Create a Message
api/beta/messages/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/beta/messages/create Changed · +984 / -690 lines
# Create a Message ## Headers ## Body parameters ## Returns ## Example ### Response (200) ## Create a Message ### 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.
---- -title: Create a Message -url: https://platform.claude.com/docs/en/api/beta/messages/create ---- - -## Create a Message - -**post** `/v1/messages` +# Create a Message + +**POST** `/v1/messages` Send a structured list of input messages with text and/or image content, and the model will generate the next message in the conversation.
Learn more about the Messages API in our [user guide](https://platform.claude.com/docs/en/get-started) -### Header Parameters +## Headers - `"anthropic-beta": optional array of AnthropicBeta`
The user profile ID to attribute this request to. Use when acting on behalf of a party other than your organization. Requires the `user-profiles` beta header. -### Body Parameters +## Body parameters - `max_tokens: number`
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 BetaMessageParam`
- `array of BetaContentBlockParam` - - `BetaTextBlockParam object { text, type, cache_control, citations }` + - `BetaTextBlockParam object` - `text: string` + minLength: 1 + - `type: "text"` - - `"text"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - - - `"ephemeral"` - `ttl: optional "5m" or "1h"`
- `citations: optional array of BetaTextCitationParam or null` - - `BetaCitationCharLocationParam object { cited_text, document_index, document_title, 3 more }` + - `BetaCitationCharLocationParam 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"` - - - `BetaCitationPageLocationParam object { cited_text, document_index, document_title, 3 more }` + - `BetaCitationPageLocationParam 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"` - - - `BetaCitationContentBlockLocationParam object { cited_text, document_index, document_title, 3 more }` + - `BetaCitationContentBlockLocationParam object` - `cited_text: string`
- `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.
0-based index of the first cited block in the source's `content` array. + minimum: 0 + - `type: "content_block_location"` - - `"content_block_location"` - - - `BetaCitationWebSearchResultLocationParam object { cited_text, encrypted_index, title, 2 more }` + - `BetaCitationWebSearchResultLocationParam object` - `cited_text: string`
- `title: string or null` + maxLength: 512, minLength: 1 + - `type: "web_search_result_location"` - - `"web_search_result_location"` - - `url: string` - - `BetaCitationSearchResultLocationParam object { cited_text, end_block_index, search_result_index, 4 more }` + minLength: 1 + + - `BetaCitationSearchResultLocationParam object` - `cited_text: string`
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"` - - - `BetaImageBlockParam object { source, type, cache_control, transformations }` + - `BetaImageBlockParam object` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - - `BetaBase64ImageSource object { data, media_type, type }` + - `BetaBase64ImageSource object` - `data: string` + format: byte + - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"`
- `type: "base64"` - - `"base64"` - - - `BetaURLImageSource object { type, url }` + - `BetaURLImageSource object` - `type: "url"` - - `"url"` - - `url: string` - - `BetaFileImageSource object { file_id, type }` + - `BetaFileImageSource object` - `file_id: string` - `type: "file"` - - `"file"` - - `type: "image"` - - `"image"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block.
- `"error"` - - `BetaRequestDocumentBlock object { source, type, cache_control, 3 more }` + - `BetaRequestDocumentBlock object` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - - `BetaBase64PDFSource object { data, media_type, type }` + - `BetaBase64PDFSource object` - `data: string` + format: byte + - `media_type: "application/pdf"` - - `"application/pdf"` - - `type: "base64"` - - `"base64"` - - - `BetaPlainTextSource object { data, media_type, type }` + - `BetaPlainTextSource object` - `data: string` - `media_type: "text/plain"` - - `"text/plain"` - - `type: "text"` - - `"text"` - - - `BetaContentBlockSource object { content, type }` + - `BetaContentBlockSource object` - `content: string or array of BetaContentBlockSourceContent`
- `BetaContentBlockSourceContent = array of BetaContentBlockSourceContent` - - `BetaTextBlockParam object { text, type, cache_control, citations }` - - - `BetaImageBlockParam object { source, type, cache_control, transformations }` + - `BetaTextBlockParam object` + + - `BetaImageBlockParam object` - `type: "content"` - - `"content"` - - - `BetaURLPDFSource object { type, url }` + - `BetaURLPDFSource object` - `type: "url"` - - `"url"` - - `url: string` - - `BetaFileDocumentSource object { file_id, type }` + - `BetaFileDocumentSource object` - `file_id: string` - `type: "file"` - - `"file"` - - `type: "document"` - - `"document"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block.
- `context: optional string or null` + minLength: 1 + - `title: optional string or null` - - `BetaSearchResultBlockParam object { content, source, title, 3 more }` + maxLength: 500, minLength: 1 + + - `BetaSearchResultBlockParam object` - `content: array of BetaTextBlockParam` - `text: string` + minLength: 1 + - `type: "text"` - `cache_control: optional BetaCacheControlEphemeral or null`
- `type: "search_result"` - - `"search_result"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam` - - `BetaThinkingBlockParam object { signature, thinking, type }` + - `BetaThinkingBlockParam object` - `signature: string`
- `type: "thinking"` - - `"thinking"` - - - `BetaRedactedThinkingBlockParam object { data, type }` + - `BetaRedactedThinkingBlockParam object` - `data: string`
- `type: "redacted_thinking"` - - `"redacted_thinking"` - - - `BetaToolUseBlockParam object { id, input, name, 4 more }` + - `BetaToolUseBlockParam 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 BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block.
Tool invocation directly from the model. - - `BetaDirectCaller object { type }` + - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - - `"direct"` - - - `BetaServerToolCaller object { tool_id, type }` + - `BetaServerToolCaller 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"` - - - `BetaServerToolCaller20260120 object { tool_id, type }` + - `BetaServerToolCaller20260120 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. - - `BetaToolResultBlockParam object { tool_use_id, type, cache_control, 3 more }` + maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ + + - `BetaToolResultBlockParam object` - `tool_use_id: string` + pattern: ^[a-zA-Z0-9_-]+$ + - `type: "tool_result"` - - `"tool_result"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block.
- `array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - - `BetaTextBlockParam object { text, type, cache_control, citations }` - - - `BetaImageBlockParam object { source, type, cache_control, transformations }` - - - `BetaSearchResultBlockParam object { content, source, title, 3 more }` - - - `BetaRequestDocumentBlock object { source, type, cache_control, 3 more }` - - - `BetaToolReferenceBlockParam object { tool_name, type, cache_control }` + - `BetaTextBlockParam object` + + - `BetaImageBlockParam object` + + - `BetaSearchResultBlockParam object` + + - `BetaRequestDocumentBlock object` + + - `BetaToolReferenceBlockParam 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 BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `BetaBrowserStateBlockParam object { tabs, type, cache_control, state_changes }` + - `BetaBrowserStateBlockParam 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
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 BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block.
Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. - - `BetaBrowserStateChangeTabOpened object { tab_id, type }` + maxItems: 200, minItems: 1 + + - `BetaBrowserStateChangeTabOpened 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.
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"` - - - `BetaBrowserStateChangeDownloadStarted object { download_id, type, url }` + - `BetaBrowserStateChangeDownloadStarted object` A file download that started during this call.
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. - - `BetaBrowserStateChangeDownloadCompleted object { download_id, type, url, 2 more }` + maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ + + - `BetaBrowserStateChangeDownloadCompleted object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior
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]*$, maxLength: 4096 + - `size_bytes: optional number or null` The completed download's size. - - `BetaBrowserStateChangeDownloadFailed object { download_id, type, url, error }` + minimum: 0 + + - `BetaBrowserStateChangeDownloadFailed object` A file download that failed — or was cancelled — during this call.
