SPB Git

Repository Public

messages.md 965.4 KB


# title: Messages url: https://platform.claude.com/docs/en/api/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

# Headers

  • "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 without generating a response.

    Different models have different maximum values for this parameter. See models for details.

    minimum: 0

  • messages: array of MessageParam

    Input messages.

    Our models are trained to operate on alternating user and assistant conversational turns. When creating a new Message, you specify the prior conversational turns with the messages parameter, and the model then generates the next Message in the conversation. Consecutive user or assistant turns in your request will be combined into a single turn.

    Each input message must be an object with a role and content. You can specify a single user-role message, or you can include multiple user and assistant messages.

    If the final message uses the assistant role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response.

    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.

    Note that if you want to include a system prompt, 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 ContentBlockParam

      • string

      • array of ContentBlockParam

        • TextBlockParam object

          • type: "text"

          • text: string

            minLength: 1

          • cache_control: optional CacheControlEphemeral 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 for details.

              • "5m"

              • "1h"

          • citations: optional array of TextCitationParam or null

            • CitationCharLocationParam 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

            • CitationPageLocationParam 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

            • CitationContentBlockLocationParam 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

            • CitationWebSearchResultLocationParam object

              • type: "web_search_result_location"

              • cited_text: string

              • encrypted_index: string

              • title: string or null

                maxLength: 512, minLength: 1

              • url: string

                minLength: 1

            • CitationSearchResultLocationParam 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

        • ImageBlockParam object

          • type: "image"

          • source: Base64ImageSource or URLImageSource or FileImageSource

            • Base64ImageSource 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"

            • URLImageSource object

              • type: "url"

              • url: string

            • FileImageSource object

              • type: "file"

              • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • transformations: optional ImageTransformationsParam 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"

        • DocumentBlockParam object

          • type: "document"

          • source: Base64PDFSource or PlainTextSource or ContentBlockSource or 2 more

            • Base64PDFSource object

              • type: "base64"

              • data: string

                format: byte

              • media_type: "application/pdf"

            • PlainTextSource object

              • type: "text"

              • data: string

              • media_type: "text/plain"

            • ContentBlockSource object

              • type: "content"

              • content: string or array of ContentBlockSourceContent

                • string

                • ContentBlockSourceContent = array of ContentBlockSourceContent

                  • TextBlockParam object

                  • ImageBlockParam object

            • URLPDFSource object

              • type: "url"

              • url: string

            • FileDocumentSource object

              • type: "file"

              • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam or null

            • enabled: optional boolean
          • context: optional string or null

            minLength: 1

          • title: optional string or null

            maxLength: 500, minLength: 1

        • SearchResultBlockParam object

          • type: "search_result"

          • content: array of TextBlockParam

            • type: "text"

            • text: string

              minLength: 1

            • cache_control: optional CacheControlEphemeral or null

              Create a cache control breakpoint at this content block.

            • citations: optional array of TextCitationParam or null

          • source: string

          • title: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam

        • ThinkingBlockParam 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.

        • RedactedThinkingBlockParam 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.

        • ToolUseBlockParam object

          • type: "tool_use"

          • id: string

            pattern: [1]+$

          • input: map[unknown]

          • name: string

            maxLength: 200, minLength: 1

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

            • DirectCaller object

              Tool invocation directly from the model.

              • type: "direct"
            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

              • type: "code_execution_20250825"

              • tool_id: string

                pattern: ^srvtoolu_[a-zA-Z0-9_]+$

            • ServerToolCaller20260120 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: [2]+$

        • ToolResultBlockParam object

          • type: "tool_result"

          • tool_use_id: string

            pattern: [3]+$

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • content: optional string or array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more

            • string

            • array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more

              • TextBlockParam object

              • ImageBlockParam object

              • SearchResultBlockParam object

              • DocumentBlockParam object

              • ToolReferenceBlockParam object

                Tool reference block that can be included in tool_result content.

                • type: "tool_reference"

                • tool_name: string

                  maxLength: 256, minLength: 1, pattern: [4]{1,256}$

                • cache_control: optional CacheControlEphemeral or null

                  Create a cache control breakpoint at this content block.

              • BrowserStateBlockParam object

                The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side 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 BrowserStateTabEntry

                  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: [5]*$

                  • title: string

                    The title of the page the tab is showing. May be empty.

                    maxLength: 4096, pattern: [6]*$

                  • url: string

                    The URL of the page the tab is showing. May be empty.

                    maxLength: 4096, pattern: [7]*$

                  • 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 CacheControlEphemeral or null

                  Create a cache control breakpoint at this content block.

                • state_changes: optional array of BrowserStateChange 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

                  • BrowserStateChangeTabOpened object

                    A tab this call's execution opened that remains open at its end — the creation delta of the tabs inventory, not an event log.

                    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: [8]*$

                  • BrowserStateChangeDownloadStarted 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: [9]*$

                    • url: string

                      The final post-redirect URL the download was served from.

                      maxLength: 4096, pattern: [10]*$

                  • BrowserStateChangeDownloadCompleted 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: [11]*$

                    • url: string

                      The final post-redirect URL the download was served from.

                      maxLength: 4096, pattern: [12]*$

                    • 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: [13]*$, maxLength: 4096

                    • size_bytes: optional number or null

                      The completed download's size.

                      minimum: 0

                  • BrowserStateChangeDownloadFailed 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: [14]*$

                    • url: string

                      The final post-redirect URL the download was served from.

                      maxLength: 4096, pattern: [15]*$

                    • error: optional string or null

                      The failure or cancellation detail, when known.

                      pattern: [16]*$, 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: [17]+$

        • ServerToolUseBlockParam object

          • type: "server_tool_use"

          • id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • input: map[unknown]

          • name: "web_search" or "web_fetch" or "code_execution" or 4 more

            • "web_search"

            • "web_fetch"

            • "code_execution"

            • "bash_code_execution"

            • "text_editor_code_execution"

            • "tool_search_tool_regex"

            • "tool_search_tool_bm25"

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

            • DirectCaller object

              Tool invocation directly from the model.

            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

            • ServerToolCaller20260120 object

        • WebSearchToolResultBlockParam object

          • type: "web_search_tool_result"

          • content: WebSearchToolResultBlockParamContent

            • WebSearchToolResultBlockItem = array of WebSearchResultBlockParam

              • type: "web_search_result"

              • encrypted_content: string

              • title: string

              • url: string

              • page_age: optional string or null

            • WebSearchToolRequestError object

              • type: "web_search_tool_result_error"

              • error_code: WebSearchToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "max_uses_exceeded"

                • "too_many_requests"

                • "query_too_long"

                • "request_too_large"

          • tool_use_id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

            • DirectCaller object

              Tool invocation directly from the model.

            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

            • ServerToolCaller20260120 object

        • WebFetchToolResultBlockParam object

          • type: "web_fetch_tool_result"

          • content: WebFetchToolResultErrorBlockParam or WebFetchBlockParam

            • WebFetchToolResultErrorBlockParam object

              • type: "web_fetch_tool_result_error"

              • error_code: WebFetchToolResultErrorCode

                • "invalid_tool_input"

                • "url_too_long"

                • "url_not_allowed"

                • "url_not_in_prior_context"

                • "url_not_accessible"

                • "unsupported_content_type"

                • "too_many_requests"

                • "max_uses_exceeded"

                • "unavailable"

                • "content_too_large"

            • WebFetchBlockParam object

              • type: "web_fetch_result"

              • content: DocumentBlockParam

              • 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

            • DirectCaller object

              Tool invocation directly from the model.

            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

            • ServerToolCaller20260120 object

        • CodeExecutionToolResultBlockParam object

          • type: "code_execution_tool_result"

          • content: CodeExecutionToolResultBlockParamContent

            • CodeExecutionToolResultErrorParam object

              • type: "code_execution_tool_result_error"

              • error_code: CodeExecutionToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

            • CodeExecutionResultBlockParam object

              • type: "code_execution_result"

              • content: array of CodeExecutionOutputBlockParam

                • type: "code_execution_output"

                • file_id: string

              • return_code: number

              • stderr: string

              • stdout: string

            • EncryptedCodeExecutionResultBlockParam object

              Code execution result with encrypted stdout for PFC + web_search results.

