_20250825"` + - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` + + - `"direct"` + - `"code_execution_20250825"` + - `"code_execution_20260120"` + + - `"code_execution_20260521"` + + - `cache_control: optional CacheControlEphemeral or null` + + Create a cache control breakpoint at this content block. + + - `defer_loading: optional boolean` + + If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. + + - `strict: optional boolean` + + When true, guarantees schema validation on tool names and inputs + + - `CodeExecutionTool20260120 object` + + Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). + + - `name: "code_execution"` + + Name of the tool. + + This is how the tool will be called by the model and in `tool_use` blocks. + + - `type: "code_execution_20260120"` + - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 1642
When true, guarantees schema validation on tool names and inputs - - `CodeExecutionTool20260120 object { name, type, allowed_callers, 3 more }` - - Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). + - `CodeExecutionTool20260521 object` + + Code execution tool with REPL state persistence. - `name: "code_execution"`
from line 1652
This is how the tool will be called by the model and in `tool_use` blocks. - - `"code_execution"` - - - `type: "code_execution_20260120"` + - `type: "code_execution_20260521"` + + - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` + + - `"direct"` + + - `"code_execution_20250825"` - `"code_execution_20260120"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - - - `"direct"` - - - `"code_execution_20250825"` - - - `"code_execution_20260120"` - - `"code_execution_20260521"` - `cache_control: optional CacheControlEphemeral or null`
from line 1676
When true, guarantees schema validation on tool names and inputs - - `CodeExecutionTool20260521 object { name, type, allowed_callers, 3 more }` - - Code execution tool with REPL state persistence. - - - `name: "code_execution"` - - Name of the tool. - - This is how the tool will be called by the model and in `tool_use` blocks. - - - `"code_execution"` - - - `type: "code_execution_20260521"` - - - `"code_execution_20260521"` - - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - - - `"direct"` - - - `"code_execution_20250825"` - - - `"code_execution_20260120"` - - - `"code_execution_20260521"` - - - `cache_control: optional CacheControlEphemeral or null` - - Create a cache control breakpoint at this content block. - - - `defer_loading: optional boolean` - - If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - - - `strict: optional boolean` - - When true, guarantees schema validation on tool names and inputs - - - `BrowserToolset20260801 object { type, allowed_callers, cache_control, configs }` + - `BrowserToolset20260801 object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served
from line 1684
from its schema. - `type: "browser_toolset_20260801"` - - - `"browser_toolset_20260801"` - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"`
from line 2080
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - - `MemoryTool20250818 object { name, type, allowed_callers, 4 more }` + - `MemoryTool20250818 object` - `name: "memory"`
from line 2088
This is how the tool will be called by the model and in `tool_use` blocks. - - `"memory"` - - `type: "memory_20250818"` - - `"memory_20250818"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2114
When true, guarantees schema validation on tool names and inputs - - `ComputerToolset20260801 object { type, allowed_callers, cache_control, configs }` + - `ComputerToolset20260801 object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is
from line 2127
- `type: "computer_toolset_20260801"` - - `"computer_toolset_20260801"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2354
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - - `ToolTextEditor20250124 object { name, type, allowed_callers, 4 more }` + - `ToolTextEditor20250124 object` - `name: "str_replace_editor"`
from line 2362
This is how the tool will be called by the model and in `tool_use` blocks. - - `"str_replace_editor"` - - `type: "text_editor_20250124"` - - `"text_editor_20250124"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2388
When true, guarantees schema validation on tool names and inputs - - `ToolTextEditor20250429 object { name, type, allowed_callers, 4 more }` + - `ToolTextEditor20250429 object` - `name: "str_replace_based_edit_tool"`
from line 2396
This is how the tool will be called by the model and in `tool_use` blocks. - - `"str_replace_based_edit_tool"` - - `type: "text_editor_20250429"` - - `"text_editor_20250429"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2422
When true, guarantees schema validation on tool names and inputs - - `ToolTextEditor20250728 object { name, type, allowed_callers, 5 more }` + - `ToolTextEditor20250728 object` - `name: "str_replace_based_edit_tool"`
from line 2430
This is how the tool will be called by the model and in `tool_use` blocks. - - `"str_replace_based_edit_tool"` - - `type: "text_editor_20250728"` - - `"text_editor_20250728"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2456
Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. + minimum: 1 + - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - - `WebSearchTool20250305 object { name, type, allowed_callers, 7 more }` + - `WebSearchTool20250305 object` - `name: "web_search"`
from line 2470
This is how the tool will be called by the model and in `tool_use` blocks. - - `"web_search"` - - `type: "web_search_20250305"` - - `"web_search_20250305"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2502
Maximum number of times the tool can be used in the API request. + exclusiveMinimum: 0 + - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs
from line 2514
- `type: "approximate"` - - `"approximate"` - - `city: optional string or null` The city of the user. + maxLength: 255, minLength: 1 + - `country: optional string or null` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. + maxLength: 2, minLength: 2 + - `region: optional string or null` The region of the user. + maxLength: 255, minLength: 1 + - `timezone: optional string or null` The [IANA timezone](https://nodatime.org/TimeZones) of the user. - - `WebFetchTool20250910 object { name, type, allowed_callers, 8 more }` + maxLength: 255, minLength: 1 + + - `WebFetchTool20250910 object` - `name: "web_fetch"`
from line 2546
This is how the tool will be called by the model and in `tool_use` blocks. - - `"web_fetch"` - - `type: "web_fetch_20250910"` - - `"web_fetch_20250910"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2582
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. + exclusiveMinimum: 0 + - `max_uses: optional number or null` Maximum number of times the tool can be used in the API request. + exclusiveMinimum: 0 + - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - - `WebSearchTool20260209 object { name, type, allowed_callers, 7 more }` + - `WebSearchTool20260209 object` - `name: "web_search"`
from line 2602
This is how the tool will be called by the model and in `tool_use` blocks. - - `"web_search"` - - `type: "web_search_20260209"` - - `"web_search_20260209"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2634
Maximum number of times the tool can be used in the API request. + exclusiveMinimum: 0 + - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs
from line 2644
Parameters for the user's location. Used to provide more relevant search results. - - `WebFetchTool20260209 object { name, type, allowed_callers, 8 more }` + - `WebFetchTool20260209 object` - `name: "web_fetch"`
from line 2652
This is how the tool will be called by the model and in `tool_use` blocks. - - `"web_fetch"` - - `type: "web_fetch_20260209"` - - `"web_fetch_20260209"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2688
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. + exclusiveMinimum: 0 + - `max_uses: optional number or null` Maximum number of times the tool can be used in the API request. + exclusiveMinimum: 0 + - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - - `WebFetchTool20260309 object { name, type, allowed_callers, 9 more }` + - `WebFetchTool20260309 object` Web fetch tool with use_cache parameter for bypassing cached content.