The caller-assigned identifier for this download, stable across the state changes reporting it. + maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ + - `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]*$, maxLength: 4096 + - `is_error: optional boolean` - `toolset_name: optional string or null` For a toolset member tool_result, the toolset family of the paired tool_use. - - `BetaServerToolUseBlockParam object { id, input, name, 3 more }` + maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ + + - `BetaServerToolUseBlockParam object` - `id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more`
- `type: "server_tool_use"` - - `"server_tool_use"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block.
Tool invocation directly from the model. - - `BetaDirectCaller object { type }` + - `BetaDirectCaller object` Tool invocation directly from the model. - - `BetaServerToolCaller object { tool_id, type }` + - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - - `BetaServerToolCaller20260120 object { tool_id, type }` - - - `BetaWebSearchToolResultBlockParam object { content, tool_use_id, type, 2 more }` + - `BetaServerToolCaller20260120 object` + + - `BetaWebSearchToolResultBlockParam object` - `content: BetaWebSearchToolResultBlockParamContent`
- `type: "web_search_result"` - - `"web_search_result"` - - `url: string` - `page_age: optional string or null` - - `BetaWebSearchToolRequestError object { error_code, type }` + - `BetaWebSearchToolRequestError object` - `error_code: BetaWebSearchToolResultErrorCode`
- `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 BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block.
Tool invocation directly from the model. - - `BetaDirectCaller object { type }` + - `BetaDirectCaller object` Tool invocation directly from the model. - - `BetaServerToolCaller object { tool_id, type }` + - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - - `BetaServerToolCaller20260120 object { tool_id, type }` - - - `BetaWebFetchToolResultBlockParam object { content, tool_use_id, type, 2 more }` + - `BetaServerToolCaller20260120 object` + + - `BetaWebFetchToolResultBlockParam object` - `content: BetaWebFetchToolResultErrorBlockParam or BetaWebFetchBlockParam` - - `BetaWebFetchToolResultErrorBlockParam object { error_code, type }` + - `BetaWebFetchToolResultErrorBlockParam object` - `error_code: BetaWebFetchToolResultErrorCode`
- `type: "web_fetch_tool_result_error"` - - `"web_fetch_tool_result_error"` - - - `BetaWebFetchBlockParam object { content, type, url, retrieved_at }` + - `BetaWebFetchBlockParam object` - `content: BetaRequestDocumentBlock` - `type: "web_fetch_result"` - - `"web_fetch_result"` - - `url: string` Fetched content URL
- `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "web_fetch_tool_result"` - - `"web_fetch_tool_result"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block.
Tool invocation directly from the model. - - `BetaDirectCaller object { type }` + - `BetaDirectCaller object` Tool invocation directly from the model. - - `BetaServerToolCaller object { tool_id, type }` + - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - - `BetaServerToolCaller20260120 object { tool_id, type }` - - - `BetaAdvisorToolResultBlockParam object { content, tool_use_id, type, cache_control }` + - `BetaServerToolCaller20260120 object` + + - `BetaAdvisorToolResultBlockParam object` - `content: BetaAdvisorToolResultErrorParam or BetaAdvisorResultBlockParam or BetaAdvisorRedactedResultBlockParam` - - `BetaAdvisorToolResultErrorParam object { error_code, type }` + - `BetaAdvisorToolResultErrorParam object` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more`
- `type: "advisor_tool_result_error"` - - `"advisor_tool_result_error"` - - - `BetaAdvisorResultBlockParam object { text, type, stop_reason }` + - `BetaAdvisorResultBlockParam object` - `text: string` - `type: "advisor_result"` - - `"advisor_result"` - - `stop_reason: optional string or null` - - `BetaAdvisorRedactedResultBlockParam object { encrypted_content, type, stop_reason }` + - `BetaAdvisorRedactedResultBlockParam object` - `encrypted_content: string`
- `type: "advisor_redacted_result"` - - `"advisor_redacted_result"` - - `stop_reason: optional string or null` - `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "advisor_tool_result"` - - `"advisor_tool_result"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `BetaCodeExecutionToolResultBlockParam object { content, tool_use_id, type, cache_control }` + - `BetaCodeExecutionToolResultBlockParam object` - `content: BetaCodeExecutionToolResultBlockParamContent` Code execution result with encrypted stdout for PFC + web_search results. - - `BetaCodeExecutionToolResultErrorParam object { error_code, type }` + - `BetaCodeExecutionToolResultErrorParam object` - `error_code: BetaCodeExecutionToolResultErrorCode`
- `type: "code_execution_tool_result_error"` - - `"code_execution_tool_result_error"` - - - `BetaCodeExecutionResultBlockParam object { content, return_code, stderr, 2 more }` + - `BetaCodeExecutionResultBlockParam object` - `content: array of BetaCodeExecutionOutputBlockParam`
- `type: "code_execution_output"` - - `"code_execution_output"` - - `return_code: number` - `stderr: string`
- `type: "code_execution_result"` - - `"code_execution_result"` - - - `BetaEncryptedCodeExecutionResultBlockParam object { content, encrypted_stdout, return_code, 2 more }` + - `BetaEncryptedCodeExecutionResultBlockParam object` Code execution result with encrypted stdout for PFC + web_search results.
- `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 BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `BetaBashCodeExecutionToolResultBlockParam object { content, tool_use_id, type, cache_control }` + - `BetaBashCodeExecutionToolResultBlockParam object` - `content: BetaBashCodeExecutionToolResultErrorParam or BetaBashCodeExecutionResultBlockParam` - - `BetaBashCodeExecutionToolResultErrorParam object { error_code, type }` + - `BetaBashCodeExecutionToolResultErrorParam object` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more`
- `type: "bash_code_execution_tool_result_error"` - - `"bash_code_execution_tool_result_error"` - - - `BetaBashCodeExecutionResultBlockParam object { content, return_code, stderr, 2 more }` + - `BetaBashCodeExecutionResultBlockParam object` - `content: array of BetaBashCodeExecutionOutputBlockParam`
- `type: "bash_code_execution_output"` - - `"bash_code_execution_output"` - - `return_code: number` - `stderr: string`
- `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 BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `BetaTextEditorCodeExecutionToolResultBlockParam object { content, tool_use_id, type, cache_control }` + - `BetaTextEditorCodeExecutionToolResultBlockParam object` - `content: BetaTextEditorCodeExecutionToolResultErrorParam or BetaTextEditorCodeExecutionViewResultBlockParam or BetaTextEditorCodeExecutionCreateResultBlockParam or BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - - `BetaTextEditorCodeExecutionToolResultErrorParam object { error_code, type, error_message }` + - `BetaTextEditorCodeExecutionToolResultErrorParam object` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more`
- `type: "text_editor_code_execution_tool_result_error"` - - `"text_editor_code_execution_tool_result_error"` - - `error_message: optional string or null` - - `BetaTextEditorCodeExecutionViewResultBlockParam object { content, file_type, type, 3 more }` + - `BetaTextEditorCodeExecutionViewResultBlockParam object` - `content: string`
- `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` - - `BetaTextEditorCodeExecutionCreateResultBlockParam object { is_file_update, type }` + - `BetaTextEditorCodeExecutionCreateResultBlockParam object` - `is_file_update: boolean` - `type: "text_editor_code_execution_create_result"` - - `"text_editor_code_execution_create_result"` - - - `BetaTextEditorCodeExecutionStrReplaceResultBlockParam object { type, lines, new_lines, 3 more }` + - `BetaTextEditorCodeExecutionStrReplaceResultBlockParam 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`
- `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 BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `BetaToolSearchToolResultBlockParam object { content, tool_use_id, type, cache_control }` + - `BetaToolSearchToolResultBlockParam object` - `content: BetaToolSearchToolResultErrorParam or BetaToolSearchToolSearchResultBlockParam` - - `BetaToolSearchToolResultErrorParam object { error_code, type, error_message }` + - `BetaToolSearchToolResultErrorParam object` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"`
- `type: "tool_search_tool_result_error"` - - `"tool_search_tool_result_error"` - - `error_message: optional string or null` - - `BetaToolSearchToolSearchResultBlockParam object { tool_references, type }` + - `BetaToolSearchToolSearchResultBlockParam object` - `tool_references: array of BetaToolReferenceBlockParam` - `tool_name: string` + maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ + - `type: "tool_reference"` - `cache_control: optional BetaCacheControlEphemeral or null`
- `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 BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `BetaMCPToolUseBlockParam object { id, input, name, 3 more }` + - `BetaMCPToolUseBlockParam object` - `id: string` + pattern: ^[a-zA-Z0-9_-]+$ + - `input: map[unknown]` - `name: string`
- `type: "mcp_tool_use"` - - `"mcp_tool_use"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `BetaRequestMCPToolResultBlockParam object { tool_use_id, type, cache_control, 2 more }` + - `BetaRequestMCPToolResultBlockParam object` - `tool_use_id: string` + pattern: ^[a-zA-Z0-9_-]+$ + - `type: "mcp_tool_result"` - - `"mcp_tool_result"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block.