              • type: "encrypted_code_execution_result"

              • content: array of CodeExecutionOutputBlockParam

                • 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • BashCodeExecutionToolResultBlockParam object

          • type: "bash_code_execution_tool_result"

          • content: BashCodeExecutionToolResultErrorParam or BashCodeExecutionResultBlockParam

            • BashCodeExecutionToolResultErrorParam object

              • type: "bash_code_execution_tool_result_error"

              • error_code: BashCodeExecutionToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

                • "output_file_too_large"

            • BashCodeExecutionResultBlockParam object

              • type: "bash_code_execution_result"

              • content: array of BashCodeExecutionOutputBlockParam

                • 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • TextEditorCodeExecutionToolResultBlockParam object

          • type: "text_editor_code_execution_tool_result"

          • content: TextEditorCodeExecutionToolResultErrorParam or TextEditorCodeExecutionViewResultBlockParam or TextEditorCodeExecutionCreateResultBlockParam or TextEditorCodeExecutionStrReplaceResultBlockParam

            • TextEditorCodeExecutionToolResultErrorParam object

              • type: "text_editor_code_execution_tool_result_error"

              • error_code: TextEditorCodeExecutionToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

                • "file_not_found"

              • error_message: optional string or null

            • TextEditorCodeExecutionViewResultBlockParam 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

            • TextEditorCodeExecutionCreateResultBlockParam object

              • type: "text_editor_code_execution_create_result"

              • is_file_update: boolean

            • TextEditorCodeExecutionStrReplaceResultBlockParam 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • ToolSearchToolResultBlockParam object

          • type: "tool_search_tool_result"

          • content: ToolSearchToolResultErrorParam or ToolSearchToolSearchResultBlockParam

            • ToolSearchToolResultErrorParam object

              • type: "tool_search_tool_result_error"

              • error_code: ToolSearchToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

              • error_message: optional string or null

            • ToolSearchToolSearchResultBlockParam object

              • type: "tool_search_tool_search_result"

              • tool_references: array of ToolReferenceBlockParam

                • type: "tool_reference"

                • tool_name: string

                  maxLength: 256, minLength: 1, pattern: [18]{1,256}$

                • cache_control: optional CacheControlEphemeral or null

                  Create a cache control breakpoint at this content block.

          • tool_use_id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • ContainerUploadBlockParam object

          A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory.

          • type: "container_upload"

          • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

    • role: "user" or "assistant" or "system"

      • "user"

      • "assistant"

      • "system"

  • model: Model

    The model that will complete your prompt.

    See models 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 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

  • cache_control: optional CacheControlEphemeral or null

    Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request.

  • container: optional MessageCreateParamsContainer or null

    Container identifier for reuse across requests.

    • ContainerParams object

      Container parameters with skills to be loaded.

      • id: optional string or null

        Container id

      • skills: optional array of SkillParams 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

  • inference_geo: optional string or null

    Specifies the geographic region for inference processing. If not specified, the workspace's default_inference_geo is used.

  • metadata: optional Metadata

    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 OutputConfig

    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 JSONOutputFormat or null

      A schema to specify Claude's output format in responses. See structured outputs

      • type: "json_schema"

      • schema: map[unknown]

        The JSON schema of the 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 for details.

    • "auto"

    • "standard_only"

  • 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 for details.

  • system: optional string or array of TextBlockParam

    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.

    • string

    • array of TextBlockParam

      • type: "text"

      • text: string

        minLength: 1

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional array of TextCitationParam or null

  • thinking: optional ThinkingConfigParam

    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 for details.

    • ThinkingConfigEnabled 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 for details.

        minimum: 1024

      • display: optional "summarized" or "omitted" or null

        Controls how thinking content appears in the response. When set to summarized, thinking is returned normally. When set to omitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to summarized.

        • "summarized"

        • "omitted"

    • ThinkingConfigDisabled object

      • type: "disabled"
    • ThinkingConfigAdaptive object

      • type: "adaptive"

      • display: optional "summarized" or "omitted" or null

        Controls how thinking content appears in the response. When set to summarized, thinking is returned normally. When set to omitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to summarized.

        • "summarized"

        • "omitted"

  • tool_choice: optional ToolChoice

    How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.

    • ToolChoiceAuto 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.

    • ToolChoiceAny 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.

    • ToolChoiceTool 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.

    • ToolChoiceNone object

      The model will not be allowed to use tools.

      • type: "none"
  • tools: optional array of ToolUnion

    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, see their individual documentation as each has its own behavior (e.g., the 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 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 for more details.

    • Tool object

      • type: optional "custom" or null

      • input_schema: object

        JSON schema 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: [19]{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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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

    • ToolBash20250124 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20250522 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20250825 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20260120 object

      Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint).

      • 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20260521 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • BrowserToolset20260801 object

      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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • configs: optional BrowserToolsetConfigs 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 BrowserTypeConfig 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 BrowserCloseTabConfig 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 BrowserDoubleClickConfig 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 BrowserFileUploadConfig 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 BrowserFindConfig 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 BrowserFormInputConfig 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 BrowserGetPageTextConfig 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 BrowserHoldKeyConfig 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 BrowserHoverConfig 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 BrowserJavascriptExecConfig 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 BrowserKeyConfig 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 BrowserLeftClickConfig 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 BrowserLeftClickDragConfig 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 BrowserLeftMouseDownConfig 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 BrowserLeftMouseUpConfig 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 BrowserListTabsConfig 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 BrowserMiddleClickConfig 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 BrowserMouseMoveConfig 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 BrowserNavigateConfig 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 BrowserNewTabConfig 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 BrowserReadConsoleConfig 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 BrowserReadNetworkConfig 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 BrowserReadPageConfig 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 BrowserRightClickConfig 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 BrowserScreenshotConfig 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 BrowserScrollConfig 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 BrowserScrollToConfig 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 BrowserSwitchTabConfig 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 BrowserTripleClickConfig 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 BrowserWaitConfig 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 BrowserZoomConfig 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.

    • MemoryTool20250818 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ComputerToolset20260801 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • configs: optional ComputerToolsetConfigs 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 ComputerTypeConfig 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 ComputerCursorPositionConfig 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 ComputerDoubleClickConfig 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 ComputerHoldKeyConfig 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 ComputerKeyConfig 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 ComputerLeftClickConfig 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 ComputerLeftClickDragConfig 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 ComputerLeftMouseDownConfig 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 ComputerLeftMouseUpConfig 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 ComputerMiddleClickConfig 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 ComputerMouseMoveConfig 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 ComputerRightClickConfig 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 ComputerScreenshotConfig 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 ComputerScrollConfig 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 ComputerTripleClickConfig 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 ComputerWaitConfig 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 ComputerZoomConfig 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.

    • ToolTextEditor20250124 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ToolTextEditor20250429 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ToolTextEditor20250728 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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

    • WebSearchTool20250305 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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 UserLocation 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 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 of the user.

          maxLength: 255, minLength: 1

    • WebFetchTool20250910 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

        • client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

          Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].

          • WebFetchURLSourceAll object

            The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

            • type: "all"
          • WebFetchURLSourceNone object

            The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

            • type: "none"
          • WebFetchURLSourceOnly object

            The tool filter variant under which only the named tools' results contribute.

            • type: "only"

            • tools: array of WebFetchURLSourceToolReference

              • type: "tool_reference"

              • name: string

          • WebFetchURLSourceExcept object

            The tool filter variant under which every result but the named tools' contributes.

            • type: "except"

            • tools: array of WebFetchURLSourceToolReference

              • type: "tool_reference"

              • name: string

        • server_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

          Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute.

          • WebFetchURLSourceAll object

            The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

          • WebFetchURLSourceNone object

            The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

          • WebFetchURLSourceOnly object

            The tool filter variant under which only the named tools' results contribute.

          • WebFetchURLSourceExcept object

            The tool filter variant under which every result but the named tools' contributes.

        • user_input: optional WebFetchURLSourceAll or WebFetchURLSourceNone

          Whether URLs in user messages are fetchable: "all" or "none".

          • WebFetchURLSourceAll object

            The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

          • WebFetchURLSourceNone object

            The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

    • WebSearchTool20260209 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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 UserLocation or null

        Parameters for the user's location. Used to provide more relevant search results.

    • WebFetchTool20260209 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

    • WebFetchTool20260309 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

      • 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.

    • WebSearchTool20260318 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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 UserLocation or null

        Parameters for the user's location. Used to provide more relevant search results.

    • WebFetchTool20260318 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

      • 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.

    • ToolSearchToolBm25_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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ToolSearchToolRegex20251119 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

  • temperature: optional number

    Deprecated: Deprecated. Models released after Claude Opus 4.6 do not support setting temperature. A value of 1.0 will be accepted for backwards compatibility, all other values will be rejected with a 400 error.

    Amount of randomness injected into the response.

    Defaults to 1.0. Ranges from 0.0 to 1.0. Use temperature closer to 0.0 for analytical / multiple choice, and closer to 1.0 for creative and generative tasks.

    Note that even with temperature of 0.0, the results will not be fully deterministic.

    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.

    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

  • Message 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: Container 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 ContainerSkill 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 ContentBlock

      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)"}]
      • TextBlock object

        • type: "text"

          default: text

        • citations: array of TextCitation 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.

          • CitationCharLocation 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

          • CitationPageLocation 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

          • CitationContentBlockLocation 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

          • CitationsWebSearchResultLocation 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

          • CitationsSearchResultLocation 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

      • ThinkingBlock 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 for details.

        • thinking: string

          The text of Claude's thinking process for this block.

      • RedactedThinkingBlock 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 for details.

      • ToolUseBlock object

        • type: "tool_use"

          default: tool_use

        • id: string

          pattern: [20]+$

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          default: {"type":"direct"}

          • DirectCaller object

            Tool invocation directly from the model.

            • type: "direct"
          • ServerToolCaller object

            Tool invocation generated by a server-side tool.

            • type: "code_execution_20250825"

            • tool_id: string

              pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • ServerToolCaller20260120 object

            • type: "code_execution_20260120"

            • tool_id: string

              pattern: ^srvtoolu_[a-zA-Z0-9_]+$

        • input: map[unknown]

        • name: string

          minLength: 1

        • toolset_name: optional string or null

          For a toolset member tool_use, the toolset family.

          maxLength: 64, minLength: 1, pattern: [21]+$

      • ServerToolUseBlock object

        • type: "server_tool_use"

          default: server_tool_use

        • id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          default: {"type":"direct"}

          • DirectCaller object

            Tool invocation directly from the model.

