--- title: Messages url: https://platform.claude.com/docs/en/api/beta/messages --- # 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. The Messages API can be used for either single queries or stateless multi-turn conversations. Learn more about the Messages API in our [user guide](https://platform.claude.com/docs/en/get-started) ### Headers - `"anthropic-beta": optional array of AnthropicBeta` Optional header to specify the beta version(s) you want to use. - `string` - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"anthropic-user-profile-id": optional string` 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. - `"anthropic-workspace-id": optional string` ### Body parameters - `max_tokens: number` The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. Set to `0` to populate the [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#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` Input messages. Our models are trained to operate on alternating `user` and `assistant` conversational turns. When creating a new `Message`, you specify the prior conversational turns with the `messages` parameter, and the model then generates the next `Message` in the conversation. Consecutive `user` or `assistant` turns in your request will be combined into a single turn. Each input message must be an object with a `role` and `content`. You can specify a single `user`-role message, or you can include multiple `user` and `assistant` messages. If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response. Example with a single `user` message: ```json [{"role": "user", "content": "Hello, Claude"}] ``` Example with multiple conversational turns: ```json [ {"role": "user", "content": "Hello there."}, {"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"}, {"role": "user", "content": "Can you explain LLMs in plain English?"}, ] ``` Example with a partially-filled response from Claude: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("}, ] ``` Each input message `content` may be either a single `string` or an array of content blocks, where each block has a specific `type`. Using a `string` for `content` is shorthand for an array of one content block of type `"text"`. The following input messages are equivalent: ```json {"role": "user", "content": "Hello, Claude"} ``` ```json {"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]} ``` See [input examples](https://platform.claude.com/docs/en/build-with-claude/working-with-messages). Note that if you want to include a [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role), you can use the top-level `system` parameter — there is no `"system"` role for input messages in the Messages API. There is a limit of 100,000 messages in a single request. - `content: string or array of BetaContentBlockParam` - `string` - `array of BetaContentBlockParam` - `BetaTextBlockParam object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaImageBlockParam object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `BetaURLImageSource object` - `type: "url"` - `url: string` - `BetaFileImageSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `transformations: optional BetaImageTransformationsParam or null` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `BetaRequestDocumentBlock object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `BetaContentBlockSource object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `string` - `BetaContentBlockSourceContent = array of BetaContentBlockSourceContent` - `BetaTextBlockParam object` - `BetaImageBlockParam object` - `BetaURLPDFSource object` - `type: "url"` - `url: string` - `BetaFileDocumentSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` - `enabled: optional boolean` - `context: optional string or null` minLength: 1 - `title: optional string or null` maxLength: 500, minLength: 1 - `BetaSearchResultBlockParam object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `source: string` - `title: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam` - `BetaThinkingBlockParam object` - `type: "thinking"` - `signature: string` The `signature` value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude. Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`. - `thinking: string` The `thinking` text of this block as returned by the API. - `BetaRedactedThinkingBlockParam object` - `type: "redacted_thinking"` - `data: string` The `data` value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged. - `BetaToolUseBlockParam object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` maxLength: 200, minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family this member belongs to. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaToolResultBlockParam object` - `type: "tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `string` - `array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `BetaTextBlockParam object` - `BetaImageBlockParam object` - `BetaSearchResultBlockParam object` - `BetaRequestDocumentBlock object` - `BetaToolReferenceBlockParam object` Tool reference block that can be included in tool_result content. - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `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 effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: "browser_state"` - `tabs: array of BetaBrowserStateTabEntry` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: 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`. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `state_changes: optional array of BetaBrowserStateChange or null` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. 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. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadStarted object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadCompleted object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: 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]*$, maxLength: 4096 - `size_bytes: optional number or null` The completed download's size. minimum: 0 - `BetaBrowserStateChangeDownloadFailed object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string or null` The failure or cancellation detail, when known. pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096 - `is_error: optional boolean` - `toolset_name: optional string or null` For a toolset member tool_result, the toolset family of the paired tool_use. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaServerToolUseBlockParam object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebSearchToolResultBlockParam object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultBlockParamContent` - `ResultBlock = array of BetaWebSearchResultBlockParam` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string or null` - `BetaWebSearchToolRequestError object` - `type: "web_search_tool_result_error"` - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebFetchToolResultBlockParam object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlockParam or BetaWebFetchBlockParam` - `BetaWebFetchToolResultErrorBlockParam object` - `type: "web_fetch_tool_result_error"` - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlockParam object` - `type: "web_fetch_result"` - `content: BetaRequestDocumentBlock` - `url: string` Fetched content URL - `retrieved_at: optional string or null` ISO 8601 timestamp when the content was retrieved - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaAdvisorToolResultBlockParam object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultErrorParam or BetaAdvisorResultBlockParam or BetaAdvisorRedactedResultBlockParam` - `BetaAdvisorToolResultErrorParam object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlockParam object` - `type: "advisor_result"` - `text: string` - `stop_reason: optional string or null` - `BetaAdvisorRedactedResultBlockParam object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: optional string or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaCodeExecutionToolResultBlockParam object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultBlockParamContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultErrorParam object` - `type: "code_execution_tool_result_error"` - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlockParam object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlockParam object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaBashCodeExecutionToolResultBlockParam object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultErrorParam or BetaBashCodeExecutionResultBlockParam` - `BetaBashCodeExecutionToolResultErrorParam object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlockParam object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlockParam` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaTextEditorCodeExecutionToolResultBlockParam object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultErrorParam or BetaTextEditorCodeExecutionViewResultBlockParam or BetaTextEditorCodeExecutionCreateResultBlockParam or BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - `BetaTextEditorCodeExecutionToolResultErrorParam object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: optional string or null` - `BetaTextEditorCodeExecutionViewResultBlockParam object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: optional number or null` - `start_line: optional number or null` - `total_lines: optional number or null` - `BetaTextEditorCodeExecutionCreateResultBlockParam object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlockParam object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: optional array of string or null` - `new_lines: optional number or null` - `new_start: optional number or null` - `old_lines: optional number or null` - `old_start: optional number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaToolSearchToolResultBlockParam object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultErrorParam or BetaToolSearchToolSearchResultBlockParam` - `BetaToolSearchToolResultErrorParam object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: optional string or null` - `BetaToolSearchToolSearchResultBlockParam object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlockParam` - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaMCPToolUseBlockParam object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` - `server_name: string` The name of the MCP server - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaRequestMCPToolResultBlockParam object` - `type: "mcp_tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or array of BetaTextBlockParam` - `string` - `BetaMCPToolResultBlockParamContent = array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `is_error: optional boolean` - `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"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaCompactionBlockParam object` A compaction block containing summary of previous context. Users should round-trip these blocks from responses to subsequent requests to maintain context across compaction boundaries. When content is None, the block represents a failed compaction. The server treats these as no-ops. Empty string content is not allowed. - `type: "compaction"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or null` Summary of previously compacted content, or null if compaction failed - `encrypted_content: optional string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `BetaRequestToolAdditionBlock object` Mid-conversation directive to surface a declared tool. `tool` references a tool (or MCP toolset) by name from the request's `tools`; it is offered to the model from this point in the conversation onward. - `type: "tool_addition"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` 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. - `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. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `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"` - `name: string` - `server_name: string` - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaRequestToolRemovalBlock object` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name from the request's `tools`; it is no longer offered to the model from this point in the conversation onward. - `type: "tool_removal"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` 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. - `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` Reference to a single MCP tool by its server and remote name — the same `server_name`/`name` pair `mcp_tool_use` carries. - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaFallbackBlockParam object` A `fallback` block echoed back from a prior response. Accepted in `messages[].content` and not rendered into the prompt; not validated against the request's `fallbacks` chain or top-level `model`. Echo the assistant turn back verbatim, including this block in its original position. The block marks the boundary between content produced before and after a fallback hop, and the server relies on that boundary to validate the turn: when thinking runs flank the boundary, omitting the block merges them into one span the server cannot validate (the request is rejected), and moving it into the middle of a single run is likewise rejected; between non-thinking blocks the block's placement has no validation effect. - `type: "fallback"` - `from: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `trigger: optional unknown` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed. - `role: "user" or "assistant" or "system"` - `"user"` - `"assistant"` - `"system"` - `clear_at: optional "next_user_message" or "never" or null` How long this system message's text stays in front of the model. `"never"` (the default) renders it on every request that includes it. `"next_user_message"` renders it only for the user turn it follows: once a later `role: "user"` message exists in `messages` the message stays in the array (send it unchanged) but is no longer shown to the model. Only permitted on `role: "system"` messages. - `"next_user_message"` - `"never"` - `output_config: optional BetaSystemMessageOutputConfig or null` Per-message output configuration on a role:"system" input message. Fields here apply per-turn; `format` remains top-level only. An empty `{}` is accepted on a message that carries content; a message with neither content nor output_config fields is rejected. - `effort: optional "low" or "medium" or "high" or 2 more or null` All possible effort levels. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `cache_control: optional BetaCacheControlEphemeral or null` Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. - `container: optional BetaContainerParams or string or null` Container identifier for reuse across requests. - `BetaContainerParams object` Container parameters with skills to be loaded. - `id: optional string or null` Container id - `skills: optional array of BetaSkillParams or null` List of skills to load in the container maxItems: 20 - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID maxLength: 64, minLength: 1 - `version: optional string` Skill version or 'latest' for most recent version maxLength: 64, minLength: 1 - `string` - `context_management: optional BetaContextManagementConfig or null` Context management configuration. This allows you to control how Claude manages context across multiple requests, such as whether to clear function results or not. - `edits: optional array of BetaClearToolUses20250919Edit or BetaClearThinking20251015Edit or BetaCompact20260112Edit` List of context management edits to apply minItems: 0 - `BetaClearToolUses20250919Edit object` - `type: "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"` - `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) - `boolean` - `array of string` - `exclude_tools: optional array of string or null` Tool names whose uses are preserved from clearing - `keep: optional BetaToolUsesKeep` Number of tool uses to retain in the conversation - `type: "tool_uses"` - `value: number` minimum: 0 - `trigger: optional BetaInputTokensTrigger or BetaToolUsesTrigger` Condition that triggers the context management strategy - `BetaInputTokensTrigger object` - `type: "input_tokens"` - `value: number` minimum: 1 - `BetaToolUsesTrigger object` - `type: "tool_uses"` - `value: number` minimum: 1 - `BetaClearThinking20251015Edit object` - `type: "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: "thinking_turns"` - `value: number` minimum: 1 - `BetaAllThinkingTurns object` - `type: "all"` - `"all"` - `BetaCompact20260112Edit object` Automatically compact older context when reaching the configured trigger threshold. - `type: "compact_20260112"` - `instructions: optional string or null` Additional instructions for summarization. - `pause_after_compaction: optional boolean` Whether to pause after compaction and return the compaction block to the user. - `trigger: optional BetaInputTokensTrigger or null` When to trigger compaction. Defaults to 150000 input tokens. - `diagnostics: optional BetaDiagnosticsParam or null` Request-level diagnostics. Currently carries the previous response id for prompt-cache divergence reporting. - `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` The `fallback_credit_token` from a prior refusal's `stop_details`. When a preceding request was refused and returned a `fallback_credit_token`, pass that code here on the retry to have the retry's cache-creation tokens for the prefix that was warm on the refused model billed at the cache-read rate. Must be redeemed by the same organization and workspace, with the same request body (optionally extended by one appended `assistant` message whose content is the partial text — with any trailing whitespace stripped from the final text block — and paired server-tool blocks streamed before the refusal; the appended-assistant form is not available for requests with `output_format` set or forced `tool_choice`), on an eligible fallback model, on the same platform, and within 5 minutes of the refusal; a mismatch is a 400. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed with the appended-assistant form — if an exact-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry with the appended-assistant form instead. When the appended-assistant form is used on a model that otherwise disallows assistant-turn prefill, this token also authorizes that one prefill. - `string` - `BetaFallbackCreditTokenParam object` Object form of `fallback_credit_token`: the token plus a redemption mode. Requires `anthropic-beta: fallback-credit-2026-07-01`; without that header the field accepts the bare string only. The bare string and the mode-less object are equivalent (both select `strict`), so wrapping an existing token changes nothing by itself. - `token: string` 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`. - `"strict"` - `"best_effort"` - `fallbacks: optional BetaFallbacksParam or null` Opt-in server-side retry on one or more substitute models when the requested model declines for policy reasons. Tried in order: if the first entry also declines, the second is tried, and so on. The string "default" requests the requested model's server-defined default fallback configuration. - `array of BetaFallbackParam` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `max_tokens: optional number or null` - `output_config: optional BetaOutputConfig or null` - `effort: optional "low" or "medium" or "high" or 2 more or null` All possible effort levels. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `format: optional BetaJSONOutputFormat or null` A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) - `type: "json_schema"` - `schema: map[unknown]` The JSON schema of the format - `task_budget: optional BetaTokenTaskBudget or null` User-configurable total token budget across contexts. - `type: "tokens"` The budget type. Currently only 'tokens' is supported. - `total: number` Total token budget across all contexts in the session. minimum: 1024 - `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. - `"standard"` - `"fast"` - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigAdaptive or null` - `BetaThinkingConfigEnabled object` - `type: "enabled"` - `budget_tokens: number` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. minimum: 1024 - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `prefix_mismatch_behavior: optional BetaThinkingPrefixMismatchBehavior or null` What happens when a thinking block in `messages` fails the conversation check: it was created in a different conversation, or the messages before it have changed since. `"error"` (the default) fails the request with a 400 error. `"drop_block"` removes the failing blocks and the request proceeds; the model no longer sees the dropped reasoning. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` - `BetaThinkingConfigDisabled object` - `type: "disabled"` - `BetaThinkingConfigAdaptive object` - `type: "adaptive"` - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` - `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: optional array of BetaRequestMCPServerURLDefinition` MCP servers to be utilized in this request maxItems: 20 - `type: "url"` - `name: string` - `url: string` - `authorization_token: optional string or null` - `tool_configuration: optional BetaRequestMCPServerToolConfiguration or null` - `allowed_tools: optional array of string or null` - `enabled: optional boolean or null` - `metadata: optional BetaMetadata` An object describing metadata about the request. - `user_id: optional string or null` An external identifier for the user who is associated with the request. This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number. maxLength: 512 - `output_config: optional BetaOutputConfig` Configuration options for the model's output, such as the output format. - `service_tier: optional "auto" or "standard_only"` Determines whether to use priority capacity (if available) or standard capacity for this request. Anthropic offers different levels of service for your API requests. See [service-tiers](https://platform.claude.com/docs/en/api/service-tiers) for details. - `"auto"` - `"standard_only"` - `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. - `"standard"` - `"fast"` - `stop_sequences: optional array of string` Custom text sequences that will cause the model to stop generating. Our models will normally stop when they have naturally completed their turn, which will result in a response `stop_reason` of `"end_turn"`. If you want the model to stop generating when it encounters custom strings of text, you can use the `stop_sequences` parameter. If the model encounters one of the custom sequences, the response `stop_reason` value will be `"stop_sequence"` and the response `stop_sequence` value will contain the matched stop sequence. - `stream: optional boolean` Whether to incrementally stream the response using server-sent events. See [streaming](https://platform.claude.com/docs/en/build-with-claude/streaming) for details. - `system: optional string or array of BetaTextBlockParam` System prompt. A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role). - `string` - `array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `thinking: optional BetaThinkingConfigParam` Configuration for enabling Claude's extended thinking. When enabled, responses include `thinking` content blocks showing Claude's thinking process before the final answer. Requires a minimum budget of 1,024 tokens and counts towards your `max_tokens` limit. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - `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` The model will automatically decide whether to use tools. - `type: "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` The model will use any available tools. - `type: "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` The model will use the specified tool with `tool_choice.name`. - `type: "tool"` - `name: string` The name of the tool to use. - `disable_parallel_tool_use: 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` The model will not be allowed to use tools. - `type: "none"` - `tools: optional array of BetaToolUnion` Definitions of tools that the model may use. If you include `tools` in your API request, the model may return `tool_use` content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using `tool_result` content blocks. There are two types of tools: **client tools** and **server tools**. The behavior described below applies to client tools. For [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools), see their individual documentation as each has its own behavior (e.g., the [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool)). Each tool definition includes: * `name`: Name of the tool. * `description`: Optional, but strongly-recommended description of the tool. * `input_schema`: [JSON schema](https://json-schema.org/draft/2020-12) for the tool `input` shape that the model will produce in `tool_use` output content blocks. For example, if you defined `tools` as: ```json [ { "name": "get_stock_price", "description": "Get the current stock price for a given ticker symbol.", "input_schema": { "type": "object", "properties": { "ticker": { "type": "string", "description": "The stock ticker symbol, e.g. AAPL for Apple Inc." } }, "required": ["ticker"] } } ] ``` And then asked the model "What's the S&P 500 at today?", the model might produce `tool_use` content blocks in the response like this: ```json [ { "type": "tool_use", "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "name": "get_stock_price", "input": { "ticker": "^GSPC" } } ] ``` You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an input, and return the following back to the model in a subsequent `user` message: ```json [ { "type": "tool_result", "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "content": "259.75 USD" } ] ``` Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output. See our [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) for more details. - `BetaTool object` - `type: optional "custom" or null` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown] or null` - `required: optional array of string or null` - `name: string` Name of the tool. 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"` - `"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. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean or null` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolBash20241022 object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolBash20250124 object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaCodeExecutionTool20250522 object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaCodeExecutionTool20250825 object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaCodeExecutionTool20260521 object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `configs: optional BetaBrowserToolsetConfigs or null` Per-member configuration for `browser_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional BetaBrowserTypeConfig or null` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional BetaBrowserCloseTabConfig or null` `close_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional BetaBrowserDoubleClickConfig or null` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional BetaBrowserFileUploadConfig or null` `file_upload`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional BetaBrowserFindConfig or null` `find`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional BetaBrowserFormInputConfig or null` `form_input`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional BetaBrowserGetPageTextConfig or null` `get_page_text`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional BetaBrowserHoldKeyConfig or null` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional BetaBrowserHoverConfig or null` `hover`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional BetaBrowserJavascriptExecConfig or null` `javascript_exec`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional BetaBrowserKeyConfig or null` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional BetaBrowserLeftClickConfig or null` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional BetaBrowserLeftClickDragConfig or null` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional BetaBrowserLeftMouseDownConfig or null` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional BetaBrowserLeftMouseUpConfig or null` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional BetaBrowserListTabsConfig or null` `list_tabs`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional BetaBrowserMiddleClickConfig or null` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional BetaBrowserMouseMoveConfig or null` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional BetaBrowserNavigateConfig or null` `navigate`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional BetaBrowserNewTabConfig or null` `new_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional BetaBrowserReadConsoleConfig or null` `read_console`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional BetaBrowserReadNetworkConfig or null` `read_network`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional BetaBrowserReadPageConfig or null` `read_page`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional BetaBrowserRightClickConfig or null` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional BetaBrowserScreenshotConfig or null` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional BetaBrowserScrollConfig or null` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional BetaBrowserScrollToConfig or null` `scroll_to`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional BetaBrowserSwitchTabConfig or null` `switch_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional BetaBrowserTripleClickConfig or null` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional BetaBrowserWaitConfig or null` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional BetaBrowserZoomConfig or null` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `BetaToolComputerUse20241022 object` - `type: "computer_20241022"` - `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. - `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. - `display_number: optional number or null` 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` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolComputerUse20250124 object` - `type: "computer_20250124"` - `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. - `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. - `display_number: optional number or null` 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` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolComputerUse20251124 object` - `type: "computer_20251124"` - `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. - `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. - `display_number: optional number or null` 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaComputerToolset20260801 object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `configs: optional BetaComputerToolsetConfigs or null` Per-member configuration for `computer_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional BetaComputerTypeConfig or null` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional BetaComputerCursorPositionConfig or null` `cursor_position`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional BetaComputerDoubleClickConfig or null` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional BetaComputerHoldKeyConfig or null` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional BetaComputerKeyConfig or null` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional BetaComputerLeftClickConfig or null` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional BetaComputerLeftClickDragConfig or null` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional BetaComputerLeftMouseDownConfig or null` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional BetaComputerLeftMouseUpConfig or null` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional BetaComputerMiddleClickConfig or null` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional BetaComputerMouseMoveConfig or null` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional BetaComputerRightClickConfig or null` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional BetaComputerScreenshotConfig or null` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional BetaComputerScrollConfig or null` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional BetaComputerTripleClickConfig or null` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional BetaComputerWaitConfig or null` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional BetaComputerZoomConfig or null` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `BetaToolTextEditor20250124 object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolTextEditor20250429 object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolTextEditor20250728 object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `max_characters: optional number or null` 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` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `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. - `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 - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `type: "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. maxLength: 255, minLength: 1 - `BetaWebFetchTool20250910 object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `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. - `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 - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `BetaWebFetchTool20260209 object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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 - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `BetaWebSearchTool20260318 object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `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. - `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. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `BetaWebFetchTool20260318 object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `BetaAdvisorTool20260301 object` - `type: "advisor_20260301"` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `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. - `caching: optional BetaCacheControlEphemeral or null` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number or null` 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` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaToolSearchToolRegex20251119 object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaMCPToolset object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for maxLength: 255, minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `configs: optional map[BetaMCPToolConfig] or null` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional BetaMCPToolDefaultConfig` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `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. maximum: 1, minimum: 0 ### Returns - `BetaMessage object` - `type: "message"` Object type. For Messages, this is always `"message"`. default: message - `id: string` Unique object identifier. The format and length of IDs may change over time. - `container: BetaContainer or null` Information about the container used in the request (for the code execution tool) - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill or null` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID maxLength: 64, minLength: 1 - `version: string` The resolved version: a skill version ID for custom skills. maxLength: 64, minLength: 1 - `content: array of BetaContentBlock` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `BetaTextBlock object` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `text: string` minLength: 0 - `BetaThinkingBlock object` - `type: "thinking"` default: thinking - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - `thinking: string` The text of Claude's thinking process for this block. - `BetaRedactedThinkingBlock object` - `type: "redacted_thinking"` default: redacted_thinking - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#redacted-thinking-blocks) for details. - `BetaToolUseBlock object` - `type: "tool_use"` default: tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaServerToolUseBlock object` - `type: "server_tool_use"` default: server_tool_use - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebSearchToolResultBlock object` - `type: "web_search_tool_result"` default: web_search_tool_result - `content: BetaWebSearchToolResultBlockContent` - `BetaWebSearchToolResultError object` - `type: "web_search_tool_result_error"` default: web_search_tool_result_error - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `array of BetaWebSearchResultBlock` - `type: "web_search_result"` default: web_search_result - `encrypted_content: string` - `page_age: string or null` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebFetchToolResultBlock object` - `type: "web_fetch_tool_result"` default: web_fetch_tool_result - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `BetaWebFetchToolResultErrorBlock object` - `type: "web_fetch_tool_result_error"` default: web_fetch_tool_result_error - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlock object` - `type: "web_fetch_result"` default: web_fetch_result - `content: BetaDocumentBlock` - `type: "document"` default: document - `citations: BetaCitationConfig or null` Citation configuration for the document - `enabled: boolean` default: false - `source: BetaBase64PDFSource or BetaPlainTextSource` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string or null` The title of the document - `retrieved_at: string or null` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaAdvisorToolResultBlock object` - `type: "advisor_tool_result"` default: advisor_tool_result - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `BetaAdvisorToolResultError object` - `type: "advisor_tool_result_error"` default: advisor_tool_result_error - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlock object` - `type: "advisor_result"` default: advisor_result - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `BetaAdvisorRedactedResultBlock object` - `type: "advisor_redacted_result"` default: advisor_redacted_result - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaCodeExecutionToolResultBlock object` - `type: "code_execution_tool_result"` default: code_execution_tool_result - `content: BetaCodeExecutionToolResultBlockContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultError object` - `type: "code_execution_tool_result_error"` default: code_execution_tool_result_error - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlock object` - `type: "code_execution_result"` default: code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlock object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` default: encrypted_code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaBashCodeExecutionToolResultBlock object` - `type: "bash_code_execution_tool_result"` default: bash_code_execution_tool_result - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `BetaBashCodeExecutionToolResultError object` - `type: "bash_code_execution_tool_result_error"` default: bash_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlock object` - `type: "bash_code_execution_result"` default: bash_code_execution_result - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` default: bash_code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaTextEditorCodeExecutionToolResultBlock object` - `type: "text_editor_code_execution_tool_result"` default: text_editor_code_execution_tool_result - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `BetaTextEditorCodeExecutionToolResultError object` - `type: "text_editor_code_execution_tool_result_error"` default: text_editor_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string or null` - `BetaTextEditorCodeExecutionViewResultBlock object` - `type: "text_editor_code_execution_view_result"` default: text_editor_code_execution_view_result - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number or null` - `start_line: number or null` - `total_lines: number or null` - `BetaTextEditorCodeExecutionCreateResultBlock object` - `type: "text_editor_code_execution_create_result"` default: text_editor_code_execution_create_result - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlock object` - `type: "text_editor_code_execution_str_replace_result"` default: text_editor_code_execution_str_replace_result - `lines: array of string or null` - `new_lines: number or null` - `new_start: number or null` - `old_lines: number or null` - `old_start: number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaToolSearchToolResultBlock object` - `type: "tool_search_tool_result"` default: tool_search_tool_result - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `BetaToolSearchToolResultError object` - `type: "tool_search_tool_result_error"` default: tool_search_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string or null` - `BetaToolSearchToolSearchResultBlock object` - `type: "tool_search_tool_search_result"` default: tool_search_tool_search_result - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` default: tool_reference - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaMCPToolUseBlock object` - `type: "mcp_tool_use"` default: mcp_tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `BetaMCPToolResultBlock object` - `type: "mcp_tool_result"` default: mcp_tool_result - `content: string or array of BetaTextBlock` - `string` - `BetaMCPToolResultBlockContent = array of BetaTextBlock` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` minLength: 0 - `is_error: boolean` default: false - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `BetaContainerUploadBlock object` Response model for a file uploaded to the container. - `type: "container_upload"` default: container_upload - `file_id: string` - `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. - `type: "compaction"` default: compaction - `content: string or null` Summary of compacted content, or null if compaction failed - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `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. - `type: "fallback"` default: fallback - `from: BetaFallbackInfo` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfo` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `trigger: BetaFallbackRefusalTrigger` What caused the `from` model to hand over at this hop. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `context_management: BetaContextManagementResponse or null` Context management response. Information about context management strategies applied during the request. - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `BetaClearToolUses20250919EditResponse object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. default: clear_tool_uses_20250919 - `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 - `BetaClearThinking20251015EditResponse object` - `type: "clear_thinking_20251015"` The type of context management edit applied. default: clear_thinking_20251015 - `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 - `diagnostics: BetaDiagnostics or null` Response envelope for request-level diagnostics. Present (possibly null) whenever the caller supplied `diagnostics` on the request. - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more 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` - `type: "model_changed"` default: model_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissSystemChanged object` - `type: "system_changed"` default: system_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissToolsChanged object` - `type: "tools_changed"` default: tools_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissMessagesChanged object` - `type: "messages_changed"` default: messages_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissPreviousMessageNotFound object` - `type: "previous_message_not_found"` default: previous_message_not_found - `BetaCacheMissUnavailable object` - `type: "unavailable"` default: unavailable - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `role: "assistant"` Conversational role of the generated message. This will always be `"assistant"`. default: assistant - `stop_details: BetaRefusalStopDetails or null` Structured information about a refusal. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string or null` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string or null` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean or null` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string or null` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: BetaStopReason or null` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string or null` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: BetaUsage` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number 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` Outcome of the `fallback_credit_token` presented on this request. - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `BetaFallbackCreditRedeemed object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` default: redeemed - `BetaFallbackCreditNotApplied object` No reprice was applied; `reason` says why. - `type: "not_applied"` default: not_applied - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string or null` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: string or null` The geographic region where inference was performed for this request. - `input_tokens: number` The 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, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Determine which iterations exceeded long context thresholds (>=200k tokens) - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `BetaMessageIterationUsage object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration default: message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaCompactionIterationUsage object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration default: compaction - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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 - `BetaAdvisorMessageIterationUsage object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration default: advisor_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaFallbackMessageIterationUsage object` Token usage for the fallback-model attempt of a server-side fallback request. Produced in place of a `message` entry for whichever hop served the response. A declined hop produces the existing `message` entry. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response default: fallback_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `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. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. default: 0, minimum: 0 - `server_tool_use: BetaServerToolUsage or null` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. default: 0, minimum: 0 - `web_search_requests: number` The number of web search tool requests. default: 0, minimum: 0 - `service_tier: "standard" or "priority" or "batch" or null` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: "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. - `"standard"` - `"fast"` - `input_transformations: optional array of BetaThinkingDroppedInputTransformation or null` Changes the API made to the request's input before showing it to the model: one entry per change, in request order. Today the only entry type is `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when nothing was changed; without the beta, blocks are removed all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. default: thinking_dropped - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `BetaRawMessageStreamEvent = BetaRawMessageStartEvent or BetaRawMessageDeltaEvent or BetaRawMessageStopEvent or 3 more` - `BetaRawMessageStartEvent object` - `type: "message_start"` default: message_start - `message: BetaMessage` - `BetaRawMessageDeltaEvent object` - `type: "message_delta"` default: message_delta - `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` - `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, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Determine which iterations exceeded long context thresholds (>=200k tokens) - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `output_tokens: 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. - `input_transformations: optional array of BetaThinkingDroppedInputTransformation or null` Changes the API made to the request's input before showing it to the model: one entry per change, in request order. Today the only entry type is `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when nothing was changed; without the beta, blocks are removed all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. default: thinking_dropped - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `BetaRawMessageStopEvent object` - `type: "message_stop"` default: message_stop - `BetaRawContentBlockStartEvent object` - `type: "content_block_start"` default: content_block_start - `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` - `BetaRawContentBlockDeltaEvent object` - `type: "content_block_delta"` default: content_block_delta - `delta: BetaRawContentBlockDelta` - `BetaTextDelta object` - `type: "text_delta"` default: text_delta - `text: string` - `BetaInputJSONDelta object` - `type: "input_json_delta"` default: input_json_delta - `partial_json: string` - `BetaCitationsDelta object` - `type: "citations_delta"` default: citations_delta - `citation: BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` - `BetaCitationCharLocation object` - `BetaCitationPageLocation object` - `BetaCitationContentBlockLocation object` - `BetaCitationsWebSearchResultLocation object` - `BetaCitationSearchResultLocation object` - `BetaThinkingDelta object` - `type: "thinking_delta"` default: thinking_delta - `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. - `BetaSignatureDelta object` - `type: "signature_delta"` default: signature_delta - `signature: string` The `signature` for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a `signature_delta` event just before the block's `content_block_stop` event. - `BetaCompactionContentBlockDelta object` - `type: "compaction_delta"` default: compaction_delta - `content: string or null` - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `index: number` - `BetaRawContentBlockStopEvent object` - `type: "content_block_stop"` default: content_block_stop - `index: number` ### Example ```bash curl https://api.anthropic.com/v1/messages \ -H 'Content-Type: application/json' \ -H 'anthropic-version: 2023-06-01' \ -H "X-Api-Key: $ANTHROPIC_API_KEY" \ --max-time 600 \ -d '{ "max_tokens": 1024, "messages": [ { "content": "Hello, world", "role": "user" } ], "model": "claude-opus-5", "stream": false, "system": [ { "text": "Today'\''s date is 2024-06-01.", "type": "text" } ], "temperature": 1, "thinking": { "type": "adaptive" }, "tools": [ { "input_schema": { "type": "object", "properties": { "location": "bar", "unit": "bar" }, "required": [ "location" ] }, "name": "name" } ], "top_k": 5, "top_p": 0.7 }' ``` #### Response (200) ```json { "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF", "container": { "id": "container_011CpZohnwH4vuy7gazohgSP", "expires_at": "2019-12-27T18:11:19.117Z", "skills": [ { "skill_id": "pdf", "type": "anthropic", "version": "latest" } ] }, "content": [ { "citations": [ { "cited_text": "The grass is green. The sky is blue.", "document_index": 0, "document_title": "My Document", "end_char_index": 0, "file_id": "file_011CNha8iCJcU1wXNR6q4V8w", "start_char_index": 0, "type": "char_location" } ], "text": "Hi! My name is Claude.", "type": "text" } ], "context_management": { "applied_edits": [ { "cleared_input_tokens": 0, "cleared_tool_uses": 0, "type": "clear_tool_uses_20250919" } ] }, "diagnostics": { "cache_miss_reason": { "cache_missed_input_tokens": 0, "type": "model_changed" } }, "model": "claude-opus-5", "role": "assistant", "stop_details": { "category": "cyber", "explanation": "This request was declined because it conflicts with Anthropic's Usage Policy.", "fallback_credit_token": "QW50aHJvcGljL0NsYXVkZQ==", "fallback_has_prefill_claim": true, "recommended_model": "claude-opus-4-8", "type": "refusal" }, "stop_reason": "end_turn", "stop_sequence": null, "type": "message", "usage": { "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_creation_input_tokens": 2051, "cache_read_input_tokens": 2051, "fallback_credit": { "status": { "type": "redeemed" } }, "inference_geo": "global", "input_tokens": 2095, "iterations": [ { "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, "input_tokens": 0, "model": "claude-fable-5-1", "output_tokens": 0, "type": "message" } ], "output_tokens": 503, "output_tokens_details": { "thinking_tokens": 0 }, "server_tool_use": { "web_fetch_requests": 2, "web_search_requests": 0 }, "service_tier": "standard", "speed": "standard" }, "input_transformations": [ { "path": "path", "reason": "model_binding_mismatch", "type": "thinking_dropped" } ] } ``` ## Count tokens in a Message **POST** `/v1/messages/count_tokens` Count the number of tokens in a Message. The Token Count API can be used to count the number of tokens in a Message, including tools, images, and documents, without creating it. Learn more about token counting in our [user guide](https://platform.claude.com/docs/en/build-with-claude/token-counting) ### Headers - `"anthropic-beta": optional array of AnthropicBeta` Optional header to specify the beta version(s) you want to use. - `string` - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"anthropic-user-profile-id": optional string` 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. - `"anthropic-workspace-id": optional string` ### Body parameters - `messages: array of BetaMessageParam` Input messages. Our models are trained to operate on alternating `user` and `assistant` conversational turns. When creating a new `Message`, you specify the prior conversational turns with the `messages` parameter, and the model then generates the next `Message` in the conversation. Consecutive `user` or `assistant` turns in your request will be combined into a single turn. Each input message must be an object with a `role` and `content`. You can specify a single `user`-role message, or you can include multiple `user` and `assistant` messages. If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response. Example with a single `user` message: ```json [{"role": "user", "content": "Hello, Claude"}] ``` Example with multiple conversational turns: ```json [ {"role": "user", "content": "Hello there."}, {"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"}, {"role": "user", "content": "Can you explain LLMs in plain English?"}, ] ``` Example with a partially-filled response from Claude: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("}, ] ``` Each input message `content` may be either a single `string` or an array of content blocks, where each block has a specific `type`. Using a `string` for `content` is shorthand for an array of one content block of type `"text"`. The following input messages are equivalent: ```json {"role": "user", "content": "Hello, Claude"} ``` ```json {"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]} ``` See [input examples](https://platform.claude.com/docs/en/build-with-claude/working-with-messages). Note that if you want to include a [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role), you can use the top-level `system` parameter — there is no `"system"` role for input messages in the Messages API. There is a limit of 100,000 messages in a single request. - `content: string or array of BetaContentBlockParam` - `string` - `array of BetaContentBlockParam` - `BetaTextBlockParam object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaImageBlockParam object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `BetaURLImageSource object` - `type: "url"` - `url: string` - `BetaFileImageSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `transformations: optional BetaImageTransformationsParam or null` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `BetaRequestDocumentBlock object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `BetaContentBlockSource object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `string` - `BetaContentBlockSourceContent = array of BetaContentBlockSourceContent` - `BetaTextBlockParam object` - `BetaImageBlockParam object` - `BetaURLPDFSource object` - `type: "url"` - `url: string` - `BetaFileDocumentSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` - `enabled: optional boolean` - `context: optional string or null` minLength: 1 - `title: optional string or null` maxLength: 500, minLength: 1 - `BetaSearchResultBlockParam object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `source: string` - `title: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam` - `BetaThinkingBlockParam object` - `type: "thinking"` - `signature: string` The `signature` value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude. Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`. - `thinking: string` The `thinking` text of this block as returned by the API. - `BetaRedactedThinkingBlockParam object` - `type: "redacted_thinking"` - `data: string` The `data` value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged. - `BetaToolUseBlockParam object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` maxLength: 200, minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family this member belongs to. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaToolResultBlockParam object` - `type: "tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `string` - `array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `BetaTextBlockParam object` - `BetaImageBlockParam object` - `BetaSearchResultBlockParam object` - `BetaRequestDocumentBlock object` - `BetaToolReferenceBlockParam object` Tool reference block that can be included in tool_result content. - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `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 effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: "browser_state"` - `tabs: array of BetaBrowserStateTabEntry` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: 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`. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `state_changes: optional array of BetaBrowserStateChange or null` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. 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. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadStarted object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadCompleted object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: 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]*$, maxLength: 4096 - `size_bytes: optional number or null` The completed download's size. minimum: 0 - `BetaBrowserStateChangeDownloadFailed object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string or null` The failure or cancellation detail, when known. pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096 - `is_error: optional boolean` - `toolset_name: optional string or null` For a toolset member tool_result, the toolset family of the paired tool_use. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaServerToolUseBlockParam object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebSearchToolResultBlockParam object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultBlockParamContent` - `ResultBlock = array of BetaWebSearchResultBlockParam` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string or null` - `BetaWebSearchToolRequestError object` - `type: "web_search_tool_result_error"` - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebFetchToolResultBlockParam object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlockParam or BetaWebFetchBlockParam` - `BetaWebFetchToolResultErrorBlockParam object` - `type: "web_fetch_tool_result_error"` - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlockParam object` - `type: "web_fetch_result"` - `content: BetaRequestDocumentBlock` - `url: string` Fetched content URL - `retrieved_at: optional string or null` ISO 8601 timestamp when the content was retrieved - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaAdvisorToolResultBlockParam object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultErrorParam or BetaAdvisorResultBlockParam or BetaAdvisorRedactedResultBlockParam` - `BetaAdvisorToolResultErrorParam object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlockParam object` - `type: "advisor_result"` - `text: string` - `stop_reason: optional string or null` - `BetaAdvisorRedactedResultBlockParam object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: optional string or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaCodeExecutionToolResultBlockParam object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultBlockParamContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultErrorParam object` - `type: "code_execution_tool_result_error"` - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlockParam object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlockParam object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaBashCodeExecutionToolResultBlockParam object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultErrorParam or BetaBashCodeExecutionResultBlockParam` - `BetaBashCodeExecutionToolResultErrorParam object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlockParam object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlockParam` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaTextEditorCodeExecutionToolResultBlockParam object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultErrorParam or BetaTextEditorCodeExecutionViewResultBlockParam or BetaTextEditorCodeExecutionCreateResultBlockParam or BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - `BetaTextEditorCodeExecutionToolResultErrorParam object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: optional string or null` - `BetaTextEditorCodeExecutionViewResultBlockParam object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: optional number or null` - `start_line: optional number or null` - `total_lines: optional number or null` - `BetaTextEditorCodeExecutionCreateResultBlockParam object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlockParam object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: optional array of string or null` - `new_lines: optional number or null` - `new_start: optional number or null` - `old_lines: optional number or null` - `old_start: optional number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaToolSearchToolResultBlockParam object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultErrorParam or BetaToolSearchToolSearchResultBlockParam` - `BetaToolSearchToolResultErrorParam object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: optional string or null` - `BetaToolSearchToolSearchResultBlockParam object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlockParam` - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaMCPToolUseBlockParam object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` - `server_name: string` The name of the MCP server - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaRequestMCPToolResultBlockParam object` - `type: "mcp_tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or array of BetaTextBlockParam` - `string` - `BetaMCPToolResultBlockParamContent = array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `is_error: optional boolean` - `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"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaCompactionBlockParam object` A compaction block containing summary of previous context. Users should round-trip these blocks from responses to subsequent requests to maintain context across compaction boundaries. When content is None, the block represents a failed compaction. The server treats these as no-ops. Empty string content is not allowed. - `type: "compaction"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or null` Summary of previously compacted content, or null if compaction failed - `encrypted_content: optional string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `BetaRequestToolAdditionBlock object` Mid-conversation directive to surface a declared tool. `tool` references a tool (or MCP toolset) by name from the request's `tools`; it is offered to the model from this point in the conversation onward. - `type: "tool_addition"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` 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. - `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. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `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"` - `name: string` - `server_name: string` - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaRequestToolRemovalBlock object` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name from the request's `tools`; it is no longer offered to the model from this point in the conversation onward. - `type: "tool_removal"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` 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. - `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` Reference to a single MCP tool by its server and remote name — the same `server_name`/`name` pair `mcp_tool_use` carries. - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaFallbackBlockParam object` A `fallback` block echoed back from a prior response. Accepted in `messages[].content` and not rendered into the prompt; not validated against the request's `fallbacks` chain or top-level `model`. Echo the assistant turn back verbatim, including this block in its original position. The block marks the boundary between content produced before and after a fallback hop, and the server relies on that boundary to validate the turn: when thinking runs flank the boundary, omitting the block merges them into one span the server cannot validate (the request is rejected), and moving it into the middle of a single run is likewise rejected; between non-thinking blocks the block's placement has no validation effect. - `type: "fallback"` - `from: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `trigger: optional unknown` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed. - `role: "user" or "assistant" or "system"` - `"user"` - `"assistant"` - `"system"` - `clear_at: optional "next_user_message" or "never" or null` How long this system message's text stays in front of the model. `"never"` (the default) renders it on every request that includes it. `"next_user_message"` renders it only for the user turn it follows: once a later `role: "user"` message exists in `messages` the message stays in the array (send it unchanged) but is no longer shown to the model. Only permitted on `role: "system"` messages. - `"next_user_message"` - `"never"` - `output_config: optional BetaSystemMessageOutputConfig or null` Per-message output configuration on a role:"system" input message. Fields here apply per-turn; `format` remains top-level only. An empty `{}` is accepted on a message that carries content; a message with neither content nor output_config fields is rejected. - `effort: optional "low" or "medium" or "high" or 2 more or null` All possible effort levels. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `cache_control: optional BetaCacheControlEphemeral or null` Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. - `context_management: optional BetaContextManagementConfig or null` Context management configuration. This allows you to control how Claude manages context across multiple requests, such as whether to clear function results or not. - `edits: optional array of BetaClearToolUses20250919Edit or BetaClearThinking20251015Edit or BetaCompact20260112Edit` List of context management edits to apply minItems: 0 - `BetaClearToolUses20250919Edit object` - `type: "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"` - `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) - `boolean` - `array of string` - `exclude_tools: optional array of string or null` Tool names whose uses are preserved from clearing - `keep: optional BetaToolUsesKeep` Number of tool uses to retain in the conversation - `type: "tool_uses"` - `value: number` minimum: 0 - `trigger: optional BetaInputTokensTrigger or BetaToolUsesTrigger` Condition that triggers the context management strategy - `BetaInputTokensTrigger object` - `type: "input_tokens"` - `value: number` minimum: 1 - `BetaToolUsesTrigger object` - `type: "tool_uses"` - `value: number` minimum: 1 - `BetaClearThinking20251015Edit object` - `type: "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: "thinking_turns"` - `value: number` minimum: 1 - `BetaAllThinkingTurns object` - `type: "all"` - `"all"` - `BetaCompact20260112Edit object` Automatically compact older context when reaching the configured trigger threshold. - `type: "compact_20260112"` - `instructions: optional string or null` Additional instructions for summarization. - `pause_after_compaction: optional boolean` Whether to pause after compaction and return the compaction block to the user. - `trigger: optional BetaInputTokensTrigger or null` When to trigger compaction. Defaults to 150000 input tokens. - `mcp_servers: optional array of BetaRequestMCPServerURLDefinition` MCP servers to be utilized in this request maxItems: 20 - `type: "url"` - `name: string` - `url: string` - `authorization_token: optional string or null` - `tool_configuration: optional BetaRequestMCPServerToolConfiguration or null` - `allowed_tools: optional array of string or null` - `enabled: optional boolean or null` - `output_config: optional BetaOutputConfig` Configuration options for the model's output, such as the output format. - `effort: optional "low" or "medium" or "high" or 2 more or null` All possible effort levels. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `format: optional BetaJSONOutputFormat or null` A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) - `type: "json_schema"` - `schema: map[unknown]` The JSON schema of the format - `task_budget: optional BetaTokenTaskBudget or null` User-configurable total token budget across contexts. - `type: "tokens"` The budget type. Currently only 'tokens' is supported. - `total: number` Total token budget across all contexts in the session. minimum: 1024 - `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. - `"standard"` - `"fast"` - `system: optional string or array of BetaTextBlockParam` System prompt. A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role). - `string` - `array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `thinking: optional BetaThinkingConfigParam` Configuration for enabling Claude's extended thinking. When enabled, responses include `thinking` content blocks showing Claude's thinking process before the final answer. Requires a minimum budget of 1,024 tokens and counts towards your `max_tokens` limit. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - `BetaThinkingConfigEnabled object` - `type: "enabled"` - `budget_tokens: number` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. minimum: 1024 - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `prefix_mismatch_behavior: optional BetaThinkingPrefixMismatchBehavior or null` What happens when a thinking block in `messages` fails the conversation check: it was created in a different conversation, or the messages before it have changed since. `"error"` (the default) fails the request with a 400 error. `"drop_block"` removes the failing blocks and the request proceeds; the model no longer sees the dropped reasoning. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` - `BetaThinkingConfigDisabled object` - `type: "disabled"` - `BetaThinkingConfigAdaptive object` - `type: "adaptive"` - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` - `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` The model will automatically decide whether to use tools. - `type: "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` The model will use any available tools. - `type: "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` The model will use the specified tool with `tool_choice.name`. - `type: "tool"` - `name: string` The name of the tool to use. - `disable_parallel_tool_use: 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` The model will not be allowed to use tools. - `type: "none"` - `tools: optional array of BetaTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` Definitions of tools that the model may use. If you include `tools` in your API request, the model may return `tool_use` content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using `tool_result` content blocks. There are two types of tools: **client tools** and **server tools**. The behavior described below applies to client tools. For [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools), see their individual documentation as each has its own behavior (e.g., the [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool)). Each tool definition includes: * `name`: Name of the tool. * `description`: Optional, but strongly-recommended description of the tool. * `input_schema`: [JSON schema](https://json-schema.org/draft/2020-12) for the tool `input` shape that the model will produce in `tool_use` output content blocks. For example, if you defined `tools` as: ```json [ { "name": "get_stock_price", "description": "Get the current stock price for a given ticker symbol.", "input_schema": { "type": "object", "properties": { "ticker": { "type": "string", "description": "The stock ticker symbol, e.g. AAPL for Apple Inc." } }, "required": ["ticker"] } } ] ``` And then asked the model "What's the S&P 500 at today?", the model might produce `tool_use` content blocks in the response like this: ```json [ { "type": "tool_use", "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "name": "get_stock_price", "input": { "ticker": "^GSPC" } } ] ``` You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an input, and return the following back to the model in a subsequent `user` message: ```json [ { "type": "tool_result", "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "content": "259.75 USD" } ] ``` Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output. See our [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) for more details. - `BetaTool object` - `type: optional "custom" or null` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown] or null` - `required: optional array of string or null` - `name: string` Name of the tool. 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"` - `"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. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean or null` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolBash20241022 object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolBash20250124 object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaCodeExecutionTool20250522 object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaCodeExecutionTool20250825 object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaCodeExecutionTool20260521 object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `configs: optional BetaBrowserToolsetConfigs or null` Per-member configuration for `browser_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional BetaBrowserTypeConfig or null` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional BetaBrowserCloseTabConfig or null` `close_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional BetaBrowserDoubleClickConfig or null` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional BetaBrowserFileUploadConfig or null` `file_upload`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional BetaBrowserFindConfig or null` `find`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional BetaBrowserFormInputConfig or null` `form_input`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional BetaBrowserGetPageTextConfig or null` `get_page_text`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional BetaBrowserHoldKeyConfig or null` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional BetaBrowserHoverConfig or null` `hover`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional BetaBrowserJavascriptExecConfig or null` `javascript_exec`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional BetaBrowserKeyConfig or null` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional BetaBrowserLeftClickConfig or null` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional BetaBrowserLeftClickDragConfig or null` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional BetaBrowserLeftMouseDownConfig or null` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional BetaBrowserLeftMouseUpConfig or null` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional BetaBrowserListTabsConfig or null` `list_tabs`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional BetaBrowserMiddleClickConfig or null` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional BetaBrowserMouseMoveConfig or null` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional BetaBrowserNavigateConfig or null` `navigate`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional BetaBrowserNewTabConfig or null` `new_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional BetaBrowserReadConsoleConfig or null` `read_console`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional BetaBrowserReadNetworkConfig or null` `read_network`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional BetaBrowserReadPageConfig or null` `read_page`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional BetaBrowserRightClickConfig or null` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional BetaBrowserScreenshotConfig or null` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional BetaBrowserScrollConfig or null` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional BetaBrowserScrollToConfig or null` `scroll_to`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional BetaBrowserSwitchTabConfig or null` `switch_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional BetaBrowserTripleClickConfig or null` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional BetaBrowserWaitConfig or null` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional BetaBrowserZoomConfig or null` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `BetaToolComputerUse20241022 object` - `type: "computer_20241022"` - `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. - `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. - `display_number: optional number or null` 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` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolComputerUse20250124 object` - `type: "computer_20250124"` - `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. - `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. - `display_number: optional number or null` 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` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolComputerUse20251124 object` - `type: "computer_20251124"` - `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. - `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. - `display_number: optional number or null` 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaComputerToolset20260801 object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `configs: optional BetaComputerToolsetConfigs or null` Per-member configuration for `computer_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional BetaComputerTypeConfig or null` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional BetaComputerCursorPositionConfig or null` `cursor_position`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional BetaComputerDoubleClickConfig or null` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional BetaComputerHoldKeyConfig or null` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional BetaComputerKeyConfig or null` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional BetaComputerLeftClickConfig or null` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional BetaComputerLeftClickDragConfig or null` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional BetaComputerLeftMouseDownConfig or null` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional BetaComputerLeftMouseUpConfig or null` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional BetaComputerMiddleClickConfig or null` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional BetaComputerMouseMoveConfig or null` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional BetaComputerRightClickConfig or null` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional BetaComputerScreenshotConfig or null` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional BetaComputerScrollConfig or null` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional BetaComputerTripleClickConfig or null` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional BetaComputerWaitConfig or null` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional BetaComputerZoomConfig or null` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `BetaToolTextEditor20250124 object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolTextEditor20250429 object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolTextEditor20250728 object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `max_characters: optional number or null` 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` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `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. - `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 - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `type: "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. maxLength: 255, minLength: 1 - `BetaWebFetchTool20250910 object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `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. - `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 - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `BetaWebFetchTool20260209 object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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 - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `BetaWebSearchTool20260318 object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `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. - `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. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `BetaWebFetchTool20260318 object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `BetaAdvisorTool20260301 object` - `type: "advisor_20260301"` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `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. - `caching: optional BetaCacheControlEphemeral or null` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number or null` 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` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaToolSearchToolRegex20251119 object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaMCPToolset object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for maxLength: 255, minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `configs: optional map[BetaMCPToolConfig] or null` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional BetaMCPToolDefaultConfig` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `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. ### Returns - `BetaMessageTokensCount object` - `context_management: BetaCountTokensContextManagementResponse or null` Information about context management applied to the message. - `original_input_tokens: number` The original token count before context management was applied - `input_tokens: number` The total number of tokens across the provided list of messages, system prompt, and tools. ### Example ```bash curl https://api.anthropic.com/v1/messages/count_tokens \ -H 'Content-Type: application/json' \ -H 'anthropic-version: 2023-06-01' \ -H "X-Api-Key: $ANTHROPIC_API_KEY" \ -d '{ "messages": [ { "content": "Hello, world", "role": "user" } ], "model": "claude-opus-5", "system": [ { "text": "Today'\''s date is 2024-06-01.", "type": "text" } ], "thinking": { "type": "adaptive" }, "tools": [ { "input_schema": { "type": "object", "properties": { "location": "bar", "unit": "bar" }, "required": [ "location" ] }, "name": "name" } ] }' ``` #### Response (200) ```json { "context_management": { "original_input_tokens": 0 }, "input_tokens": 2095 } ``` ## Domain types ### Beta Advisor Message Iteration Usage - `BetaAdvisorMessageIterationUsage object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration default: advisor_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `output_tokens: number` The number of output tokens which were used. minimum: 0 ### Beta Advisor Redacted Result Block - `BetaAdvisorRedactedResultBlock object` - `type: "advisor_redacted_result"` default: advisor_redacted_result - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). ### Beta Advisor Redacted Result Block Param - `BetaAdvisorRedactedResultBlockParam object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: optional string or null` ### Beta Advisor Result Block - `BetaAdvisorResultBlock object` - `type: "advisor_result"` default: advisor_result - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` ### Beta Advisor Result Block Param - `BetaAdvisorResultBlockParam object` - `type: "advisor_result"` - `text: string` - `stop_reason: optional string or null` ### Beta Advisor Tool 20260301 - `BetaAdvisorTool20260301 object` - `type: "advisor_20260301"` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `caching: optional BetaCacheControlEphemeral or null` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number or null` 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 ### Beta Advisor Tool Result Block - `BetaAdvisorToolResultBlock object` - `type: "advisor_tool_result"` default: advisor_tool_result - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `BetaAdvisorToolResultError object` - `type: "advisor_tool_result_error"` default: advisor_tool_result_error - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlock object` - `type: "advisor_result"` default: advisor_result - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `BetaAdvisorRedactedResultBlock object` - `type: "advisor_redacted_result"` default: advisor_redacted_result - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Advisor Tool Result Block Param - `BetaAdvisorToolResultBlockParam object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultErrorParam or BetaAdvisorResultBlockParam or BetaAdvisorRedactedResultBlockParam` - `BetaAdvisorToolResultErrorParam object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlockParam object` - `type: "advisor_result"` - `text: string` - `stop_reason: optional string or null` - `BetaAdvisorRedactedResultBlockParam object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: optional string or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` ### Beta Advisor Tool Result Error - `BetaAdvisorToolResultError object` - `type: "advisor_tool_result_error"` default: advisor_tool_result_error - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` ### Beta Advisor Tool Result Error Param - `BetaAdvisorToolResultErrorParam object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` ### Beta All Thinking Turns - `BetaAllThinkingTurns object` - `type: "all"` ### Beta Base64 Image Source - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` ### Beta Base64 PDF Source - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` ### Beta Bash Code Execution Output Block - `BetaBashCodeExecutionOutputBlock object` - `type: "bash_code_execution_output"` default: bash_code_execution_output - `file_id: string` ### Beta Bash Code Execution Output Block Param - `BetaBashCodeExecutionOutputBlockParam object` - `type: "bash_code_execution_output"` - `file_id: string` ### Beta Bash Code Execution Result Block - `BetaBashCodeExecutionResultBlock object` - `type: "bash_code_execution_result"` default: bash_code_execution_result - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` default: bash_code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` ### Beta Bash Code Execution Result Block Param - `BetaBashCodeExecutionResultBlockParam object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlockParam` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` ### Beta Bash Code Execution Tool Result Block - `BetaBashCodeExecutionToolResultBlock object` - `type: "bash_code_execution_tool_result"` default: bash_code_execution_tool_result - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `BetaBashCodeExecutionToolResultError object` - `type: "bash_code_execution_tool_result_error"` default: bash_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlock object` - `type: "bash_code_execution_result"` default: bash_code_execution_result - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` default: bash_code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Bash Code Execution Tool Result Block Param - `BetaBashCodeExecutionToolResultBlockParam object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultErrorParam or BetaBashCodeExecutionResultBlockParam` - `BetaBashCodeExecutionToolResultErrorParam object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlockParam object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlockParam` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` ### Beta Bash Code Execution Tool Result Error - `BetaBashCodeExecutionToolResultError object` - `type: "bash_code_execution_tool_result_error"` default: bash_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` ### Beta Bash Code Execution Tool Result Error Param - `BetaBashCodeExecutionToolResultErrorParam object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` ### Beta Browser Close Tab Config - `BetaBrowserCloseTabConfig object` `close_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Double Click Config - `BetaBrowserDoubleClickConfig object` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser File Upload Config - `BetaBrowserFileUploadConfig object` `file_upload`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Find Config - `BetaBrowserFindConfig object` `find`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Form Input Config - `BetaBrowserFormInputConfig object` `form_input`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Get Page Text Config - `BetaBrowserGetPageTextConfig object` `get_page_text`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Hold Key Config - `BetaBrowserHoldKeyConfig object` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Hover Config - `BetaBrowserHoverConfig object` `hover`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Javascript Exec Config - `BetaBrowserJavascriptExecConfig object` `javascript_exec`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Key Config - `BetaBrowserKeyConfig object` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Left Click Config - `BetaBrowserLeftClickConfig object` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Left Click Drag Config - `BetaBrowserLeftClickDragConfig object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Left Mouse Down Config - `BetaBrowserLeftMouseDownConfig object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Left Mouse Up Config - `BetaBrowserLeftMouseUpConfig object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser List Tabs Config - `BetaBrowserListTabsConfig object` `list_tabs`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Middle Click Config - `BetaBrowserMiddleClickConfig object` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Mouse Move Config - `BetaBrowserMouseMoveConfig object` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Navigate Config - `BetaBrowserNavigateConfig object` `navigate`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser New Tab Config - `BetaBrowserNewTabConfig object` `new_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Read Console Config - `BetaBrowserReadConsoleConfig object` `read_console`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Read Network Config - `BetaBrowserReadNetworkConfig object` `read_network`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Read Page Config - `BetaBrowserReadPageConfig object` `read_page`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Right Click Config - `BetaBrowserRightClickConfig object` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Screenshot Config - `BetaBrowserScreenshotConfig object` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Scroll Config - `BetaBrowserScrollConfig object` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Scroll To Config - `BetaBrowserScrollToConfig object` `scroll_to`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser State Block Param - `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 effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: "browser_state"` - `tabs: array of BetaBrowserStateTabEntry` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: 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`. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `state_changes: optional array of BetaBrowserStateChange or null` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. 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. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadStarted object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadCompleted object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: 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]*$, maxLength: 4096 - `size_bytes: optional number or null` The completed download's size. minimum: 0 - `BetaBrowserStateChangeDownloadFailed object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string or null` The failure or cancellation detail, when known. pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096 ### Beta Browser State Change - `BetaBrowserStateChange = BetaBrowserStateChangeTabOpened or BetaBrowserStateChangeDownloadStarted or BetaBrowserStateChangeDownloadCompleted or BetaBrowserStateChangeDownloadFailed` A tab this call's execution opened that remains open at its end — the creation delta of the `tabs` inventory, not an event log. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `BetaBrowserStateChangeTabOpened object` A tab this call's execution opened that remains open at its end — the creation delta of the `tabs` inventory, not an event log. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadStarted object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadCompleted object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: 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]*$, maxLength: 4096 - `size_bytes: optional number or null` The completed download's size. minimum: 0 - `BetaBrowserStateChangeDownloadFailed object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string or null` The failure or cancellation detail, when known. pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096 ### Beta Browser State Change Download Completed - `BetaBrowserStateChangeDownloadCompleted object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: 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]*$, maxLength: 4096 - `size_bytes: optional number or null` The completed download's size. minimum: 0 ### Beta Browser State Change Download Failed - `BetaBrowserStateChangeDownloadFailed object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string or null` The failure or cancellation detail, when known. pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096 ### Beta Browser State Change Download Started - `BetaBrowserStateChangeDownloadStarted object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ ### Beta Browser State Change Tab Opened - `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. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ ### Beta Browser State Tab Entry - `BetaBrowserStateTabEntry object` One open browser tab reported in a `browser_state` block's `tabs` inventory. `tab_id` is the caller-assigned identifier for the tab; `title` and `url` describe the page the tab is currently showing and may be empty strings (a blank tab legitimately has both empty). `active` marks the tab that is active after this call; whenever `tabs` is non-empty, exactly one entry is marked. - `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`. ### Beta Browser Switch Tab Config - `BetaBrowserSwitchTabConfig object` `switch_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Toolset 20260801 - `BetaBrowserToolset20260801 object` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `configs: optional BetaBrowserToolsetConfigs or null` Per-member configuration for `browser_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional BetaBrowserTypeConfig or null` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional BetaBrowserCloseTabConfig or null` `close_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional BetaBrowserDoubleClickConfig or null` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional BetaBrowserFileUploadConfig or null` `file_upload`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional BetaBrowserFindConfig or null` `find`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional BetaBrowserFormInputConfig or null` `form_input`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional BetaBrowserGetPageTextConfig or null` `get_page_text`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional BetaBrowserHoldKeyConfig or null` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional BetaBrowserHoverConfig or null` `hover`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional BetaBrowserJavascriptExecConfig or null` `javascript_exec`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional BetaBrowserKeyConfig or null` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional BetaBrowserLeftClickConfig or null` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional BetaBrowserLeftClickDragConfig or null` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional BetaBrowserLeftMouseDownConfig or null` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional BetaBrowserLeftMouseUpConfig or null` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional BetaBrowserListTabsConfig or null` `list_tabs`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional BetaBrowserMiddleClickConfig or null` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional BetaBrowserMouseMoveConfig or null` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional BetaBrowserNavigateConfig or null` `navigate`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional BetaBrowserNewTabConfig or null` `new_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional BetaBrowserReadConsoleConfig or null` `read_console`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional BetaBrowserReadNetworkConfig or null` `read_network`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional BetaBrowserReadPageConfig or null` `read_page`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional BetaBrowserRightClickConfig or null` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional BetaBrowserScreenshotConfig or null` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional BetaBrowserScrollConfig or null` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional BetaBrowserScrollToConfig or null` `scroll_to`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional BetaBrowserSwitchTabConfig or null` `switch_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional BetaBrowserTripleClickConfig or null` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional BetaBrowserWaitConfig or null` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional BetaBrowserZoomConfig or null` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Toolset Configs - `BetaBrowserToolsetConfigs object` Per-member configuration for `browser_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional BetaBrowserTypeConfig or null` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional BetaBrowserCloseTabConfig or null` `close_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional BetaBrowserDoubleClickConfig or null` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional BetaBrowserFileUploadConfig or null` `file_upload`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional BetaBrowserFindConfig or null` `find`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional BetaBrowserFormInputConfig or null` `form_input`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional BetaBrowserGetPageTextConfig or null` `get_page_text`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional BetaBrowserHoldKeyConfig or null` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional BetaBrowserHoverConfig or null` `hover`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional BetaBrowserJavascriptExecConfig or null` `javascript_exec`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional BetaBrowserKeyConfig or null` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional BetaBrowserLeftClickConfig or null` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional BetaBrowserLeftClickDragConfig or null` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional BetaBrowserLeftMouseDownConfig or null` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional BetaBrowserLeftMouseUpConfig or null` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional BetaBrowserListTabsConfig or null` `list_tabs`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional BetaBrowserMiddleClickConfig or null` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional BetaBrowserMouseMoveConfig or null` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional BetaBrowserNavigateConfig or null` `navigate`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional BetaBrowserNewTabConfig or null` `new_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional BetaBrowserReadConsoleConfig or null` `read_console`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional BetaBrowserReadNetworkConfig or null` `read_network`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional BetaBrowserReadPageConfig or null` `read_page`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional BetaBrowserRightClickConfig or null` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional BetaBrowserScreenshotConfig or null` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional BetaBrowserScrollConfig or null` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional BetaBrowserScrollToConfig or null` `scroll_to`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional BetaBrowserSwitchTabConfig or null` `switch_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional BetaBrowserTripleClickConfig or null` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional BetaBrowserWaitConfig or null` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional BetaBrowserZoomConfig or null` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Triple Click Config - `BetaBrowserTripleClickConfig object` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Type Config - `BetaBrowserTypeConfig object` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Wait Config - `BetaBrowserWaitConfig object` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Browser Zoom Config - `BetaBrowserZoomConfig object` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Cache Control Ephemeral - `BetaCacheControlEphemeral object` - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` ### Beta Cache Creation - `BetaCacheCreation object` - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 ### Beta Cache Miss Messages Changed - `BetaCacheMissMessagesChanged object` - `type: "messages_changed"` default: messages_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. ### Beta Cache Miss Model Changed - `BetaCacheMissModelChanged object` - `type: "model_changed"` default: model_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. ### Beta Cache Miss Previous Message Not Found - `BetaCacheMissPreviousMessageNotFound object` - `type: "previous_message_not_found"` default: previous_message_not_found ### Beta Cache Miss System Changed - `BetaCacheMissSystemChanged object` - `type: "system_changed"` default: system_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. ### Beta Cache Miss Tools Changed - `BetaCacheMissToolsChanged object` - `type: "tools_changed"` default: tools_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. ### Beta Cache Miss Unavailable - `BetaCacheMissUnavailable object` - `type: "unavailable"` default: unavailable ### Beta Citation Char Location - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 ### Beta Citation Char Location Param - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 ### Beta Citation Config - `BetaCitationConfig object` - `enabled: boolean` default: false ### Beta Citation Content Block Location - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 ### Beta Citation Content Block Location Param - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 ### Beta Citation Page Location - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 ### Beta Citation Page Location Param - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 ### Beta Citation Search Result Location - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` ### Beta Citation Search Result Location Param - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` ### Beta Citation Web Search Result Location Param - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 ### Beta Citations Config Param - `BetaCitationsConfigParam object` - `enabled: optional boolean` ### Beta Citations Delta - `BetaCitationsDelta object` - `type: "citations_delta"` default: citations_delta - `citation: BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` ### Beta Citations Web Search Result Location - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` ### Beta Clear Thinking 20251015 Edit - `BetaClearThinking20251015Edit object` - `type: "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: "thinking_turns"` - `value: number` minimum: 1 - `BetaAllThinkingTurns object` - `type: "all"` - `"all"` ### Beta Clear Thinking 20251015 Edit Response - `BetaClearThinking20251015EditResponse object` - `type: "clear_thinking_20251015"` The type of context management edit applied. default: clear_thinking_20251015 - `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 ### Beta Clear Tool Uses 20250919 Edit - `BetaClearToolUses20250919Edit object` - `type: "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"` - `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) - `boolean` - `array of string` - `exclude_tools: optional array of string or null` Tool names whose uses are preserved from clearing - `keep: optional BetaToolUsesKeep` Number of tool uses to retain in the conversation - `type: "tool_uses"` - `value: number` minimum: 0 - `trigger: optional BetaInputTokensTrigger or BetaToolUsesTrigger` Condition that triggers the context management strategy - `BetaInputTokensTrigger object` - `type: "input_tokens"` - `value: number` minimum: 1 - `BetaToolUsesTrigger object` - `type: "tool_uses"` - `value: number` minimum: 1 ### Beta Clear Tool Uses 20250919 Edit Response - `BetaClearToolUses20250919EditResponse object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. default: clear_tool_uses_20250919 - `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 ### Beta Code Execution Output Block - `BetaCodeExecutionOutputBlock object` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` ### Beta Code Execution Output Block Param - `BetaCodeExecutionOutputBlockParam object` - `type: "code_execution_output"` - `file_id: string` ### Beta Code Execution Result Block - `BetaCodeExecutionResultBlock object` - `type: "code_execution_result"` default: code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` ### Beta Code Execution Result Block Param - `BetaCodeExecutionResultBlockParam object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` ### Beta Code Execution Tool 20250522 - `BetaCodeExecutionTool20250522 object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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 ### Beta Code Execution Tool 20250825 - `BetaCodeExecutionTool20250825 object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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 ### Beta Code Execution Tool 20260120 - `BetaCodeExecutionTool20260120 object` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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 ### Beta Code Execution Tool 20260521 - `BetaCodeExecutionTool20260521 object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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 ### Beta Code Execution Tool Result Block - `BetaCodeExecutionToolResultBlock object` - `type: "code_execution_tool_result"` default: code_execution_tool_result - `content: BetaCodeExecutionToolResultBlockContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultError object` - `type: "code_execution_tool_result_error"` default: code_execution_tool_result_error - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlock object` - `type: "code_execution_result"` default: code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlock object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` default: encrypted_code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Code Execution Tool Result Block Content - `BetaCodeExecutionToolResultBlockContent = BetaCodeExecutionToolResultError or BetaCodeExecutionResultBlock or BetaEncryptedCodeExecutionResultBlock` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultError object` - `type: "code_execution_tool_result_error"` default: code_execution_tool_result_error - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlock object` - `type: "code_execution_result"` default: code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlock object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` default: encrypted_code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` ### Beta Code Execution Tool Result Block Param - `BetaCodeExecutionToolResultBlockParam object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultBlockParamContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultErrorParam object` - `type: "code_execution_tool_result_error"` - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlockParam object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlockParam object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` ### Beta Code Execution Tool Result Block Param Content - `BetaCodeExecutionToolResultBlockParamContent = BetaCodeExecutionToolResultErrorParam or BetaCodeExecutionResultBlockParam or BetaEncryptedCodeExecutionResultBlockParam` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultErrorParam object` - `type: "code_execution_tool_result_error"` - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlockParam object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlockParam object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` ### Beta Code Execution Tool Result Error - `BetaCodeExecutionToolResultError object` - `type: "code_execution_tool_result_error"` default: code_execution_tool_result_error - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` ### Beta Code Execution Tool Result Error Code - `BetaCodeExecutionToolResultErrorCode = "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` ### Beta Code Execution Tool Result Error Param - `BetaCodeExecutionToolResultErrorParam object` - `type: "code_execution_tool_result_error"` - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` ### Beta Compact 20260112 Edit - `BetaCompact20260112Edit object` Automatically compact older context when reaching the configured trigger threshold. - `type: "compact_20260112"` - `instructions: optional string or null` Additional instructions for summarization. - `pause_after_compaction: optional boolean` Whether to pause after compaction and return the compaction block to the user. - `trigger: optional BetaInputTokensTrigger or null` When to trigger compaction. Defaults to 150000 input tokens. - `type: "input_tokens"` - `value: number` minimum: 1 ### Beta Compaction Block - `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. - `type: "compaction"` default: compaction - `content: string or null` Summary of compacted content, or null if compaction failed - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim ### Beta Compaction Block Param - `BetaCompactionBlockParam object` A compaction block containing summary of previous context. Users should round-trip these blocks from responses to subsequent requests to maintain context across compaction boundaries. When content is None, the block represents a failed compaction. The server treats these as no-ops. Empty string content is not allowed. - `type: "compaction"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `content: optional string or null` Summary of previously compacted content, or null if compaction failed - `encrypted_content: optional string or null` Opaque metadata from prior compaction, to be round-tripped verbatim ### Beta Compaction Content Block Delta - `BetaCompactionContentBlockDelta object` - `type: "compaction_delta"` default: compaction_delta - `content: string or null` - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim ### Beta Compaction Iteration Usage - `BetaCompactionIterationUsage object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration default: compaction - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number` 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 ### Beta Computer Cursor Position Config - `BetaComputerCursorPositionConfig object` `cursor_position`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Double Click Config - `BetaComputerDoubleClickConfig object` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Hold Key Config - `BetaComputerHoldKeyConfig object` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Key Config - `BetaComputerKeyConfig object` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Left Click Config - `BetaComputerLeftClickConfig object` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Left Click Drag Config - `BetaComputerLeftClickDragConfig object` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Left Mouse Down Config - `BetaComputerLeftMouseDownConfig object` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Left Mouse Up Config - `BetaComputerLeftMouseUpConfig object` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Middle Click Config - `BetaComputerMiddleClickConfig object` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Mouse Move Config - `BetaComputerMouseMoveConfig object` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Right Click Config - `BetaComputerRightClickConfig object` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Screenshot Config - `BetaComputerScreenshotConfig object` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Scroll Config - `BetaComputerScrollConfig object` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Toolset 20260801 - `BetaComputerToolset20260801 object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `configs: optional BetaComputerToolsetConfigs or null` Per-member configuration for `computer_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional BetaComputerTypeConfig or null` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional BetaComputerCursorPositionConfig or null` `cursor_position`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional BetaComputerDoubleClickConfig or null` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional BetaComputerHoldKeyConfig or null` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional BetaComputerKeyConfig or null` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional BetaComputerLeftClickConfig or null` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional BetaComputerLeftClickDragConfig or null` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional BetaComputerLeftMouseDownConfig or null` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional BetaComputerLeftMouseUpConfig or null` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional BetaComputerMiddleClickConfig or null` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional BetaComputerMouseMoveConfig or null` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional BetaComputerRightClickConfig or null` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional BetaComputerScreenshotConfig or null` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional BetaComputerScrollConfig or null` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional BetaComputerTripleClickConfig or null` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional BetaComputerWaitConfig or null` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional BetaComputerZoomConfig or null` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Toolset Configs - `BetaComputerToolsetConfigs object` Per-member configuration for `computer_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional BetaComputerTypeConfig or null` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional BetaComputerCursorPositionConfig or null` `cursor_position`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional BetaComputerDoubleClickConfig or null` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional BetaComputerHoldKeyConfig or null` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional BetaComputerKeyConfig or null` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional BetaComputerLeftClickConfig or null` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional BetaComputerLeftClickDragConfig or null` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional BetaComputerLeftMouseDownConfig or null` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional BetaComputerLeftMouseUpConfig or null` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional BetaComputerMiddleClickConfig or null` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional BetaComputerMouseMoveConfig or null` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional BetaComputerRightClickConfig or null` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional BetaComputerScreenshotConfig or null` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional BetaComputerScrollConfig or null` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional BetaComputerTripleClickConfig or null` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional BetaComputerWaitConfig or null` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional BetaComputerZoomConfig or null` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Triple Click Config - `BetaComputerTripleClickConfig object` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Type Config - `BetaComputerTypeConfig object` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Wait Config - `BetaComputerWaitConfig object` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Computer Zoom Config - `BetaComputerZoomConfig object` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. ### Beta Container - `BetaContainer object` Information about the container used in the request (for the code execution tool) - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill or null` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID maxLength: 64, minLength: 1 - `version: string` The resolved version: a skill version ID for custom skills. maxLength: 64, minLength: 1 ### Beta Container Params - `BetaContainerParams object` Container parameters with skills to be loaded. - `id: optional string or null` Container id - `skills: optional array of BetaSkillParams or null` List of skills to load in the container maxItems: 20 - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID maxLength: 64, minLength: 1 - `version: optional string` Skill version or 'latest' for most recent version maxLength: 64, minLength: 1 ### Beta Container Skill - `BetaContainerSkill object` A skill that was loaded in a container (response model). - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID maxLength: 64, minLength: 1 - `version: string` The resolved version: a skill version ID for custom skills. maxLength: 64, minLength: 1 ### Beta Container Upload Block - `BetaContainerUploadBlock object` Response model for a file uploaded to the container. - `type: "container_upload"` default: container_upload - `file_id: string` ### Beta Container Upload Block Param - `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"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` ### Beta Content Block - `BetaContentBlock = BetaTextBlock or BetaThinkingBlock or BetaRedactedThinkingBlock or 14 more` Response model for a file uploaded to the container. - `BetaTextBlock object` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `text: string` minLength: 0 - `BetaThinkingBlock object` - `type: "thinking"` default: thinking - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - `thinking: string` The text of Claude's thinking process for this block. - `BetaRedactedThinkingBlock object` - `type: "redacted_thinking"` default: redacted_thinking - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#redacted-thinking-blocks) for details. - `BetaToolUseBlock object` - `type: "tool_use"` default: tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaServerToolUseBlock object` - `type: "server_tool_use"` default: server_tool_use - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebSearchToolResultBlock object` - `type: "web_search_tool_result"` default: web_search_tool_result - `content: BetaWebSearchToolResultBlockContent` - `BetaWebSearchToolResultError object` - `type: "web_search_tool_result_error"` default: web_search_tool_result_error - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `array of BetaWebSearchResultBlock` - `type: "web_search_result"` default: web_search_result - `encrypted_content: string` - `page_age: string or null` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebFetchToolResultBlock object` - `type: "web_fetch_tool_result"` default: web_fetch_tool_result - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `BetaWebFetchToolResultErrorBlock object` - `type: "web_fetch_tool_result_error"` default: web_fetch_tool_result_error - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlock object` - `type: "web_fetch_result"` default: web_fetch_result - `content: BetaDocumentBlock` - `type: "document"` default: document - `citations: BetaCitationConfig or null` Citation configuration for the document - `enabled: boolean` default: false - `source: BetaBase64PDFSource or BetaPlainTextSource` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string or null` The title of the document - `retrieved_at: string or null` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaAdvisorToolResultBlock object` - `type: "advisor_tool_result"` default: advisor_tool_result - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `BetaAdvisorToolResultError object` - `type: "advisor_tool_result_error"` default: advisor_tool_result_error - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlock object` - `type: "advisor_result"` default: advisor_result - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `BetaAdvisorRedactedResultBlock object` - `type: "advisor_redacted_result"` default: advisor_redacted_result - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaCodeExecutionToolResultBlock object` - `type: "code_execution_tool_result"` default: code_execution_tool_result - `content: BetaCodeExecutionToolResultBlockContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultError object` - `type: "code_execution_tool_result_error"` default: code_execution_tool_result_error - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlock object` - `type: "code_execution_result"` default: code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlock object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` default: encrypted_code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaBashCodeExecutionToolResultBlock object` - `type: "bash_code_execution_tool_result"` default: bash_code_execution_tool_result - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `BetaBashCodeExecutionToolResultError object` - `type: "bash_code_execution_tool_result_error"` default: bash_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlock object` - `type: "bash_code_execution_result"` default: bash_code_execution_result - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` default: bash_code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaTextEditorCodeExecutionToolResultBlock object` - `type: "text_editor_code_execution_tool_result"` default: text_editor_code_execution_tool_result - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `BetaTextEditorCodeExecutionToolResultError object` - `type: "text_editor_code_execution_tool_result_error"` default: text_editor_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string or null` - `BetaTextEditorCodeExecutionViewResultBlock object` - `type: "text_editor_code_execution_view_result"` default: text_editor_code_execution_view_result - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number or null` - `start_line: number or null` - `total_lines: number or null` - `BetaTextEditorCodeExecutionCreateResultBlock object` - `type: "text_editor_code_execution_create_result"` default: text_editor_code_execution_create_result - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlock object` - `type: "text_editor_code_execution_str_replace_result"` default: text_editor_code_execution_str_replace_result - `lines: array of string or null` - `new_lines: number or null` - `new_start: number or null` - `old_lines: number or null` - `old_start: number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaToolSearchToolResultBlock object` - `type: "tool_search_tool_result"` default: tool_search_tool_result - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `BetaToolSearchToolResultError object` - `type: "tool_search_tool_result_error"` default: tool_search_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string or null` - `BetaToolSearchToolSearchResultBlock object` - `type: "tool_search_tool_search_result"` default: tool_search_tool_search_result - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` default: tool_reference - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaMCPToolUseBlock object` - `type: "mcp_tool_use"` default: mcp_tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `BetaMCPToolResultBlock object` - `type: "mcp_tool_result"` default: mcp_tool_result - `content: string or array of BetaTextBlock` - `string` - `BetaMCPToolResultBlockContent = array of BetaTextBlock` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` minLength: 0 - `is_error: boolean` default: false - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `BetaContainerUploadBlock object` Response model for a file uploaded to the container. - `type: "container_upload"` default: container_upload - `file_id: string` - `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. - `type: "compaction"` default: compaction - `content: string or null` Summary of compacted content, or null if compaction failed - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `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. - `type: "fallback"` default: fallback - `from: BetaFallbackInfo` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfo` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `trigger: BetaFallbackRefusalTrigger` What caused the `from` model to hand over at this hop. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. ### Beta Content Block Param - `BetaContentBlockParam = BetaTextBlockParam or BetaImageBlockParam or BetaRequestDocumentBlock or 20 more` Regular text content. - `BetaTextBlockParam object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaImageBlockParam object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `BetaURLImageSource object` - `type: "url"` - `url: string` - `BetaFileImageSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `transformations: optional BetaImageTransformationsParam or null` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `BetaRequestDocumentBlock object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `BetaContentBlockSource object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `string` - `BetaContentBlockSourceContent = array of BetaContentBlockSourceContent` - `BetaTextBlockParam object` - `BetaImageBlockParam object` - `BetaURLPDFSource object` - `type: "url"` - `url: string` - `BetaFileDocumentSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` - `enabled: optional boolean` - `context: optional string or null` minLength: 1 - `title: optional string or null` maxLength: 500, minLength: 1 - `BetaSearchResultBlockParam object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `source: string` - `title: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam` - `BetaThinkingBlockParam object` - `type: "thinking"` - `signature: string` The `signature` value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude. Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`. - `thinking: string` The `thinking` text of this block as returned by the API. - `BetaRedactedThinkingBlockParam object` - `type: "redacted_thinking"` - `data: string` The `data` value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged. - `BetaToolUseBlockParam object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` maxLength: 200, minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family this member belongs to. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaToolResultBlockParam object` - `type: "tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `string` - `array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `BetaTextBlockParam object` - `BetaImageBlockParam object` - `BetaSearchResultBlockParam object` - `BetaRequestDocumentBlock object` - `BetaToolReferenceBlockParam object` Tool reference block that can be included in tool_result content. - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `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 effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: "browser_state"` - `tabs: array of BetaBrowserStateTabEntry` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: 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`. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `state_changes: optional array of BetaBrowserStateChange or null` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. 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. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadStarted object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadCompleted object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: 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]*$, maxLength: 4096 - `size_bytes: optional number or null` The completed download's size. minimum: 0 - `BetaBrowserStateChangeDownloadFailed object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string or null` The failure or cancellation detail, when known. pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096 - `is_error: optional boolean` - `toolset_name: optional string or null` For a toolset member tool_result, the toolset family of the paired tool_use. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaServerToolUseBlockParam object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebSearchToolResultBlockParam object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultBlockParamContent` - `ResultBlock = array of BetaWebSearchResultBlockParam` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string or null` - `BetaWebSearchToolRequestError object` - `type: "web_search_tool_result_error"` - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebFetchToolResultBlockParam object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlockParam or BetaWebFetchBlockParam` - `BetaWebFetchToolResultErrorBlockParam object` - `type: "web_fetch_tool_result_error"` - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlockParam object` - `type: "web_fetch_result"` - `content: BetaRequestDocumentBlock` - `url: string` Fetched content URL - `retrieved_at: optional string or null` ISO 8601 timestamp when the content was retrieved - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaAdvisorToolResultBlockParam object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultErrorParam or BetaAdvisorResultBlockParam or BetaAdvisorRedactedResultBlockParam` - `BetaAdvisorToolResultErrorParam object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlockParam object` - `type: "advisor_result"` - `text: string` - `stop_reason: optional string or null` - `BetaAdvisorRedactedResultBlockParam object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: optional string or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaCodeExecutionToolResultBlockParam object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultBlockParamContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultErrorParam object` - `type: "code_execution_tool_result_error"` - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlockParam object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlockParam object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaBashCodeExecutionToolResultBlockParam object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultErrorParam or BetaBashCodeExecutionResultBlockParam` - `BetaBashCodeExecutionToolResultErrorParam object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlockParam object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlockParam` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaTextEditorCodeExecutionToolResultBlockParam object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultErrorParam or BetaTextEditorCodeExecutionViewResultBlockParam or BetaTextEditorCodeExecutionCreateResultBlockParam or BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - `BetaTextEditorCodeExecutionToolResultErrorParam object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: optional string or null` - `BetaTextEditorCodeExecutionViewResultBlockParam object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: optional number or null` - `start_line: optional number or null` - `total_lines: optional number or null` - `BetaTextEditorCodeExecutionCreateResultBlockParam object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlockParam object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: optional array of string or null` - `new_lines: optional number or null` - `new_start: optional number or null` - `old_lines: optional number or null` - `old_start: optional number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaToolSearchToolResultBlockParam object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultErrorParam or BetaToolSearchToolSearchResultBlockParam` - `BetaToolSearchToolResultErrorParam object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: optional string or null` - `BetaToolSearchToolSearchResultBlockParam object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlockParam` - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaMCPToolUseBlockParam object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` - `server_name: string` The name of the MCP server - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaRequestMCPToolResultBlockParam object` - `type: "mcp_tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or array of BetaTextBlockParam` - `string` - `BetaMCPToolResultBlockParamContent = array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `is_error: optional boolean` - `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"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaCompactionBlockParam object` A compaction block containing summary of previous context. Users should round-trip these blocks from responses to subsequent requests to maintain context across compaction boundaries. When content is None, the block represents a failed compaction. The server treats these as no-ops. Empty string content is not allowed. - `type: "compaction"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or null` Summary of previously compacted content, or null if compaction failed - `encrypted_content: optional string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `BetaRequestToolAdditionBlock object` Mid-conversation directive to surface a declared tool. `tool` references a tool (or MCP toolset) by name from the request's `tools`; it is offered to the model from this point in the conversation onward. - `type: "tool_addition"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` 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. - `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. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `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"` - `name: string` - `server_name: string` - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaRequestToolRemovalBlock object` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name from the request's `tools`; it is no longer offered to the model from this point in the conversation onward. - `type: "tool_removal"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` 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. - `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` Reference to a single MCP tool by its server and remote name — the same `server_name`/`name` pair `mcp_tool_use` carries. - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaFallbackBlockParam object` A `fallback` block echoed back from a prior response. Accepted in `messages[].content` and not rendered into the prompt; not validated against the request's `fallbacks` chain or top-level `model`. Echo the assistant turn back verbatim, including this block in its original position. The block marks the boundary between content produced before and after a fallback hop, and the server relies on that boundary to validate the turn: when thinking runs flank the boundary, omitting the block merges them into one span the server cannot validate (the request is rejected), and moving it into the middle of a single run is likewise rejected; between non-thinking blocks the block's placement has no validation effect. - `type: "fallback"` - `from: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `trigger: optional unknown` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed. ### Beta Content Block Source - `BetaContentBlockSource object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `string` - `BetaContentBlockSourceContent = array of BetaContentBlockSourceContent` - `BetaTextBlockParam object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaImageBlockParam object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `BetaURLImageSource object` - `type: "url"` - `url: string` - `BetaFileImageSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `transformations: optional BetaImageTransformationsParam or null` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` ### Beta Content Block Source Content - `BetaContentBlockSourceContent = BetaTextBlockParam or BetaImageBlockParam` - `BetaTextBlockParam object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaImageBlockParam object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `BetaURLImageSource object` - `type: "url"` - `url: string` - `BetaFileImageSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `transformations: optional BetaImageTransformationsParam or null` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` ### Beta Context Management Config - `BetaContextManagementConfig object` - `edits: optional array of BetaClearToolUses20250919Edit or BetaClearThinking20251015Edit or BetaCompact20260112Edit` List of context management edits to apply minItems: 0 - `BetaClearToolUses20250919Edit object` - `type: "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"` - `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) - `boolean` - `array of string` - `exclude_tools: optional array of string or null` Tool names whose uses are preserved from clearing - `keep: optional BetaToolUsesKeep` Number of tool uses to retain in the conversation - `type: "tool_uses"` - `value: number` minimum: 0 - `trigger: optional BetaInputTokensTrigger or BetaToolUsesTrigger` Condition that triggers the context management strategy - `BetaInputTokensTrigger object` - `type: "input_tokens"` - `value: number` minimum: 1 - `BetaToolUsesTrigger object` - `type: "tool_uses"` - `value: number` minimum: 1 - `BetaClearThinking20251015Edit object` - `type: "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: "thinking_turns"` - `value: number` minimum: 1 - `BetaAllThinkingTurns object` - `type: "all"` - `"all"` - `BetaCompact20260112Edit object` Automatically compact older context when reaching the configured trigger threshold. - `type: "compact_20260112"` - `instructions: optional string or null` Additional instructions for summarization. - `pause_after_compaction: optional boolean` Whether to pause after compaction and return the compaction block to the user. - `trigger: optional BetaInputTokensTrigger or null` When to trigger compaction. Defaults to 150000 input tokens. ### Beta Context Management Response - `BetaContextManagementResponse object` - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `BetaClearToolUses20250919EditResponse object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. default: clear_tool_uses_20250919 - `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 - `BetaClearThinking20251015EditResponse object` - `type: "clear_thinking_20251015"` The type of context management edit applied. default: clear_thinking_20251015 - `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 ### Beta Count Tokens Context Management Response - `BetaCountTokensContextManagementResponse object` - `original_input_tokens: number` The original token count before context management was applied ### Beta Diagnostics - `BetaDiagnostics object` Response envelope for request-level diagnostics. Present (possibly null) whenever the caller supplied `diagnostics` on the request. - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more 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` - `type: "model_changed"` default: model_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissSystemChanged object` - `type: "system_changed"` default: system_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissToolsChanged object` - `type: "tools_changed"` default: tools_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissMessagesChanged object` - `type: "messages_changed"` default: messages_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissPreviousMessageNotFound object` - `type: "previous_message_not_found"` default: previous_message_not_found - `BetaCacheMissUnavailable object` - `type: "unavailable"` default: unavailable ### Beta Diagnostics Param - `BetaDiagnosticsParam object` Request-level diagnostics. Currently carries the previous response id for prompt-cache divergence reporting. - `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 ### Beta Direct Caller - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` ### Beta Document Block - `BetaDocumentBlock object` - `type: "document"` default: document - `citations: BetaCitationConfig or null` Citation configuration for the document - `enabled: boolean` default: false - `source: BetaBase64PDFSource or BetaPlainTextSource` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string or null` The title of the document ### Beta Encrypted Code Execution Result Block - `BetaEncryptedCodeExecutionResultBlock object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` default: encrypted_code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` ### Beta Encrypted Code Execution Result Block Param - `BetaEncryptedCodeExecutionResultBlockParam object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` ### Beta Fallback Block - `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. - `type: "fallback"` default: fallback - `from: BetaFallbackInfo` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfo` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `trigger: BetaFallbackRefusalTrigger` What caused the `from` model to hand over at this hop. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. ### Beta Fallback Block Param - `BetaFallbackBlockParam object` A `fallback` block echoed back from a prior response. Accepted in `messages[].content` and not rendered into the prompt; not validated against the request's `fallbacks` chain or top-level `model`. Echo the assistant turn back verbatim, including this block in its original position. The block marks the boundary between content produced before and after a fallback hop, and the server relies on that boundary to validate the turn: when thinking runs flank the boundary, omitting the block merges them into one span the server cannot validate (the request is rejected), and moving it into the middle of a single run is likewise rejected; between non-thinking blocks the block's placement has no validation effect. - `type: "fallback"` - `from: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `trigger: optional unknown` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed. ### Beta Fallback Credit Not Applied - `BetaFallbackCreditNotApplied object` No reprice was applied; `reason` says why. - `type: "not_applied"` default: not_applied - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string or null` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. ### Beta Fallback Credit Redeemed - `BetaFallbackCreditRedeemed object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` default: redeemed ### Beta Fallback Credit Token Param - `BetaFallbackCreditTokenParam object` Object form of `fallback_credit_token`: the token plus a redemption mode. Requires `anthropic-beta: fallback-credit-2026-07-01`; without that header the field accepts the bare string only. The bare string and the mode-less object are equivalent (both select `strict`), so wrapping an existing token changes nothing by itself. - `token: string` 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`. - `"strict"` - `"best_effort"` ### Beta Fallback Credit Usage - `BetaFallbackCreditUsage object` Outcome of the `fallback_credit_token` presented on this request. - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `BetaFallbackCreditRedeemed object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` default: redeemed - `BetaFallbackCreditNotApplied object` No reprice was applied; `reason` says why. - `type: "not_applied"` default: not_applied - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string or null` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. ### Beta Fallback Info - `BetaFallbackInfo object` Identifies one hop of a fallback transition. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` ### Beta Fallback Info Param - `BetaFallbackInfoParam object` Identifies one hop of a fallback transition. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` ### Beta Fallback Message Iteration Usage - `BetaFallbackMessageIterationUsage object` Token usage for the fallback-model attempt of a server-side fallback request. Produced in place of a `message` entry for whichever hop served the response. A declined hop produces the existing `message` entry. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response default: fallback_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `output_tokens: number` The number of output tokens which were used. minimum: 0 ### Beta Fallback Param - `BetaFallbackParam object` One entry in the `fallbacks` chain on a `/v1/messages` request. `model` is required. The override fields (`max_tokens`, `thinking`, `output_config`, and `speed`) set the corresponding parameter for this attempt only and are validated as if the request were made to `model`. Any other key is rejected at parse time. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `max_tokens: optional number or null` - `output_config: optional BetaOutputConfig or null` - `effort: optional "low" or "medium" or "high" or 2 more or null` All possible effort levels. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `format: optional BetaJSONOutputFormat or null` A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) - `type: "json_schema"` - `schema: map[unknown]` The JSON schema of the format - `task_budget: optional BetaTokenTaskBudget or null` User-configurable total token budget across contexts. - `type: "tokens"` The budget type. Currently only 'tokens' is supported. - `total: number` Total token budget across all contexts in the session. minimum: 1024 - `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. - `"standard"` - `"fast"` - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigAdaptive or null` - `BetaThinkingConfigEnabled object` - `type: "enabled"` - `budget_tokens: number` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. minimum: 1024 - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `prefix_mismatch_behavior: optional BetaThinkingPrefixMismatchBehavior or null` What happens when a thinking block in `messages` fails the conversation check: it was created in a different conversation, or the messages before it have changed since. `"error"` (the default) fails the request with a 400 error. `"drop_block"` removes the failing blocks and the request proceeds; the model no longer sees the dropped reasoning. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` - `BetaThinkingConfigDisabled object` - `type: "disabled"` - `BetaThinkingConfigAdaptive object` - `type: "adaptive"` - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` ### Beta Fallback Refusal Trigger - `BetaFallbackRefusalTrigger object` The `from` model declined for policy reasons. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. ### Beta Fallbacks Param - `BetaFallbacksParam = array of BetaFallbackParam or "default"` Opt-in server-side retry on one or more substitute models when the requested model declines for policy reasons. Tried in order: if the first entry also declines, the second is tried, and so on. The string "default" requests the requested model's server-defined default fallback configuration. - `array of BetaFallbackParam` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `max_tokens: optional number or null` - `output_config: optional BetaOutputConfig or null` - `effort: optional "low" or "medium" or "high" or 2 more or null` All possible effort levels. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `format: optional BetaJSONOutputFormat or null` A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) - `type: "json_schema"` - `schema: map[unknown]` The JSON schema of the format - `task_budget: optional BetaTokenTaskBudget or null` User-configurable total token budget across contexts. - `type: "tokens"` The budget type. Currently only 'tokens' is supported. - `total: number` Total token budget across all contexts in the session. minimum: 1024 - `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. - `"standard"` - `"fast"` - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigAdaptive or null` - `BetaThinkingConfigEnabled object` - `type: "enabled"` - `budget_tokens: number` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. minimum: 1024 - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `prefix_mismatch_behavior: optional BetaThinkingPrefixMismatchBehavior or null` What happens when a thinking block in `messages` fails the conversation check: it was created in a different conversation, or the messages before it have changed since. `"error"` (the default) fails the request with a 400 error. `"drop_block"` removes the failing blocks and the request proceeds; the model no longer sees the dropped reasoning. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` - `BetaThinkingConfigDisabled object` - `type: "disabled"` - `BetaThinkingConfigAdaptive object` - `type: "adaptive"` - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` - `Default = "default"` ### Beta File Document Source - `BetaFileDocumentSource object` - `type: "file"` - `file_id: string` ### Beta File Image Source - `BetaFileImageSource object` - `type: "file"` - `file_id: string` ### Beta Image Block Param - `BetaImageBlockParam object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `BetaURLImageSource object` - `type: "url"` - `url: string` - `BetaFileImageSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `transformations: optional BetaImageTransformationsParam or null` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` ### Beta Image Transformations Param - `BetaImageTransformationsParam object` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` ### Beta Input JSON Delta - `BetaInputJSONDelta object` - `type: "input_json_delta"` default: input_json_delta - `partial_json: string` ### Beta Input Tokens Clear At Least - `BetaInputTokensClearAtLeast object` - `type: "input_tokens"` - `value: number` minimum: 0 ### Beta Input Tokens Trigger - `BetaInputTokensTrigger object` - `type: "input_tokens"` - `value: number` minimum: 1 ### Beta Iterations Usage - `BetaIterationsUsage = array of BetaMessageIterationUsage or BetaCompactionIterationUsage or BetaAdvisorMessageIterationUsage or BetaFallbackMessageIterationUsage` Per-iteration token usage breakdown. Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Determine which iterations exceeded long context thresholds (>=200k tokens) - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `BetaMessageIterationUsage object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration default: message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaCompactionIterationUsage object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration default: compaction - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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 - `BetaAdvisorMessageIterationUsage object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration default: advisor_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaFallbackMessageIterationUsage object` Token usage for the fallback-model attempt of a server-side fallback request. Produced in place of a `message` entry for whichever hop served the response. A declined hop produces the existing `message` entry. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response default: fallback_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 ### Beta JSON Output Format - `BetaJSONOutputFormat object` - `type: "json_schema"` - `schema: map[unknown]` The JSON schema of the format ### Beta MCP Tool Config - `BetaMCPToolConfig object` Configuration for a specific tool in an MCP toolset. - `defer_loading: optional boolean` - `enabled: optional boolean` ### Beta MCP Tool Default Config - `BetaMCPToolDefaultConfig object` Default configuration for tools in an MCP toolset. - `defer_loading: optional boolean` - `enabled: optional boolean` ### Beta MCP Tool Result Block - `BetaMCPToolResultBlock object` - `type: "mcp_tool_result"` default: mcp_tool_result - `content: string or array of BetaTextBlock` - `string` - `BetaMCPToolResultBlockContent = array of BetaTextBlock` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `text: string` minLength: 0 - `is_error: boolean` default: false - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ ### Beta MCP Tool Use Block - `BetaMCPToolUseBlock object` - `type: "mcp_tool_use"` default: mcp_tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server ### Beta MCP Tool Use Block Param - `BetaMCPToolUseBlockParam object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` - `server_name: string` The name of the MCP server - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` ### Beta MCP Toolset - `BetaMCPToolset object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for maxLength: 255, minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `configs: optional map[BetaMCPToolConfig] or null` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional BetaMCPToolDefaultConfig` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` ### Beta Memory Tool 20250818 - `BetaMemoryTool20250818 object` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Memory Tool 20250818 Command - `BetaMemoryTool20250818Command = BetaMemoryTool20250818ViewCommand or BetaMemoryTool20250818CreateCommand or BetaMemoryTool20250818StrReplaceCommand or 3 more` - `BetaMemoryTool20250818ViewCommand object` - `command: "view"` Command type identifier default: view - `path: string` Path to directory or file to view - `view_range: optional array of number` Optional line range for viewing specific lines minItems: 2, maxItems: 2 - `BetaMemoryTool20250818CreateCommand object` - `command: "create"` Command type identifier default: create - `file_text: string` Content to write to the file - `path: string` Path where the file should be created - `BetaMemoryTool20250818StrReplaceCommand object` - `command: "str_replace"` Command type identifier default: str_replace - `new_str: string` Text to replace with - `old_str: string` Text to search for and replace - `path: string` Path to the file where text should be replaced - `BetaMemoryTool20250818InsertCommand object` - `command: "insert"` Command type identifier default: insert - `insert_line: number` Line number where text should be inserted minimum: 1 - `insert_text: string` Text to insert at the specified line - `path: string` Path to the file where text should be inserted - `BetaMemoryTool20250818DeleteCommand object` - `command: "delete"` Command type identifier default: delete - `path: string` Path to the file or directory to delete - `BetaMemoryTool20250818RenameCommand object` - `command: "rename"` Command type identifier default: rename - `new_path: string` New path for the file or directory - `old_path: string` Current path of the file or directory ### Beta Memory Tool 20250818 Create Command - `BetaMemoryTool20250818CreateCommand object` - `command: "create"` Command type identifier default: create - `file_text: string` Content to write to the file - `path: string` Path where the file should be created ### Beta Memory Tool 20250818 Delete Command - `BetaMemoryTool20250818DeleteCommand object` - `command: "delete"` Command type identifier default: delete - `path: string` Path to the file or directory to delete ### Beta Memory Tool 20250818 Insert Command - `BetaMemoryTool20250818InsertCommand object` - `command: "insert"` Command type identifier default: insert - `insert_line: number` Line number where text should be inserted minimum: 1 - `insert_text: string` Text to insert at the specified line - `path: string` Path to the file where text should be inserted ### Beta Memory Tool 20250818 Rename Command - `BetaMemoryTool20250818RenameCommand object` - `command: "rename"` Command type identifier default: rename - `new_path: string` New path for the file or directory - `old_path: string` Current path of the file or directory ### Beta Memory Tool 20250818 Str Replace Command - `BetaMemoryTool20250818StrReplaceCommand object` - `command: "str_replace"` Command type identifier default: str_replace - `new_str: string` Text to replace with - `old_str: string` Text to search for and replace - `path: string` Path to the file where text should be replaced ### Beta Memory Tool 20250818 View Command - `BetaMemoryTool20250818ViewCommand object` - `command: "view"` Command type identifier default: view - `path: string` Path to directory or file to view - `view_range: optional array of number` Optional line range for viewing specific lines minItems: 2, maxItems: 2 ### Beta Message - `BetaMessage object` - `type: "message"` Object type. For Messages, this is always `"message"`. default: message - `id: string` Unique object identifier. The format and length of IDs may change over time. - `container: BetaContainer or null` Information about the container used in the request (for the code execution tool) - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill or null` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID maxLength: 64, minLength: 1 - `version: string` The resolved version: a skill version ID for custom skills. maxLength: 64, minLength: 1 - `content: array of BetaContentBlock` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `BetaTextBlock object` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `text: string` minLength: 0 - `BetaThinkingBlock object` - `type: "thinking"` default: thinking - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - `thinking: string` The text of Claude's thinking process for this block. - `BetaRedactedThinkingBlock object` - `type: "redacted_thinking"` default: redacted_thinking - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#redacted-thinking-blocks) for details. - `BetaToolUseBlock object` - `type: "tool_use"` default: tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaServerToolUseBlock object` - `type: "server_tool_use"` default: server_tool_use - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebSearchToolResultBlock object` - `type: "web_search_tool_result"` default: web_search_tool_result - `content: BetaWebSearchToolResultBlockContent` - `BetaWebSearchToolResultError object` - `type: "web_search_tool_result_error"` default: web_search_tool_result_error - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `array of BetaWebSearchResultBlock` - `type: "web_search_result"` default: web_search_result - `encrypted_content: string` - `page_age: string or null` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebFetchToolResultBlock object` - `type: "web_fetch_tool_result"` default: web_fetch_tool_result - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `BetaWebFetchToolResultErrorBlock object` - `type: "web_fetch_tool_result_error"` default: web_fetch_tool_result_error - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlock object` - `type: "web_fetch_result"` default: web_fetch_result - `content: BetaDocumentBlock` - `type: "document"` default: document - `citations: BetaCitationConfig or null` Citation configuration for the document - `enabled: boolean` default: false - `source: BetaBase64PDFSource or BetaPlainTextSource` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string or null` The title of the document - `retrieved_at: string or null` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaAdvisorToolResultBlock object` - `type: "advisor_tool_result"` default: advisor_tool_result - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `BetaAdvisorToolResultError object` - `type: "advisor_tool_result_error"` default: advisor_tool_result_error - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlock object` - `type: "advisor_result"` default: advisor_result - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `BetaAdvisorRedactedResultBlock object` - `type: "advisor_redacted_result"` default: advisor_redacted_result - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaCodeExecutionToolResultBlock object` - `type: "code_execution_tool_result"` default: code_execution_tool_result - `content: BetaCodeExecutionToolResultBlockContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultError object` - `type: "code_execution_tool_result_error"` default: code_execution_tool_result_error - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlock object` - `type: "code_execution_result"` default: code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlock object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` default: encrypted_code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaBashCodeExecutionToolResultBlock object` - `type: "bash_code_execution_tool_result"` default: bash_code_execution_tool_result - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `BetaBashCodeExecutionToolResultError object` - `type: "bash_code_execution_tool_result_error"` default: bash_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlock object` - `type: "bash_code_execution_result"` default: bash_code_execution_result - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` default: bash_code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaTextEditorCodeExecutionToolResultBlock object` - `type: "text_editor_code_execution_tool_result"` default: text_editor_code_execution_tool_result - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `BetaTextEditorCodeExecutionToolResultError object` - `type: "text_editor_code_execution_tool_result_error"` default: text_editor_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string or null` - `BetaTextEditorCodeExecutionViewResultBlock object` - `type: "text_editor_code_execution_view_result"` default: text_editor_code_execution_view_result - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number or null` - `start_line: number or null` - `total_lines: number or null` - `BetaTextEditorCodeExecutionCreateResultBlock object` - `type: "text_editor_code_execution_create_result"` default: text_editor_code_execution_create_result - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlock object` - `type: "text_editor_code_execution_str_replace_result"` default: text_editor_code_execution_str_replace_result - `lines: array of string or null` - `new_lines: number or null` - `new_start: number or null` - `old_lines: number or null` - `old_start: number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaToolSearchToolResultBlock object` - `type: "tool_search_tool_result"` default: tool_search_tool_result - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `BetaToolSearchToolResultError object` - `type: "tool_search_tool_result_error"` default: tool_search_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string or null` - `BetaToolSearchToolSearchResultBlock object` - `type: "tool_search_tool_search_result"` default: tool_search_tool_search_result - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` default: tool_reference - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaMCPToolUseBlock object` - `type: "mcp_tool_use"` default: mcp_tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `BetaMCPToolResultBlock object` - `type: "mcp_tool_result"` default: mcp_tool_result - `content: string or array of BetaTextBlock` - `string` - `BetaMCPToolResultBlockContent = array of BetaTextBlock` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` minLength: 0 - `is_error: boolean` default: false - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `BetaContainerUploadBlock object` Response model for a file uploaded to the container. - `type: "container_upload"` default: container_upload - `file_id: string` - `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. - `type: "compaction"` default: compaction - `content: string or null` Summary of compacted content, or null if compaction failed - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `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. - `type: "fallback"` default: fallback - `from: BetaFallbackInfo` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfo` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `trigger: BetaFallbackRefusalTrigger` What caused the `from` model to hand over at this hop. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `context_management: BetaContextManagementResponse or null` Context management response. Information about context management strategies applied during the request. - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `BetaClearToolUses20250919EditResponse object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. default: clear_tool_uses_20250919 - `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 - `BetaClearThinking20251015EditResponse object` - `type: "clear_thinking_20251015"` The type of context management edit applied. default: clear_thinking_20251015 - `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 - `diagnostics: BetaDiagnostics or null` Response envelope for request-level diagnostics. Present (possibly null) whenever the caller supplied `diagnostics` on the request. - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more 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` - `type: "model_changed"` default: model_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissSystemChanged object` - `type: "system_changed"` default: system_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissToolsChanged object` - `type: "tools_changed"` default: tools_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissMessagesChanged object` - `type: "messages_changed"` default: messages_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissPreviousMessageNotFound object` - `type: "previous_message_not_found"` default: previous_message_not_found - `BetaCacheMissUnavailable object` - `type: "unavailable"` default: unavailable - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `role: "assistant"` Conversational role of the generated message. This will always be `"assistant"`. default: assistant - `stop_details: BetaRefusalStopDetails or null` Structured information about a refusal. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string or null` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string or null` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean or null` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string or null` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: BetaStopReason or null` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string or null` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: BetaUsage` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number 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` Outcome of the `fallback_credit_token` presented on this request. - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `BetaFallbackCreditRedeemed object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` default: redeemed - `BetaFallbackCreditNotApplied object` No reprice was applied; `reason` says why. - `type: "not_applied"` default: not_applied - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string or null` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: string or null` The geographic region where inference was performed for this request. - `input_tokens: number` The 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, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Determine which iterations exceeded long context thresholds (>=200k tokens) - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `BetaMessageIterationUsage object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration default: message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaCompactionIterationUsage object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration default: compaction - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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 - `BetaAdvisorMessageIterationUsage object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration default: advisor_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaFallbackMessageIterationUsage object` Token usage for the fallback-model attempt of a server-side fallback request. Produced in place of a `message` entry for whichever hop served the response. A declined hop produces the existing `message` entry. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response default: fallback_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `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. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. default: 0, minimum: 0 - `server_tool_use: BetaServerToolUsage or null` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. default: 0, minimum: 0 - `web_search_requests: number` The number of web search tool requests. default: 0, minimum: 0 - `service_tier: "standard" or "priority" or "batch" or null` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: "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. - `"standard"` - `"fast"` - `input_transformations: optional array of BetaThinkingDroppedInputTransformation or null` Changes the API made to the request's input before showing it to the model: one entry per change, in request order. Today the only entry type is `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when nothing was changed; without the beta, blocks are removed all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. default: thinking_dropped - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` ### Beta Message Delta Usage - `BetaMessageDeltaUsage object` - `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. - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `BetaFallbackCreditRedeemed object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` default: redeemed - `BetaFallbackCreditNotApplied object` No reprice was applied; `reason` says why. - `type: "not_applied"` default: not_applied - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string or null` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `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, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Determine which iterations exceeded long context thresholds (>=200k tokens) - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `BetaMessageIterationUsage object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration default: message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaCompactionIterationUsage object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration default: compaction - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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 - `BetaAdvisorMessageIterationUsage object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration default: advisor_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaFallbackMessageIterationUsage object` Token usage for the fallback-model attempt of a server-side fallback request. Produced in place of a `message` entry for whichever hop served the response. A declined hop produces the existing `message` entry. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response default: fallback_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `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. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. default: 0, minimum: 0 - `server_tool_use: BetaServerToolUsage or null` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. default: 0, minimum: 0 - `web_search_requests: number` The number of web search tool requests. default: 0, minimum: 0 ### Beta Message Iteration Usage - `BetaMessageIterationUsage object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration default: message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `output_tokens: number` The number of output tokens which were used. minimum: 0 ### Beta Message Param - `BetaMessageParam object` - `content: string or array of BetaContentBlockParam` - `string` - `array of BetaContentBlockParam` - `BetaTextBlockParam object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaImageBlockParam object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `BetaURLImageSource object` - `type: "url"` - `url: string` - `BetaFileImageSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `transformations: optional BetaImageTransformationsParam or null` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `BetaRequestDocumentBlock object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `BetaContentBlockSource object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `string` - `BetaContentBlockSourceContent = array of BetaContentBlockSourceContent` - `BetaTextBlockParam object` - `BetaImageBlockParam object` - `BetaURLPDFSource object` - `type: "url"` - `url: string` - `BetaFileDocumentSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` - `enabled: optional boolean` - `context: optional string or null` minLength: 1 - `title: optional string or null` maxLength: 500, minLength: 1 - `BetaSearchResultBlockParam object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `source: string` - `title: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam` - `BetaThinkingBlockParam object` - `type: "thinking"` - `signature: string` The `signature` value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude. Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`. - `thinking: string` The `thinking` text of this block as returned by the API. - `BetaRedactedThinkingBlockParam object` - `type: "redacted_thinking"` - `data: string` The `data` value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged. - `BetaToolUseBlockParam object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` maxLength: 200, minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family this member belongs to. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaToolResultBlockParam object` - `type: "tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `string` - `array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `BetaTextBlockParam object` - `BetaImageBlockParam object` - `BetaSearchResultBlockParam object` - `BetaRequestDocumentBlock object` - `BetaToolReferenceBlockParam object` Tool reference block that can be included in tool_result content. - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `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 effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: "browser_state"` - `tabs: array of BetaBrowserStateTabEntry` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: 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`. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `state_changes: optional array of BetaBrowserStateChange or null` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. 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. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadStarted object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadCompleted object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: 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]*$, maxLength: 4096 - `size_bytes: optional number or null` The completed download's size. minimum: 0 - `BetaBrowserStateChangeDownloadFailed object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string or null` The failure or cancellation detail, when known. pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096 - `is_error: optional boolean` - `toolset_name: optional string or null` For a toolset member tool_result, the toolset family of the paired tool_use. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaServerToolUseBlockParam object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebSearchToolResultBlockParam object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultBlockParamContent` - `ResultBlock = array of BetaWebSearchResultBlockParam` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string or null` - `BetaWebSearchToolRequestError object` - `type: "web_search_tool_result_error"` - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebFetchToolResultBlockParam object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlockParam or BetaWebFetchBlockParam` - `BetaWebFetchToolResultErrorBlockParam object` - `type: "web_fetch_tool_result_error"` - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlockParam object` - `type: "web_fetch_result"` - `content: BetaRequestDocumentBlock` - `url: string` Fetched content URL - `retrieved_at: optional string or null` ISO 8601 timestamp when the content was retrieved - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaAdvisorToolResultBlockParam object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultErrorParam or BetaAdvisorResultBlockParam or BetaAdvisorRedactedResultBlockParam` - `BetaAdvisorToolResultErrorParam object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlockParam object` - `type: "advisor_result"` - `text: string` - `stop_reason: optional string or null` - `BetaAdvisorRedactedResultBlockParam object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: optional string or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaCodeExecutionToolResultBlockParam object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultBlockParamContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultErrorParam object` - `type: "code_execution_tool_result_error"` - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlockParam object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlockParam object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaBashCodeExecutionToolResultBlockParam object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultErrorParam or BetaBashCodeExecutionResultBlockParam` - `BetaBashCodeExecutionToolResultErrorParam object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlockParam object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlockParam` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaTextEditorCodeExecutionToolResultBlockParam object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultErrorParam or BetaTextEditorCodeExecutionViewResultBlockParam or BetaTextEditorCodeExecutionCreateResultBlockParam or BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - `BetaTextEditorCodeExecutionToolResultErrorParam object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: optional string or null` - `BetaTextEditorCodeExecutionViewResultBlockParam object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: optional number or null` - `start_line: optional number or null` - `total_lines: optional number or null` - `BetaTextEditorCodeExecutionCreateResultBlockParam object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlockParam object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: optional array of string or null` - `new_lines: optional number or null` - `new_start: optional number or null` - `old_lines: optional number or null` - `old_start: optional number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaToolSearchToolResultBlockParam object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultErrorParam or BetaToolSearchToolSearchResultBlockParam` - `BetaToolSearchToolResultErrorParam object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: optional string or null` - `BetaToolSearchToolSearchResultBlockParam object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlockParam` - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaMCPToolUseBlockParam object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` - `server_name: string` The name of the MCP server - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaRequestMCPToolResultBlockParam object` - `type: "mcp_tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or array of BetaTextBlockParam` - `string` - `BetaMCPToolResultBlockParamContent = array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `is_error: optional boolean` - `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"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaCompactionBlockParam object` A compaction block containing summary of previous context. Users should round-trip these blocks from responses to subsequent requests to maintain context across compaction boundaries. When content is None, the block represents a failed compaction. The server treats these as no-ops. Empty string content is not allowed. - `type: "compaction"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or null` Summary of previously compacted content, or null if compaction failed - `encrypted_content: optional string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `BetaRequestToolAdditionBlock object` Mid-conversation directive to surface a declared tool. `tool` references a tool (or MCP toolset) by name from the request's `tools`; it is offered to the model from this point in the conversation onward. - `type: "tool_addition"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` 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. - `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. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `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"` - `name: string` - `server_name: string` - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaRequestToolRemovalBlock object` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name from the request's `tools`; it is no longer offered to the model from this point in the conversation onward. - `type: "tool_removal"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` 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. - `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` Reference to a single MCP tool by its server and remote name — the same `server_name`/`name` pair `mcp_tool_use` carries. - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaFallbackBlockParam object` A `fallback` block echoed back from a prior response. Accepted in `messages[].content` and not rendered into the prompt; not validated against the request's `fallbacks` chain or top-level `model`. Echo the assistant turn back verbatim, including this block in its original position. The block marks the boundary between content produced before and after a fallback hop, and the server relies on that boundary to validate the turn: when thinking runs flank the boundary, omitting the block merges them into one span the server cannot validate (the request is rejected), and moving it into the middle of a single run is likewise rejected; between non-thinking blocks the block's placement has no validation effect. - `type: "fallback"` - `from: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `trigger: optional unknown` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed. - `role: "user" or "assistant" or "system"` - `"user"` - `"assistant"` - `"system"` - `clear_at: optional "next_user_message" or "never" or null` How long this system message's text stays in front of the model. `"never"` (the default) renders it on every request that includes it. `"next_user_message"` renders it only for the user turn it follows: once a later `role: "user"` message exists in `messages` the message stays in the array (send it unchanged) but is no longer shown to the model. Only permitted on `role: "system"` messages. - `"next_user_message"` - `"never"` - `output_config: optional BetaSystemMessageOutputConfig or null` Per-message output configuration on a role:"system" input message. Fields here apply per-turn; `format` remains top-level only. An empty `{}` is accepted on a message that carries content; a message with neither content nor output_config fields is rejected. - `effort: optional "low" or "medium" or "high" or 2 more or null` All possible effort levels. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` ### Beta Message Tokens Count - `BetaMessageTokensCount object` - `context_management: BetaCountTokensContextManagementResponse or null` Information about context management applied to the message. - `original_input_tokens: number` The original token count before context management was applied - `input_tokens: number` The total number of tokens across the provided list of messages, system prompt, and tools. ### Beta Metadata - `BetaMetadata object` - `user_id: optional string or null` An external identifier for the user who is associated with the request. This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number. maxLength: 512 ### Beta Output Config - `BetaOutputConfig object` - `effort: optional "low" or "medium" or "high" or 2 more or null` All possible effort levels. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `format: optional BetaJSONOutputFormat or null` A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) - `type: "json_schema"` - `schema: map[unknown]` The JSON schema of the format - `task_budget: optional BetaTokenTaskBudget or null` User-configurable total token budget across contexts. - `type: "tokens"` The budget type. Currently only 'tokens' is supported. - `total: number` Total token budget across all contexts in the session. minimum: 1024 - `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 ### Beta Output Tokens Details - `BetaOutputTokensDetails object` - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. default: 0, minimum: 0 ### Beta Plain Text Source - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` ### Beta Raw Content Block Delta - `BetaRawContentBlockDelta = BetaTextDelta or BetaInputJSONDelta or BetaCitationsDelta or 3 more` - `BetaTextDelta object` - `type: "text_delta"` default: text_delta - `text: string` - `BetaInputJSONDelta object` - `type: "input_json_delta"` default: input_json_delta - `partial_json: string` - `BetaCitationsDelta object` - `type: "citations_delta"` default: citations_delta - `citation: BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaThinkingDelta object` - `type: "thinking_delta"` default: thinking_delta - `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. - `BetaSignatureDelta object` - `type: "signature_delta"` default: signature_delta - `signature: string` The `signature` for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a `signature_delta` event just before the block's `content_block_stop` event. - `BetaCompactionContentBlockDelta object` - `type: "compaction_delta"` default: compaction_delta - `content: string or null` - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim ### Beta Raw Content Block Delta Event - `BetaRawContentBlockDeltaEvent object` - `type: "content_block_delta"` default: content_block_delta - `delta: BetaRawContentBlockDelta` - `BetaTextDelta object` - `type: "text_delta"` default: text_delta - `text: string` - `BetaInputJSONDelta object` - `type: "input_json_delta"` default: input_json_delta - `partial_json: string` - `BetaCitationsDelta object` - `type: "citations_delta"` default: citations_delta - `citation: BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaThinkingDelta object` - `type: "thinking_delta"` default: thinking_delta - `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. - `BetaSignatureDelta object` - `type: "signature_delta"` default: signature_delta - `signature: string` The `signature` for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a `signature_delta` event just before the block's `content_block_stop` event. - `BetaCompactionContentBlockDelta object` - `type: "compaction_delta"` default: compaction_delta - `content: string or null` - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `index: number` ### Beta Raw Content Block Start Event - `BetaRawContentBlockStartEvent object` - `type: "content_block_start"` default: content_block_start - `content_block: BetaTextBlock or BetaThinkingBlock or BetaRedactedThinkingBlock or 14 more` Response model for a file uploaded to the container. - `BetaTextBlock object` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `text: string` minLength: 0 - `BetaThinkingBlock object` - `type: "thinking"` default: thinking - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - `thinking: string` The text of Claude's thinking process for this block. - `BetaRedactedThinkingBlock object` - `type: "redacted_thinking"` default: redacted_thinking - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#redacted-thinking-blocks) for details. - `BetaToolUseBlock object` - `type: "tool_use"` default: tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaServerToolUseBlock object` - `type: "server_tool_use"` default: server_tool_use - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebSearchToolResultBlock object` - `type: "web_search_tool_result"` default: web_search_tool_result - `content: BetaWebSearchToolResultBlockContent` - `BetaWebSearchToolResultError object` - `type: "web_search_tool_result_error"` default: web_search_tool_result_error - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `array of BetaWebSearchResultBlock` - `type: "web_search_result"` default: web_search_result - `encrypted_content: string` - `page_age: string or null` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebFetchToolResultBlock object` - `type: "web_fetch_tool_result"` default: web_fetch_tool_result - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `BetaWebFetchToolResultErrorBlock object` - `type: "web_fetch_tool_result_error"` default: web_fetch_tool_result_error - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlock object` - `type: "web_fetch_result"` default: web_fetch_result - `content: BetaDocumentBlock` - `type: "document"` default: document - `citations: BetaCitationConfig or null` Citation configuration for the document - `enabled: boolean` default: false - `source: BetaBase64PDFSource or BetaPlainTextSource` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string or null` The title of the document - `retrieved_at: string or null` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaAdvisorToolResultBlock object` - `type: "advisor_tool_result"` default: advisor_tool_result - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `BetaAdvisorToolResultError object` - `type: "advisor_tool_result_error"` default: advisor_tool_result_error - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlock object` - `type: "advisor_result"` default: advisor_result - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `BetaAdvisorRedactedResultBlock object` - `type: "advisor_redacted_result"` default: advisor_redacted_result - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaCodeExecutionToolResultBlock object` - `type: "code_execution_tool_result"` default: code_execution_tool_result - `content: BetaCodeExecutionToolResultBlockContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultError object` - `type: "code_execution_tool_result_error"` default: code_execution_tool_result_error - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlock object` - `type: "code_execution_result"` default: code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlock object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` default: encrypted_code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaBashCodeExecutionToolResultBlock object` - `type: "bash_code_execution_tool_result"` default: bash_code_execution_tool_result - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `BetaBashCodeExecutionToolResultError object` - `type: "bash_code_execution_tool_result_error"` default: bash_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlock object` - `type: "bash_code_execution_result"` default: bash_code_execution_result - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` default: bash_code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaTextEditorCodeExecutionToolResultBlock object` - `type: "text_editor_code_execution_tool_result"` default: text_editor_code_execution_tool_result - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `BetaTextEditorCodeExecutionToolResultError object` - `type: "text_editor_code_execution_tool_result_error"` default: text_editor_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string or null` - `BetaTextEditorCodeExecutionViewResultBlock object` - `type: "text_editor_code_execution_view_result"` default: text_editor_code_execution_view_result - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number or null` - `start_line: number or null` - `total_lines: number or null` - `BetaTextEditorCodeExecutionCreateResultBlock object` - `type: "text_editor_code_execution_create_result"` default: text_editor_code_execution_create_result - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlock object` - `type: "text_editor_code_execution_str_replace_result"` default: text_editor_code_execution_str_replace_result - `lines: array of string or null` - `new_lines: number or null` - `new_start: number or null` - `old_lines: number or null` - `old_start: number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaToolSearchToolResultBlock object` - `type: "tool_search_tool_result"` default: tool_search_tool_result - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `BetaToolSearchToolResultError object` - `type: "tool_search_tool_result_error"` default: tool_search_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string or null` - `BetaToolSearchToolSearchResultBlock object` - `type: "tool_search_tool_search_result"` default: tool_search_tool_search_result - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` default: tool_reference - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaMCPToolUseBlock object` - `type: "mcp_tool_use"` default: mcp_tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `BetaMCPToolResultBlock object` - `type: "mcp_tool_result"` default: mcp_tool_result - `content: string or array of BetaTextBlock` - `string` - `BetaMCPToolResultBlockContent = array of BetaTextBlock` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` minLength: 0 - `is_error: boolean` default: false - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `BetaContainerUploadBlock object` Response model for a file uploaded to the container. - `type: "container_upload"` default: container_upload - `file_id: string` - `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. - `type: "compaction"` default: compaction - `content: string or null` Summary of compacted content, or null if compaction failed - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `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. - `type: "fallback"` default: fallback - `from: BetaFallbackInfo` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfo` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `trigger: BetaFallbackRefusalTrigger` What caused the `from` model to hand over at this hop. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `index: number` ### Beta Raw Content Block Stop Event - `BetaRawContentBlockStopEvent object` - `type: "content_block_stop"` default: content_block_stop - `index: number` ### Beta Raw Message Delta Event - `BetaRawMessageDeltaEvent object` - `type: "message_delta"` default: message_delta - `context_management: BetaContextManagementResponse or null` Information about context management strategies applied during the request - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `BetaClearToolUses20250919EditResponse object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. default: clear_tool_uses_20250919 - `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 - `BetaClearThinking20251015EditResponse object` - `type: "clear_thinking_20251015"` The type of context management edit applied. default: clear_thinking_20251015 - `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 - `delta: object` - `container: BetaContainer or null` Information about the container used in the request (for the code execution tool) - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill or null` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID maxLength: 64, minLength: 1 - `version: string` The resolved version: a skill version ID for custom skills. maxLength: 64, minLength: 1 - `stop_details: BetaRefusalStopDetails or null` Structured information about a refusal. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string or null` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string or null` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean or null` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string or null` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: BetaStopReason or null` - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string or null` - `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. - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `BetaFallbackCreditRedeemed object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` default: redeemed - `BetaFallbackCreditNotApplied object` No reprice was applied; `reason` says why. - `type: "not_applied"` default: not_applied - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string or null` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `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, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Determine which iterations exceeded long context thresholds (>=200k tokens) - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `BetaMessageIterationUsage object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration default: message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaCompactionIterationUsage object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration default: compaction - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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 - `BetaAdvisorMessageIterationUsage object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration default: advisor_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaFallbackMessageIterationUsage object` Token usage for the fallback-model attempt of a server-side fallback request. Produced in place of a `message` entry for whichever hop served the response. A declined hop produces the existing `message` entry. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response default: fallback_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `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. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. default: 0, minimum: 0 - `server_tool_use: BetaServerToolUsage or null` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. default: 0, minimum: 0 - `web_search_requests: number` The number of web search tool requests. default: 0, minimum: 0 - `input_transformations: optional array of BetaThinkingDroppedInputTransformation or null` Changes the API made to the request's input before showing it to the model: one entry per change, in request order. Today the only entry type is `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when nothing was changed; without the beta, blocks are removed all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. default: thinking_dropped - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` ### Beta Raw Message Start Event - `BetaRawMessageStartEvent object` - `type: "message_start"` default: message_start - `message: BetaMessage` - `type: "message"` Object type. For Messages, this is always `"message"`. default: message - `id: string` Unique object identifier. The format and length of IDs may change over time. - `container: BetaContainer or null` Information about the container used in the request (for the code execution tool) - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill or null` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID maxLength: 64, minLength: 1 - `version: string` The resolved version: a skill version ID for custom skills. maxLength: 64, minLength: 1 - `content: array of BetaContentBlock` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `BetaTextBlock object` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `text: string` minLength: 0 - `BetaThinkingBlock object` - `type: "thinking"` default: thinking - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - `thinking: string` The text of Claude's thinking process for this block. - `BetaRedactedThinkingBlock object` - `type: "redacted_thinking"` default: redacted_thinking - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#redacted-thinking-blocks) for details. - `BetaToolUseBlock object` - `type: "tool_use"` default: tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaServerToolUseBlock object` - `type: "server_tool_use"` default: server_tool_use - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebSearchToolResultBlock object` - `type: "web_search_tool_result"` default: web_search_tool_result - `content: BetaWebSearchToolResultBlockContent` - `BetaWebSearchToolResultError object` - `type: "web_search_tool_result_error"` default: web_search_tool_result_error - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `array of BetaWebSearchResultBlock` - `type: "web_search_result"` default: web_search_result - `encrypted_content: string` - `page_age: string or null` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebFetchToolResultBlock object` - `type: "web_fetch_tool_result"` default: web_fetch_tool_result - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `BetaWebFetchToolResultErrorBlock object` - `type: "web_fetch_tool_result_error"` default: web_fetch_tool_result_error - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlock object` - `type: "web_fetch_result"` default: web_fetch_result - `content: BetaDocumentBlock` - `type: "document"` default: document - `citations: BetaCitationConfig or null` Citation configuration for the document - `enabled: boolean` default: false - `source: BetaBase64PDFSource or BetaPlainTextSource` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string or null` The title of the document - `retrieved_at: string or null` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaAdvisorToolResultBlock object` - `type: "advisor_tool_result"` default: advisor_tool_result - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `BetaAdvisorToolResultError object` - `type: "advisor_tool_result_error"` default: advisor_tool_result_error - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlock object` - `type: "advisor_result"` default: advisor_result - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `BetaAdvisorRedactedResultBlock object` - `type: "advisor_redacted_result"` default: advisor_redacted_result - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaCodeExecutionToolResultBlock object` - `type: "code_execution_tool_result"` default: code_execution_tool_result - `content: BetaCodeExecutionToolResultBlockContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultError object` - `type: "code_execution_tool_result_error"` default: code_execution_tool_result_error - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlock object` - `type: "code_execution_result"` default: code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlock object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` default: encrypted_code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaBashCodeExecutionToolResultBlock object` - `type: "bash_code_execution_tool_result"` default: bash_code_execution_tool_result - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `BetaBashCodeExecutionToolResultError object` - `type: "bash_code_execution_tool_result_error"` default: bash_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlock object` - `type: "bash_code_execution_result"` default: bash_code_execution_result - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` default: bash_code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaTextEditorCodeExecutionToolResultBlock object` - `type: "text_editor_code_execution_tool_result"` default: text_editor_code_execution_tool_result - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `BetaTextEditorCodeExecutionToolResultError object` - `type: "text_editor_code_execution_tool_result_error"` default: text_editor_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string or null` - `BetaTextEditorCodeExecutionViewResultBlock object` - `type: "text_editor_code_execution_view_result"` default: text_editor_code_execution_view_result - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number or null` - `start_line: number or null` - `total_lines: number or null` - `BetaTextEditorCodeExecutionCreateResultBlock object` - `type: "text_editor_code_execution_create_result"` default: text_editor_code_execution_create_result - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlock object` - `type: "text_editor_code_execution_str_replace_result"` default: text_editor_code_execution_str_replace_result - `lines: array of string or null` - `new_lines: number or null` - `new_start: number or null` - `old_lines: number or null` - `old_start: number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaToolSearchToolResultBlock object` - `type: "tool_search_tool_result"` default: tool_search_tool_result - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `BetaToolSearchToolResultError object` - `type: "tool_search_tool_result_error"` default: tool_search_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string or null` - `BetaToolSearchToolSearchResultBlock object` - `type: "tool_search_tool_search_result"` default: tool_search_tool_search_result - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` default: tool_reference - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaMCPToolUseBlock object` - `type: "mcp_tool_use"` default: mcp_tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `BetaMCPToolResultBlock object` - `type: "mcp_tool_result"` default: mcp_tool_result - `content: string or array of BetaTextBlock` - `string` - `BetaMCPToolResultBlockContent = array of BetaTextBlock` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` minLength: 0 - `is_error: boolean` default: false - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `BetaContainerUploadBlock object` Response model for a file uploaded to the container. - `type: "container_upload"` default: container_upload - `file_id: string` - `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. - `type: "compaction"` default: compaction - `content: string or null` Summary of compacted content, or null if compaction failed - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `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. - `type: "fallback"` default: fallback - `from: BetaFallbackInfo` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfo` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `trigger: BetaFallbackRefusalTrigger` What caused the `from` model to hand over at this hop. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `context_management: BetaContextManagementResponse or null` Context management response. Information about context management strategies applied during the request. - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `BetaClearToolUses20250919EditResponse object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. default: clear_tool_uses_20250919 - `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 - `BetaClearThinking20251015EditResponse object` - `type: "clear_thinking_20251015"` The type of context management edit applied. default: clear_thinking_20251015 - `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 - `diagnostics: BetaDiagnostics or null` Response envelope for request-level diagnostics. Present (possibly null) whenever the caller supplied `diagnostics` on the request. - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more 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` - `type: "model_changed"` default: model_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissSystemChanged object` - `type: "system_changed"` default: system_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissToolsChanged object` - `type: "tools_changed"` default: tools_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissMessagesChanged object` - `type: "messages_changed"` default: messages_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissPreviousMessageNotFound object` - `type: "previous_message_not_found"` default: previous_message_not_found - `BetaCacheMissUnavailable object` - `type: "unavailable"` default: unavailable - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `role: "assistant"` Conversational role of the generated message. This will always be `"assistant"`. default: assistant - `stop_details: BetaRefusalStopDetails or null` Structured information about a refusal. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string or null` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string or null` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean or null` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string or null` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: BetaStopReason or null` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string or null` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: BetaUsage` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number 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` Outcome of the `fallback_credit_token` presented on this request. - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `BetaFallbackCreditRedeemed object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` default: redeemed - `BetaFallbackCreditNotApplied object` No reprice was applied; `reason` says why. - `type: "not_applied"` default: not_applied - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string or null` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: string or null` The geographic region where inference was performed for this request. - `input_tokens: number` The 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, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Determine which iterations exceeded long context thresholds (>=200k tokens) - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `BetaMessageIterationUsage object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration default: message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaCompactionIterationUsage object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration default: compaction - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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 - `BetaAdvisorMessageIterationUsage object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration default: advisor_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaFallbackMessageIterationUsage object` Token usage for the fallback-model attempt of a server-side fallback request. Produced in place of a `message` entry for whichever hop served the response. A declined hop produces the existing `message` entry. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response default: fallback_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `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. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. default: 0, minimum: 0 - `server_tool_use: BetaServerToolUsage or null` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. default: 0, minimum: 0 - `web_search_requests: number` The number of web search tool requests. default: 0, minimum: 0 - `service_tier: "standard" or "priority" or "batch" or null` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: "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. - `"standard"` - `"fast"` - `input_transformations: optional array of BetaThinkingDroppedInputTransformation or null` Changes the API made to the request's input before showing it to the model: one entry per change, in request order. Today the only entry type is `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when nothing was changed; without the beta, blocks are removed all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. default: thinking_dropped - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` ### Beta Raw Message Stop Event - `BetaRawMessageStopEvent object` - `type: "message_stop"` default: message_stop ### Beta Raw Message Stream Event - `BetaRawMessageStreamEvent = BetaRawMessageStartEvent or BetaRawMessageDeltaEvent or BetaRawMessageStopEvent or 3 more` - `BetaRawMessageStartEvent object` - `type: "message_start"` default: message_start - `message: BetaMessage` - `type: "message"` Object type. For Messages, this is always `"message"`. default: message - `id: string` Unique object identifier. The format and length of IDs may change over time. - `container: BetaContainer or null` Information about the container used in the request (for the code execution tool) - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill or null` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID maxLength: 64, minLength: 1 - `version: string` The resolved version: a skill version ID for custom skills. maxLength: 64, minLength: 1 - `content: array of BetaContentBlock` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `BetaTextBlock object` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `text: string` minLength: 0 - `BetaThinkingBlock object` - `type: "thinking"` default: thinking - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - `thinking: string` The text of Claude's thinking process for this block. - `BetaRedactedThinkingBlock object` - `type: "redacted_thinking"` default: redacted_thinking - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#redacted-thinking-blocks) for details. - `BetaToolUseBlock object` - `type: "tool_use"` default: tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaServerToolUseBlock object` - `type: "server_tool_use"` default: server_tool_use - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebSearchToolResultBlock object` - `type: "web_search_tool_result"` default: web_search_tool_result - `content: BetaWebSearchToolResultBlockContent` - `BetaWebSearchToolResultError object` - `type: "web_search_tool_result_error"` default: web_search_tool_result_error - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `array of BetaWebSearchResultBlock` - `type: "web_search_result"` default: web_search_result - `encrypted_content: string` - `page_age: string or null` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebFetchToolResultBlock object` - `type: "web_fetch_tool_result"` default: web_fetch_tool_result - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `BetaWebFetchToolResultErrorBlock object` - `type: "web_fetch_tool_result_error"` default: web_fetch_tool_result_error - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlock object` - `type: "web_fetch_result"` default: web_fetch_result - `content: BetaDocumentBlock` - `type: "document"` default: document - `citations: BetaCitationConfig or null` Citation configuration for the document - `enabled: boolean` default: false - `source: BetaBase64PDFSource or BetaPlainTextSource` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string or null` The title of the document - `retrieved_at: string or null` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaAdvisorToolResultBlock object` - `type: "advisor_tool_result"` default: advisor_tool_result - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `BetaAdvisorToolResultError object` - `type: "advisor_tool_result_error"` default: advisor_tool_result_error - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlock object` - `type: "advisor_result"` default: advisor_result - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `BetaAdvisorRedactedResultBlock object` - `type: "advisor_redacted_result"` default: advisor_redacted_result - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaCodeExecutionToolResultBlock object` - `type: "code_execution_tool_result"` default: code_execution_tool_result - `content: BetaCodeExecutionToolResultBlockContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultError object` - `type: "code_execution_tool_result_error"` default: code_execution_tool_result_error - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlock object` - `type: "code_execution_result"` default: code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlock object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` default: encrypted_code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaBashCodeExecutionToolResultBlock object` - `type: "bash_code_execution_tool_result"` default: bash_code_execution_tool_result - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `BetaBashCodeExecutionToolResultError object` - `type: "bash_code_execution_tool_result_error"` default: bash_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlock object` - `type: "bash_code_execution_result"` default: bash_code_execution_result - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` default: bash_code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaTextEditorCodeExecutionToolResultBlock object` - `type: "text_editor_code_execution_tool_result"` default: text_editor_code_execution_tool_result - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `BetaTextEditorCodeExecutionToolResultError object` - `type: "text_editor_code_execution_tool_result_error"` default: text_editor_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string or null` - `BetaTextEditorCodeExecutionViewResultBlock object` - `type: "text_editor_code_execution_view_result"` default: text_editor_code_execution_view_result - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number or null` - `start_line: number or null` - `total_lines: number or null` - `BetaTextEditorCodeExecutionCreateResultBlock object` - `type: "text_editor_code_execution_create_result"` default: text_editor_code_execution_create_result - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlock object` - `type: "text_editor_code_execution_str_replace_result"` default: text_editor_code_execution_str_replace_result - `lines: array of string or null` - `new_lines: number or null` - `new_start: number or null` - `old_lines: number or null` - `old_start: number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaToolSearchToolResultBlock object` - `type: "tool_search_tool_result"` default: tool_search_tool_result - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `BetaToolSearchToolResultError object` - `type: "tool_search_tool_result_error"` default: tool_search_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string or null` - `BetaToolSearchToolSearchResultBlock object` - `type: "tool_search_tool_search_result"` default: tool_search_tool_search_result - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` default: tool_reference - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaMCPToolUseBlock object` - `type: "mcp_tool_use"` default: mcp_tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `BetaMCPToolResultBlock object` - `type: "mcp_tool_result"` default: mcp_tool_result - `content: string or array of BetaTextBlock` - `string` - `BetaMCPToolResultBlockContent = array of BetaTextBlock` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` minLength: 0 - `is_error: boolean` default: false - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `BetaContainerUploadBlock object` Response model for a file uploaded to the container. - `type: "container_upload"` default: container_upload - `file_id: string` - `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. - `type: "compaction"` default: compaction - `content: string or null` Summary of compacted content, or null if compaction failed - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `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. - `type: "fallback"` default: fallback - `from: BetaFallbackInfo` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfo` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `trigger: BetaFallbackRefusalTrigger` What caused the `from` model to hand over at this hop. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `context_management: BetaContextManagementResponse or null` Context management response. Information about context management strategies applied during the request. - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `BetaClearToolUses20250919EditResponse object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. default: clear_tool_uses_20250919 - `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 - `BetaClearThinking20251015EditResponse object` - `type: "clear_thinking_20251015"` The type of context management edit applied. default: clear_thinking_20251015 - `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 - `diagnostics: BetaDiagnostics or null` Response envelope for request-level diagnostics. Present (possibly null) whenever the caller supplied `diagnostics` on the request. - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more 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` - `type: "model_changed"` default: model_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissSystemChanged object` - `type: "system_changed"` default: system_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissToolsChanged object` - `type: "tools_changed"` default: tools_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissMessagesChanged object` - `type: "messages_changed"` default: messages_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissPreviousMessageNotFound object` - `type: "previous_message_not_found"` default: previous_message_not_found - `BetaCacheMissUnavailable object` - `type: "unavailable"` default: unavailable - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `role: "assistant"` Conversational role of the generated message. This will always be `"assistant"`. default: assistant - `stop_details: BetaRefusalStopDetails or null` Structured information about a refusal. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string or null` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string or null` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean or null` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string or null` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: BetaStopReason or null` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string or null` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: BetaUsage` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number 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` Outcome of the `fallback_credit_token` presented on this request. - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `BetaFallbackCreditRedeemed object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` default: redeemed - `BetaFallbackCreditNotApplied object` No reprice was applied; `reason` says why. - `type: "not_applied"` default: not_applied - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string or null` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: string or null` The geographic region where inference was performed for this request. - `input_tokens: number` The 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, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Determine which iterations exceeded long context thresholds (>=200k tokens) - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `BetaMessageIterationUsage object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration default: message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaCompactionIterationUsage object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration default: compaction - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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 - `BetaAdvisorMessageIterationUsage object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration default: advisor_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaFallbackMessageIterationUsage object` Token usage for the fallback-model attempt of a server-side fallback request. Produced in place of a `message` entry for whichever hop served the response. A declined hop produces the existing `message` entry. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response default: fallback_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `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. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. default: 0, minimum: 0 - `server_tool_use: BetaServerToolUsage or null` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. default: 0, minimum: 0 - `web_search_requests: number` The number of web search tool requests. default: 0, minimum: 0 - `service_tier: "standard" or "priority" or "batch" or null` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: "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. - `"standard"` - `"fast"` - `input_transformations: optional array of BetaThinkingDroppedInputTransformation or null` Changes the API made to the request's input before showing it to the model: one entry per change, in request order. Today the only entry type is `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when nothing was changed; without the beta, blocks are removed all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. default: thinking_dropped - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `BetaRawMessageDeltaEvent object` - `type: "message_delta"` default: message_delta - `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` - `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, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Determine which iterations exceeded long context thresholds (>=200k tokens) - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `output_tokens: 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. - `input_transformations: optional array of BetaThinkingDroppedInputTransformation or null` Changes the API made to the request's input before showing it to the model: one entry per change, in request order. Today the only entry type is `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when nothing was changed; without the beta, blocks are removed all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. default: thinking_dropped - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `BetaRawMessageStopEvent object` - `type: "message_stop"` default: message_stop - `BetaRawContentBlockStartEvent object` - `type: "content_block_start"` default: content_block_start - `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` - `BetaRawContentBlockDeltaEvent object` - `type: "content_block_delta"` default: content_block_delta - `delta: BetaRawContentBlockDelta` - `BetaTextDelta object` - `type: "text_delta"` default: text_delta - `text: string` - `BetaInputJSONDelta object` - `type: "input_json_delta"` default: input_json_delta - `partial_json: string` - `BetaCitationsDelta object` - `type: "citations_delta"` default: citations_delta - `citation: BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` - `BetaCitationCharLocation object` - `BetaCitationPageLocation object` - `BetaCitationContentBlockLocation object` - `BetaCitationsWebSearchResultLocation object` - `BetaCitationSearchResultLocation object` - `BetaThinkingDelta object` - `type: "thinking_delta"` default: thinking_delta - `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. - `BetaSignatureDelta object` - `type: "signature_delta"` default: signature_delta - `signature: string` The `signature` for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a `signature_delta` event just before the block's `content_block_stop` event. - `BetaCompactionContentBlockDelta object` - `type: "compaction_delta"` default: compaction_delta - `content: string or null` - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `index: number` - `BetaRawContentBlockStopEvent object` - `type: "content_block_stop"` default: content_block_stop - `index: number` ### Beta Redacted Thinking Block - `BetaRedactedThinkingBlock object` - `type: "redacted_thinking"` default: redacted_thinking - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#redacted-thinking-blocks) for details. ### Beta Redacted Thinking Block Param - `BetaRedactedThinkingBlockParam object` - `type: "redacted_thinking"` - `data: string` The `data` value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged. ### Beta Refusal Stop Details - `BetaRefusalStopDetails object` Structured information about a refusal. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string or null` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string or null` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean or null` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string or null` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. ### Beta Request Document Block - `BetaRequestDocumentBlock object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `BetaContentBlockSource object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `string` - `BetaContentBlockSourceContent = array of BetaContentBlockSourceContent` - `BetaTextBlockParam object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaImageBlockParam object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `BetaURLImageSource object` - `type: "url"` - `url: string` - `BetaFileImageSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `transformations: optional BetaImageTransformationsParam or null` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `BetaURLPDFSource object` - `type: "url"` - `url: string` - `BetaFileDocumentSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` - `enabled: optional boolean` - `context: optional string or null` minLength: 1 - `title: optional string or null` maxLength: 500, minLength: 1 ### Beta Request MCP Server Tool Configuration - `BetaRequestMCPServerToolConfiguration object` - `allowed_tools: optional array of string or null` - `enabled: optional boolean or null` ### Beta Request MCP Server URL Definition - `BetaRequestMCPServerURLDefinition object` - `type: "url"` - `name: string` - `url: string` - `authorization_token: optional string or null` - `tool_configuration: optional BetaRequestMCPServerToolConfiguration or null` - `allowed_tools: optional array of string or null` - `enabled: optional boolean or null` ### Beta Request MCP Tool Result Block Param - `BetaRequestMCPToolResultBlockParam object` - `type: "mcp_tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `content: optional string or array of BetaTextBlockParam` - `string` - `BetaMCPToolResultBlockParamContent = array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `is_error: optional boolean` ### Beta Request Tool Addition Block - `BetaRequestToolAdditionBlock object` Mid-conversation directive to surface a declared tool. `tool` references a tool (or MCP toolset) by name from the request's `tools`; it is offered to the model from this point in the conversation onward. - `type: "tool_addition"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` 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. - `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. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `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"` - `name: string` - `server_name: string` - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` ### Beta Request Tool Removal Block - `BetaRequestToolRemovalBlock object` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name from the request's `tools`; it is no longer offered to the model from this point in the conversation onward. - `type: "tool_removal"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` 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. - `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. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `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"` - `name: string` - `server_name: string` - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` ### Beta Search Result Block Param - `BetaSearchResultBlockParam object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `source: string` - `title: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam` - `enabled: optional boolean` ### Beta Server Tool Caller - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Server Tool Caller 20260120 - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Server Tool Usage - `BetaServerToolUsage object` - `web_fetch_requests: number` The number of web fetch tool requests. default: 0, minimum: 0 - `web_search_requests: number` The number of web search tool requests. default: 0, minimum: 0 ### Beta Server Tool Use Block - `BetaServerToolUseBlock object` - `type: "server_tool_use"` default: server_tool_use - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Server Tool Use Block Param - `BetaServerToolUseBlockParam object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Signature Delta - `BetaSignatureDelta object` - `type: "signature_delta"` default: signature_delta - `signature: string` The `signature` for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a `signature_delta` event just before the block's `content_block_stop` event. ### Beta Skill Params - `BetaSkillParams object` Specification for a skill to be loaded in a container (request model). - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID maxLength: 64, minLength: 1 - `version: optional string` Skill version or 'latest' for most recent version maxLength: 64, minLength: 1 ### Beta Stop Reason - `BetaStopReason = "end_turn" or "max_tokens" or "stop_sequence" or 5 more` - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` ### Beta System Message Output Config - `BetaSystemMessageOutputConfig object` Per-message output configuration on a role:"system" input message. Fields here apply per-turn; `format` remains top-level only. An empty `{}` is accepted on a message that carries content; a message with neither content nor output_config fields is rejected. - `effort: optional "low" or "medium" or "high" or 2 more or null` All possible effort levels. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` ### Beta Text Block - `BetaTextBlock object` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `text: string` minLength: 0 ### Beta Text Block Param - `BetaTextBlockParam object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` ### Beta Text Citation - `BetaTextCitation = BetaCitationCharLocation or BetaCitationPageLocation or BetaCitationContentBlockLocation or 2 more` - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` ### Beta Text Citation Param - `BetaTextCitationParam = BetaCitationCharLocationParam or BetaCitationPageLocationParam or BetaCitationContentBlockLocationParam or 2 more` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` ### Beta Text Delta - `BetaTextDelta object` - `type: "text_delta"` default: text_delta - `text: string` ### Beta Text Editor Code Execution Create Result Block - `BetaTextEditorCodeExecutionCreateResultBlock object` - `type: "text_editor_code_execution_create_result"` default: text_editor_code_execution_create_result - `is_file_update: boolean` ### Beta Text Editor Code Execution Create Result Block Param - `BetaTextEditorCodeExecutionCreateResultBlockParam object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` ### Beta Text Editor Code Execution Str Replace Result Block - `BetaTextEditorCodeExecutionStrReplaceResultBlock object` - `type: "text_editor_code_execution_str_replace_result"` default: text_editor_code_execution_str_replace_result - `lines: array of string or null` - `new_lines: number or null` - `new_start: number or null` - `old_lines: number or null` - `old_start: number or null` ### Beta Text Editor Code Execution Str Replace Result Block Param - `BetaTextEditorCodeExecutionStrReplaceResultBlockParam object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: optional array of string or null` - `new_lines: optional number or null` - `new_start: optional number or null` - `old_lines: optional number or null` - `old_start: optional number or null` ### Beta Text Editor Code Execution Tool Result Block - `BetaTextEditorCodeExecutionToolResultBlock object` - `type: "text_editor_code_execution_tool_result"` default: text_editor_code_execution_tool_result - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `BetaTextEditorCodeExecutionToolResultError object` - `type: "text_editor_code_execution_tool_result_error"` default: text_editor_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string or null` - `BetaTextEditorCodeExecutionViewResultBlock object` - `type: "text_editor_code_execution_view_result"` default: text_editor_code_execution_view_result - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number or null` - `start_line: number or null` - `total_lines: number or null` - `BetaTextEditorCodeExecutionCreateResultBlock object` - `type: "text_editor_code_execution_create_result"` default: text_editor_code_execution_create_result - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlock object` - `type: "text_editor_code_execution_str_replace_result"` default: text_editor_code_execution_str_replace_result - `lines: array of string or null` - `new_lines: number or null` - `new_start: number or null` - `old_lines: number or null` - `old_start: number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Text Editor Code Execution Tool Result Block Param - `BetaTextEditorCodeExecutionToolResultBlockParam object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultErrorParam or BetaTextEditorCodeExecutionViewResultBlockParam or BetaTextEditorCodeExecutionCreateResultBlockParam or BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - `BetaTextEditorCodeExecutionToolResultErrorParam object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: optional string or null` - `BetaTextEditorCodeExecutionViewResultBlockParam object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: optional number or null` - `start_line: optional number or null` - `total_lines: optional number or null` - `BetaTextEditorCodeExecutionCreateResultBlockParam object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlockParam object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: optional array of string or null` - `new_lines: optional number or null` - `new_start: optional number or null` - `old_lines: optional number or null` - `old_start: optional number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` ### Beta Text Editor Code Execution Tool Result Error - `BetaTextEditorCodeExecutionToolResultError object` - `type: "text_editor_code_execution_tool_result_error"` default: text_editor_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string or null` ### Beta Text Editor Code Execution Tool Result Error Param - `BetaTextEditorCodeExecutionToolResultErrorParam object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: optional string or null` ### Beta Text Editor Code Execution View Result Block - `BetaTextEditorCodeExecutionViewResultBlock object` - `type: "text_editor_code_execution_view_result"` default: text_editor_code_execution_view_result - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number or null` - `start_line: number or null` - `total_lines: number or null` ### Beta Text Editor Code Execution View Result Block Param - `BetaTextEditorCodeExecutionViewResultBlockParam object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: optional number or null` - `start_line: optional number or null` - `total_lines: optional number or null` ### Beta Thinking Block - `BetaThinkingBlock object` - `type: "thinking"` default: thinking - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - `thinking: string` The text of Claude's thinking process for this block. ### Beta Thinking Block Binding - `BetaThinkingBlockBinding object` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `prefix_mismatch_behavior: optional BetaThinkingPrefixMismatchBehavior or null` What happens when a thinking block in `messages` fails the conversation check: it was created in a different conversation, or the messages before it have changed since. `"error"` (the default) fails the request with a 400 error. `"drop_block"` removes the failing blocks and the request proceeds; the model no longer sees the dropped reasoning. - `"error"` - `"drop_block"` ### Beta Thinking Block Param - `BetaThinkingBlockParam object` - `type: "thinking"` - `signature: string` The `signature` value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude. Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`. - `thinking: string` The `thinking` text of this block as returned by the API. ### Beta Thinking Config Adaptive - `BetaThinkingConfigAdaptive object` - `type: "adaptive"` - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `prefix_mismatch_behavior: optional BetaThinkingPrefixMismatchBehavior or null` What happens when a thinking block in `messages` fails the conversation check: it was created in a different conversation, or the messages before it have changed since. `"error"` (the default) fails the request with a 400 error. `"drop_block"` removes the failing blocks and the request proceeds; the model no longer sees the dropped reasoning. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` ### Beta Thinking Config Disabled - `BetaThinkingConfigDisabled object` - `type: "disabled"` ### Beta Thinking Config Enabled - `BetaThinkingConfigEnabled object` - `type: "enabled"` - `budget_tokens: number` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. minimum: 1024 - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `prefix_mismatch_behavior: optional BetaThinkingPrefixMismatchBehavior or null` What happens when a thinking block in `messages` fails the conversation check: it was created in a different conversation, or the messages before it have changed since. `"error"` (the default) fails the request with a 400 error. `"drop_block"` removes the failing blocks and the request proceeds; the model no longer sees the dropped reasoning. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` ### Beta Thinking Config Param - `BetaThinkingConfigParam = BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigAdaptive` Configuration for enabling Claude's extended thinking. When enabled, responses include `thinking` content blocks showing Claude's thinking process before the final answer. Requires a minimum budget of 1,024 tokens and counts towards your `max_tokens` limit. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - `BetaThinkingConfigEnabled object` - `type: "enabled"` - `budget_tokens: number` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. minimum: 1024 - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `prefix_mismatch_behavior: optional BetaThinkingPrefixMismatchBehavior or null` What happens when a thinking block in `messages` fails the conversation check: it was created in a different conversation, or the messages before it have changed since. `"error"` (the default) fails the request with a 400 error. `"drop_block"` removes the failing blocks and the request proceeds; the model no longer sees the dropped reasoning. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` - `BetaThinkingConfigDisabled object` - `type: "disabled"` - `BetaThinkingConfigAdaptive object` - `type: "adaptive"` - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` ### Beta Thinking Delta - `BetaThinkingDelta object` - `type: "thinking_delta"` default: thinking_delta - `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. ### Beta Thinking Dropped Input Transformation - `BetaThinkingDroppedInputTransformation object` - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. default: thinking_dropped - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` ### Beta Thinking Prefix Mismatch Behavior - `BetaThinkingPrefixMismatchBehavior = "error" or "drop_block"` What happens when a thinking block in `messages` fails the conversation check: it was created in a different conversation, or the messages before it have changed since. `"error"` (the default) fails the request with a 400 error. `"drop_block"` removes the failing blocks and the request proceeds; the model no longer sees the dropped reasoning. - `"error"` - `"drop_block"` ### Beta Thinking Turns - `BetaThinkingTurns object` - `type: "thinking_turns"` - `value: number` minimum: 1 ### Beta Token Task Budget - `BetaTokenTaskBudget object` User-configurable total token budget across contexts. - `type: "tokens"` The budget type. Currently only 'tokens' is supported. - `total: number` Total token budget across all contexts in the session. minimum: 1024 - `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 ### Beta Tool - `BetaTool object` - `type: optional "custom" or null` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown] or null` - `required: optional array of string or null` - `name: string` Name of the tool. 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"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean or null` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Bash 20241022 - `BetaToolBash20241022 object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Bash 20250124 - `BetaToolBash20250124 object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Change MCP Tool Reference - `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"` - `name: string` - `server_name: string` ### Beta Tool Change MCP Toolset Reference - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` ### Beta Tool Change Tool Reference - `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. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ ### Beta Tool Choice - `BetaToolChoice = BetaToolChoiceAuto or BetaToolChoiceAny or BetaToolChoiceTool or BetaToolChoiceNone` 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` The model will automatically decide whether to use tools. - `type: "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` The model will use any available tools. - `type: "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` The model will use the specified tool with `tool_choice.name`. - `type: "tool"` - `name: string` The name of the tool to use. - `disable_parallel_tool_use: 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` The model will not be allowed to use tools. - `type: "none"` ### Beta Tool Choice Any - `BetaToolChoiceAny object` The model will use any available tools. - `type: "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. ### Beta Tool Choice Auto - `BetaToolChoiceAuto object` The model will automatically decide whether to use tools. - `type: "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. ### Beta Tool Choice None - `BetaToolChoiceNone object` The model will not be allowed to use tools. - `type: "none"` ### Beta Tool Choice Tool - `BetaToolChoiceTool object` The model will use the specified tool with `tool_choice.name`. - `type: "tool"` - `name: string` The name of the tool to use. - `disable_parallel_tool_use: optional boolean` Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output exactly one tool use. ### Beta Tool Computer Use 20241022 - `BetaToolComputerUse20241022 object` - `type: "computer_20241022"` - `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. - `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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `display_number: optional number or null` 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 ### Beta Tool Computer Use 20250124 - `BetaToolComputerUse20250124 object` - `type: "computer_20250124"` - `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. - `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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `display_number: optional number or null` 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 ### Beta Tool Computer Use 20251124 - `BetaToolComputerUse20251124 object` - `type: "computer_20251124"` - `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. - `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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `display_number: optional number or null` 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Reference Block - `BetaToolReferenceBlock object` - `type: "tool_reference"` default: tool_reference - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ ### Beta Tool Reference Block Param - `BetaToolReferenceBlockParam object` Tool reference block that can be included in tool_result content. - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` ### Beta Tool Result Block Param - `BetaToolResultBlockParam object` - `type: "tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `content: optional string or array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `string` - `array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `BetaTextBlockParam object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaImageBlockParam object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `BetaURLImageSource object` - `type: "url"` - `url: string` - `BetaFileImageSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `transformations: optional BetaImageTransformationsParam or null` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `BetaSearchResultBlockParam object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `source: string` - `title: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam` - `enabled: optional boolean` - `BetaRequestDocumentBlock object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `BetaContentBlockSource object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `string` - `BetaContentBlockSourceContent = array of BetaContentBlockSourceContent` - `BetaTextBlockParam object` - `BetaImageBlockParam object` - `BetaURLPDFSource object` - `type: "url"` - `url: string` - `BetaFileDocumentSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` - `context: optional string or null` minLength: 1 - `title: optional string or null` maxLength: 500, minLength: 1 - `BetaToolReferenceBlockParam object` Tool reference block that can be included in tool_result content. - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `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 effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: "browser_state"` - `tabs: array of BetaBrowserStateTabEntry` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: 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`. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `state_changes: optional array of BetaBrowserStateChange or null` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. 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. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadStarted object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadCompleted object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: 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]*$, maxLength: 4096 - `size_bytes: optional number or null` The completed download's size. minimum: 0 - `BetaBrowserStateChangeDownloadFailed object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string or null` The failure or cancellation detail, when known. pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096 - `is_error: optional boolean` - `toolset_name: optional string or null` For a toolset member tool_result, the toolset family of the paired tool_use. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ ### Beta Tool Search Tool Bm25 20251119 - `BetaToolSearchToolBm25_20251119 object` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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 ### Beta Tool Search Tool Regex 20251119 - `BetaToolSearchToolRegex20251119 object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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 ### Beta Tool Search Tool Result Block - `BetaToolSearchToolResultBlock object` - `type: "tool_search_tool_result"` default: tool_search_tool_result - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `BetaToolSearchToolResultError object` - `type: "tool_search_tool_result_error"` default: tool_search_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string or null` - `BetaToolSearchToolSearchResultBlock object` - `type: "tool_search_tool_search_result"` default: tool_search_tool_search_result - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` default: tool_reference - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Tool Search Tool Result Block Param - `BetaToolSearchToolResultBlockParam object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultErrorParam or BetaToolSearchToolSearchResultBlockParam` - `BetaToolSearchToolResultErrorParam object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: optional string or null` - `BetaToolSearchToolSearchResultBlockParam object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlockParam` - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. ### Beta Tool Search Tool Result Error - `BetaToolSearchToolResultError object` - `type: "tool_search_tool_result_error"` default: tool_search_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string or null` ### Beta Tool Search Tool Result Error Param - `BetaToolSearchToolResultErrorParam object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: optional string or null` ### Beta Tool Search Tool Search Result Block - `BetaToolSearchToolSearchResultBlock object` - `type: "tool_search_tool_search_result"` default: tool_search_tool_search_result - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` default: tool_reference - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ ### Beta Tool Search Tool Search Result Block Param - `BetaToolSearchToolSearchResultBlockParam object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlockParam` - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` ### Beta Tool Text Editor 20241022 - `BetaToolTextEditor20241022 object` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Text Editor 20250124 - `BetaToolTextEditor20250124 object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Text Editor 20250429 - `BetaToolTextEditor20250429 object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs ### Beta Tool Text Editor 20250728 - `BetaToolTextEditor20250728 object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `input_examples: optional array of map[unknown]` - `max_characters: optional number or null` 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 ### Beta Tool Union - `BetaToolUnion = BetaTool or BetaToolBash20241022 or BetaToolBash20250124 or 25 more` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `BetaTool object` - `type: optional "custom" or null` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown] or null` - `required: optional array of string or null` - `name: string` Name of the tool. 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"` - `"code_execution_20250825"` - `"code_execution_20260120"` - `"code_execution_20260521"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean or null` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolBash20241022 object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolBash20250124 object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaCodeExecutionTool20250522 object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaCodeExecutionTool20250825 object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaCodeExecutionTool20260521 object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `configs: optional BetaBrowserToolsetConfigs or null` Per-member configuration for `browser_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional BetaBrowserTypeConfig or null` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional BetaBrowserCloseTabConfig or null` `close_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional BetaBrowserDoubleClickConfig or null` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional BetaBrowserFileUploadConfig or null` `file_upload`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional BetaBrowserFindConfig or null` `find`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional BetaBrowserFormInputConfig or null` `form_input`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional BetaBrowserGetPageTextConfig or null` `get_page_text`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional BetaBrowserHoldKeyConfig or null` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional BetaBrowserHoverConfig or null` `hover`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional BetaBrowserJavascriptExecConfig or null` `javascript_exec`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional BetaBrowserKeyConfig or null` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional BetaBrowserLeftClickConfig or null` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional BetaBrowserLeftClickDragConfig or null` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional BetaBrowserLeftMouseDownConfig or null` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional BetaBrowserLeftMouseUpConfig or null` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional BetaBrowserListTabsConfig or null` `list_tabs`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional BetaBrowserMiddleClickConfig or null` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional BetaBrowserMouseMoveConfig or null` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional BetaBrowserNavigateConfig or null` `navigate`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional BetaBrowserNewTabConfig or null` `new_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional BetaBrowserReadConsoleConfig or null` `read_console`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional BetaBrowserReadNetworkConfig or null` `read_network`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional BetaBrowserReadPageConfig or null` `read_page`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional BetaBrowserRightClickConfig or null` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional BetaBrowserScreenshotConfig or null` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional BetaBrowserScrollConfig or null` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional BetaBrowserScrollToConfig or null` `scroll_to`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional BetaBrowserSwitchTabConfig or null` `switch_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional BetaBrowserTripleClickConfig or null` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional BetaBrowserWaitConfig or null` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional BetaBrowserZoomConfig or null` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `BetaToolComputerUse20241022 object` - `type: "computer_20241022"` - `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. - `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. - `display_number: optional number or null` 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` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolComputerUse20250124 object` - `type: "computer_20250124"` - `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. - `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. - `display_number: optional number or null` 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` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolComputerUse20251124 object` - `type: "computer_20251124"` - `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. - `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. - `display_number: optional number or null` 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaComputerToolset20260801 object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `configs: optional BetaComputerToolsetConfigs or null` Per-member configuration for `computer_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional BetaComputerTypeConfig or null` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional BetaComputerCursorPositionConfig or null` `cursor_position`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional BetaComputerDoubleClickConfig or null` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional BetaComputerHoldKeyConfig or null` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional BetaComputerKeyConfig or null` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional BetaComputerLeftClickConfig or null` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional BetaComputerLeftClickDragConfig or null` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional BetaComputerLeftMouseDownConfig or null` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional BetaComputerLeftMouseUpConfig or null` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional BetaComputerMiddleClickConfig or null` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional BetaComputerMouseMoveConfig or null` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional BetaComputerRightClickConfig or null` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional BetaComputerScreenshotConfig or null` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional BetaComputerScrollConfig or null` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional BetaComputerTripleClickConfig or null` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional BetaComputerWaitConfig or null` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional BetaComputerZoomConfig or null` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `BetaToolTextEditor20250124 object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolTextEditor20250429 object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolTextEditor20250728 object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `max_characters: optional number or null` 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` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `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. - `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 - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `type: "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. maxLength: 255, minLength: 1 - `BetaWebFetchTool20250910 object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `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. - `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 - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `BetaWebFetchTool20260209 object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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 - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `BetaWebSearchTool20260318 object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `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. - `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. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `BetaWebFetchTool20260318 object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `BetaAdvisorTool20260301 object` - `type: "advisor_20260301"` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `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. - `caching: optional BetaCacheControlEphemeral or null` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number or null` 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` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaToolSearchToolRegex20251119 object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaMCPToolset object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for maxLength: 255, minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `configs: optional map[BetaMCPToolConfig] or null` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional BetaMCPToolDefaultConfig` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `enabled: optional boolean` ### Beta Tool Use Block - `BetaToolUseBlock object` - `type: "tool_use"` default: tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ ### Beta Tool Use Block Param - `BetaToolUseBlockParam object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` maxLength: 200, minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family this member belongs to. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ ### Beta Tool Uses Keep - `BetaToolUsesKeep object` - `type: "tool_uses"` - `value: number` minimum: 0 ### Beta Tool Uses Trigger - `BetaToolUsesTrigger object` - `type: "tool_uses"` - `value: number` minimum: 1 ### Beta URL Image Source - `BetaURLImageSource object` - `type: "url"` - `url: string` ### Beta URL PDF Source - `BetaURLPDFSource object` - `type: "url"` - `url: string` ### Beta Usage - `BetaUsage object` - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number 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` Outcome of the `fallback_credit_token` presented on this request. - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `BetaFallbackCreditRedeemed object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` default: redeemed - `BetaFallbackCreditNotApplied object` No reprice was applied; `reason` says why. - `type: "not_applied"` default: not_applied - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string or null` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: string or null` The geographic region where inference was performed for this request. - `input_tokens: number` The 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, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Determine which iterations exceeded long context thresholds (>=200k tokens) - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `BetaMessageIterationUsage object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration default: message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaCompactionIterationUsage object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration default: compaction - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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 - `BetaAdvisorMessageIterationUsage object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration default: advisor_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaFallbackMessageIterationUsage object` Token usage for the fallback-model attempt of a server-side fallback request. Produced in place of a `message` entry for whichever hop served the response. A declined hop produces the existing `message` entry. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response default: fallback_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `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. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. default: 0, minimum: 0 - `server_tool_use: BetaServerToolUsage or null` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. default: 0, minimum: 0 - `web_search_requests: number` The number of web search tool requests. default: 0, minimum: 0 - `service_tier: "standard" or "priority" or "batch" or null` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: "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. - `"standard"` - `"fast"` ### Beta User Location - `BetaUserLocation object` - `type: "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. maxLength: 255, minLength: 1 ### Beta Web Fetch Block - `BetaWebFetchBlock object` - `type: "web_fetch_result"` default: web_fetch_result - `content: BetaDocumentBlock` - `type: "document"` default: document - `citations: BetaCitationConfig or null` Citation configuration for the document - `enabled: boolean` default: false - `source: BetaBase64PDFSource or BetaPlainTextSource` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string or null` The title of the document - `retrieved_at: string or null` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL ### Beta Web Fetch Block Param - `BetaWebFetchBlockParam object` - `type: "web_fetch_result"` - `content: BetaRequestDocumentBlock` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `BetaContentBlockSource object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `string` - `BetaContentBlockSourceContent = array of BetaContentBlockSourceContent` - `BetaTextBlockParam object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaImageBlockParam object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `BetaURLImageSource object` - `type: "url"` - `url: string` - `BetaFileImageSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `transformations: optional BetaImageTransformationsParam or null` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `BetaURLPDFSource object` - `type: "url"` - `url: string` - `BetaFileDocumentSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` - `enabled: optional boolean` - `context: optional string or null` minLength: 1 - `title: optional string or null` maxLength: 500, minLength: 1 - `url: string` Fetched content URL - `retrieved_at: optional string or null` ISO 8601 timestamp when the content was retrieved ### Beta Web Fetch Tool 20250910 - `BetaWebFetchTool20250910 object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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 ### Beta Web Fetch Tool 20260209 - `BetaWebFetchTool20260209 object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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 ### Beta Web Fetch Tool 20260309 - `BetaWebFetchTool20260309 object` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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 - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. ### Beta Web Fetch Tool 20260318 - `BetaWebFetchTool20260318 object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `enabled: optional boolean` - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. ### Beta Web Fetch Tool Result Block - `BetaWebFetchToolResultBlock object` - `type: "web_fetch_tool_result"` default: web_fetch_tool_result - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `BetaWebFetchToolResultErrorBlock object` - `type: "web_fetch_tool_result_error"` default: web_fetch_tool_result_error - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlock object` - `type: "web_fetch_result"` default: web_fetch_result - `content: BetaDocumentBlock` - `type: "document"` default: document - `citations: BetaCitationConfig or null` Citation configuration for the document - `enabled: boolean` default: false - `source: BetaBase64PDFSource or BetaPlainTextSource` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string or null` The title of the document - `retrieved_at: string or null` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Web Fetch Tool Result Block Param - `BetaWebFetchToolResultBlockParam object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlockParam or BetaWebFetchBlockParam` - `BetaWebFetchToolResultErrorBlockParam object` - `type: "web_fetch_tool_result_error"` - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlockParam object` - `type: "web_fetch_result"` - `content: BetaRequestDocumentBlock` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `BetaContentBlockSource object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `string` - `BetaContentBlockSourceContent = array of BetaContentBlockSourceContent` - `BetaTextBlockParam object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaImageBlockParam object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `BetaURLImageSource object` - `type: "url"` - `url: string` - `BetaFileImageSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `transformations: optional BetaImageTransformationsParam or null` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `BetaURLPDFSource object` - `type: "url"` - `url: string` - `BetaFileDocumentSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` - `enabled: optional boolean` - `context: optional string or null` minLength: 1 - `title: optional string or null` maxLength: 500, minLength: 1 - `url: string` Fetched content URL - `retrieved_at: optional string or null` ISO 8601 timestamp when the content was retrieved - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Web Fetch Tool Result Error Block - `BetaWebFetchToolResultErrorBlock object` - `type: "web_fetch_tool_result_error"` default: web_fetch_tool_result_error - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` ### Beta Web Fetch Tool Result Error Block Param - `BetaWebFetchToolResultErrorBlockParam object` - `type: "web_fetch_tool_result_error"` - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` ### Beta Web Fetch Tool Result Error Code - `BetaWebFetchToolResultErrorCode = "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` ### Beta Web Search Result Block - `BetaWebSearchResultBlock object` - `type: "web_search_result"` default: web_search_result - `encrypted_content: string` - `page_age: string or null` - `title: string` - `url: string` ### Beta Web Search Result Block Param - `BetaWebSearchResultBlockParam object` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string or null` ### Beta Web Search Tool 20250305 - `BetaWebSearchTool20250305 object` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `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 - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `type: "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. maxLength: 255, minLength: 1 ### Beta Web Search Tool 20260209 - `BetaWebSearchTool20260209 object` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `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 - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `type: "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. maxLength: 255, minLength: 1 ### Beta Web Search Tool 20260318 - `BetaWebSearchTool20260318 object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `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. - `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. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `type: "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. maxLength: 255, minLength: 1 ### Beta Web Search Tool Request Error - `BetaWebSearchToolRequestError object` - `type: "web_search_tool_result_error"` - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` ### Beta Web Search Tool Result Block - `BetaWebSearchToolResultBlock object` - `type: "web_search_tool_result"` default: web_search_tool_result - `content: BetaWebSearchToolResultBlockContent` - `BetaWebSearchToolResultError object` - `type: "web_search_tool_result_error"` default: web_search_tool_result_error - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `array of BetaWebSearchResultBlock` - `type: "web_search_result"` default: web_search_result - `encrypted_content: string` - `page_age: string or null` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Web Search Tool Result Block Content - `BetaWebSearchToolResultBlockContent = BetaWebSearchToolResultError or array of BetaWebSearchResultBlock` - `BetaWebSearchToolResultError object` - `type: "web_search_tool_result_error"` default: web_search_tool_result_error - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `array of BetaWebSearchResultBlock` - `type: "web_search_result"` default: web_search_result - `encrypted_content: string` - `page_age: string or null` - `title: string` - `url: string` ### Beta Web Search Tool Result Block Param - `BetaWebSearchToolResultBlockParam object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultBlockParamContent` - `ResultBlock = array of BetaWebSearchResultBlockParam` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string or null` - `BetaWebSearchToolRequestError object` - `type: "web_search_tool_result_error"` - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ ### Beta Web Search Tool Result Block Param Content - `BetaWebSearchToolResultBlockParamContent = array of BetaWebSearchResultBlockParam or BetaWebSearchToolRequestError` - `ResultBlock = array of BetaWebSearchResultBlockParam` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string or null` - `BetaWebSearchToolRequestError object` - `type: "web_search_tool_result_error"` - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` ### Beta Web Search Tool Result Error - `BetaWebSearchToolResultError object` - `type: "web_search_tool_result_error"` default: web_search_tool_result_error - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` ### Beta Web Search Tool Result Error Code - `BetaWebSearchToolResultErrorCode = "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` ## Messages › Batches ### Create a Message Batch **POST** `/v1/messages/batches` Send a batch of Message creation requests. The Message Batches API can be used to process multiple Messages API requests at once. Once a Message Batch is created, it begins processing immediately. Batches can take up to 24 hours to complete. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing) #### Headers - `"anthropic-beta": optional array of AnthropicBeta` Optional header to specify the beta version(s) you want to use. - `string` - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"anthropic-user-profile-id": optional string` The user profile ID to attribute the requests in this batch to. Use when acting on behalf of a party other than your organization. Requires the `user-profiles` beta header. Applies to every request in the batch; an individual request whose `user_profile_id` body field conflicts with this header is errored. - `"anthropic-workspace-id": optional string` #### Body parameters - `requests: array of object` List of requests for prompt completion. Each is an individual request to create a Message. maxItems: 100000, minItems: 1 - `custom_id: string` Developer-provided ID created for each request in a Message Batch. Useful for matching results to requests, as results may be given out of request order. Must be unique for each request within the Message Batch. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,64}$ - `params: object` Messages API creation parameters for the individual request. See the [Messages API reference](https://platform.claude.com/docs/en/api/messages) for full documentation on available parameters. - `max_tokens: number` The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. Set to `0` to populate the [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#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` Input messages. Our models are trained to operate on alternating `user` and `assistant` conversational turns. When creating a new `Message`, you specify the prior conversational turns with the `messages` parameter, and the model then generates the next `Message` in the conversation. Consecutive `user` or `assistant` turns in your request will be combined into a single turn. Each input message must be an object with a `role` and `content`. You can specify a single `user`-role message, or you can include multiple `user` and `assistant` messages. If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response. Example with a single `user` message: ```json [{"role": "user", "content": "Hello, Claude"}] ``` Example with multiple conversational turns: ```json [ {"role": "user", "content": "Hello there."}, {"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"}, {"role": "user", "content": "Can you explain LLMs in plain English?"}, ] ``` Example with a partially-filled response from Claude: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("}, ] ``` Each input message `content` may be either a single `string` or an array of content blocks, where each block has a specific `type`. Using a `string` for `content` is shorthand for an array of one content block of type `"text"`. The following input messages are equivalent: ```json {"role": "user", "content": "Hello, Claude"} ``` ```json {"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]} ``` See [input examples](https://platform.claude.com/docs/en/build-with-claude/working-with-messages). Note that if you want to include a [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role), you can use the top-level `system` parameter — there is no `"system"` role for input messages in the Messages API. There is a limit of 100,000 messages in a single request. - `content: string or array of BetaContentBlockParam` - `string` - `array of BetaContentBlockParam` - `BetaTextBlockParam object` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `type: "ephemeral"` - `ttl: optional "5m" or "1h"` The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details. - `"5m"` - `"1h"` - `citations: optional array of BetaTextCitationParam or null` - `BetaCitationCharLocationParam object` - `type: "char_location"` - `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 - `BetaCitationPageLocationParam object` - `type: "page_location"` - `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 - `BetaCitationContentBlockLocationParam object` - `type: "content_block_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string 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. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationWebSearchResultLocationParam object` - `type: "web_search_result_location"` - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512, minLength: 1 - `url: string` minLength: 1 - `BetaCitationSearchResultLocationParam object` - `type: "search_result_location"` - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `BetaImageBlockParam object` - `type: "image"` - `source: BetaBase64ImageSource or BetaURLImageSource or BetaFileImageSource` - `BetaBase64ImageSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"` - `"image/jpeg"` - `"image/png"` - `"image/gif"` - `"image/webp"` - `BetaURLImageSource object` - `type: "url"` - `url: string` - `BetaFileImageSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `transformations: optional BetaImageTransformationsParam or null` Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field. - `oversized_image: optional "downsize" or "error"` What the server does when this image exceeds the model's maximum image size. `"downsize"` (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. `"error"` instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down. - `"downsize"` - `"error"` - `BetaRequestDocumentBlock object` - `type: "document"` - `source: BetaBase64PDFSource or BetaPlainTextSource or BetaContentBlockSource or 2 more` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `BetaContentBlockSource object` - `type: "content"` - `content: string or array of BetaContentBlockSourceContent` - `string` - `BetaContentBlockSourceContent = array of BetaContentBlockSourceContent` - `BetaTextBlockParam object` - `BetaImageBlockParam object` - `BetaURLPDFSource object` - `type: "url"` - `url: string` - `BetaFileDocumentSource object` - `type: "file"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` - `enabled: optional boolean` - `context: optional string or null` minLength: 1 - `title: optional string or null` maxLength: 500, minLength: 1 - `BetaSearchResultBlockParam object` - `type: "search_result"` - `content: array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `source: string` - `title: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam` - `BetaThinkingBlockParam object` - `type: "thinking"` - `signature: string` The `signature` value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude. Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 `invalid_request_error`. - `thinking: string` The `thinking` text of this block as returned by the API. - `BetaRedactedThinkingBlockParam object` - `type: "redacted_thinking"` - `data: string` The `data` value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged. - `BetaToolUseBlockParam object` - `type: "tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` maxLength: 200, minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family this member belongs to. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaToolResultBlockParam object` - `type: "tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `string` - `array of BetaTextBlockParam or BetaImageBlockParam or BetaSearchResultBlockParam or 3 more` - `BetaTextBlockParam object` - `BetaImageBlockParam object` - `BetaSearchResultBlockParam object` - `BetaRequestDocumentBlock object` - `BetaToolReferenceBlockParam object` Tool reference block that can be included in tool_result content. - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `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 effects (tabs opened, download state changes) the call produced. At most one per `tool_result`, only on a non-error result answering a browser toolset member `tool_use`. The server renders the model-visible text from it; the model never sees the raw fields. - `type: "browser_state"` - `tabs: array of BetaBrowserStateTabEntry` All tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries `active: true`. maxItems: 100 - `tab_id: 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`. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `state_changes: optional array of BetaBrowserStateChange or null` Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list. 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. Carries only the `tab_id`; the tab's `title` and `url` live on its `tabs` entry, which must include the same `tab_id`. A tab opened during a failed call gets no deferred `tab_opened`; it simply appears in the next result's `tabs` inventory. - `type: "tab_opened"` - `tab_id: string` The `tab_id` of the opened tab, present in `tabs`. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadStarted object` A file download that started during this call. - `type: "download_started"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `BetaBrowserStateChangeDownloadCompleted object` A file download that finished during this call, reported with the same `download_id` as its `download_started` — or without a prior `download_started`, when the download finished during the call that started it (at most one state change per `download_id` per result). - `type: "download_completed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `path: 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]*$, maxLength: 4096 - `size_bytes: optional number or null` The completed download's size. minimum: 0 - `BetaBrowserStateChangeDownloadFailed object` A file download that failed — or was cancelled — during this call. - `type: "download_failed"` - `download_id: string` The caller-assigned identifier for this download, stable across the state changes reporting it. maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `url: string` The final post-redirect URL the download was served from. maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$ - `error: optional string or null` The failure or cancellation detail, when known. pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096 - `is_error: optional boolean` - `toolset_name: optional string or null` For a toolset member tool_result, the toolset family of the paired tool_use. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaServerToolUseBlockParam object` - `type: "server_tool_use"` - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebSearchToolResultBlockParam object` - `type: "web_search_tool_result"` - `content: BetaWebSearchToolResultBlockParamContent` - `ResultBlock = array of BetaWebSearchResultBlockParam` - `type: "web_search_result"` - `encrypted_content: string` - `title: string` - `url: string` - `page_age: optional string or null` - `BetaWebSearchToolRequestError object` - `type: "web_search_tool_result_error"` - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebFetchToolResultBlockParam object` - `type: "web_fetch_tool_result"` - `content: BetaWebFetchToolResultErrorBlockParam or BetaWebFetchBlockParam` - `BetaWebFetchToolResultErrorBlockParam object` - `type: "web_fetch_tool_result_error"` - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlockParam object` - `type: "web_fetch_result"` - `content: BetaRequestDocumentBlock` - `url: string` Fetched content URL - `retrieved_at: optional string or null` ISO 8601 timestamp when the content was retrieved - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaAdvisorToolResultBlockParam object` - `type: "advisor_tool_result"` - `content: BetaAdvisorToolResultErrorParam or BetaAdvisorResultBlockParam or BetaAdvisorRedactedResultBlockParam` - `BetaAdvisorToolResultErrorParam object` - `type: "advisor_tool_result_error"` - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlockParam object` - `type: "advisor_result"` - `text: string` - `stop_reason: optional string or null` - `BetaAdvisorRedactedResultBlockParam object` - `type: "advisor_redacted_result"` - `encrypted_content: string` Opaque blob produced by a prior response; must be round-tripped verbatim. - `stop_reason: optional string or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaCodeExecutionToolResultBlockParam object` - `type: "code_execution_tool_result"` - `content: BetaCodeExecutionToolResultBlockParamContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultErrorParam object` - `type: "code_execution_tool_result_error"` - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlockParam object` - `type: "code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlockParam object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` - `content: array of BetaCodeExecutionOutputBlockParam` - `type: "code_execution_output"` - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaBashCodeExecutionToolResultBlockParam object` - `type: "bash_code_execution_tool_result"` - `content: BetaBashCodeExecutionToolResultErrorParam or BetaBashCodeExecutionResultBlockParam` - `BetaBashCodeExecutionToolResultErrorParam object` - `type: "bash_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlockParam object` - `type: "bash_code_execution_result"` - `content: array of BetaBashCodeExecutionOutputBlockParam` - `type: "bash_code_execution_output"` - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaTextEditorCodeExecutionToolResultBlockParam object` - `type: "text_editor_code_execution_tool_result"` - `content: BetaTextEditorCodeExecutionToolResultErrorParam or BetaTextEditorCodeExecutionViewResultBlockParam or BetaTextEditorCodeExecutionCreateResultBlockParam or BetaTextEditorCodeExecutionStrReplaceResultBlockParam` - `BetaTextEditorCodeExecutionToolResultErrorParam object` - `type: "text_editor_code_execution_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: optional string or null` - `BetaTextEditorCodeExecutionViewResultBlockParam object` - `type: "text_editor_code_execution_view_result"` - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: optional number or null` - `start_line: optional number or null` - `total_lines: optional number or null` - `BetaTextEditorCodeExecutionCreateResultBlockParam object` - `type: "text_editor_code_execution_create_result"` - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlockParam object` - `type: "text_editor_code_execution_str_replace_result"` - `lines: optional array of string or null` - `new_lines: optional number or null` - `new_start: optional number or null` - `old_lines: optional number or null` - `old_start: optional number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaToolSearchToolResultBlockParam object` - `type: "tool_search_tool_result"` - `content: BetaToolSearchToolResultErrorParam or BetaToolSearchToolSearchResultBlockParam` - `BetaToolSearchToolResultErrorParam object` - `type: "tool_search_tool_result_error"` - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: optional string or null` - `BetaToolSearchToolSearchResultBlockParam object` - `type: "tool_search_tool_search_result"` - `tool_references: array of BetaToolReferenceBlockParam` - `type: "tool_reference"` - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaMCPToolUseBlockParam object` - `type: "mcp_tool_use"` - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` - `server_name: string` The name of the MCP server - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaRequestMCPToolResultBlockParam object` - `type: "mcp_tool_result"` - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or array of BetaTextBlockParam` - `string` - `BetaMCPToolResultBlockParamContent = array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `is_error: optional boolean` - `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"` - `file_id: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaCompactionBlockParam object` A compaction block containing summary of previous context. Users should round-trip these blocks from responses to subsequent requests to maintain context across compaction boundaries. When content is None, the block represents a failed compaction. The server treats these as no-ops. Empty string content is not allowed. - `type: "compaction"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `content: optional string or null` Summary of previously compacted content, or null if compaction failed - `encrypted_content: optional string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `BetaRequestToolAdditionBlock object` Mid-conversation directive to surface a declared tool. `tool` references a tool (or MCP toolset) by name from the request's `tools`; it is offered to the model from this point in the conversation onward. - `type: "tool_addition"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` 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. - `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. - `type: "tool_reference"` - `name: string` pattern: ^[a-zA-Z0-9_-]{1,128}$ - `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"` - `name: string` - `server_name: string` - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `type: "mcp_toolset_reference"` - `server_name: string` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaRequestToolRemovalBlock object` Mid-conversation directive to withdraw a tool. `tool` references a tool (or MCP toolset) by name from the request's `tools`; it is no longer offered to the model from this point in the conversation onward. - `type: "tool_removal"` - `tool: BetaToolChangeToolReference or BetaToolChangeMCPToolReference or BetaToolChangeMCPToolsetReference` 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. - `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` Reference to a single MCP tool by its server and remote name — the same `server_name`/`name` pair `mcp_tool_use` carries. - `BetaToolChangeMCPToolsetReference object` Reference to every tool in the named MCP server's toolset. - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `BetaFallbackBlockParam object` A `fallback` block echoed back from a prior response. Accepted in `messages[].content` and not rendered into the prompt; not validated against the request's `fallbacks` chain or top-level `model`. Echo the assistant turn back verbatim, including this block in its original position. The block marks the boundary between content produced before and after a fallback hop, and the server relies on that boundary to validate the turn: when thinking runs flank the boundary, omitting the block merges them into one span the server cannot validate (the request is rejected), and moving it into the middle of a single run is likewise rejected; between non-thinking blocks the block's placement has no validation effect. - `type: "fallback"` - `from: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfoParam` Identifies one hop of a fallback transition. - `trigger: optional unknown` The response block's `trigger`, echoed verbatim. Accepted and ignored by the server; any object or `null` is allowed. - `role: "user" or "assistant" or "system"` - `"user"` - `"assistant"` - `"system"` - `clear_at: optional "next_user_message" or "never" or null` How long this system message's text stays in front of the model. `"never"` (the default) renders it on every request that includes it. `"next_user_message"` renders it only for the user turn it follows: once a later `role: "user"` message exists in `messages` the message stays in the array (send it unchanged) but is no longer shown to the model. Only permitted on `role: "system"` messages. - `"next_user_message"` - `"never"` - `output_config: optional BetaSystemMessageOutputConfig or null` Per-message output configuration on a role:"system" input message. Fields here apply per-turn; `format` remains top-level only. An empty `{}` is accepted on a message that carries content; a message with neither content nor output_config fields is rejected. - `effort: optional "low" or "medium" or "high" or 2 more or null` All possible effort levels. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `cache_control: optional BetaCacheControlEphemeral or null` Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. - `container: optional BetaContainerParams or string or null` Container identifier for reuse across requests. - `BetaContainerParams object` Container parameters with skills to be loaded. - `id: optional string or null` Container id - `skills: optional array of BetaSkillParams or null` List of skills to load in the container maxItems: 20 - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID maxLength: 64, minLength: 1 - `version: optional string` Skill version or 'latest' for most recent version maxLength: 64, minLength: 1 - `string` - `context_management: optional BetaContextManagementConfig or null` Context management configuration. This allows you to control how Claude manages context across multiple requests, such as whether to clear function results or not. - `edits: optional array of BetaClearToolUses20250919Edit or BetaClearThinking20251015Edit or BetaCompact20260112Edit` List of context management edits to apply minItems: 0 - `BetaClearToolUses20250919Edit object` - `type: "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"` - `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) - `boolean` - `array of string` - `exclude_tools: optional array of string or null` Tool names whose uses are preserved from clearing - `keep: optional BetaToolUsesKeep` Number of tool uses to retain in the conversation - `type: "tool_uses"` - `value: number` minimum: 0 - `trigger: optional BetaInputTokensTrigger or BetaToolUsesTrigger` Condition that triggers the context management strategy - `BetaInputTokensTrigger object` - `type: "input_tokens"` - `value: number` minimum: 1 - `BetaToolUsesTrigger object` - `type: "tool_uses"` - `value: number` minimum: 1 - `BetaClearThinking20251015Edit object` - `type: "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: "thinking_turns"` - `value: number` minimum: 1 - `BetaAllThinkingTurns object` - `type: "all"` - `"all"` - `BetaCompact20260112Edit object` Automatically compact older context when reaching the configured trigger threshold. - `type: "compact_20260112"` - `instructions: optional string or null` Additional instructions for summarization. - `pause_after_compaction: optional boolean` Whether to pause after compaction and return the compaction block to the user. - `trigger: optional BetaInputTokensTrigger or null` When to trigger compaction. Defaults to 150000 input tokens. - `diagnostics: optional BetaDiagnosticsParam or null` Request-level diagnostics. Currently carries the previous response id for prompt-cache divergence reporting. - `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` The `fallback_credit_token` from a prior refusal's `stop_details`. When a preceding request was refused and returned a `fallback_credit_token`, pass that code here on the retry to have the retry's cache-creation tokens for the prefix that was warm on the refused model billed at the cache-read rate. Must be redeemed by the same organization and workspace, with the same request body (optionally extended by one appended `assistant` message whose content is the partial text — with any trailing whitespace stripped from the final text block — and paired server-tool blocks streamed before the refusal; the appended-assistant form is not available for requests with `output_format` set or forced `tool_choice`), on an eligible fallback model, on the same platform, and within 5 minutes of the refusal; a mismatch is a 400. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed with the appended-assistant form — if an exact-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry with the appended-assistant form instead. When the appended-assistant form is used on a model that otherwise disallows assistant-turn prefill, this token also authorizes that one prefill. - `string` - `BetaFallbackCreditTokenParam object` Object form of `fallback_credit_token`: the token plus a redemption mode. Requires `anthropic-beta: fallback-credit-2026-07-01`; without that header the field accepts the bare string only. The bare string and the mode-less object are equivalent (both select `strict`), so wrapping an existing token changes nothing by itself. - `token: string` 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`. - `"strict"` - `"best_effort"` - `fallbacks: optional BetaFallbacksParam or null` Opt-in server-side retry on one or more substitute models when the requested model declines for policy reasons. Tried in order: if the first entry also declines, the second is tried, and so on. The string "default" requests the requested model's server-defined default fallback configuration. - `array of BetaFallbackParam` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `max_tokens: optional number or null` - `output_config: optional BetaOutputConfig or null` - `effort: optional "low" or "medium" or "high" or 2 more or null` All possible effort levels. - `"low"` - `"medium"` - `"high"` - `"xhigh"` - `"max"` - `format: optional BetaJSONOutputFormat or null` A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) - `type: "json_schema"` - `schema: map[unknown]` The JSON schema of the format - `task_budget: optional BetaTokenTaskBudget or null` User-configurable total token budget across contexts. - `type: "tokens"` The budget type. Currently only 'tokens' is supported. - `total: number` Total token budget across all contexts in the session. minimum: 1024 - `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. - `"standard"` - `"fast"` - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigAdaptive or null` - `BetaThinkingConfigEnabled object` - `type: "enabled"` - `budget_tokens: number` Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. minimum: 1024 - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `prefix_mismatch_behavior: optional BetaThinkingPrefixMismatchBehavior or null` What happens when a thinking block in `messages` fails the conversation check: it was created in a different conversation, or the messages before it have changed since. `"error"` (the default) fails the request with a 400 error. `"drop_block"` removes the failing blocks and the request proceeds; the model no longer sees the dropped reasoning. - `"error"` - `"drop_block"` - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` - `BetaThinkingConfigDisabled object` - `type: "disabled"` - `BetaThinkingConfigAdaptive object` - `type: "adaptive"` - `block_binding: optional BetaThinkingBlockBinding or null` Controls for block binding: what happens when a thinking block this request sends back fails the conversation check. Every field is optional; an empty object means every default. - `display: optional "summarized" or "omitted" or "updates" 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`. - `"summarized"` - `"omitted"` - `"updates"` - `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: optional array of BetaRequestMCPServerURLDefinition` MCP servers to be utilized in this request maxItems: 20 - `type: "url"` - `name: string` - `url: string` - `authorization_token: optional string or null` - `tool_configuration: optional BetaRequestMCPServerToolConfiguration or null` - `allowed_tools: optional array of string or null` - `enabled: optional boolean or null` - `metadata: optional BetaMetadata` An object describing metadata about the request. - `user_id: optional string or null` An external identifier for the user who is associated with the request. This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number. maxLength: 512 - `output_config: optional BetaOutputConfig` Configuration options for the model's output, such as the output format. - `service_tier: optional "auto" or "standard_only"` Determines whether to use priority capacity (if available) or standard capacity for this request. Anthropic offers different levels of service for your API requests. See [service-tiers](https://platform.claude.com/docs/en/api/service-tiers) for details. - `"auto"` - `"standard_only"` - `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. - `"standard"` - `"fast"` - `stop_sequences: optional array of string` Custom text sequences that will cause the model to stop generating. Our models will normally stop when they have naturally completed their turn, which will result in a response `stop_reason` of `"end_turn"`. If you want the model to stop generating when it encounters custom strings of text, you can use the `stop_sequences` parameter. If the model encounters one of the custom sequences, the response `stop_reason` value will be `"stop_sequence"` and the response `stop_sequence` value will contain the matched stop sequence. - `stream: optional boolean` Whether to incrementally stream the response using server-sent events. See [streaming](https://platform.claude.com/docs/en/build-with-claude/streaming) for details. - `system: optional string or array of BetaTextBlockParam` System prompt. A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role). - `string` - `array of BetaTextBlockParam` - `type: "text"` - `text: string` minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional array of BetaTextCitationParam or null` - `thinking: optional BetaThinkingConfigParam` Configuration for enabling Claude's extended thinking. When enabled, responses include `thinking` content blocks showing Claude's thinking process before the final answer. Requires a minimum budget of 1,024 tokens and counts towards your `max_tokens` limit. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - `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` The model will automatically decide whether to use tools. - `type: "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` The model will use any available tools. - `type: "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` The model will use the specified tool with `tool_choice.name`. - `type: "tool"` - `name: string` The name of the tool to use. - `disable_parallel_tool_use: 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` The model will not be allowed to use tools. - `type: "none"` - `tools: optional array of BetaToolUnion` Definitions of tools that the model may use. If you include `tools` in your API request, the model may return `tool_use` content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using `tool_result` content blocks. There are two types of tools: **client tools** and **server tools**. The behavior described below applies to client tools. For [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools), see their individual documentation as each has its own behavior (e.g., the [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool)). Each tool definition includes: * `name`: Name of the tool. * `description`: Optional, but strongly-recommended description of the tool. * `input_schema`: [JSON schema](https://json-schema.org/draft/2020-12) for the tool `input` shape that the model will produce in `tool_use` output content blocks. For example, if you defined `tools` as: ```json [ { "name": "get_stock_price", "description": "Get the current stock price for a given ticker symbol.", "input_schema": { "type": "object", "properties": { "ticker": { "type": "string", "description": "The stock ticker symbol, e.g. AAPL for Apple Inc." } }, "required": ["ticker"] } } ] ``` And then asked the model "What's the S&P 500 at today?", the model might produce `tool_use` content blocks in the response like this: ```json [ { "type": "tool_use", "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "name": "get_stock_price", "input": { "ticker": "^GSPC" } } ] ``` You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an input, and return the following back to the model in a subsequent `user` message: ```json [ { "type": "tool_result", "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "content": "259.75 USD" } ] ``` Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output. See our [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) for more details. - `BetaTool object` - `type: optional "custom" or null` - `input_schema: object` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `type: "object"` - `properties: optional map[unknown] or null` - `required: optional array of string or null` - `name: string` Name of the tool. 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"` - `"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. - `description: optional string` Description of what this tool does. Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema. - `eager_input_streaming: optional boolean or null` Enable eager input streaming for this tool. When true, tool input parameters will be streamed incrementally as they are generated, and types will be inferred on-the-fly rather than buffering the full JSON output. When false, streaming is disabled for this tool even if the fine-grained-tool-streaming beta is active. When null (default), uses the default behavior based on beta headers. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolBash20241022 object` - `type: "bash_20241022"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolBash20250124 object` - `type: "bash_20250124"` - `name: "bash"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaCodeExecutionTool20250522 object` - `type: "code_execution_20250522"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaCodeExecutionTool20250825 object` - `type: "code_execution_20250825"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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). - `type: "code_execution_20260120"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaCodeExecutionTool20260521 object` Code execution tool with REPL state persistence. - `type: "code_execution_20260521"` - `name: "code_execution"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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` The browser toolset: a single `tools[]` entry (carrying no `name`) that declares the browser tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. - `type: "browser_toolset_20260801"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `configs: optional BetaBrowserToolsetConfigs or null` Per-member configuration for `browser_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional BetaBrowserTypeConfig or null` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `close_tab: optional BetaBrowserCloseTabConfig or null` `close_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional BetaBrowserDoubleClickConfig or null` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `file_upload: optional BetaBrowserFileUploadConfig or null` `file_upload`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `find: optional BetaBrowserFindConfig or null` `find`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `form_input: optional BetaBrowserFormInputConfig or null` `form_input`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `get_page_text: optional BetaBrowserGetPageTextConfig or null` `get_page_text`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional BetaBrowserHoldKeyConfig or null` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hover: optional BetaBrowserHoverConfig or null` `hover`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `javascript_exec: optional BetaBrowserJavascriptExecConfig or null` `javascript_exec`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional BetaBrowserKeyConfig or null` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional BetaBrowserLeftClickConfig or null` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional BetaBrowserLeftClickDragConfig or null` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional BetaBrowserLeftMouseDownConfig or null` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional BetaBrowserLeftMouseUpConfig or null` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `list_tabs: optional BetaBrowserListTabsConfig or null` `list_tabs`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional BetaBrowserMiddleClickConfig or null` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional BetaBrowserMouseMoveConfig or null` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `navigate: optional BetaBrowserNavigateConfig or null` `navigate`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `new_tab: optional BetaBrowserNewTabConfig or null` `new_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_console: optional BetaBrowserReadConsoleConfig or null` `read_console`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_network: optional BetaBrowserReadNetworkConfig or null` `read_network`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `read_page: optional BetaBrowserReadPageConfig or null` `read_page`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional BetaBrowserRightClickConfig or null` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional BetaBrowserScreenshotConfig or null` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional BetaBrowserScrollConfig or null` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll_to: optional BetaBrowserScrollToConfig or null` `scroll_to`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `switch_tab: optional BetaBrowserSwitchTabConfig or null` `switch_tab`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional BetaBrowserTripleClickConfig or null` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional BetaBrowserWaitConfig or null` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional BetaBrowserZoomConfig or null` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `BetaToolComputerUse20241022 object` - `type: "computer_20241022"` - `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. - `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. - `display_number: optional number or null` 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` - `type: "memory_20250818"` - `name: "memory"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolComputerUse20250124 object` - `type: "computer_20250124"` - `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. - `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. - `display_number: optional number or null` 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` - `type: "text_editor_20241022"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolComputerUse20251124 object` - `type: "computer_20251124"` - `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. - `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. - `display_number: optional number or null` 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaComputerToolset20260801 object` The computer toolset: a single `tools[]` entry (carrying no `name`) that declares the computer tool family. The model is served the family's tool with any members disabled via `configs` removed from its schema. Every member is enabled by default, zoom included. The single-tool options `display_number` and `enable_zoom` are not fields of a toolset entry — it carries only `type`, `configs`, and `cache_control`; zoom is controlled via `configs.zoom.enabled`. - `type: "computer_toolset_20260801"` - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `configs: optional BetaComputerToolsetConfigs or null` Per-member configuration for `computer_toolset_20260801`: one optional field per member tool, keyed by the member name — the same name the member's `tool_use` blocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set. - `type: optional BetaComputerTypeConfig or null` `type`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `cursor_position: optional BetaComputerCursorPositionConfig or null` `cursor_position`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `double_click: optional BetaComputerDoubleClickConfig or null` `double_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `hold_key: optional BetaComputerHoldKeyConfig or null` `hold_key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `key: optional BetaComputerKeyConfig or null` `key`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click: optional BetaComputerLeftClickConfig or null` `left_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_click_drag: optional BetaComputerLeftClickDragConfig or null` `left_click_drag`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_down: optional BetaComputerLeftMouseDownConfig or null` `left_mouse_down`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `left_mouse_up: optional BetaComputerLeftMouseUpConfig or null` `left_mouse_up`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `middle_click: optional BetaComputerMiddleClickConfig or null` `middle_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `mouse_move: optional BetaComputerMouseMoveConfig or null` `mouse_move`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `right_click: optional BetaComputerRightClickConfig or null` `right_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `screenshot: optional BetaComputerScreenshotConfig or null` `screenshot`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `scroll: optional BetaComputerScrollConfig or null` `scroll`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `triple_click: optional BetaComputerTripleClickConfig or null` `triple_click`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `wait: optional BetaComputerWaitConfig or null` `wait`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `zoom: optional BetaComputerZoomConfig or null` `zoom`'s config overrides. - `defer_loading: optional boolean or null` Defer loading for this member. Must resolve to the same value on every enabled member of the toolset. - `enabled: optional boolean or null` Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema. - `BetaToolTextEditor20250124 object` - `type: "text_editor_20250124"` - `name: "str_replace_editor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolTextEditor20250429 object` - `type: "text_editor_20250429"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `BetaToolTextEditor20250728 object` - `type: "text_editor_20250728"` - `name: "str_replace_based_edit_tool"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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. - `input_examples: optional array of map[unknown]` - `max_characters: optional number or null` 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` - `type: "web_search_20250305"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `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. - `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 - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `type: "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. maxLength: 255, minLength: 1 - `BetaWebFetchTool20250910 object` - `type: "web_fetch_20250910"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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` - `type: "web_search_20260209"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `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. - `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 - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `BetaWebFetchTool20260209 object` - `type: "web_fetch_20260209"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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` Web fetch tool with use_cache parameter for bypassing cached content. - `type: "web_fetch_20260309"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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 - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `BetaWebSearchTool20260318 object` - `type: "web_search_20260318"` - `name: "web_search"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `blocked_domains: optional array of string or null` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `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. - `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. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `user_location: optional BetaUserLocation or null` Parameters for the user's location. Used to provide more relevant search results. - `BetaWebFetchTool20260318 object` - `type: "web_fetch_20260318"` - `name: "web_fetch"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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"` - `allowed_domains: optional array of string or null` List of domains to allow fetching from - `blocked_domains: optional array of string or null` List of domains to block fetching from - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `citations: optional BetaCitationsConfigParam or null` Citations configuration for fetched documents. Citations are disabled by default. - `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. - `max_content_tokens: optional number or null` Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs. 