- `text: string` + minLength: 1 + - `type: "text"` - `cache_control: optional BetaCacheControlEphemeral or null`
- `is_error: optional boolean` - - `BetaContainerUploadBlockParam object { file_id, type, cache_control }` + - `BetaContainerUploadBlockParam 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.
- `type: "container_upload"` - - `"container_upload"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `BetaCompactionBlockParam object { type, cache_control, content, encrypted_content }` + - `BetaCompactionBlockParam object` A compaction block containing summary of previous context.
- `type: "compaction"` - - `"compaction"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block.
Opaque metadata from prior compaction, to be round-tripped verbatim - - `BetaRequestToolAdditionBlock object { tool, type, cache_control }` + - `BetaRequestToolAdditionBlock object` Mid-conversation directive to surface a declared tool.
server assigns to MCP-resolved tools — use `mcp_tool_reference` or `mcp_toolset_reference` for those. - - `BetaToolChangeToolReference object { name, type }` + - `BetaToolChangeToolReference object` Reference to a single tool the caller declared directly in `tools[]`. Does not accept the composed `{server}_{name}` form the
- `name: string` + pattern: ^[a-zA-Z0-9_-]{1,128}$ + - `type: "tool_reference"` - - `"tool_reference"` - - - `BetaToolChangeMCPToolReference object { name, server_name, type }` + - `BetaToolChangeMCPToolReference object` Reference to a single MCP tool by its server and remote name — the same `server_name`/`name` pair `mcp_tool_use` carries.
- `type: "mcp_tool_reference"` - - `"mcp_tool_reference"` - - - `BetaToolChangeMCPToolsetReference object { server_name, type }` + - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset.
- `type: "mcp_toolset_reference"` - - `"mcp_toolset_reference"` - - `type: "tool_addition"` - - `"tool_addition"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `BetaRequestToolRemovalBlock object { tool, type, cache_control }` + - `BetaRequestToolRemovalBlock object` Mid-conversation directive to withdraw a tool.
server assigns to MCP-resolved tools — use `mcp_tool_reference` or `mcp_toolset_reference` for those. - - `BetaToolChangeToolReference object { name, type }` + - `BetaToolChangeToolReference object` Reference to a single tool the caller declared directly in `tools[]`. Does not accept the composed `{server}_{name}` form the server assigns to MCP-resolved tools — use `mcp_tool_reference` or `mcp_toolset_reference` for those. - - `BetaToolChangeMCPToolReference object { name, server_name, type }` + - `BetaToolChangeMCPToolReference object` Reference to a single MCP tool by its server and remote name — the same `server_name`/`name` pair `mcp_tool_use` carries. - - `BetaToolChangeMCPToolsetReference object { server_name, type }` + - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `type: "tool_removal"` - - `"tool_removal"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - - `BetaFallbackBlockParam object { from, to, type, trigger }` + - `BetaFallbackBlockParam object` A `fallback` block echoed back from a prior response.
- `type: "fallback"` - - `"fallback"` - - `trigger: optional unknown` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed.
Container identifier for reuse across requests. - - `BetaContainerParams object { id, skills }` + - `BetaContainerParams object` Container parameters with skills to be loaded.
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)
Skill version or 'latest' for most recent version + maxLength: 64, minLength: 1 + - `string` - `context_management: optional BetaContextManagementConfig or null`
List of context management edits to apply - - `BetaClearToolUses20250919Edit object { type, clear_at_least, clear_tool_inputs, 3 more }` + minItems: 0 + + - `BetaClearToolUses20250919Edit object` - `type: "clear_tool_uses_20250919"` - - `"clear_tool_uses_20250919"` - - `clear_at_least: optional BetaInputTokensClearAtLeast or null` Minimum number of tokens that must be cleared when triggered. Context will only be modified if at least this many tokens can be removed. - `type: "input_tokens"` - - `"input_tokens"` - - `value: number` + minimum: 0 + - `clear_tool_inputs: optional boolean or array of string or null` Whether to clear all tool inputs (bool) or specific tool inputs to clear (list)
- `type: "tool_uses"` - - `"tool_uses"` - - `value: number` + minimum: 0 + - `trigger: optional BetaInputTokensTrigger or BetaToolUsesTrigger` Condition that triggers the context management strategy - - `BetaInputTokensTrigger object { type, value }` + - `BetaInputTokensTrigger object` - `type: "input_tokens"` - - `"input_tokens"` - - `value: number` - - `BetaToolUsesTrigger object { type, value }` + minimum: 1 + + - `BetaToolUsesTrigger object` - `type: "tool_uses"` - - `"tool_uses"` - - `value: number` - - `BetaClearThinking20251015Edit object { type, keep }` + minimum: 1 + + - `BetaClearThinking20251015Edit object` - `type: "clear_thinking_20251015"` - - `"clear_thinking_20251015"` - - `keep: optional BetaThinkingTurns or BetaAllThinkingTurns or "all"` Number of most recent assistant turns to keep thinking blocks for. Older turns will have their thinking blocks removed. - - `BetaThinkingTurns object { type, value }` + - `BetaThinkingTurns object` - `type: "thinking_turns"` - - `"thinking_turns"` - - `value: number` - - `BetaAllThinkingTurns object { type }` + minimum: 1 + + - `BetaAllThinkingTurns object` - `type: "all"` - - `"all"` - - `"all"` - - `"all"` - - - `BetaCompact20260112Edit object { type, instructions, pause_after_compaction, trigger }` + - `BetaCompact20260112Edit object` Automatically compact older context when reaching the configured trigger threshold. - `type: "compact_20260112"` - - - `"compact_20260112"` - `instructions: optional string or null`
- `previous_message_id: optional string or null` The `id` (`msg_...`) from this client's previous /v1/messages response. The server compares that request's prompt fingerprint against this one and returns `diagnostics.cache_miss_reason` when the prompt-cache prefix could not be reused. Pass `null` on the first turn to opt in without a prior message to compare. + + maxLength: 256 - `fallback_credit_token: optional string or BetaFallbackCreditTokenParam or null`
- `string` - - `BetaFallbackCreditTokenParam object { token, mode }` + - `BetaFallbackCreditTokenParam object` Object form of `fallback_credit_token`: the token plus a redemption mode.
The opaque `fallback_credit_token` from a prior refusal's `stop_details` — the same string the bare-string form carries. + maxLength: 2048, minLength: 1 + - `mode: optional "strict" or "best_effort"` How a failing token affects the retry. `strict` (the default, and the bare-string behavior): a failing redemption is a 400 and the retry is not served. `best_effort`: the retry is served either way — a token-layer failure no longer rejects the request; the retry proceeds at normal price and the outcome is reported on the response's `usage.fallback_credit`. Two failures stay hard in both modes: a malformed token, and combining `fallback_credit_token` with `fallbacks`.