          • ServerToolCaller object

            Tool invocation generated by a server-side tool.

          • ServerToolCaller20260120 object

        • input: map[unknown]

        • name: "web_search" or "web_fetch" or "code_execution" or 4 more

          • "web_search"

          • "web_fetch"

          • "code_execution"

          • "bash_code_execution"

          • "text_editor_code_execution"

          • "tool_search_tool_regex"

          • "tool_search_tool_bm25"

      • WebSearchToolResultBlock object

        • type: "web_search_tool_result"

          default: web_search_tool_result

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          default: {"type":"direct"}

          • DirectCaller object

            Tool invocation directly from the model.

          • ServerToolCaller object

            Tool invocation generated by a server-side tool.

          • ServerToolCaller20260120 object

        • content: WebSearchToolResultBlockContent

          • WebSearchToolResultError object

            • type: "web_search_tool_result_error"

              default: web_search_tool_result_error

            • error_code: WebSearchToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "max_uses_exceeded"

              • "too_many_requests"

              • "query_too_long"

              • "request_too_large"

          • array of WebSearchResultBlock

            • 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_]+$

      • WebFetchToolResultBlock object

        • type: "web_fetch_tool_result"

          default: web_fetch_tool_result

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          default: {"type":"direct"}

          • DirectCaller object

            Tool invocation directly from the model.

          • ServerToolCaller object

            Tool invocation generated by a server-side tool.

          • ServerToolCaller20260120 object

        • content: WebFetchToolResultErrorBlock or WebFetchBlock

          • WebFetchToolResultErrorBlock object

            • type: "web_fetch_tool_result_error"

              default: web_fetch_tool_result_error

            • error_code: WebFetchToolResultErrorCode

              • "invalid_tool_input"

              • "url_too_long"

              • "url_not_allowed"

              • "url_not_in_prior_context"

              • "url_not_accessible"

              • "unsupported_content_type"

              • "too_many_requests"

              • "max_uses_exceeded"

              • "unavailable"

              • "content_too_large"

          • WebFetchBlock object

            • type: "web_fetch_result"

              default: web_fetch_result

            • content: DocumentBlock

              • type: "document"

                default: document

              • citations: CitationsConfig or null

                Citation configuration for the document

                • enabled: boolean

                  default: false

              • source: Base64PDFSource or PlainTextSource

                • Base64PDFSource object

                  • type: "base64"

                  • data: string

                    format: byte

                  • media_type: "application/pdf"

                • PlainTextSource 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_]+$

      • CodeExecutionToolResultBlock object

        • type: "code_execution_tool_result"

          default: code_execution_tool_result

        • content: CodeExecutionToolResultBlockContent

          • CodeExecutionToolResultError object

            • type: "code_execution_tool_result_error"

              default: code_execution_tool_result_error

            • error_code: CodeExecutionToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

          • CodeExecutionResultBlock object

            • type: "code_execution_result"

              default: code_execution_result

            • content: array of CodeExecutionOutputBlock

              • type: "code_execution_output"

                default: code_execution_output

              • file_id: string

            • return_code: number

            • stderr: string

            • stdout: string

          • EncryptedCodeExecutionResultBlock 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 CodeExecutionOutputBlock

              • 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_]+$

      • BashCodeExecutionToolResultBlock object

        • type: "bash_code_execution_tool_result"

          default: bash_code_execution_tool_result

        • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

          • BashCodeExecutionToolResultError object

            • type: "bash_code_execution_tool_result_error"

              default: bash_code_execution_tool_result_error

            • error_code: BashCodeExecutionToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

              • "output_file_too_large"

          • BashCodeExecutionResultBlock object

            • type: "bash_code_execution_result"

              default: bash_code_execution_result

            • content: array of BashCodeExecutionOutputBlock

              • 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_]+$

      • TextEditorCodeExecutionToolResultBlock object

        • type: "text_editor_code_execution_tool_result"

          default: text_editor_code_execution_tool_result

        • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

          • TextEditorCodeExecutionToolResultError object

            • type: "text_editor_code_execution_tool_result_error"

              default: text_editor_code_execution_tool_result_error

            • error_code: TextEditorCodeExecutionToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

              • "file_not_found"

            • error_message: string or null

          • TextEditorCodeExecutionViewResultBlock 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

          • TextEditorCodeExecutionCreateResultBlock object

            • type: "text_editor_code_execution_create_result"

              default: text_editor_code_execution_create_result

            • is_file_update: boolean

          • TextEditorCodeExecutionStrReplaceResultBlock 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_]+$

      • ToolSearchToolResultBlock object

        • type: "tool_search_tool_result"

          default: tool_search_tool_result

        • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

          • ToolSearchToolResultError object

            • type: "tool_search_tool_result_error"

              default: tool_search_tool_result_error

            • error_code: ToolSearchToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

            • error_message: string or null

          • ToolSearchToolSearchResultBlock object

            • type: "tool_search_tool_search_result"

              default: tool_search_tool_search_result

            • tool_references: array of ToolReferenceBlock

              • type: "tool_reference"

                default: tool_reference

              • tool_name: string

                maxLength: 256, minLength: 1, pattern: [22]{1,256}$

        • tool_use_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • ContainerUploadBlock object

        Response model for a file uploaded to the container.

        • type: "container_upload"

          default: container_upload

        • file_id: string

    • model: Model

      The model that will complete your prompt.

      See models 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 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

    • role: "assistant"

      Conversational role of the generated message.

      This will always be "assistant".

      default: assistant

    • stop_details: RefusalStopDetails 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. 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.

        • "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.

    • stop_reason: StopReason 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"

      • "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: Usage

      Billing and rate-limit usage.

      Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.

      Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.

      For example, output_tokens will be non-zero, even for an empty string response from Claude.

      Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.

      • cache_creation: CacheCreation 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

      • 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

      • output_tokens: number

        The number of output tokens which were used.

        minimum: 0

      • output_tokens_details: OutputTokensDetails 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: ServerToolUsage 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"

  • RawMessageStreamEvent = RawMessageStartEvent or RawMessageDeltaEvent or RawMessageStopEvent or 3 more

    • RawMessageStartEvent object

      • type: "message_start"

        default: message_start

      • message: Message

    • RawMessageDeltaEvent object

      • type: "message_delta"

        default: message_delta

      • delta: object

        • container: Container or null

          Information about the container used in the request (for the code execution tool)

        • stop_details: RefusalStopDetails or null

          Structured information about a refusal.

        • stop_reason: StopReason or null

        • stop_sequence: string or null

      • usage: MessageDeltaUsage

        Billing and rate-limit usage.

        Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.

        Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.

        For example, output_tokens will be non-zero, even for an empty string response from Claude.

        Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.

        • cache_creation_input_tokens: number 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

        • input_tokens: number or null

          The cumulative number of input tokens which were used.

          minimum: 0

        • output_tokens: number

          The cumulative number of output tokens which were used.

        • output_tokens_details: OutputTokensDetails 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: ServerToolUsage or null

          The number of server tool requests.

    • RawMessageStopEvent object

      • type: "message_stop"

        default: message_stop

    • RawContentBlockStartEvent object

      • type: "content_block_start"

        default: content_block_start

      • content_block: TextBlock or ThinkingBlock or RedactedThinkingBlock or 9 more

        • TextBlock object

        • ThinkingBlock object

        • RedactedThinkingBlock object

        • ToolUseBlock object

        • ServerToolUseBlock object

        • WebSearchToolResultBlock object

        • WebFetchToolResultBlock object

        • CodeExecutionToolResultBlock object

        • BashCodeExecutionToolResultBlock object

        • TextEditorCodeExecutionToolResultBlock object

        • ToolSearchToolResultBlock object

        • ContainerUploadBlock object

          Response model for a file uploaded to the container.

      • index: number

    • RawContentBlockDeltaEvent object

      • type: "content_block_delta"

        default: content_block_delta

      • delta: RawContentBlockDelta

        • TextDelta object

          • type: "text_delta"

            default: text_delta

          • text: string

        • InputJSONDelta object

          • type: "input_json_delta"

            default: input_json_delta

          • partial_json: string

        • CitationsDelta object

          • type: "citations_delta"

            default: citations_delta

          • citation: CitationCharLocation or CitationPageLocation or CitationContentBlockLocation or 2 more

            • CitationCharLocation object

            • CitationPageLocation object

            • CitationContentBlockLocation object

            • CitationsWebSearchResultLocation object

            • CitationsSearchResultLocation object

        • ThinkingDelta object

          • type: "thinking_delta"

            default: thinking_delta

          • thinking: string

            The incremental thinking text for this content block. Concatenate the thinking values of successive thinking_delta events to assemble the block's full thinking value.

        • SignatureDelta 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.