from line 2710
This is how the tool will be called by the model and in `tool_use` blocks. - - `"web_fetch"` - - `type: "web_fetch_20260309"` - - `"web_fetch_20260309"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2746
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. + exclusiveMinimum: 0 + - `max_uses: optional number or null` Maximum number of times the tool can be used in the API request. + exclusiveMinimum: 0 + - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs
from line 2762
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. - - `WebSearchTool20260318 object { name, type, allowed_callers, 8 more }` + - `WebSearchTool20260318 object` - `name: "web_search"`
from line 2770
This is how the tool will be called by the model and in `tool_use` blocks. - - `"web_search"` - - `type: "web_search_20260318"` - - `"web_search_20260318"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2802
Maximum number of times the tool can be used in the API request. + exclusiveMinimum: 0 + - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn.
from line 2820
Parameters for the user's location. Used to provide more relevant search results. - - `WebFetchTool20260318 object { name, type, allowed_callers, 10 more }` + - `WebFetchTool20260318 object` - `name: "web_fetch"`
from line 2828
This is how the tool will be called by the model and in `tool_use` blocks. - - `"web_fetch"` - - `type: "web_fetch_20260318"` - - `"web_fetch_20260318"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2864
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. + exclusiveMinimum: 0 + - `max_uses: optional number or null` Maximum number of times the tool can be used in the API request. + exclusiveMinimum: 0 + - `response_inclusion: optional "full" or "excluded"` How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn.
from line 2888
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. - - `ToolSearchToolBm25_20251119 object { name, type, allowed_callers, 3 more }` + - `ToolSearchToolBm25_20251119 object` - `name: "tool_search_tool_bm25"`
from line 2896
This is how the tool will be called by the model and in `tool_use` blocks. + - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` + + - `"tool_search_tool_bm25_20251119"` + - `"tool_search_tool_bm25"` - - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - - - `"tool_search_tool_bm25_20251119"` - - - `"tool_search_tool_bm25"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2924
When true, guarantees schema validation on tool names and inputs - - `ToolSearchToolRegex20251119 object { name, type, allowed_callers, 3 more }` + - `ToolSearchToolRegex20251119 object` - `name: "tool_search_tool_regex"`
from line 2932
This is how the tool will be called by the model and in `tool_use` blocks. + - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` + + - `"tool_search_tool_regex_20251119"` + - `"tool_search_tool_regex"` - - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - - - `"tool_search_tool_regex_20251119"` - - - `"tool_search_tool_regex"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
from line 2960
When true, guarantees schema validation on tool names and inputs + - `temperature: optional number` + + **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not support setting temperature. A value of 1.0 of 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. + + maximum: 1, minimum: 0 + - `top_k: optional number` + **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not accept top_k; any value will be rejected with a 400 error. + Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277). Recommended for advanced use cases only. + minimum: 0 + - `top_p: optional number` + **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not support setting top_p. A value >= 0.99 will be accepted for backwards compatibility, all other values will be rejected with a 400 error. + Use nucleus sampling. In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`. Recommended for advanced use cases only. -### Returns - -- `MessageBatch object { id, archived_at, cancel_initiated_at, 7 more }` + maximum: 1, minimum: 0 + +## Returns + +- `MessageBatch object` - `id: string`
from line 3010
RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. + format: date-time + - `cancel_initiated_at: string or null` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. + format: date-time + - `created_at: string` RFC 3339 datetime string representing the time at which the Message Batch was created. + format: date-time + - `ended_at: string or null` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. + format: date-time + - `expires_at: string` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. + format: date-time + - `processing_status: "in_progress" or "canceling" or "ended"` Processing status of the Message Batch.
from line 3060
This is zero until processing of the entire Message Batch has ended. + default: 0 + - `errored: number` 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: number` 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: number` Number of requests in the Message Batch that are processing. + default: 0 + - `succeeded: number` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. + default: 0 + - `results_url: string or null` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends.
from line 3104
For Message Batches, this is always `"message_batch"`. - - `"message_batch"` - -### Example - -```http + default: message_batch + +## Example + +```bash curl https://api.anthropic.com/v1/messages/batches \ -H 'Content-Type: application/json' \ -H 'anthropic-version: 2023-06-01' \
from line 3132
}' ``` -#### Response +### Response (200) ```json {