- `type: "json_schema"` - - `"json_schema"` - - `task_budget: optional BetaTokenTaskBudget or null` User-configurable total token budget across contexts.
Total token budget across all contexts in the session. + minimum: 1024 + - `type: "tokens"` The budget type. Currently only 'tokens' is supported. - - `"tokens"` - - `remaining: optional number or null` Remaining tokens in the budget. Use this to track usage across contexts when implementing compaction client-side. Defaults to total if not provided. + minimum: 0 + - `speed: optional "standard" or "fast" or null` Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Not all models support `fast`; invalid combinations are rejected at create time.
- `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigAdaptive or null` - - `BetaThinkingConfigEnabled object { budget_tokens, type, display }` + - `BetaThinkingConfigEnabled object` - `budget_tokens: number`
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`.
- `"omitted"` - - `BetaThinkingConfigDisabled object { type }` + - `BetaThinkingConfigDisabled object` - `type: "disabled"` - - `"disabled"` - - - `BetaThinkingConfigAdaptive object { type, display }` + - `BetaThinkingConfigAdaptive 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`.
- `Default = "default"` - - `"default"` - - `inference_geo: optional string or null` Specifies the geographic region for inference processing. If not specified, the workspace's `default_inference_geo` is used.
MCP servers to be utilized in this request + maxItems: 20 + - `name: string` - `type: "url"` - - `"url"` - - `url: string` - `authorization_token: optional string or null`
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 BetaOutputConfig` Configuration options for the model's output, such as the output format. -- `output_format: optional BetaJSONOutputFormat or null` - - Deprecated: Use `output_config.format` instead. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) - - A schema to specify Claude's output format in responses. This parameter will be removed in a future release. - - `service_tier: optional "auto" or "standard_only"` Determines whether to use priority capacity (if available) or standard capacity for this request.
- `text: string` + minLength: 1 + - `type: "text"` - `cache_control: optional BetaCacheControlEphemeral or null`
- `citations: optional array of BetaTextCitationParam 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 BetaThinkingConfigParam` Configuration for enabling Claude's extended thinking.
See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - - `BetaThinkingConfigEnabled object { budget_tokens, type, display }` - - - `BetaThinkingConfigDisabled object { type }` - - - `BetaThinkingConfigAdaptive object { type, display }` + - `BetaThinkingConfigEnabled object` + + - `BetaThinkingConfigDisabled object` + + - `BetaThinkingConfigAdaptive object` - `tool_choice: optional BetaToolChoice` 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. - - `BetaToolChoiceAuto object { type, disable_parallel_tool_use }` + - `BetaToolChoiceAuto 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. - - `BetaToolChoiceAny object { type, disable_parallel_tool_use }` + - `BetaToolChoiceAny 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. - - `BetaToolChoiceTool object { name, type, disable_parallel_tool_use }` + - `BetaToolChoiceTool object` The model will use the specified tool with `tool_choice.name`.
- `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. - - `BetaToolChoiceNone object { type }` + - `BetaToolChoiceNone object` The model will not be allowed to use tools. - `type: "none"` - - - `"none"` - `tools: optional array of BetaToolUnion`
See our [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) for more details. - - `BetaTool object { input_schema, name, allowed_callers, 7 more }` - - - `input_schema: object { type, properties, required }` + - `BetaTool object` + + - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input.
- `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
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"`
- `type: optional "custom" or null` - - `"custom"` - - - `BetaToolBash20241022 object { name, type, allowed_callers, 4 more }` + - `BetaToolBash20241022 object` - `name: "bash"`
This is how the tool will be called by the model and in `tool_use` blocks. - - `"bash"` - - `type: "bash_20241022"` - - `"bash_20241022"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
When true, guarantees schema validation on tool names and inputs - - `BetaToolBash20250124 object { name, type, allowed_callers, 4 more }` + - `BetaToolBash20250124 object` - `name: "bash"`
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"`
When true, guarantees schema validation on tool names and inputs - - `BetaCodeExecutionTool20250522 object { name, type, allowed_callers, 3 more }` + - `BetaCodeExecutionTool20250522 object` - `name: "code_execution"`
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"`
When true, guarantees schema validation on tool names and inputs - - `BetaCodeExecutionTool20250825 object { name, type, allowed_callers, 3 more }` + - `BetaCodeExecutionTool20250825 object` - `name: "code_execution"`
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 BetaCacheControlEphemeral 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 + + - `BetaCodeExecutionTool20260120 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"`
When true, guarantees schema validation on tool names and inputs - - `BetaCodeExecutionTool20260120 object { name, type, allowed_callers, 3 more }` - - Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). + - `BetaCodeExecutionTool20260521 object` + + Code execution tool with REPL state persistence. - `name: "code_execution"`
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 BetaCacheControlEphemeral or null`
When true, guarantees schema validation on tool names and inputs - - `BetaCodeExecutionTool20260521 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 BetaCacheControlEphemeral 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 - - - `BetaBrowserToolset20260801 object { type, allowed_callers, cache_control, configs }` + - `BetaBrowserToolset20260801 object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served
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"`
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - - `BetaToolComputerUse20241022 object { display_height_px, display_width_px, name, 7 more }` + - `BetaToolComputerUse20241022 object` - `display_height_px: number` The height of the display in pixels. + minimum: 1 + - `display_width_px: number` The width of the display in pixels. + minimum: 1 + - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - - `"computer"` - - `type: "computer_20241022"` - - `"computer_20241022"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
The X11 display number (e.g. 0, 1) for the display. + minimum: 0 + - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - - `BetaMemoryTool20250818 object { name, type, allowed_callers, 4 more }` + - `BetaMemoryTool20250818 object` - `name: "memory"`
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"`
When true, guarantees schema validation on tool names and inputs - - `BetaToolComputerUse20250124 object { display_height_px, display_width_px, name, 7 more }` + - `BetaToolComputerUse20250124 object` - `display_height_px: number` The height of the display in pixels. + minimum: 1 + - `display_width_px: number` The width of the display in pixels. + minimum: 1 + - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - - `"computer"` - - `type: "computer_20250124"` - - `"computer_20250124"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
The X11 display number (e.g. 0, 1) for the display. + minimum: 0 + - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - - `BetaToolTextEditor20241022 object { name, type, allowed_callers, 4 more }` + - `BetaToolTextEditor20241022 object` - `name: "str_replace_editor"`
This is how the tool will be called by the model and in `tool_use` blocks. - - `"str_replace_editor"` - - `type: "text_editor_20241022"` - - `"text_editor_20241022"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
When true, guarantees schema validation on tool names and inputs - - `BetaToolComputerUse20251124 object { display_height_px, display_width_px, name, 8 more }` + - `BetaToolComputerUse20251124 object` - `display_height_px: number` The height of the display in pixels. + minimum: 1 + - `display_width_px: number` The width of the display in pixels. + minimum: 1 + - `name: "computer"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - - `"computer"` - - `type: "computer_20251124"` - - `"computer_20251124"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
The X11 display number (e.g. 0, 1) for the display. + minimum: 0 + - `enable_zoom: optional boolean` Whether to enable an action to take a zoomed-in screenshot of the screen.