      • index: number

    • RawContentBlockStopEvent 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"
    }
  ],
  "model": "claude-opus-5",
  "role": "assistant",
  "stop_details": {
    "category": "cyber",
    "explanation": "This request was declined because it conflicts with Anthropic's Usage Policy.",
    "type": "refusal"
  },
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "type": "message",
  "usage": {
    "cache_creation": {
      "ephemeral_1h_input_tokens": 0,
      "ephemeral_5m_input_tokens": 0
    },
    "cache_creation_input_tokens": 2051,
    "cache_read_input_tokens": 2051,
    "inference_geo": "global",
    "input_tokens": 2095,
    "output_tokens": 503,
    "output_tokens_details": {
      "thinking_tokens": 0
    },
    "server_tool_use": {
      "web_fetch_requests": 2,
      "web_search_requests": 0
    },
    "service_tier": "standard"
  }
}

# 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

# Headers

  • "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 MessageParam

    Input messages.

    Our models are trained to operate on alternating user and assistant conversational turns. When creating a new Message, you specify the prior conversational turns with the messages parameter, and the model then generates the next Message in the conversation. Consecutive user or assistant turns in your request will be combined into a single turn.

    Each input message must be an object with a role and content. You can specify a single user-role message, or you can include multiple user and assistant messages.

    If the final message uses the assistant role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response.

    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.

    Note that if you want to include a system prompt, 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 ContentBlockParam

      • string

      • array of ContentBlockParam

        • TextBlockParam object

          • type: "text"

          • text: string

            minLength: 1

          • cache_control: optional CacheControlEphemeral 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 for details.

              • "5m"

              • "1h"

          • citations: optional array of TextCitationParam or null

            • CitationCharLocationParam 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

            • CitationPageLocationParam 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

            • CitationContentBlockLocationParam 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

            • CitationWebSearchResultLocationParam object

              • type: "web_search_result_location"

              • cited_text: string

              • encrypted_index: string

              • title: string or null

                maxLength: 512, minLength: 1

              • url: string

                minLength: 1

            • CitationSearchResultLocationParam 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

        • ImageBlockParam object

          • type: "image"

          • source: Base64ImageSource or URLImageSource or FileImageSource

            • Base64ImageSource 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"

            • URLImageSource object

              • type: "url"

              • url: string

            • FileImageSource object

              • type: "file"

              • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • transformations: optional ImageTransformationsParam 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"

        • DocumentBlockParam object

          • type: "document"

          • source: Base64PDFSource or PlainTextSource or ContentBlockSource or 2 more

            • Base64PDFSource object

              • type: "base64"

              • data: string

                format: byte

              • media_type: "application/pdf"

            • PlainTextSource object

              • type: "text"

              • data: string

              • media_type: "text/plain"

            • ContentBlockSource object

              • type: "content"

              • content: string or array of ContentBlockSourceContent

                • string

                • ContentBlockSourceContent = array of ContentBlockSourceContent

                  • TextBlockParam object

                  • ImageBlockParam object

            • URLPDFSource object

              • type: "url"

              • url: string

            • FileDocumentSource object

              • type: "file"

              • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam or null

            • enabled: optional boolean
          • context: optional string or null

            minLength: 1

          • title: optional string or null

            maxLength: 500, minLength: 1

        • SearchResultBlockParam object

          • type: "search_result"

          • content: array of TextBlockParam

            • type: "text"

            • text: string

              minLength: 1

            • cache_control: optional CacheControlEphemeral or null

              Create a cache control breakpoint at this content block.

            • citations: optional array of TextCitationParam or null

          • source: string

          • title: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam

        • ThinkingBlockParam 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.

        • RedactedThinkingBlockParam 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.

        • ToolUseBlockParam object

          • type: "tool_use"

          • id: string

            pattern: [23]+$

          • input: map[unknown]

          • name: string

            maxLength: 200, minLength: 1

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

            • DirectCaller object

              Tool invocation directly from the model.

              • type: "direct"
            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

              • type: "code_execution_20250825"

              • tool_id: string

                pattern: ^srvtoolu_[a-zA-Z0-9_]+$

            • ServerToolCaller20260120 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: [24]+$

        • ToolResultBlockParam object

          • type: "tool_result"

          • tool_use_id: string

            pattern: [25]+$

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • content: optional string or array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more

            • string

            • array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more

              • TextBlockParam object

              • ImageBlockParam object

              • SearchResultBlockParam object

              • DocumentBlockParam object

              • ToolReferenceBlockParam object

                Tool reference block that can be included in tool_result content.

                • type: "tool_reference"

                • tool_name: string

                  maxLength: 256, minLength: 1, pattern: [26]{1,256}$

                • cache_control: optional CacheControlEphemeral or null

                  Create a cache control breakpoint at this content block.

              • BrowserStateBlockParam object

                The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side 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 BrowserStateTabEntry

                  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: [27]*$

                  • title: string

                    The title of the page the tab is showing. May be empty.

                    maxLength: 4096, pattern: [28]*$

                  • url: string

                    The URL of the page the tab is showing. May be empty.

                    maxLength: 4096, pattern: [29]*$

                  • 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 CacheControlEphemeral or null

                  Create a cache control breakpoint at this content block.

                • state_changes: optional array of BrowserStateChange 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

                  • BrowserStateChangeTabOpened object

                    A tab this call's execution opened that remains open at its end — the creation delta of the tabs inventory, not an event log.

                    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: [30]*$

                  • BrowserStateChangeDownloadStarted 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: [31]*$

                    • url: string

                      The final post-redirect URL the download was served from.

                      maxLength: 4096, pattern: [32]*$

                  • BrowserStateChangeDownloadCompleted 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: [33]*$

                    • url: string

                      The final post-redirect URL the download was served from.

                      maxLength: 4096, pattern: [34]*$

                    • 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: [35]*$, maxLength: 4096

                    • size_bytes: optional number or null

                      The completed download's size.

                      minimum: 0

                  • BrowserStateChangeDownloadFailed 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: [36]*$

                    • url: string

                      The final post-redirect URL the download was served from.

                      maxLength: 4096, pattern: [37]*$

                    • error: optional string or null

                      The failure or cancellation detail, when known.

                      pattern: [38]*$, 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: [39]+$

        • ServerToolUseBlockParam object

          • type: "server_tool_use"

          • id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • input: map[unknown]

          • name: "web_search" or "web_fetch" or "code_execution" or 4 more

            • "web_search"

            • "web_fetch"

            • "code_execution"

            • "bash_code_execution"

            • "text_editor_code_execution"

            • "tool_search_tool_regex"

            • "tool_search_tool_bm25"

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

            • DirectCaller object

              Tool invocation directly from the model.

            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

            • ServerToolCaller20260120 object

        • WebSearchToolResultBlockParam object

          • type: "web_search_tool_result"

          • content: WebSearchToolResultBlockParamContent

            • WebSearchToolResultBlockItem = array of WebSearchResultBlockParam

              • type: "web_search_result"

              • encrypted_content: string

              • title: string

              • url: string

              • page_age: optional string or null

            • WebSearchToolRequestError object

              • type: "web_search_tool_result_error"

              • error_code: WebSearchToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "max_uses_exceeded"

                • "too_many_requests"

                • "query_too_long"

                • "request_too_large"

          • tool_use_id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

            • DirectCaller object

              Tool invocation directly from the model.

            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

            • ServerToolCaller20260120 object

        • WebFetchToolResultBlockParam object

          • type: "web_fetch_tool_result"

          • content: WebFetchToolResultErrorBlockParam or WebFetchBlockParam

            • WebFetchToolResultErrorBlockParam object

              • type: "web_fetch_tool_result_error"

              • error_code: WebFetchToolResultErrorCode

                • "invalid_tool_input"

                • "url_too_long"

                • "url_not_allowed"

                • "url_not_in_prior_context"

                • "url_not_accessible"

                • "unsupported_content_type"

                • "too_many_requests"

                • "max_uses_exceeded"

                • "unavailable"

                • "content_too_large"

            • WebFetchBlockParam object

              • type: "web_fetch_result"

              • content: DocumentBlockParam

              • 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

            • DirectCaller object

              Tool invocation directly from the model.

            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

            • ServerToolCaller20260120 object

        • CodeExecutionToolResultBlockParam object

          • type: "code_execution_tool_result"

          • content: CodeExecutionToolResultBlockParamContent

            • CodeExecutionToolResultErrorParam object

              • type: "code_execution_tool_result_error"

              • error_code: CodeExecutionToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

            • CodeExecutionResultBlockParam object

              • type: "code_execution_result"

              • content: array of CodeExecutionOutputBlockParam

                • type: "code_execution_output"

                • file_id: string

              • return_code: number

              • stderr: string

              • stdout: string

            • EncryptedCodeExecutionResultBlockParam object

              Code execution result with encrypted stdout for PFC + web_search results.