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. - `"full"` - `"excluded"` - `strict: optional boolean` When true, guarantees schema validation on tool names and inputs - `use_cache: optional boolean` Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources. - `BetaAdvisorTool20260301 object` - `type: "advisor_20260301"` - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `name: "advisor"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `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. - `caching: optional BetaCacheControlEphemeral or null` Caching for the advisor's own prompt. When set, each advisor call writes a cache entry at the given TTL so subsequent calls in the same conversation read the stable prefix. When omitted, the advisor prompt is not cached. - `defer_loading: optional boolean` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `max_tokens: optional number or null` 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` - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"` - `"tool_search_tool_bm25_20251119"` - `"tool_search_tool_bm25"` - `name: "tool_search_tool_bm25"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaToolSearchToolRegex20251119 object` - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"` - `"tool_search_tool_regex_20251119"` - `"tool_search_tool_regex"` - `name: "tool_search_tool_regex"` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `allowed_callers: 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 - `BetaMCPToolset object` Configuration for a group of tools from an MCP server. Allows configuring enabled status and defer_loading for all tools from an MCP server, with optional per-tool overrides. - `type: "mcp_toolset"` - `mcp_server_name: string` Name of the MCP server to configure tools for maxLength: 255, minLength: 1 - `cache_control: optional BetaCacheControlEphemeral or null` Create a cache control breakpoint at this content block. - `configs: optional map[BetaMCPToolConfig] or null` Configuration overrides for specific tools, keyed by tool name - `defer_loading: optional boolean` - `enabled: optional boolean` - `default_config: optional BetaMCPToolDefaultConfig` Default configuration applied to all tools from this server - `defer_loading: optional boolean` - `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. maximum: 1, minimum: 0 #### Returns - `BetaMessageBatch object` - `type: "message_batch"` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `id: string` Unique object identifier. The format and length of IDs may change over time. - `archived_at: string or null` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `cancel_initiated_at: string or null` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `created_at: string` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `ended_at: string or null` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `expires_at: string` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `processing_status: "in_progress" or "canceling" or "ended"` Processing status of the Message Batch. - `"in_progress"` - `"canceling"` - `"ended"` - `request_counts: BetaMessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `canceled: number` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `errored: number` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `expired: number` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `processing: number` Number of requests in the Message Batch that are processing. default: 0 - `succeeded: number` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `results_url: string or null` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. #### Example ```bash curl https://api.anthropic.com/v1/messages/batches \ -H 'Content-Type: application/json' \ -H 'anthropic-version: 2023-06-01' \ -H 'anthropic-beta: message-batches-2024-09-24' \ -H "X-Api-Key: $ANTHROPIC_API_KEY" \ -d '{ "requests": [ { "custom_id": "my-custom-id-1", "params": { "max_tokens": 1024, "messages": [ { "content": "Hello, world", "role": "user" } ], "model": "claude-opus-5" } } ] }' ``` ##### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ``` ### Retrieve a Message Batch **GET** `/v1/messages/batches/{message_batch_id}` This endpoint is idempotent and can be used to poll for Message Batch completion. To access the results of a Message Batch, make a request to the `results_url` field in the response. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing) #### Path parameters - `message_batch_id: string` ID of the Message Batch. #### Headers - `"anthropic-beta": optional array of AnthropicBeta` Optional header to specify the beta version(s) you want to use. - `string` - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"anthropic-workspace-id": optional string` #### Returns - `BetaMessageBatch object` - `type: "message_batch"` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `id: string` Unique object identifier. The format and length of IDs may change over time. - `archived_at: string or null` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `cancel_initiated_at: string or null` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `created_at: string` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `ended_at: string or null` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `expires_at: string` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `processing_status: "in_progress" or "canceling" or "ended"` Processing status of the Message Batch. - `"in_progress"` - `"canceling"` - `"ended"` - `request_counts: BetaMessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `canceled: number` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `errored: number` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `expired: number` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `processing: number` Number of requests in the Message Batch that are processing. default: 0 - `succeeded: number` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `results_url: string or null` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. #### Example ```bash curl https://api.anthropic.com/v1/messages/batches/$MESSAGE_BATCH_ID \ -H 'anthropic-version: 2023-06-01' \ -H 'anthropic-beta: message-batches-2024-09-24' \ -H "X-Api-Key: $ANTHROPIC_API_KEY" ``` ##### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ``` ### List Message Batches **GET** `/v1/messages/batches` List all Message Batches within a Workspace. Most recently created batches are returned first. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing) #### Query parameters - `after_id: optional string` ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately after this object. - `before_id: optional string` ID of the object to use as a cursor for pagination. When provided, returns the page of results immediately before this object. - `limit: optional number` Number of items to return per page. Defaults to `20`. Ranges from `1` to `1000`. default: 20, maximum: 1000, minimum: 1 #### Headers - `"anthropic-beta": optional array of AnthropicBeta` Optional header to specify the beta version(s) you want to use. - `string` - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"anthropic-workspace-id": optional string` #### Returns - `data: array of BetaMessageBatch` - `type: "message_batch"` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `id: string` Unique object identifier. The format and length of IDs may change over time. - `archived_at: string or null` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `cancel_initiated_at: string or null` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `created_at: string` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `ended_at: string or null` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `expires_at: string` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `processing_status: "in_progress" or "canceling" or "ended"` Processing status of the Message Batch. - `"in_progress"` - `"canceling"` - `"ended"` - `request_counts: BetaMessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `canceled: number` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `errored: number` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `expired: number` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `processing: number` Number of requests in the Message Batch that are processing. default: 0 - `succeeded: number` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `results_url: string or null` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. - `first_id: string or null` First ID in the `data` list. Can be used as the `before_id` for the previous page. - `has_more: boolean` Indicates if there are more results in the requested page direction. - `last_id: string or null` Last ID in the `data` list. Can be used as the `after_id` for the next page. #### Example ```bash curl https://api.anthropic.com/v1/messages/batches \ -H 'anthropic-version: 2023-06-01' \ -H 'anthropic-beta: message-batches-2024-09-24' \ -H "X-Api-Key: $ANTHROPIC_API_KEY" ``` ##### Response (200) ```json { "data": [ { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ], "first_id": "first_id", "has_more": true, "last_id": "last_id" } ``` ### Cancel a Message Batch **POST** `/v1/messages/batches/{message_batch_id}/cancel` Batches may be canceled any time before processing ends. Once cancellation is initiated, the batch enters a `canceling` state, at which time the system may complete any in-progress, non-interruptible requests before finalizing cancellation. The number of canceled requests is specified in `request_counts`. To determine which requests were canceled, check the individual results within the batch. Note that cancellation may not result in any canceled requests if they were non-interruptible. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing) #### Path parameters - `message_batch_id: string` ID of the Message Batch. #### Headers - `"anthropic-beta": optional array of AnthropicBeta` Optional header to specify the beta version(s) you want to use. - `string` - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"anthropic-workspace-id": optional string` #### Returns - `BetaMessageBatch object` - `type: "message_batch"` Object type. For Message Batches, this is always `"message_batch"`. default: message_batch - `id: string` Unique object identifier. The format and length of IDs may change over time. - `archived_at: string or null` RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable. format: date-time - `cancel_initiated_at: string or null` RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated. format: date-time - `created_at: string` RFC 3339 datetime string representing the time at which the Message Batch was created. format: date-time - `ended_at: string or null` RFC 3339 datetime string representing the time at which processing for the Message Batch ended. Specified only once processing ends. Processing ends when every request in a Message Batch has either succeeded, errored, canceled, or expired. format: date-time - `expires_at: string` RFC 3339 datetime string representing the time at which the Message Batch will expire and end processing, which is 24 hours after creation. format: date-time - `processing_status: "in_progress" or "canceling" or "ended"` Processing status of the Message Batch. - `"in_progress"` - `"canceling"` - `"ended"` - `request_counts: BetaMessageBatchRequestCounts` Tallies requests within the Message Batch, categorized by their status. Requests start as `processing` and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch. - `canceled: number` Number of requests in the Message Batch that have been canceled. This is zero until processing of the entire Message Batch has ended. default: 0 - `errored: number` Number of requests in the Message Batch that encountered an error. This is zero until processing of the entire Message Batch has ended. default: 0 - `expired: number` Number of requests in the Message Batch that have expired. This is zero until processing of the entire Message Batch has ended. default: 0 - `processing: number` Number of requests in the Message Batch that are processing. default: 0 - `succeeded: number` Number of requests in the Message Batch that have completed successfully. This is zero until processing of the entire Message Batch has ended. default: 0 - `results_url: string or null` URL to a `.jsonl` file containing the results of the Message Batch requests. Specified only once processing ends. Results in the file are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. #### Example ```bash curl https://api.anthropic.com/v1/messages/batches/$MESSAGE_BATCH_ID/cancel \ -X POST \ -H 'anthropic-version: 2023-06-01' \ -H 'anthropic-beta: message-batches-2024-09-24' \ -H "X-Api-Key: $ANTHROPIC_API_KEY" ``` ##### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "archived_at": "2024-08-20T18:37:24.100435Z", "cancel_initiated_at": "2024-08-20T18:37:24.100435Z", "created_at": "2024-08-20T18:37:24.100435Z", "ended_at": "2024-08-20T18:37:24.100435Z", "expires_at": "2024-08-20T18:37:24.100435Z", "processing_status": "in_progress", "request_counts": { "canceled": 10, "errored": 30, "expired": 10, "processing": 100, "succeeded": 50 }, "results_url": "https://api.anthropic.com/v1/messages/batches/msgbatch_013Zva2CMHLNnXjNJJKqJ2EF/results", "type": "message_batch" } ``` ### Delete a Message Batch **DELETE** `/v1/messages/batches/{message_batch_id}` Delete a Message Batch. Message Batches can only be deleted once they've finished processing. If you'd like to delete an in-progress batch, you must first cancel it. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing) #### Path parameters - `message_batch_id: string` ID of the Message Batch. #### Headers - `"anthropic-beta": optional array of AnthropicBeta` Optional header to specify the beta version(s) you want to use. - `string` - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"anthropic-workspace-id": optional string` #### Returns - `BetaDeletedMessageBatch object` - `type: "message_batch_deleted"` Deleted object type. For Message Batches, this is always `"message_batch_deleted"`. default: message_batch_deleted - `id: string` ID of the Message Batch. #### Example ```bash curl https://api.anthropic.com/v1/messages/batches/$MESSAGE_BATCH_ID \ -X DELETE \ -H 'anthropic-version: 2023-06-01' \ -H 'anthropic-beta: message-batches-2024-09-24' \ -H "X-Api-Key: $ANTHROPIC_API_KEY" ``` ##### Response (200) ```json { "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF", "type": "message_batch_deleted" } ``` ### Retrieve Message Batch results **GET** `/v1/messages/batches/{message_batch_id}/results` Streams the results of a Message Batch as a `.jsonl` file. Each line in the file is a JSON object containing the result of a single request in the Message Batch. Results are not guaranteed to be in the same order as requests. Use the `custom_id` field to match results to requests. Learn more about the Message Batches API in our [user guide](https://platform.claude.com/docs/en/build-with-claude/batch-processing) #### Path parameters - `message_batch_id: string` ID of the Message Batch. #### Headers - `"anthropic-beta": optional array of AnthropicBeta` Optional header to specify the beta version(s) you want to use. - `string` - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more` - `"message-batches-2024-09-24"` - `"prompt-caching-2024-07-31"` - `"computer-use-2024-10-22"` - `"computer-use-2025-01-24"` - `"pdfs-2024-09-25"` - `"token-counting-2024-11-01"` - `"token-efficient-tools-2025-02-19"` - `"output-128k-2025-02-19"` - `"files-api-2025-04-14"` - `"mcp-client-2025-04-04"` - `"mcp-client-2025-11-20"` - `"dev-full-thinking-2025-05-14"` - `"interleaved-thinking-2025-05-14"` - `"code-execution-2025-05-22"` - `"extended-cache-ttl-2025-04-11"` - `"context-1m-2025-08-07"` - `"context-management-2025-06-27"` - `"model-context-window-exceeded-2025-08-26"` - `"skills-2025-10-02"` - `"fast-mode-2026-02-01"` - `"output-300k-2026-03-24"` - `"user-profiles-2026-03-24"` - `"user-profiles-2026-08-18"` - `"user-profiles-2026-09-04"` - `"advisor-tool-2026-03-01"` - `"managed-agents-2026-04-01"` - `"cache-diagnosis-2026-04-07"` - `"dreaming-2026-04-21"` - `"thinking-token-count-2026-05-13"` - `"server-side-fallback-2026-06-01"` - `"server-side-fallback-2026-07-01"` - `"fallback-credit-2026-06-01"` - `"fallback-credit-2026-07-01"` - `"agent-memory-2026-07-22"` - `"mid-conversation-tool-changes-2026-07-01"` - `"compact-2026-01-12"` - `"computer-use-2025-11-24"` - `"mcp-tunnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-output-config-2026-07-01"` - `"thinking-binding-controls-2026-08-01"` - `"mid-conversation-system-clear-at-2026-08-21"` - `"anthropic-workspace-id": optional string` #### Returns - `BetaMessageBatchIndividualResponse object` This is a single line in the response `.jsonl` file and does not represent the response as a whole. - `custom_id: string` Developer-provided ID created for each request in a Message Batch. Useful for matching results to requests, as results may be given out of request order. Must be unique for each request within the Message Batch. - `result: BetaMessageBatchResult` Processing result for this request. Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration. - `BetaMessageBatchSucceededResult object` - `type: "succeeded"` default: succeeded - `message: BetaMessage` - `type: "message"` Object type. For Messages, this is always `"message"`. default: message - `id: string` Unique object identifier. The format and length of IDs may change over time. - `container: BetaContainer or null` Information about the container used in the request (for the code execution tool) - `id: string` Identifier for the container used in this request - `expires_at: string` The time at which the container will expire. format: date-time - `skills: array of BetaContainerSkill or null` Skills loaded in the container - `type: "anthropic" or "custom"` Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined) - `"anthropic"` - `"custom"` - `skill_id: string` Skill ID maxLength: 64, minLength: 1 - `version: string` The resolved version: a skill version ID for custom skills. maxLength: 64, minLength: 1 - `content: array of BetaContentBlock` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `BetaTextBlock object` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `BetaCitationCharLocation object` - `type: "char_location"` default: char_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_char_index: number` - `file_id: string or null` - `start_char_index: number` minimum: 0 - `BetaCitationPageLocation object` - `type: "page_location"` default: page_location - `cited_text: string` - `document_index: number` minimum: 0 - `document_title: string or null` - `end_page_number: number` - `file_id: string or null` - `start_page_number: number` minimum: 1 - `BetaCitationContentBlockLocation object` - `type: "content_block_location"` default: content_block_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `document_index: number` minimum: 0 - `document_title: string or null` - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `file_id: string or null` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `BetaCitationsWebSearchResultLocation object` - `type: "web_search_result_location"` default: web_search_result_location - `cited_text: string` - `encrypted_index: string` - `title: string or null` maxLength: 512 - `url: string` - `BetaCitationSearchResultLocation object` - `type: "search_result_location"` default: search_result_location - `cited_text: string` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `end_block_index: number` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `search_result_index: number` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. minimum: 0 - `source: string` - `start_block_index: number` 0-based index of the first cited block in the source's `content` array. minimum: 0 - `title: string or null` - `text: string` minLength: 0 - `BetaThinkingBlock object` - `type: "thinking"` default: thinking - `signature: string` A value used to verify that this thinking block was generated by Claude when it is passed back to the API. This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details. - `thinking: string` The text of Claude's thinking process for this block. - `BetaRedactedThinkingBlock object` - `type: "redacted_thinking"` default: redacted_thinking - `data: string` The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content. Pass `redacted_thinking` blocks back to the API unchanged when continuing a multi-turn conversation. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking#redacted-thinking-blocks) for details. - `BetaToolUseBlock object` - `type: "tool_use"` default: tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` minLength: 1 - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `type: "direct"` - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `type: "code_execution_20250825"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaServerToolCaller20260120 object` - `type: "code_execution_20260120"` - `tool_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `toolset_name: optional string or null` For a toolset member tool_use, the toolset family. maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$ - `BetaServerToolUseBlock object` - `type: "server_tool_use"` default: server_tool_use - `id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `input: map[unknown]` - `name: "advisor" or "web_search" or "web_fetch" or 5 more` - `"advisor"` - `"web_search"` - `"web_fetch"` - `"code_execution"` - `"bash_code_execution"` - `"text_editor_code_execution"` - `"tool_search_tool_regex"` - `"tool_search_tool_bm25"` - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebSearchToolResultBlock object` - `type: "web_search_tool_result"` default: web_search_tool_result - `content: BetaWebSearchToolResultBlockContent` - `BetaWebSearchToolResultError object` - `type: "web_search_tool_result_error"` default: web_search_tool_result_error - `error_code: BetaWebSearchToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"max_uses_exceeded"` - `"too_many_requests"` - `"query_too_long"` - `"request_too_large"` - `array of BetaWebSearchResultBlock` - `type: "web_search_result"` default: web_search_result - `encrypted_content: string` - `page_age: string or null` - `title: string` - `url: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaWebFetchToolResultBlock object` - `type: "web_fetch_tool_result"` default: web_fetch_tool_result - `content: BetaWebFetchToolResultErrorBlock or BetaWebFetchBlock` - `BetaWebFetchToolResultErrorBlock object` - `type: "web_fetch_tool_result_error"` default: web_fetch_tool_result_error - `error_code: BetaWebFetchToolResultErrorCode` - `"invalid_tool_input"` - `"url_too_long"` - `"url_not_allowed"` - `"url_not_in_prior_context"` - `"url_not_accessible"` - `"unsupported_content_type"` - `"too_many_requests"` - `"max_uses_exceeded"` - `"unavailable"` - `"content_too_large"` - `BetaWebFetchBlock object` - `type: "web_fetch_result"` default: web_fetch_result - `content: BetaDocumentBlock` - `type: "document"` default: document - `citations: BetaCitationConfig or null` Citation configuration for the document - `enabled: boolean` default: false - `source: BetaBase64PDFSource or BetaPlainTextSource` - `BetaBase64PDFSource object` - `type: "base64"` - `data: string` format: byte - `media_type: "application/pdf"` - `BetaPlainTextSource object` - `type: "text"` - `data: string` - `media_type: "text/plain"` - `title: string or null` The title of the document - `retrieved_at: string or null` ISO 8601 timestamp when the content was retrieved - `url: string` Fetched content URL - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `caller: optional BetaDirectCaller or BetaServerToolCaller or BetaServerToolCaller20260120` Tool invocation directly from the model. - `BetaDirectCaller object` Tool invocation directly from the model. - `BetaServerToolCaller object` Tool invocation generated by a server-side tool. - `BetaServerToolCaller20260120 object` - `BetaAdvisorToolResultBlock object` - `type: "advisor_tool_result"` default: advisor_tool_result - `content: BetaAdvisorToolResultError or BetaAdvisorResultBlock or BetaAdvisorRedactedResultBlock` - `BetaAdvisorToolResultError object` - `type: "advisor_tool_result_error"` default: advisor_tool_result_error - `error_code: "max_uses_exceeded" or "prompt_too_long" or "too_many_requests" or 4 more` - `"max_uses_exceeded"` - `"prompt_too_long"` - `"too_many_requests"` - `"overloaded"` - `"unavailable"` - `"execution_time_exceeded"` - `"model_not_found"` - `BetaAdvisorResultBlock object` - `type: "advisor_result"` default: advisor_result - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). `max_tokens` indicates the advisor's output was truncated at the tool's `max_tokens` value or the advisor model's policy cap. - `text: string` - `BetaAdvisorRedactedResultBlock object` - `type: "advisor_redacted_result"` default: advisor_redacted_result - `encrypted_content: string` Opaque blob containing the advisor's output. Round-trip verbatim; do not inspect or modify. - `stop_reason: string or null` The advisor sub-inference's stop reason (same values as the top-level message `stop_reason`). - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaCodeExecutionToolResultBlock object` - `type: "code_execution_tool_result"` default: code_execution_tool_result - `content: BetaCodeExecutionToolResultBlockContent` Code execution result with encrypted stdout for PFC + web_search results. - `BetaCodeExecutionToolResultError object` - `type: "code_execution_tool_result_error"` default: code_execution_tool_result_error - `error_code: BetaCodeExecutionToolResultErrorCode` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `BetaCodeExecutionResultBlock object` - `type: "code_execution_result"` default: code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `BetaEncryptedCodeExecutionResultBlock object` Code execution result with encrypted stdout for PFC + web_search results. - `type: "encrypted_code_execution_result"` default: encrypted_code_execution_result - `content: array of BetaCodeExecutionOutputBlock` - `type: "code_execution_output"` default: code_execution_output - `file_id: string` - `encrypted_stdout: string` - `return_code: number` - `stderr: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaBashCodeExecutionToolResultBlock object` - `type: "bash_code_execution_tool_result"` default: bash_code_execution_tool_result - `content: BetaBashCodeExecutionToolResultError or BetaBashCodeExecutionResultBlock` - `BetaBashCodeExecutionToolResultError object` - `type: "bash_code_execution_tool_result_error"` default: bash_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"output_file_too_large"` - `BetaBashCodeExecutionResultBlock object` - `type: "bash_code_execution_result"` default: bash_code_execution_result - `content: array of BetaBashCodeExecutionOutputBlock` - `type: "bash_code_execution_output"` default: bash_code_execution_output - `file_id: string` - `return_code: number` - `stderr: string` - `stdout: string` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaTextEditorCodeExecutionToolResultBlock object` - `type: "text_editor_code_execution_tool_result"` default: text_editor_code_execution_tool_result - `content: BetaTextEditorCodeExecutionToolResultError or BetaTextEditorCodeExecutionViewResultBlock or BetaTextEditorCodeExecutionCreateResultBlock or BetaTextEditorCodeExecutionStrReplaceResultBlock` - `BetaTextEditorCodeExecutionToolResultError object` - `type: "text_editor_code_execution_tool_result_error"` default: text_editor_code_execution_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `"file_not_found"` - `error_message: string or null` - `BetaTextEditorCodeExecutionViewResultBlock object` - `type: "text_editor_code_execution_view_result"` default: text_editor_code_execution_view_result - `content: string` - `file_type: "text" or "image" or "pdf"` - `"text"` - `"image"` - `"pdf"` - `num_lines: number or null` - `start_line: number or null` - `total_lines: number or null` - `BetaTextEditorCodeExecutionCreateResultBlock object` - `type: "text_editor_code_execution_create_result"` default: text_editor_code_execution_create_result - `is_file_update: boolean` - `BetaTextEditorCodeExecutionStrReplaceResultBlock object` - `type: "text_editor_code_execution_str_replace_result"` default: text_editor_code_execution_str_replace_result - `lines: array of string or null` - `new_lines: number or null` - `new_start: number or null` - `old_lines: number or null` - `old_start: number or null` - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaToolSearchToolResultBlock object` - `type: "tool_search_tool_result"` default: tool_search_tool_result - `content: BetaToolSearchToolResultError or BetaToolSearchToolSearchResultBlock` - `BetaToolSearchToolResultError object` - `type: "tool_search_tool_result_error"` default: tool_search_tool_result_error - `error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"` - `"invalid_tool_input"` - `"unavailable"` - `"too_many_requests"` - `"execution_time_exceeded"` - `error_message: string or null` - `BetaToolSearchToolSearchResultBlock object` - `type: "tool_search_tool_search_result"` default: tool_search_tool_search_result - `tool_references: array of BetaToolReferenceBlock` - `type: "tool_reference"` default: tool_reference - `tool_name: string` maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$ - `tool_use_id: string` pattern: ^srvtoolu_[a-zA-Z0-9_]+$ - `BetaMCPToolUseBlock object` - `type: "mcp_tool_use"` default: mcp_tool_use - `id: string` pattern: ^[a-zA-Z0-9_-]+$ - `input: map[unknown]` - `name: string` The name of the MCP tool - `server_name: string` The name of the MCP server - `BetaMCPToolResultBlock object` - `type: "mcp_tool_result"` default: mcp_tool_result - `content: string or array of BetaTextBlock` - `string` - `BetaMCPToolResultBlockContent = array of BetaTextBlock` - `type: "text"` default: text - `citations: array of BetaTextCitation or null` Citations supporting the text block. The type of citation returned will depend on the type of document being cited. Citing a PDF results in `page_location`, plain text results in `char_location`, and content document results in `content_block_location`. - `text: string` minLength: 0 - `is_error: boolean` default: false - `tool_use_id: string` pattern: ^[a-zA-Z0-9_-]+$ - `BetaContainerUploadBlock object` Response model for a file uploaded to the container. - `type: "container_upload"` default: container_upload - `file_id: string` - `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. - `type: "compaction"` default: compaction - `content: string or null` Summary of compacted content, or null if compaction failed - `encrypted_content: string or null` Opaque metadata from prior compaction, to be round-tripped verbatim - `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. - `type: "fallback"` default: fallback - `from: BetaFallbackInfo` The model whose output ends at this point — the model that declined at this hop. When the declining hop is the requested model, its `model` echoes the top-level `model` string the caller sent (alias or canonical); when the declining hop is a fallback model, its `model` is that model's canonical id. - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `"claude-fable-5-1"` Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows - `"claude-mythos-5-1"` Our most capable model for cybersecurity and biology research, available through trusted access programs - `"claude-sonnet-5"` High-performance model for coding and agents - `"claude-fable-5"` Next generation of intelligence for the hardest knowledge work and coding problems - `"claude-mythos-5"` Most capable model for cybersecurity and biology research - `"claude-opus-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-8"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-7"` Powerful intelligence for long-running agents and coding - `"claude-mythos-preview"` New class of intelligence, strongest in coding and cybersecurity - `"claude-opus-4-6"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-6"` Best combination of speed and intelligence - `"claude-haiku-4-5"` Fastest model with near-frontier intelligence - `"claude-haiku-4-5-20251001"` Fastest model with near-frontier intelligence - `"claude-opus-4-5"` Powerful intelligence for long-running agents and coding - `"claude-opus-4-5-20251101"` Powerful intelligence for long-running agents and coding - `"claude-sonnet-4-5"` High-performance model for agents and coding - `"claude-sonnet-4-5-20250929"` High-performance model for agents and coding - `string` - `to: BetaFallbackInfo` The fallback model producing the content that follows this block. Its `model` is always the canonical id. - `trigger: BetaFallbackRefusalTrigger` What caused the `from` model to hand over at this hop. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `context_management: BetaContextManagementResponse or null` Context management response. Information about context management strategies applied during the request. - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse` List of context management edits that were applied. - `BetaClearToolUses20250919EditResponse object` - `type: "clear_tool_uses_20250919"` The type of context management edit applied. default: clear_tool_uses_20250919 - `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 - `BetaClearThinking20251015EditResponse object` - `type: "clear_thinking_20251015"` The type of context management edit applied. default: clear_thinking_20251015 - `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 - `diagnostics: BetaDiagnostics or null` Response envelope for request-level diagnostics. Present (possibly null) whenever the caller supplied `diagnostics` on the request. - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more 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` - `type: "model_changed"` default: model_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissSystemChanged object` - `type: "system_changed"` default: system_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissToolsChanged object` - `type: "tools_changed"` default: tools_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissMessagesChanged object` - `type: "messages_changed"` default: messages_changed - `cache_missed_input_tokens: number` Approximate number of input tokens that would have been read from cache had the prefix matched the previous request. - `BetaCacheMissPreviousMessageNotFound object` - `type: "previous_message_not_found"` default: previous_message_not_found - `BetaCacheMissUnavailable object` - `type: "unavailable"` default: unavailable - `model: Model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `role: "assistant"` Conversational role of the generated message. This will always be `"assistant"`. default: assistant - `stop_details: BetaRefusalStopDetails or null` Structured information about a refusal. - `type: "refusal"` default: refusal - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null` The policy category that triggered a refusal. - `"cyber"` The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. - `"bio"` The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. - `"frontier_llm"` The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. - `"reasoning_extraction"` The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking). - `"general_harms"` The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category. - `explanation: string or null` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `fallback_credit_token: string or null` Opaque code that refunds the cache-miss cost when retrying this refused request on the fallback model. Pass it as `fallback_credit_token` on the retry request. Expires 5 minutes after the refusal. The retry is sent either with the same request body (`system`, `messages`, `tools`, and other render-shaping fields), or with the same body plus one appended `assistant` message whose content is the partial text (with any trailing whitespace stripped from the final text block) and paired server-tool blocks from this refusal — which also authorizes that appended turn as an assistant-prefill continuation on models that otherwise disallow prefill. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed the second way — if a same-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry the second way instead. Either way: same workspace, same platform; a mismatch is a 400. Resending a token for an already-warm prefix is permitted but yields no additional credit. `null` when the refused model isn't eligible for a fallback credit. - `fallback_has_prefill_claim: boolean or null` Whether the accompanying `fallback_credit_token` may be redeemed with the appended-assistant retry form. Only set when `fallback_credit_token` is present. `true`: retry by resending the same request body plus one appended `assistant` message whose content is this response's `content` with any trailing whitespace stripped from the final text block and unpaired `tool_use` blocks omitted (the same appended-turn shape described on `fallback_credit_token`), with the token attached. `false`: retry by resending the original request body unchanged, with the token attached — the appended-assistant form is not available for this refusal (no continuable partial content, or the request uses `output_format` or a `tool_choice` that forces tool use). One exception: when the request used `output_format` or a forced `tool_choice` and the refusal arrived after server tools (including MCP connector tools) had already executed, the token may not be redeemable by either retry form; if the exact-body retry is then rejected with a 400 saying the token must be redeemed by continuing the partial response, discard the token and retry without it. Advisory: if an appended-assistant retry is rejected with a 400 despite `true`, fall back to resending the original request body with the token. - `recommended_model: string or null` The server's suggested retry target for this refusal. Populated when a fallback attempt could not be made (the fallback model's rate limit was exhausted, or it was overloaded); names the fallback model the caller can retry directly. Null otherwise. - `stop_reason: BetaStopReason or null` The reason that we stopped. This may be one the following values: * `"end_turn"`: the model reached a natural stopping point * `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum * `"stop_sequence"`: one of your provided custom `stop_sequences` was generated * `"tool_use"`: the model invoked one or more tools * `"pause_turn"`: we paused a long-running turn. You may provide the response back as-is in a subsequent request to let the model continue. * `"refusal"`: when streaming classifiers intervene to handle potential policy violations * `"model_context_window_exceeded"`: we exceeded the model's context window In non-streaming mode this value is always non-null. In streaming mode, it is null in the `message_start` event and non-null otherwise. - `"end_turn"` - `"max_tokens"` - `"stop_sequence"` - `"tool_use"` - `"pause_turn"` - `"compaction"` - `"refusal"` - `"model_context_window_exceeded"` - `stop_sequence: string or null` Which custom stop sequence was generated, if any. This value will be a non-null string if one of your custom stop sequences was generated. - `usage: BetaUsage` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `ephemeral_1h_input_tokens: number` The number of input tokens used to create the 1 hour cache entry. default: 0, minimum: 0 - `ephemeral_5m_input_tokens: number` The number of input tokens used to create the 5 minute cache entry. default: 0, minimum: 0 - `cache_creation_input_tokens: number 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` Outcome of the `fallback_credit_token` presented on this request. - `status: BetaFallbackCreditRedeemed or BetaFallbackCreditNotApplied` Whether the fallback-credit reprice was applied to this response's billing. A union discriminated on `type`. `redeemed`: the retry is billed as if the conversation had been on the retry model all along — including when the resulting shift is zero because there was nothing to move. `not_applied`: no reprice was applied; the arm's `reason` says why. - `BetaFallbackCreditRedeemed object` The reprice was applied: the retry is billed as if the conversation had been on the retry model all along. - `type: "redeemed"` default: redeemed - `BetaFallbackCreditNotApplied object` No reprice was applied; `reason` says why. - `type: "not_applied"` default: not_applied - `reason: "body_mismatch" or "continuation_excluded" or "continuation_only" or 9 more` Why the reprice was not applied. A closed enum; additions to the redemption-check vocabulary arrive as deliberate schema updates. - `"body_mismatch"` - `"continuation_excluded"` - `"continuation_only"` - `"expired"` - `"invalid_target_model"` - `"not_enabled"` - `"reprice_unavailable"` - `"temporarily_unavailable"` - `"variant_fields_present"` - `"wrong_organization"` - `"wrong_platform"` - `"wrong_workspace"` - `remove_to_redeem: optional array of string or null` Request fields to remove before retrying, so the retry can redeem this token. Present exactly when `reason` is `variant_fields_present` — never null, never an empty array; absent otherwise. Fields are named only from your own request, and only after the sealed variant hash matched. A served best-effort retry has already been billed at normal price; nothing redeems retroactively, but a corrected re-send inside the token's five-minute window can still redeem. - `inference_geo: string or null` The geographic region where inference was performed for this request. - `input_tokens: number` The 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, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to: - Determine which iterations exceeded long context thresholds (>=200k tokens) - Calculate the context window size from the last `message` entry - Understand token accumulation across server-side tool use loops A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results. - `BetaMessageIterationUsage object` Token usage for a sampling iteration. - `type: "message"` Usage for a sampling iteration default: message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaCompactionIterationUsage object` Token usage for a compaction iteration. - `type: "compaction"` Usage for a compaction iteration default: compaction - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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 - `BetaAdvisorMessageIterationUsage object` Token usage for an advisor sub-inference iteration. - `type: "advisor_message"` Usage for an advisor sub-inference iteration default: advisor_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `BetaFallbackMessageIterationUsage object` Token usage for the fallback-model attempt of a server-side fallback request. Produced in place of a `message` entry for whichever hop served the response. A declined hop produces the existing `message` entry. Whether a fallback model served the response is signalled by the presence of this entry in `usage.iterations`. - `type: "fallback_message"` Usage for the fallback-model attempt that served the response default: fallback_message - `cache_creation: BetaCacheCreation or null` Breakdown of cached tokens by TTL - `cache_creation_input_tokens: number` 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. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `output_tokens: number` The number of output tokens which were used. minimum: 0 - `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. - `thinking_tokens: number` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. default: 0, minimum: 0 - `server_tool_use: BetaServerToolUsage or null` The number of server tool requests. - `web_fetch_requests: number` The number of web fetch tool requests. default: 0, minimum: 0 - `web_search_requests: number` The number of web search tool requests. default: 0, minimum: 0 - `service_tier: "standard" or "priority" or "batch" or null` If the request used the priority, standard, or batch tier. - `"standard"` - `"priority"` - `"batch"` - `speed: "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. - `"standard"` - `"fast"` - `input_transformations: optional array of BetaThinkingDroppedInputTransformation or null` Changes the API made to the request's input before showing it to the model: one entry per change, in request order. Today the only entry type is `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text` block from the request's `messages` that was removed from the prompt instead of being shown to the model because it failed a binding check. More entry types may be added over time; ignore types you do not recognize. Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on every such response from a model that supports extended thinking, as `[]` when nothing was changed; without the beta, blocks are removed all the same but nothing is reported. Removed blocks contribute nothing to `usage.input_tokens`. When streaming, the array is final in `message_start`; the final `message_delta` event carries it only when a server-side model fallback happened mid-stream, in which case it holds the serving model's entries and replaces the one in `message_start`. - `type: "thinking_dropped"` Always `thinking_dropped` for this entry type. default: thinking_dropped - `path: string` Where the removed block was in your request, as `messages.{i}.content.{j}`: `i` indexes the `messages` array you sent and `j` that message's `content` array — the same form error messages use. - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"` Which binding check removed the block: `model_binding_mismatch` — it was created by a model whose reasoning the requested model may not read; `prefix_binding_mismatch` — the conversation before it differs from the conversation it was created in (the rest of that turn's consecutive thinking blocks are removed with it, each with this reason); `organization_binding_mismatch` — it was created under a different organization (an Anthropic organization, AWS account or Google Cloud project) and this organization is not one of its additional organizations; `end_user_binding_mismatch` — it was created for a different end user, or was removed by the consumer-organization binding. A block that would fail several checks reports one reason, in this order of precedence: `organization_binding_mismatch`, `end_user_binding_mismatch`, `model_binding_mismatch`, `prefix_binding_mismatch`. - `"model_binding_mismatch"` - `"prefix_binding_mismatch"` - `"organization_binding_mismatch"` - `"end_user_binding_mismatch"` - `BetaMessageBatchErroredResult object` - `type: "errored"` default: errored - `error: BetaErrorResponse` - `type: "error"` default: error - `error: BetaError` - `BetaInvalidRequestError object` - `type: "invalid_request_error"` default: invalid_request_error - `message: string` default: Invalid request - `BetaAuthenticationError object` - `type: "authentication_error"` default: authentication_error - `message: string` default: Authentication error - `BetaBillingError object` - `type: "billing_error"` default: billing_error - `message: string` default: Billing error - `BetaPermissionError object` - `type: "permission_error"` default: permission_error - `message: string` default: Permission denied - `BetaNotFoundError object` - `type: "not_found_error"` default: not_found_error - `message: string` default: Not found - `BetaRateLimitError object` - `type: "rate_limit_error"` default: rate_limit_error - `message: string` default: Rate limited - `BetaGatewayTimeoutError object` - `type: "timeout_error"` default: timeout_error - `message: string` default: Request timeout - `BetaAPIError object` - `type: "api_error"` default: api_error - `message: string` default: Internal server error - `BetaOverloadedError object` - `type: "overloaded_error"` default: overloaded_error - `message: string` default: Overloaded - `request_id: string or null` - `BetaMessageBatchCanceledResult object` - `type: "canceled"` default: canceled - `BetaMessageBatchExpiredResult object` - `type: "expired"` default: expired #### Example ```bash curl https://api.anthropic.com/v1/messages/batches/$MESSAGE_BATCH_ID/results \ -H 'anthropic-version: 2023-06-01' \ -H 'anthropic-beta: message-batches-2024-09-24' \ -H "X-Api-Key: $ANTHROPIC_API_KEY" ```