When true, guarantees schema validation on tool names and inputs - - `BetaComputerToolset20260801 object { type, allowed_callers, cache_control, configs }` + - `BetaComputerToolset20260801 object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is
- `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"`
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - - `BetaToolTextEditor20250124 object { name, type, allowed_callers, 4 more }` + - `BetaToolTextEditor20250124 object` - `name: "str_replace_editor"`
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"`
When true, guarantees schema validation on tool names and inputs - - `BetaToolTextEditor20250429 object { name, type, allowed_callers, 4 more }` + - `BetaToolTextEditor20250429 object` - `name: "str_replace_based_edit_tool"`
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"`
When true, guarantees schema validation on tool names and inputs - - `BetaToolTextEditor20250728 object { name, type, allowed_callers, 5 more }` + - `BetaToolTextEditor20250728 object` - `name: "str_replace_based_edit_tool"`
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"`
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 - - `BetaWebSearchTool20250305 object { name, type, allowed_callers, 7 more }` + - `BetaWebSearchTool20250305 object` - `name: "web_search"`
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"`
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
- `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. - - `BetaWebFetchTool20250910 object { name, type, allowed_callers, 8 more }` + maxLength: 255, minLength: 1 + + - `BetaWebFetchTool20250910 object` - `name: "web_fetch"`
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"`
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 - - `BetaWebSearchTool20260209 object { name, type, allowed_callers, 7 more }` + - `BetaWebSearchTool20260209 object` - `name: "web_search"`
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"`
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
Parameters for the user's location. Used to provide more relevant search results. - - `BetaWebFetchTool20260209 object { name, type, allowed_callers, 8 more }` + - `BetaWebFetchTool20260209 object` - `name: "web_fetch"`
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"`
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 - - `BetaWebFetchTool20260309 object { name, type, allowed_callers, 9 more }` + - `BetaWebFetchTool20260309 object` Web fetch tool with use_cache parameter for bypassing cached content.
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"`
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
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. - - `BetaWebSearchTool20260318 object { name, type, allowed_callers, 8 more }` + - `BetaWebSearchTool20260318 object` - `name: "web_search"`
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"`
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.
Parameters for the user's location. Used to provide more relevant search results. - - `BetaWebFetchTool20260318 object { name, type, allowed_callers, 10 more }` + - `BetaWebFetchTool20260318 object` - `name: "web_fetch"`
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"`
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.
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. - - `BetaAdvisorTool20260301 object { model, name, type, 7 more }` + - `BetaAdvisorTool20260301 object` - `model: Model`
This is how the tool will be called by the model and in `tool_use` blocks. - - `"advisor"` - - `type: "advisor_20260301"` - - `"advisor_20260301"` - - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"` - `"direct"`
Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted. + minimum: 1024 + - `max_uses: optional 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 - - `BetaToolSearchToolBm25_20251119 object { name, type, allowed_callers, 3 more }` + - `BetaToolSearchToolBm25_20251119 object` - `name: "tool_search_tool_bm25"`
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"`
When true, guarantees schema validation on tool names and inputs - - `BetaToolSearchToolRegex20251119 object { name, type, allowed_callers, 3 more }` + - `BetaToolSearchToolRegex20251119 object` - `name: "tool_search_tool_regex"`
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"`
When true, guarantees schema validation on tool names and inputs - - `BetaMCPToolset object { mcp_server_name, type, cache_control, 2 more }` + - `BetaMCPToolset object` Configuration for a group of tools from an MCP server.
Name of the MCP server to configure tools for + maxLength: 255, minLength: 1 + - `type: "mcp_toolset"` - - `"mcp_toolset"` - - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block.
- `enabled: optional boolean` +- `output_format: optional BetaJSONOutputFormat or null` + + **Deprecated** + + Deprecated: Use `output_config.format` instead. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) + + A schema to specify Claude's output format in responses. This parameter will be removed in a future release. + +- `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 - -- `BetaMessage object { id, container, content, 9 more }` + maximum: 1, minimum: 0 + +## Returns + +- `BetaMessage object` - `id: string`
The time at which the container will expire. + format: date-time + - `skills: array of BetaSkill or null` Skills loaded in the container
Skill ID + maxLength: 64, minLength: 1 + - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
- `version: string` The resolved version: a skill version ID for custom skills. + + maxLength: 64, minLength: 1 - `content: array of BetaContentBlock`
[{"type": "text", "text": "B)"}] ``` - - `BetaTextBlock object { citations, text, type }` + - `BetaTextBlock object` - `citations: array of BetaTextCitation or null`
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`. - - `BetaCitationCharLocation object { cited_text, document_index, document_title, 4 more }` + - `BetaCitationCharLocation object` - `cited_text: string` - `document_index: number` + minimum: 0 + - `document_title: string or null` - `end_char_index: number`
- `start_char_index: number` + minimum: 0 + - `type: "char_location"` - - `"char_location"` - - - `BetaCitationPageLocation object { cited_text, document_index, document_title, 4 more }` + default: char_location + + - `BetaCitationPageLocation object` - `cited_text: string` - `document_index: number` + minimum: 0 + - `document_title: string or null` - `end_page_number: number`
- `start_page_number: number` + minimum: 1 + - `type: "page_location"` - - `"page_location"` - - - `BetaCitationContentBlockLocation object { cited_text, document_index, document_title, 4 more }` + default: page_location + + - `BetaCitationContentBlockLocation object` - `cited_text: string`
- `document_index: number` + minimum: 0 + - `document_title: string or null` - `end_block_index: number`
0-based index of the first cited block in the source's `content` array. + minimum: 0 + - `type: "content_block_location"` - - `"content_block_location"` - - - `BetaCitationsWebSearchResultLocation object { cited_text, encrypted_index, title, 2 more }` + default: content_block_location + + - `BetaCitationsWebSearchResultLocation object` - `cited_text: string`
- `title: string or null` + maxLength: 512 + - `type: "web_search_result_location"` - - `"web_search_result_location"` + default: web_search_result_location - `url: string` - - `BetaCitationSearchResultLocation object { cited_text, end_block_index, search_result_index, 4 more }` + - `BetaCitationSearchResultLocation object` - `cited_text: string`
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"` + default: search_result_location - `text: string` + maxLength: 5000000, minLength: 0 + - `type: "text"` - - `"text"` - - - `BetaThinkingBlock object { signature, thinking, type }` + default: text + + - `BetaThinkingBlock object` - `signature: string`
- `type: "thinking"` - - `"thinking"` - - - `BetaRedactedThinkingBlock object { data, type }` + default: thinking + + - `BetaRedactedThinkingBlock object` - `data: string`
- `type: "redacted_thinking"` - - `"redacted_thinking"` - - - `BetaToolUseBlock object { id, input, name, 3 more }` + default: redacted_thinking + + - `BetaToolUseBlock object` - `id: string` + pattern: ^[a-zA-Z0-9_-]+$ + - `input: map[unknown]` - `name: string` + minLength: 1 + - `type: "tool_use"` - - `"tool_use"` + default: tool_use - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - - `BetaDirectCaller object { type }` + - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - - `"direct"` - - - `BetaServerToolCaller object { tool_id, type }` + - `BetaServerToolCaller 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"` - - - `BetaServerToolCaller20260120 object { tool_id, type }` + - `BetaServerToolCaller20260120 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. - - `BetaServerToolUseBlock object { id, input, name, 2 more }` + maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ + + - `BetaServerToolUseBlock object` - `id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more`
- `type: "server_tool_use"` - - `"server_tool_use"` + default: server_tool_use - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - - `BetaDirectCaller object { type }` + - `BetaDirectCaller object` Tool invocation directly from the model. - - `BetaServerToolCaller object { tool_id, type }` + - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - - `BetaServerToolCaller20260120 object { tool_id, type }` - - - `BetaWebSearchToolResultBlock object { content, tool_use_id, type, caller }` + - `BetaServerToolCaller20260120 object` + + - `BetaWebSearchToolResultBlock object` - `content: BetaWebSearchToolResultBlockContent` - - `BetaWebSearchToolResultError object { error_code, type }` + - `BetaWebSearchToolResultError object` - `error_code: BetaWebSearchToolResultErrorCode`