              • type: "encrypted_code_execution_result"

              • content: array of CodeExecutionOutputBlockParam

                • 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • BashCodeExecutionToolResultBlockParam object

          • type: "bash_code_execution_tool_result"

          • content: BashCodeExecutionToolResultErrorParam or BashCodeExecutionResultBlockParam

            • BashCodeExecutionToolResultErrorParam object

              • type: "bash_code_execution_tool_result_error"

              • error_code: BashCodeExecutionToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

                • "output_file_too_large"

            • BashCodeExecutionResultBlockParam object

              • type: "bash_code_execution_result"

              • content: array of BashCodeExecutionOutputBlockParam

                • 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • TextEditorCodeExecutionToolResultBlockParam object

          • type: "text_editor_code_execution_tool_result"

          • content: TextEditorCodeExecutionToolResultErrorParam or TextEditorCodeExecutionViewResultBlockParam or TextEditorCodeExecutionCreateResultBlockParam or TextEditorCodeExecutionStrReplaceResultBlockParam

            • TextEditorCodeExecutionToolResultErrorParam object

              • type: "text_editor_code_execution_tool_result_error"

              • error_code: TextEditorCodeExecutionToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

                • "file_not_found"

              • error_message: optional string or null

            • TextEditorCodeExecutionViewResultBlockParam 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

            • TextEditorCodeExecutionCreateResultBlockParam object

              • type: "text_editor_code_execution_create_result"

              • is_file_update: boolean

            • TextEditorCodeExecutionStrReplaceResultBlockParam 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • ToolSearchToolResultBlockParam object

          • type: "tool_search_tool_result"

          • content: ToolSearchToolResultErrorParam or ToolSearchToolSearchResultBlockParam

            • ToolSearchToolResultErrorParam object

              • type: "tool_search_tool_result_error"

              • error_code: ToolSearchToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

              • error_message: optional string or null

            • ToolSearchToolSearchResultBlockParam object

              • type: "tool_search_tool_search_result"

              • tool_references: array of ToolReferenceBlockParam

                • type: "tool_reference"

                • tool_name: string

                  maxLength: 256, minLength: 1, pattern: [40]{1,256}$

                • cache_control: optional CacheControlEphemeral or null

                  Create a cache control breakpoint at this content block.

          • tool_use_id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • ContainerUploadBlockParam object

          A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory.

          • type: "container_upload"

          • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

    • role: "user" or "assistant" or "system"

      • "user"

      • "assistant"

      • "system"

  • model: Model

    The model that will complete your prompt.

    See models 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 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

  • cache_control: optional CacheControlEphemeral or null

    Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request.

  • output_config: optional OutputConfig

    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 JSONOutputFormat or null

      A schema to specify Claude's output format in responses. See structured outputs

      • type: "json_schema"

      • schema: map[unknown]

        The JSON schema of the format

  • system: optional string or array of TextBlockParam

    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.

    • string

    • array of TextBlockParam

      • type: "text"

      • text: string

        minLength: 1

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional array of TextCitationParam or null

  • thinking: optional ThinkingConfigParam

    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 for details.

    • ThinkingConfigEnabled 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 for details.

        minimum: 1024

      • display: optional "summarized" or "omitted" or null

        Controls how thinking content appears in the response. When set to summarized, thinking is returned normally. When set to omitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to summarized.

        • "summarized"

        • "omitted"

    • ThinkingConfigDisabled object

      • type: "disabled"
    • ThinkingConfigAdaptive object

      • type: "adaptive"

      • display: optional "summarized" or "omitted" or null

        Controls how thinking content appears in the response. When set to summarized, thinking is returned normally. When set to omitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to summarized.

        • "summarized"

        • "omitted"

  • tool_choice: optional ToolChoice

    How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.

    • ToolChoiceAuto 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.

    • ToolChoiceAny 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.

    • ToolChoiceTool 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.

    • ToolChoiceNone object

      The model will not be allowed to use tools.

      • type: "none"
  • tools: optional array of MessageCountTokensTool

    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, see their individual documentation as each has its own behavior (e.g., the 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 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 for more details.

    • Tool object

      • type: optional "custom" or null

      • input_schema: object

        JSON schema 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: [41]{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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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

    • ToolBash20250124 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20250522 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20250825 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20260120 object

      Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint).

      • 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20260521 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • BrowserToolset20260801 object

      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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • configs: optional BrowserToolsetConfigs 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 BrowserTypeConfig 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 BrowserCloseTabConfig 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 BrowserDoubleClickConfig 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 BrowserFileUploadConfig 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 BrowserFindConfig 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 BrowserFormInputConfig 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 BrowserGetPageTextConfig 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 BrowserHoldKeyConfig 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 BrowserHoverConfig 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 BrowserJavascriptExecConfig 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 BrowserKeyConfig 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 BrowserLeftClickConfig 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 BrowserLeftClickDragConfig 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 BrowserLeftMouseDownConfig 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 BrowserLeftMouseUpConfig 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 BrowserListTabsConfig 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 BrowserMiddleClickConfig 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 BrowserMouseMoveConfig 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 BrowserNavigateConfig 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 BrowserNewTabConfig 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 BrowserReadConsoleConfig 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 BrowserReadNetworkConfig 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 BrowserReadPageConfig 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 BrowserRightClickConfig 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 BrowserScreenshotConfig 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 BrowserScrollConfig 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 BrowserScrollToConfig 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 BrowserSwitchTabConfig 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 BrowserTripleClickConfig 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 BrowserWaitConfig 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 BrowserZoomConfig 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.

    • MemoryTool20250818 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ComputerToolset20260801 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • configs: optional ComputerToolsetConfigs 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 ComputerTypeConfig 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 ComputerCursorPositionConfig 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 ComputerDoubleClickConfig 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 ComputerHoldKeyConfig 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 ComputerKeyConfig 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 ComputerLeftClickConfig 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 ComputerLeftClickDragConfig 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 ComputerLeftMouseDownConfig 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 ComputerLeftMouseUpConfig 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 ComputerMiddleClickConfig 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 ComputerMouseMoveConfig 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 ComputerRightClickConfig 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 ComputerScreenshotConfig 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 ComputerScrollConfig 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 ComputerTripleClickConfig 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 ComputerWaitConfig 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 ComputerZoomConfig 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.

    • ToolTextEditor20250124 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ToolTextEditor20250429 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ToolTextEditor20250728 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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

    • WebSearchTool20250305 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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 UserLocation 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 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 of the user.

          maxLength: 255, minLength: 1

    • WebFetchTool20250910 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

        • client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

          Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].

          • WebFetchURLSourceAll object

            The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

            • type: "all"
          • WebFetchURLSourceNone object

            The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

            • type: "none"
          • WebFetchURLSourceOnly object

            The tool filter variant under which only the named tools' results contribute.

            • type: "only"

            • tools: array of WebFetchURLSourceToolReference

              • type: "tool_reference"

              • name: string

          • WebFetchURLSourceExcept object

            The tool filter variant under which every result but the named tools' contributes.

            • type: "except"

            • tools: array of WebFetchURLSourceToolReference

              • type: "tool_reference"

              • name: string

        • server_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

          Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute.

          • WebFetchURLSourceAll object

            The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

          • WebFetchURLSourceNone object

            The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

          • WebFetchURLSourceOnly object

            The tool filter variant under which only the named tools' results contribute.

          • WebFetchURLSourceExcept object

            The tool filter variant under which every result but the named tools' contributes.

        • user_input: optional WebFetchURLSourceAll or WebFetchURLSourceNone

          Whether URLs in user messages are fetchable: "all" or "none".

          • WebFetchURLSourceAll object

            The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

          • WebFetchURLSourceNone object

            The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

    • WebSearchTool20260209 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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 UserLocation or null

        Parameters for the user's location. Used to provide more relevant search results.

    • WebFetchTool20260209 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

    • WebFetchTool20260309 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

      • 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.

    • WebSearchTool20260318 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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 UserLocation or null

        Parameters for the user's location. Used to provide more relevant search results.

    • WebFetchTool20260318 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

      • 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.

    • ToolSearchToolBm25_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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ToolSearchToolRegex20251119 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

# Returns

  • MessageTokensCount object

    • 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
{
  "input_tokens": 2095
}

# Domain types

# Base64 Image Source

  • Base64ImageSource 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"

# Base64 PDF Source

  • Base64PDFSource object

    • type: "base64"

    • data: string

      format: byte

    • media_type: "application/pdf"

# Bash Code Execution Output Block

  • BashCodeExecutionOutputBlock object

    • type: "bash_code_execution_output"

      default: bash_code_execution_output

    • file_id: string

# Bash Code Execution Output Block Param

  • BashCodeExecutionOutputBlockParam object

    • type: "bash_code_execution_output"

    • file_id: string

# Bash Code Execution Result Block

  • BashCodeExecutionResultBlock object

    • type: "bash_code_execution_result"

      default: bash_code_execution_result

    • content: array of BashCodeExecutionOutputBlock

      • type: "bash_code_execution_output"

        default: bash_code_execution_output

      • file_id: string

    • return_code: number

    • stderr: string

    • stdout: string

# Bash Code Execution Result Block Param

  • BashCodeExecutionResultBlockParam object

    • type: "bash_code_execution_result"

    • content: array of BashCodeExecutionOutputBlockParam

      • type: "bash_code_execution_output"

      • file_id: string

    • return_code: number

    • stderr: string

    • stdout: string

# Bash Code Execution Tool Result Block

  • BashCodeExecutionToolResultBlock object

    • type: "bash_code_execution_tool_result"

      default: bash_code_execution_tool_result

    • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

      • BashCodeExecutionToolResultError object

        • type: "bash_code_execution_tool_result_error"

          default: bash_code_execution_tool_result_error

        • error_code: BashCodeExecutionToolResultErrorCode

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

          • "output_file_too_large"