- `type: "web_search_tool_result_error"` - - `"web_search_tool_result_error"` + default: web_search_tool_result_error - `array of BetaWebSearchResultBlock`
- `type: "web_search_result"` - - `"web_search_result"` + default: web_search_result - `url: string` - `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "web_search_tool_result"` - - `"web_search_tool_result"` + default: web_search_tool_result - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - - `BetaDirectCaller object { type }` + - `BetaDirectCaller object` Tool invocation directly from the model. - - `BetaServerToolCaller object { tool_id, type }` + - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - - `BetaServerToolCaller20260120 object { tool_id, type }` - - - `BetaWebFetchToolResultBlock object { content, tool_use_id, type, caller }` + - `BetaServerToolCaller20260120 object` + + - `BetaWebFetchToolResultBlock object` - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - - `BetaWebFetchToolResultErrorBlock object { error_code, type }` + - `BetaWebFetchToolResultErrorBlock object` - `error_code: BetaWebFetchToolResultErrorCode`
- `type: "web_fetch_tool_result_error"` - - `"web_fetch_tool_result_error"` - - - `BetaWebFetchBlock object { content, retrieved_at, type, url }` + default: web_fetch_tool_result_error + + - `BetaWebFetchBlock object` - `content: BetaDocumentBlock`
- `enabled: boolean` + default: false + - `source: BetaBase64PDFSource or BetaPlainTextSource` - - `BetaBase64PDFSource object { data, media_type, type }` + - `BetaBase64PDFSource object` - `data: string` + format: byte + - `media_type: "application/pdf"` - - `"application/pdf"` - - `type: "base64"` - - `"base64"` - - - `BetaPlainTextSource object { data, media_type, type }` + - `BetaPlainTextSource object` - `data: string` - `media_type: "text/plain"` - - `"text/plain"` - - `type: "text"` - - `"text"` - - `title: string or null` The title of the document - `type: "document"` - - `"document"` + default: document - `retrieved_at: string or null`
- `type: "web_fetch_result"` - - `"web_fetch_result"` + default: web_fetch_result - `url: string`
- `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "web_fetch_tool_result"` - - `"web_fetch_tool_result"` + default: web_fetch_tool_result - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - - `BetaDirectCaller object { type }` + - `BetaDirectCaller object` Tool invocation directly from the model. - - `BetaServerToolCaller object { tool_id, type }` + - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - - `BetaServerToolCaller20260120 object { tool_id, type }` - - - `BetaAdvisorToolResultBlock object { content, tool_use_id, type }` + - `BetaServerToolCaller20260120 object` + + - `BetaAdvisorToolResultBlock object` - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - - `BetaAdvisorToolResultError object { error_code, type }` + - `BetaAdvisorToolResultError object` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more`
- `type: "advisor_tool_result_error"` - - `"advisor_tool_result_error"` - - - `BetaAdvisorResultBlock object { stop_reason, text, type }` + default: advisor_tool_result_error + + - `BetaAdvisorResultBlock object` - `stop_reason: string or null`
- `type: "advisor_result"` - - `"advisor_result"` - - - `BetaAdvisorRedactedResultBlock object { encrypted_content, stop_reason, type }` + default: advisor_result + + - `BetaAdvisorRedactedResultBlock object` - `encrypted_content: string`
- `type: "advisor_redacted_result"` - - `"advisor_redacted_result"` + default: advisor_redacted_result - `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "advisor_tool_result"` - - `"advisor_tool_result"` - - - `BetaCodeExecutionToolResultBlock object { content, tool_use_id, type }` + default: advisor_tool_result + + - `BetaCodeExecutionToolResultBlock object` - `content: BetaCodeExecutionToolResultBlockContent` Code execution result with encrypted stdout for PFC + web_search results. - - `BetaCodeExecutionToolResultError object { error_code, type }` + - `BetaCodeExecutionToolResultError object` - `error_code: BetaCodeExecutionToolResultErrorCode`
- `type: "code_execution_tool_result_error"` - - `"code_execution_tool_result_error"` - - - `BetaCodeExecutionResultBlock object { content, return_code, stderr, 2 more }` + default: code_execution_tool_result_error + + - `BetaCodeExecutionResultBlock object` - `content: array of BetaCodeExecutionOutputBlock`
- `type: "code_execution_output"` - - `"code_execution_output"` + default: code_execution_output - `return_code: number`
- `type: "code_execution_result"` - - `"code_execution_result"` - - - `BetaEncryptedCodeExecutionResultBlock object { content, encrypted_stdout, return_code, 2 more }` + default: code_execution_result + + - `BetaEncryptedCodeExecutionResultBlock object` Code execution result with encrypted stdout for PFC + web_search results.
- `type: "code_execution_output"` + default: code_execution_output + - `encrypted_stdout: string` - `return_code: number`
- `type: "encrypted_code_execution_result"` - - `"encrypted_code_execution_result"` + default: encrypted_code_execution_result - `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "code_execution_tool_result"` - - `"code_execution_tool_result"` - - - `BetaBashCodeExecutionToolResultBlock object { content, tool_use_id, type }` + default: code_execution_tool_result + + - `BetaBashCodeExecutionToolResultBlock object` - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - - `BetaBashCodeExecutionToolResultError object { error_code, type }` + - `BetaBashCodeExecutionToolResultError object` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more`
- `type: "bash_code_execution_tool_result_error"` - - `"bash_code_execution_tool_result_error"` - - - `BetaBashCodeExecutionResultBlock object { content, return_code, stderr, 2 more }` + default: bash_code_execution_tool_result_error + + - `BetaBashCodeExecutionResultBlock object` - `content: array of BetaBashCodeExecutionOutputBlock`
- `type: "bash_code_execution_output"` - - `"bash_code_execution_output"` + default: bash_code_execution_output - `return_code: number`
- `type: "bash_code_execution_result"` - - `"bash_code_execution_result"` + default: 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"` - - - `BetaTextEditorCodeExecutionToolResultBlock object { content, tool_use_id, type }` + default: bash_code_execution_tool_result + + - `BetaTextEditorCodeExecutionToolResultBlock object` - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - - `BetaTextEditorCodeExecutionToolResultError object { error_code, error_message, type }` + - `BetaTextEditorCodeExecutionToolResultError object` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more`
- `type: "text_editor_code_execution_tool_result_error"` - - `"text_editor_code_execution_tool_result_error"` - - - `BetaTextEditorCodeExecutionViewResultBlock object { content, file_type, num_lines, 3 more }` + default: text_editor_code_execution_tool_result_error + + - `BetaTextEditorCodeExecutionViewResultBlock object` - `content: string`
- `type: "text_editor_code_execution_view_result"` - - `"text_editor_code_execution_view_result"` - - - `BetaTextEditorCodeExecutionCreateResultBlock object { is_file_update, type }` + default: text_editor_code_execution_view_result + + - `BetaTextEditorCodeExecutionCreateResultBlock object` - `is_file_update: boolean` - `type: "text_editor_code_execution_create_result"` - - `"text_editor_code_execution_create_result"` - - - `BetaTextEditorCodeExecutionStrReplaceResultBlock object { lines, new_lines, new_start, 3 more }` + default: text_editor_code_execution_create_result + + - `BetaTextEditorCodeExecutionStrReplaceResultBlock object` - `lines: array of string or null`
- `type: "text_editor_code_execution_str_replace_result"` - - `"text_editor_code_execution_str_replace_result"` + default: text_editor_code_execution_str_replace_result - `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "text_editor_code_execution_tool_result"` - - `"text_editor_code_execution_tool_result"` - - - `BetaToolSearchToolResultBlock object { content, tool_use_id, type }` + default: text_editor_code_execution_tool_result + + - `BetaToolSearchToolResultBlock object` - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - - `BetaToolSearchToolResultError object { error_code, error_message, type }` + - `BetaToolSearchToolResultError object` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"`
- `type: "tool_search_tool_result_error"` - - `"tool_search_tool_result_error"` - - - `BetaToolSearchToolSearchResultBlock object { tool_references, type }` + default: tool_search_tool_result_error + + - `BetaToolSearchToolSearchResultBlock object` - `tool_references: array of BetaToolReferenceBlock` - `tool_name: string` + maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ + - `type: "tool_reference"` - - `"tool_reference"` + default: tool_reference - `type: "tool_search_tool_search_result"` - - `"tool_search_tool_search_result"` + default: tool_search_tool_search_result - `tool_use_id: string` + pattern: ^srvtoolu_[a-zA-Z0-9_]+$ + - `type: "tool_search_tool_result"` - - `"tool_search_tool_result"` - - - `BetaMCPToolUseBlock object { id, input, name, 2 more }` + default: tool_search_tool_result + + - `BetaMCPToolUseBlock object` - `id: string` + pattern: ^[a-zA-Z0-9_-]+$ + - `input: map[unknown]` - `name: string`
- `type: "mcp_tool_use"` - - `"mcp_tool_use"` - - - `BetaMCPToolResultBlock object { content, is_error, tool_use_id, type }` + default: mcp_tool_use + + - `BetaMCPToolResultBlock object` - `content: string or array of BetaTextBlock`
- `text: string` + maxLength: 5000000, minLength: 0 + - `type: "text"` + default: text + - `is_error: boolean` + default: false + - `tool_use_id: string` + pattern: ^[a-zA-Z0-9_-]+$ + - `type: "mcp_tool_result"` - - `"mcp_tool_result"` - - - `BetaContainerUploadBlock object { file_id, type }` + default: mcp_tool_result + + - `BetaContainerUploadBlock object` Response model for a file uploaded to the container.
- `type: "container_upload"` - - `"container_upload"` - - - `BetaCompactionBlock object { content, encrypted_content, type }` + default: container_upload + + - `BetaCompactionBlock object` A compaction block returned when autocompact is triggered.
- `type: "compaction"` - - `"compaction"` - - - `BetaFallbackBlock object { from, to, trigger, type }` + default: compaction + + - `BetaFallbackBlock object` Marks the point in `content` where one model's output gives way to the next.
- `type: "refusal"` - - `"refusal"` + default: refusal - `type: "fallback"` - - `"fallback"` + default: fallback - `context_management: BetaContextManagementResponse or null`
List of context management edits that were applied. - - `BetaClearToolUses20250919EditResponse object { cleared_input_tokens, cleared_tool_uses, type }` + - `BetaClearToolUses20250919EditResponse object` - `cleared_input_tokens: number` Number of input tokens cleared by this edit. + minimum: 0 + - `cleared_tool_uses: number` Number of tool uses that were cleared. + minimum: 0 + - `type: "clear_tool_uses_20250919"` The type of context management edit applied. - - `"clear_tool_uses_20250919"` - - - `BetaClearThinking20251015EditResponse object { cleared_input_tokens, cleared_thinking_turns, type }` + default: clear_tool_uses_20250919 + + - `BetaClearThinking20251015EditResponse object` - `cleared_input_tokens: number` Number of input tokens cleared by this edit. + minimum: 0 + - `cleared_thinking_turns: number` Number of thinking turns that were cleared. + minimum: 0 + - `type: "clear_thinking_20251015"` The type of context management edit applied. - - `"clear_thinking_20251015"` + default: clear_thinking_20251015 - `diagnostics: BetaDiagnostics or null`
Explains why the prompt cache could not fully reuse the prefix from the request identified by `diagnostics.previous_message_id`. `null` means diagnosis is still pending — the response was serialized before the background comparison completed. - - `BetaCacheMissModelChanged object { cache_missed_input_tokens, type }` + - `BetaCacheMissModelChanged object` - `cache_missed_input_tokens: number`
- `type: "model_changed"` - - `"model_changed"` - - - `BetaCacheMissSystemChanged object { cache_missed_input_tokens, type }` + default: model_changed + + - `BetaCacheMissSystemChanged object` - `cache_missed_input_tokens: number`
- `type: "system_changed"` - - `"system_changed"` - - - `BetaCacheMissToolsChanged object { cache_missed_input_tokens, type }` + default: system_changed + + - `BetaCacheMissToolsChanged object` - `cache_missed_input_tokens: number`
- `type: "tools_changed"` - - `"tools_changed"` - - - `BetaCacheMissMessagesChanged object { cache_missed_input_tokens, type }` + default: tools_changed + + - `BetaCacheMissMessagesChanged object` - `cache_missed_input_tokens: number`
- `type: "messages_changed"` - - `"messages_changed"` - - - `BetaCacheMissPreviousMessageNotFound object { type }` + default: messages_changed + + - `BetaCacheMissPreviousMessageNotFound object` - `type: "previous_message_not_found"` - - `"previous_message_not_found"` - - - `BetaCacheMissUnavailable object { type }` + default: previous_message_not_found + + - `BetaCacheMissUnavailable object` - `type: "unavailable"` - - `"unavailable"` + default: unavailable - `model: Model`
This will always be `"assistant"`. - - `"assistant"` + default: assistant - `stop_details: BetaRefusalStopDetails or null`
- `type: "refusal"` - - `"refusal"` + default: refusal - `stop_reason: BetaStopReason or null`
For Messages, this is always `"message"`. - - `"message"` + default: message - `usage: BetaUsage`
The number of input tokens used to create the 1 hour cache entry. + default: 0, minimum: 0 + - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. + default: 0, minimum: 0 + - `cache_creation_input_tokens: number or null` The number of input tokens used to create the cache entry. + minimum: 0 + - `cache_read_input_tokens: number or null` The number of input tokens read from the cache. + + minimum: 0 - `fallback_credit: BetaFallbackCreditUsage or null`
resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - - `BetaFallbackCreditRedeemed object { type }` + - `BetaFallbackCreditRedeemed object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` - - `"redeemed"` - - - `BetaFallbackCreditNotApplied object { reason, type, remove_to_redeem }` + default: redeemed + + - `BetaFallbackCreditNotApplied object` No reprice was applied; `reason` says why.
- `type: "not_applied"` - - `"not_applied"` + default: not_applied - `remove_to_redeem: optional array of string or null`
The number of input tokens which were used. + minimum: 0 + - `iterations: BetaIterationsUsage or null` Per-iteration token usage breakdown.
- Calculate the true context window size from the last iteration - Understand token accumulation across server-side tool use loops - - `BetaMessageIterationUsage object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 4 more }` + - `BetaMessageIterationUsage object` Token usage for a sampling iteration.
The number of input tokens used to create the cache entry. + default: 0, minimum: 0 + - `cache_read_input_tokens: number` The number of input tokens read from the cache. + default: 0, minimum: 0 + - `input_tokens: number` The number of input tokens which were used. + minimum: 0 + - `model: Model` The model that will complete your prompt.
The number of output tokens which were used. + minimum: 0 + - `type: "message"` Usage for a sampling iteration - - `"message"` - - - `BetaCompactionIterationUsage object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 3 more }` + default: message + + - `BetaCompactionIterationUsage object` Token usage for a compaction iteration.
The number of input tokens used to create the cache entry. + default: 0, minimum: 0 + - `cache_read_input_tokens: number` The number of input tokens read from the cache. + default: 0, minimum: 0 + - `input_tokens: number` The number of input tokens which were used. + minimum: 0 + - `output_tokens: number` The number of output tokens which were used. + minimum: 0 + - `type: "compaction"` Usage for a compaction iteration - - `"compaction"` - - - `BetaAdvisorMessageIterationUsage object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 4 more }` + default: compaction + + - `BetaAdvisorMessageIterationUsage object` Token usage for an advisor sub-inference iteration.
The number of input tokens used to create the cache entry. + default: 0, minimum: 0 + - `cache_read_input_tokens: number` The number of input tokens read from the cache. + default: 0, minimum: 0 + - `input_tokens: number` The number of input tokens which were used. + minimum: 0 + - `model: Model` The model that will complete your prompt.