      • BashCodeExecutionResultBlock object

        • type: "bash_code_execution_result"

          default: bash_code_execution_result

        • content: array of BashCodeExecutionOutputBlock

          • 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_]+$

# Bash Code Execution Tool Result Block Param

  • BashCodeExecutionToolResultBlockParam object

    • type: "bash_code_execution_tool_result"

    • content: BashCodeExecutionToolResultErrorParam or BashCodeExecutionResultBlockParam

      • BashCodeExecutionToolResultErrorParam object

        • type: "bash_code_execution_tool_result_error"

        • error_code: BashCodeExecutionToolResultErrorCode

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

          • "output_file_too_large"

      • BashCodeExecutionResultBlockParam object

        • type: "bash_code_execution_result"

        • content: array of BashCodeExecutionOutputBlockParam

          • 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 CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

# Bash Code Execution Tool Result Error

  • BashCodeExecutionToolResultError object

    • type: "bash_code_execution_tool_result_error"

      default: bash_code_execution_tool_result_error

    • error_code: BashCodeExecutionToolResultErrorCode

      • "invalid_tool_input"

      • "unavailable"

      • "too_many_requests"

      • "execution_time_exceeded"

      • "output_file_too_large"

# Bash Code Execution Tool Result Error Code

  • BashCodeExecutionToolResultErrorCode = "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"

# Bash Code Execution Tool Result Error Param

  • BashCodeExecutionToolResultErrorParam object

    • type: "bash_code_execution_tool_result_error"

    • error_code: BashCodeExecutionToolResultErrorCode

      • "invalid_tool_input"

      • "unavailable"

      • "too_many_requests"

      • "execution_time_exceeded"

      • "output_file_too_large"

# Browser Close Tab Config

  • BrowserCloseTabConfig 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.

# Browser Double Click Config

  • BrowserDoubleClickConfig 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.

# Browser File Upload Config

  • BrowserFileUploadConfig 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.

# Browser Find Config

  • BrowserFindConfig 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.

# Browser Form Input Config

  • BrowserFormInputConfig 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.

# Browser Get Page Text Config

  • BrowserGetPageTextConfig 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.

# Browser Hold Key Config

  • BrowserHoldKeyConfig 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.

# Browser Hover Config

  • BrowserHoverConfig 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.

# Browser Javascript Exec Config

  • BrowserJavascriptExecConfig 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.

# Browser Key Config

  • BrowserKeyConfig 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.

# Browser Left Click Config

  • BrowserLeftClickConfig 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.

# Browser Left Click Drag Config

  • BrowserLeftClickDragConfig 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.

# Browser Left Mouse Down Config

  • BrowserLeftMouseDownConfig 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.

# Browser Left Mouse Up Config

  • BrowserLeftMouseUpConfig 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.

# Browser List Tabs Config

  • BrowserListTabsConfig 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.

# Browser Middle Click Config

  • BrowserMiddleClickConfig 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.

# Browser Mouse Move Config

  • BrowserMouseMoveConfig 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.

# Browser Navigate Config

  • BrowserNavigateConfig 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.

# Browser New Tab Config

  • BrowserNewTabConfig 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.

# Browser Read Console Config

  • BrowserReadConsoleConfig 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.

# Browser Read Network Config

  • BrowserReadNetworkConfig 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.

# Browser Read Page Config

  • BrowserReadPageConfig 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.

# Browser Right Click Config

  • BrowserRightClickConfig 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.

# Browser Screenshot Config

  • BrowserScreenshotConfig 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.

# Browser Scroll Config

  • BrowserScrollConfig 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.

# Browser Scroll To Config

  • BrowserScrollToConfig 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.

# Browser State Block Param

  • BrowserStateBlockParam object

    The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side 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 BrowserStateTabEntry

      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: [42]*$

      • title: string

        The title of the page the tab is showing. May be empty.

        maxLength: 4096, pattern: [43]*$

      • url: string

        The URL of the page the tab is showing. May be empty.

        maxLength: 4096, pattern: [44]*$

      • 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 CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • state_changes: optional array of BrowserStateChange 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

      • BrowserStateChangeTabOpened object

        A tab this call's execution opened that remains open at its end — the creation delta of the tabs inventory, not an event log.

        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: [45]*$

      • BrowserStateChangeDownloadStarted 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: [46]*$

        • url: string

          The final post-redirect URL the download was served from.

          maxLength: 4096, pattern: [47]*$

      • BrowserStateChangeDownloadCompleted 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: [48]*$

        • url: string

          The final post-redirect URL the download was served from.

          maxLength: 4096, pattern: [49]*$

        • 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: [50]*$, maxLength: 4096

        • size_bytes: optional number or null

          The completed download's size.

          minimum: 0

      • BrowserStateChangeDownloadFailed 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: [51]*$

        • url: string

          The final post-redirect URL the download was served from.

          maxLength: 4096, pattern: [52]*$

        • error: optional string or null

          The failure or cancellation detail, when known.

          pattern: [53]*$, maxLength: 4096

# Browser State Change

  • BrowserStateChange = BrowserStateChangeTabOpened or BrowserStateChangeDownloadStarted or BrowserStateChangeDownloadCompleted or BrowserStateChangeDownloadFailed

    • BrowserStateChangeTabOpened object

      A tab this call's execution opened that remains open at its end — the creation delta of the tabs inventory, not an event log.

      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: [54]*$

    • BrowserStateChangeDownloadStarted 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: [55]*$

      • url: string

        The final post-redirect URL the download was served from.

        maxLength: 4096, pattern: [56]*$

    • BrowserStateChangeDownloadCompleted 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: [57]*$

      • url: string

        The final post-redirect URL the download was served from.

        maxLength: 4096, pattern: [58]*$

      • 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: [59]*$, maxLength: 4096

      • size_bytes: optional number or null

        The completed download's size.

        minimum: 0

    • BrowserStateChangeDownloadFailed 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: [60]*$

      • url: string

        The final post-redirect URL the download was served from.

        maxLength: 4096, pattern: [61]*$

      • error: optional string or null

        The failure or cancellation detail, when known.

        pattern: [62]*$, maxLength: 4096

# Browser State Change Download Completed

  • BrowserStateChangeDownloadCompleted 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: [63]*$

    • url: string

      The final post-redirect URL the download was served from.

      maxLength: 4096, pattern: [64]*$

    • 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: [65]*$, maxLength: 4096

    • size_bytes: optional number or null

      The completed download's size.

      minimum: 0

# Browser State Change Download Failed

  • BrowserStateChangeDownloadFailed 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: [66]*$

    • url: string

      The final post-redirect URL the download was served from.

      maxLength: 4096, pattern: [67]*$

    • error: optional string or null

      The failure or cancellation detail, when known.

      pattern: [68]*$, maxLength: 4096

# Browser State Change Download Started

  • BrowserStateChangeDownloadStarted 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: [69]*$

    • url: string

      The final post-redirect URL the download was served from.

      maxLength: 4096, pattern: [70]*$

# Browser State Change Tab Opened

  • BrowserStateChangeTabOpened object

    A tab this call's execution opened that remains open at its end — the creation delta of the tabs inventory, not an event log.

    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: [71]*$

# Browser State Tab Entry

  • BrowserStateTabEntry 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: [72]*$

    • title: string

      The title of the page the tab is showing. May be empty.

      maxLength: 4096, pattern: [73]*$

    • url: string

      The URL of the page the tab is showing. May be empty.

      maxLength: 4096, pattern: [74]*$

    • 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.

# Browser Switch Tab Config

  • BrowserSwitchTabConfig 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.

# Browser Toolset 20260801

  • BrowserToolset20260801 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 CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • configs: optional BrowserToolsetConfigs 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 BrowserTypeConfig 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 BrowserCloseTabConfig 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 BrowserDoubleClickConfig 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 BrowserFileUploadConfig 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 BrowserFindConfig 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 BrowserFormInputConfig 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 BrowserGetPageTextConfig 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 BrowserHoldKeyConfig 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 BrowserHoverConfig 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 BrowserJavascriptExecConfig 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 BrowserKeyConfig 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 BrowserLeftClickConfig 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 BrowserLeftClickDragConfig 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 BrowserLeftMouseDownConfig 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 BrowserLeftMouseUpConfig 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 BrowserListTabsConfig 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 BrowserMiddleClickConfig 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 BrowserMouseMoveConfig 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 BrowserNavigateConfig 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 BrowserNewTabConfig 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 BrowserReadConsoleConfig 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 BrowserReadNetworkConfig 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 BrowserReadPageConfig 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 BrowserRightClickConfig 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 BrowserScreenshotConfig 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 BrowserScrollConfig 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 BrowserScrollToConfig 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 BrowserSwitchTabConfig 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 BrowserTripleClickConfig 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 BrowserWaitConfig 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 BrowserZoomConfig 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.