The number of output tokens which were used. + minimum: 0 + - `type: "advisor_message"` Usage for an advisor sub-inference iteration - - `"advisor_message"` - - - `BetaFallbackMessageIterationUsage object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 4 more }` + default: advisor_message + + - `BetaFallbackMessageIterationUsage object` Token usage for the fallback-model attempt of a server-side fallback request.
The number of input tokens used to create the cache entry. + default: 0, minimum: 0 + - `cache_read_input_tokens: number` The number of input tokens read from the cache. + default: 0, minimum: 0 + - `input_tokens: number` The number of input tokens which were used. + minimum: 0 + - `model: Model` The model that will complete your prompt.
The number of output tokens which were used. + minimum: 0 + - `type: "fallback_message"` Usage for the fallback-model attempt that served the response - - `"fallback_message"` + default: fallback_message - `output_tokens: number` The number of output tokens which were used. + + minimum: 0 - `output_tokens_details: BetaOutputTokensDetails or null`
generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. + default: 0, minimum: 0 + - `server_tool_use: BetaServerToolUsage or null` The number of server tool requests.
The number of web fetch tool requests. + default: 0, minimum: 0 + - `web_search_requests: number` The number of web search tool requests. + default: 0, minimum: 0 + - `service_tier: "standard" or "priority" or "batch" or null` If the request used the priority, standard, or batch tier.
- `"fast"` -### Example - -```http +- `BetaRawMessageStreamEvent = BetaRawMessageStartEvent or BetaRawMessageDeltaEvent or BetaRawMessageStopEvent or 3 more` + + - `BetaRawMessageStartEvent object` + + - `message: BetaMessage` + + - `type: "message_start"` + + default: message_start + + - `BetaRawMessageDeltaEvent object` + + - `context_management: BetaContextManagementResponse or null` + + Information about context management strategies applied during the request + + - `delta: object` + + - `container: BetaContainer or null` + + Information about the container used in the request (for the code execution tool) + + - `stop_details: BetaRefusalStopDetails or null` + + Structured information about a refusal. + + - `stop_reason: BetaStopReason or null` + + - `stop_sequence: string or null` + + - `type: "message_delta"` + + default: message_delta + + - `usage: BetaMessageDeltaUsage` + + Billing and rate-limit usage. + + Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. + + Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. + + For example, `output_tokens` will be non-zero, even for an empty string response from Claude. + + Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. + + - `cache_creation_input_tokens: number or null` + + The cumulative number of input tokens used to create the cache entry. + + minimum: 0 + + - `cache_read_input_tokens: number or null` + + The cumulative number of input tokens read from the cache. + + minimum: 0 + + - `fallback_credit: BetaFallbackCreditUsage or null` + + Outcome of the `fallback_credit_token` presented on this request. + + - `input_tokens: number or null` + + The cumulative number of input tokens which were used. + + minimum: 0 + + - `iterations: BetaIterationsUsage or null` + + Per-iteration token usage breakdown. + + Each entry represents one sampling iteration, with its own input/output token counts and cache statistics. This allows you to: + + - Determine which iterations exceeded long context thresholds (>=200k tokens) + - Calculate the true context window size from the last iteration + - Understand token accumulation across server-side tool use loops + + - `output_tokens: number` + + The cumulative number of output tokens which were used. + + - `output_tokens_details: BetaOutputTokensDetails or null` + + Breakdown of output tokens by category. + + `output_tokens` remains the inclusive, authoritative total used for billing. + This object provides a read-only decomposition for observability — for example, + how many of the billed output tokens were spent on internal reasoning that may + have been summarized before being returned to you. + + - `server_tool_use: BetaServerToolUsage or null` + + The number of server tool requests. + + - `BetaRawMessageStopEvent object` + + - `type: "message_stop"` + + default: message_stop + + - `BetaRawContentBlockStartEvent object` + + - `content_block: BetaTextBlock or BetaThinkingBlock or BetaRedactedThinkingBlock or 14 more` + + Response model for a file uploaded to the container. + + - `BetaTextBlock object` + + - `BetaThinkingBlock object` + + - `BetaRedactedThinkingBlock object` + + - `BetaToolUseBlock object` + + - `BetaServerToolUseBlock object` + + - `BetaWebSearchToolResultBlock object` + + - `BetaWebFetchToolResultBlock object` + + - `BetaAdvisorToolResultBlock object` + + - `BetaCodeExecutionToolResultBlock object` + + - `BetaBashCodeExecutionToolResultBlock object` + + - `BetaTextEditorCodeExecutionToolResultBlock object` + + - `BetaToolSearchToolResultBlock object` + + - `BetaMCPToolUseBlock object` + + - `BetaMCPToolResultBlock object` + + - `BetaContainerUploadBlock object` + + Response model for a file uploaded to the container. + + - `BetaCompactionBlock object` + + A compaction block returned when autocompact is triggered. + + When content is None, it indicates the compaction failed to produce a valid + summary (e.g., malformed output from the model). Clients may round-trip + compaction blocks with null content; the server treats them as no-ops. + + - `BetaFallbackBlock object` + + Marks the point in `content` where one model's output gives way to the next. + + One block appears per hop where a preceding model actually ran this turn and + declined. A turn where no preceding model ran and declined has no such + boundary and carries no block — the signal for whether a fallback model + served the response is the presence of a `fallback_message` entry in + `usage.iterations`, not this block. + + The block is treated like a server-tool content block for streaming: it + arrives via the standard `content_block_start` / `content_block_stop` + pair and carries no deltas. + + - `index: number` + + - `type: "content_block_start"` + + default: content_block_start + + - `BetaRawContentBlockDeltaEvent object` + + - `delta: BetaRawContentBlockDelta` + + - `BetaTextDelta object` + + - `text: string` + + - `type: "text_delta"` + + default: text_delta + + - `BetaInputJSONDelta object` + + - `partial_json: string` + + - `type: "input_json_delta"` + + default: input_json_delta + + - `BetaCitationsDelta object` + + - `citation: BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` + + - `BetaCitationCharLocation object` + + - `BetaCitationPageLocation object` + + - `BetaCitationContentBlockLocation object` + + - `BetaCitationsWebSearchResultLocation object` + + - `BetaCitationSearchResultLocation object` + + - `type: "citations_delta"` + + default: citations_delta + + - `BetaThinkingDelta object` + + - `estimated_tokens: number or null` + + Per-frame increment of a coarse, running estimate of the tokens this thinking block has produced so far. Present whenever the `thinking-token-count-2026-05-13` beta is set; `null` unless `thinking.display` resolves to `"omitted"` and a count is due this frame. Sum the increments across `thinking_delta` frames on this block for a progress indicator. Each increment is a non-negative multiple of a fixed quantum and the cadence is rate-limited, so this is a deliberately lossy display hint, not a billable count; `usage.output_tokens` remains authoritative. + + - `thinking: string` + + The incremental `thinking` text for this content block. Concatenate the `thinking` values of successive `thinking_delta` events to assemble the block's full `thinking` value. + + - `type: "thinking_delta"` + + default: thinking_delta + + - `BetaSignatureDelta object` + + - `signature: string` + + The `signature` for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a `signature_delta` event just before the block's `content_block_stop` event. + + - `type: "signature_delta"` + + default: signature_delta + + - `BetaCompactionContentBlockDelta object` + + - `content: string or null` + + - `encrypted_content: string or null` + + Opaque metadata from prior compaction, to be round-tripped verbatim + + - `type: "compaction_delta"` + + default: compaction_delta + + - `index: number` + + - `type: "content_block_delta"` + + default: content_block_delta + + - `BetaRawContentBlockStopEvent object` + + - `index: number` + + - `type: "content_block_stop"` + + default: content_block_stop + +## Example + +```bash curl https://api.anthropic.com/v1/messages \ -H 'Content-Type: application/json' \ -H 'anthropic-version: 2023-06-01' \
}' ``` -#### Response +### Response (200) ```json {