# Browser Toolset Configs

  • BrowserToolsetConfigs 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 BrowserTypeConfig 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 BrowserCloseTabConfig 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 BrowserDoubleClickConfig 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 BrowserFileUploadConfig 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 BrowserFindConfig 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 BrowserFormInputConfig 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 BrowserGetPageTextConfig 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 BrowserHoldKeyConfig 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 BrowserHoverConfig 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 BrowserJavascriptExecConfig 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 BrowserKeyConfig 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 BrowserLeftClickConfig 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 BrowserLeftClickDragConfig 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 BrowserLeftMouseDownConfig 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 BrowserLeftMouseUpConfig 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 BrowserListTabsConfig 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 BrowserMiddleClickConfig 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 BrowserMouseMoveConfig 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 BrowserNavigateConfig 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 BrowserNewTabConfig 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 BrowserReadConsoleConfig 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 BrowserReadNetworkConfig 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 BrowserReadPageConfig 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 BrowserRightClickConfig 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 BrowserScreenshotConfig 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 BrowserScrollConfig 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 BrowserScrollToConfig 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 BrowserSwitchTabConfig 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 BrowserTripleClickConfig 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 BrowserWaitConfig 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 BrowserZoomConfig 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.

# Browser Triple Click Config

  • BrowserTripleClickConfig 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.

# Browser Type Config

  • BrowserTypeConfig 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.

# Browser Wait Config

  • BrowserWaitConfig 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.

# Browser Zoom Config

  • BrowserZoomConfig 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.

# Cache Control Ephemeral

  • CacheControlEphemeral 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 for details.

      • "5m"

      • "1h"

# Cache Creation

  • CacheCreation 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

# Citation Char Location

  • CitationCharLocation 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

# Citation Char Location Param

  • CitationCharLocationParam 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

# Citation Content Block Location

  • CitationContentBlockLocation 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

# Citation Content Block Location Param

  • CitationContentBlockLocationParam 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

# Citation Page Location

  • CitationPageLocation 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

# Citation Page Location Param

  • CitationPageLocationParam 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

# Citation Search Result Location Param

  • CitationSearchResultLocationParam 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

# Citation Web Search Result Location Param

  • CitationWebSearchResultLocationParam object

    • type: "web_search_result_location"

    • cited_text: string

    • encrypted_index: string

    • title: string or null

      maxLength: 512, minLength: 1

    • url: string

      minLength: 1

# Citations Config

  • CitationsConfig object

    • enabled: boolean

      default: false

# Citations Config Param

  • CitationsConfigParam object

    • enabled: optional boolean

# Citations Delta

  • CitationsDelta object

    • type: "citations_delta"

      default: citations_delta

    • citation: CitationCharLocation or CitationPageLocation or CitationContentBlockLocation or 2 more

      • CitationCharLocation 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

      • CitationPageLocation 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

      • CitationContentBlockLocation 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

      • CitationsWebSearchResultLocation 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

      • CitationsSearchResultLocation 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

# Citations Search Result Location

  • CitationsSearchResultLocation 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

# Citations Web Search Result Location

  • CitationsWebSearchResultLocation 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

# Code Execution Output Block

  • CodeExecutionOutputBlock object

    • type: "code_execution_output"

      default: code_execution_output

    • file_id: string

# Code Execution Output Block Param

  • CodeExecutionOutputBlockParam object

    • type: "code_execution_output"

    • file_id: string

# Code Execution Result Block

  • CodeExecutionResultBlock object

    • type: "code_execution_result"

      default: code_execution_result

    • content: array of CodeExecutionOutputBlock

      • type: "code_execution_output"

        default: code_execution_output

      • file_id: string

    • return_code: number

    • stderr: string

    • stdout: string

# Code Execution Result Block Param

  • CodeExecutionResultBlockParam object

    • type: "code_execution_result"

    • content: array of CodeExecutionOutputBlockParam

      • type: "code_execution_output"

      • file_id: string

    • return_code: number

    • stderr: string

    • stdout: string

# Code Execution Tool 20250522

  • CodeExecutionTool20250522 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 CacheControlEphemeral 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 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

# Code Execution Tool 20250825

  • CodeExecutionTool20250825 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 CacheControlEphemeral 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 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

# Code Execution Tool 20260120

  • CodeExecutionTool20260120 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 CacheControlEphemeral 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 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

# Code Execution Tool 20260521

  • CodeExecutionTool20260521 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 CacheControlEphemeral 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 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

# Code Execution Tool Result Block

  • CodeExecutionToolResultBlock object

    • type: "code_execution_tool_result"

      default: code_execution_tool_result

    • content: CodeExecutionToolResultBlockContent

      • CodeExecutionToolResultError object

        • type: "code_execution_tool_result_error"

          default: code_execution_tool_result_error

        • error_code: CodeExecutionToolResultErrorCode

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

      • CodeExecutionResultBlock object

        • type: "code_execution_result"

          default: code_execution_result

        • content: array of CodeExecutionOutputBlock

          • type: "code_execution_output"

            default: code_execution_output

          • file_id: string

        • return_code: number

        • stderr: string

        • stdout: string

      • EncryptedCodeExecutionResultBlock 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 CodeExecutionOutputBlock

          • 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_]+$

# Code Execution Tool Result Block Content

  • CodeExecutionToolResultBlockContent = CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

    • CodeExecutionToolResultError object

      • type: "code_execution_tool_result_error"

        default: code_execution_tool_result_error

      • error_code: CodeExecutionToolResultErrorCode

        • "invalid_tool_input"

        • "unavailable"

        • "too_many_requests"

        • "execution_time_exceeded"

    • CodeExecutionResultBlock object

      • type: "code_execution_result"

        default: code_execution_result

      • content: array of CodeExecutionOutputBlock

        • type: "code_execution_output"

          default: code_execution_output

        • file_id: string

      • return_code: number

      • stderr: string

      • stdout: string

    • EncryptedCodeExecutionResultBlock 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 CodeExecutionOutputBlock

        • type: "code_execution_output"

          default: code_execution_output

        • file_id: string

      • encrypted_stdout: string

      • return_code: number

      • stderr: string

# Code Execution Tool Result Block Param

  • CodeExecutionToolResultBlockParam object

    • type: "code_execution_tool_result"

    • content: CodeExecutionToolResultBlockParamContent

      • CodeExecutionToolResultErrorParam object

        • type: "code_execution_tool_result_error"

        • error_code: CodeExecutionToolResultErrorCode

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

      • CodeExecutionResultBlockParam object

        • type: "code_execution_result"

        • content: array of CodeExecutionOutputBlockParam

          • type: "code_execution_output"

          • file_id: string

        • return_code: number

        • stderr: string

        • stdout: string

      • EncryptedCodeExecutionResultBlockParam object

        Code execution result with encrypted stdout for PFC + web_search results.

        • type: "encrypted_code_execution_result"

        • content: array of CodeExecutionOutputBlockParam

          • 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 CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

# Code Execution Tool Result Block Param Content

  • CodeExecutionToolResultBlockParamContent = CodeExecutionToolResultErrorParam or CodeExecutionResultBlockParam or EncryptedCodeExecutionResultBlockParam

    • CodeExecutionToolResultErrorParam object

      • type: "code_execution_tool_result_error"

      • error_code: CodeExecutionToolResultErrorCode

        • "invalid_tool_input"

        • "unavailable"

        • "too_many_requests"

        • "execution_time_exceeded"

    • CodeExecutionResultBlockParam object

      • type: "code_execution_result"

      • content: array of CodeExecutionOutputBlockParam

        • type: "code_execution_output"

        • file_id: string

      • return_code: number

      • stderr: string

      • stdout: string

    • EncryptedCodeExecutionResultBlockParam object

      Code execution result with encrypted stdout for PFC + web_search results.

      • type: "encrypted_code_execution_result"

      • content: array of CodeExecutionOutputBlockParam

        • type: "code_execution_output"

        • file_id: string

      • encrypted_stdout: string

      • return_code: number

      • stderr: string

# Code Execution Tool Result Error

  • CodeExecutionToolResultError object

    • type: "code_execution_tool_result_error"

      default: code_execution_tool_result_error

    • error_code: CodeExecutionToolResultErrorCode

      • "invalid_tool_input"

      • "unavailable"

      • "too_many_requests"

      • "execution_time_exceeded"

# Code Execution Tool Result Error Code

  • CodeExecutionToolResultErrorCode = "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

    • "invalid_tool_input"

    • "unavailable"

    • "too_many_requests"

    • "execution_time_exceeded"

# Code Execution Tool Result Error Param

  • CodeExecutionToolResultErrorParam object

    • type: "code_execution_tool_result_error"

    • error_code: CodeExecutionToolResultErrorCode

      • "invalid_tool_input"

      • "unavailable"

      • "too_many_requests"

      • "execution_time_exceeded"

# Computer Cursor Position Config

  • ComputerCursorPositionConfig 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.

# Computer Double Click Config

  • ComputerDoubleClickConfig 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.

# Computer Hold Key Config

  • ComputerHoldKeyConfig 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.

# Computer Key Config

  • ComputerKeyConfig 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.

# Computer Left Click Config

  • ComputerLeftClickConfig 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.

# Computer Left Click Drag Config

  • ComputerLeftClickDragConfig 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.

# Computer Left Mouse Down Config

  • ComputerLeftMouseDownConfig 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.

# Computer Left Mouse Up Config

  • ComputerLeftMouseUpConfig 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.

# Computer Middle Click Config

  • ComputerMiddleClickConfig 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.

# Computer Mouse Move Config

  • ComputerMouseMoveConfig 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.

# Computer Right Click Config

  • ComputerRightClickConfig 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.

# Computer Screenshot Config

  • ComputerScreenshotConfig 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.

# Computer Scroll Config

  • ComputerScrollConfig 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.

# Computer Toolset 20260801

  • ComputerToolset20260801 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 CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • configs: optional ComputerToolsetConfigs 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 ComputerTypeConfig 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 ComputerCursorPositionConfig 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 ComputerDoubleClickConfig 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 ComputerHoldKeyConfig 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 ComputerKeyConfig 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 ComputerLeftClickConfig 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 ComputerLeftClickDragConfig 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 ComputerLeftMouseDownConfig 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 ComputerLeftMouseUpConfig 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 ComputerMiddleClickConfig 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 ComputerMouseMoveConfig 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 ComputerRightClickConfig 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 ComputerScreenshotConfig 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 ComputerScrollConfig 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 ComputerTripleClickConfig 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 ComputerWaitConfig 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 ComputerZoomConfig 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.

# Computer Toolset Configs

  • ComputerToolsetConfigs 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 ComputerTypeConfig 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 ComputerCursorPositionConfig 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 ComputerDoubleClickConfig 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 ComputerHoldKeyConfig 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 ComputerKeyConfig 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 ComputerLeftClickConfig 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 ComputerLeftClickDragConfig 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 ComputerLeftMouseDownConfig 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 ComputerLeftMouseUpConfig 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 ComputerMiddleClickConfig 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 ComputerMouseMoveConfig 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 ComputerRightClickConfig 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 ComputerScreenshotConfig 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 ComputerScrollConfig 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 ComputerTripleClickConfig 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 ComputerWaitConfig 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 ComputerZoomConfig 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.

# Computer Triple Click Config

  • ComputerTripleClickConfig 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.

# Computer Type Config

  • ComputerTypeConfig 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.

# Computer Wait Config

  • ComputerWaitConfig 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.

# Computer Zoom Config

  • ComputerZoomConfig 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.

# Container

  • Container 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 ContainerSkill 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

# Container Params

  • ContainerParams object

    Container parameters with skills to be loaded.

    • id: optional string or null

      Container id

    • skills: optional array of SkillParams 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

# Container Skill

  • ContainerSkill 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

# Container Upload Block

  • ContainerUploadBlock object

    Response model for a file uploaded to the container.

    • type: "container_upload"

      default: container_upload

    • file_id: string

# Container Upload Block Param

  • ContainerUploadBlockParam object

    A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory.

    • type: "container_upload"

    • file_id: string

    • cache_control: optional CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

# Content Block

  • ContentBlock = TextBlock or ThinkingBlock or RedactedThinkingBlock or 9 more

    • TextBlock object

      • type: "text"

        default: text

      • citations: array of TextCitation 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.

        • CitationCharLocation 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

        • CitationPageLocation 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

        • CitationContentBlockLocation 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

        • CitationsWebSearchResultLocation 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

        • CitationsSearchResultLocation 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

    • ThinkingBlock 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 for details.

      • thinking: string

        The text of Claude's thinking process for this block.

    • RedactedThinkingBlock 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 for details.

    • ToolUseBlock object

      • type: "tool_use"

        default: tool_use

      • id: string

        pattern: [75]+$

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        default: {"type":"direct"}

        • DirectCaller object

          Tool invocation directly from the model.

          • type: "direct"
        • ServerToolCaller object

          Tool invocation generated by a server-side tool.

          • type: "code_execution_20250825"

          • tool_id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

        • ServerToolCaller20260120 object

          • type: "code_execution_20260120"

          • tool_id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • input: map[unknown]

      • name: string

        minLength: 1

      • toolset_name: optional string or null

        For a toolset member tool_use, the toolset family.

        maxLength: 64, minLength: 1, pattern: [76]+$

    • ServerToolUseBlock object

      • type: "server_tool_use"

        default: server_tool_use

      • id: string

        pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        default: {"type":"direct"}

        • DirectCaller object

          Tool invocation directly from the model.

        • ServerToolCaller object

          Tool invocation generated by a server-side tool.

        • ServerToolCaller20260120 object

      • input: map[unknown]

      • name: "web_search" or "web_fetch" or "code_execution" or 4 more

        • "web_search"

        • "web_fetch"

        • "code_execution"

        • "bash_code_execution"

        • "text_editor_code_execution"

        • "tool_search_tool_regex"

        • "tool_search_tool_bm25"

    • WebSearchToolResultBlock object

      • type: "web_search_tool_result"

        default: web_search_tool_result

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        default: {"type":"direct"}

        • DirectCaller object

          Tool invocation directly from the model.

        • ServerToolCaller object

          Tool invocation generated by a server-side tool.

        • ServerToolCaller20260120 object

      • content: WebSearchToolResultBlockContent

        • WebSearchToolResultError object

          • type: "web_search_tool_result_error"

            default: web_search_tool_result_error

          • error_code: WebSearchToolResultErrorCode

            • "invalid_tool_input"

            • "unavailable"

            • "max_uses_exceeded"

            • "too_many_requests"

            • "query_too_long"

            • "request_too_large"

        • array of WebSearchResultBlock

          • 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_]+$

    • WebFetchToolResultBlock object

      • type: "web_fetch_tool_result"

        default: web_fetch_tool_result

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        default: {"type":"direct"}

        • DirectCaller object

          Tool invocation directly from the model.

        • ServerToolCaller object

          Tool invocation generated by a server-side tool.

        • ServerToolCaller20260120 object

      • content: WebFetchToolResultErrorBlock or WebFetchBlock

        • WebFetchToolResultErrorBlock object

          • type: "web_fetch_tool_result_error"

            default: web_fetch_tool_result_error

          • error_code: WebFetchToolResultErrorCode

            • "invalid_tool_input"

            • "url_too_long"

            • "url_not_allowed"

            • "url_not_in_prior_context"

            • "url_not_accessible"

            • "unsupported_content_type"

            • "too_many_requests"

            • "max_uses_exceeded"

            • "unavailable"

            • "content_too_large"

        • WebFetchBlock object

          • type: "web_fetch_result"

            default: web_fetch_result

          • content: DocumentBlock

            • type: "document"

              default: document

            • citations: CitationsConfig or null

              Citation configuration for the document

              • enabled: boolean

                default: false

            • source: Base64PDFSource or PlainTextSource

              • Base64PDFSource object

                • type: "base64"

                • data: string

                  format: byte

                • media_type: "application/pdf"

              • PlainTextSource 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_]+$

    • CodeExecutionToolResultBlock object

      • type: "code_execution_tool_result"

        default: code_execution_tool_result

      • content: CodeExecutionToolResultBlockContent

        • CodeExecutionToolResultError object

          • type: "code_execution_tool_result_error"

            default: code_execution_tool_result_error

          • error_code: CodeExecutionToolResultErrorCode

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

        • CodeExecutionResultBlock object

          • type: "code_execution_result"

            default: code_execution_result

          • content: array of CodeExecutionOutputBlock

            • type: "code_execution_output"

              default: code_execution_output

            • file_id: string

          • return_code: number

          • stderr: string

          • stdout: string

        • EncryptedCodeExecutionResultBlock 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 CodeExecutionOutputBlock

            • 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_]+$

    • BashCodeExecutionToolResultBlock object

      • type: "bash_code_execution_tool_result"

        default: bash_code_execution_tool_result

      • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

        • BashCodeExecutionToolResultError object

          • type: "bash_code_execution_tool_result_error"

            default: bash_code_execution_tool_result_error

          • error_code: BashCodeExecutionToolResultErrorCode

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

            • "output_file_too_large"

        • BashCodeExecutionResultBlock object

          • type: "bash_code_execution_result"

            default: bash_code_execution_result

          • content: array of BashCodeExecutionOutputBlock

            • 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_]+$

    • TextEditorCodeExecutionToolResultBlock object

      • type: "text_editor_code_execution_tool_result"

        default: text_editor_code_execution_tool_result

      • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

        • TextEditorCodeExecutionToolResultError object

          • type: "text_editor_code_execution_tool_result_error"

            default: text_editor_code_execution_tool_result_error

          • error_code: TextEditorCodeExecutionToolResultErrorCode

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

            • "file_not_found"

          • error_message: string or null

        • TextEditorCodeExecutionViewResultBlock 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

        • TextEditorCodeExecutionCreateResultBlock object

          • type: "text_editor_code_execution_create_result"

            default: text_editor_code_execution_create_result

          • is_file_update: boolean

        • TextEditorCodeExecutionStrReplaceResultBlock 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_]+$

    • ToolSearchToolResultBlock object

      • type: "tool_search_tool_result"

        default: tool_search_tool_result

      • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

        • ToolSearchToolResultError object

          • type: "tool_search_tool_result_error"

            default: tool_search_tool_result_error

          • error_code: ToolSearchToolResultErrorCode

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

          • error_message: string or null

        • ToolSearchToolSearchResultBlock object

          • type: "tool_search_tool_search_result"

            default: tool_search_tool_search_result

          • tool_references: array of ToolReferenceBlock

            • type: "tool_reference"

              default: tool_reference

            • tool_name: string

              maxLength: 256, minLength: 1, pattern: [77]{1,256}$

      • tool_use_id: string

        pattern: ^srvtoolu_[a-zA-Z0-9_]+$

    • ContainerUploadBlock object

      Response model for a file uploaded to the container.

      • type: "container_upload"

        default: container_upload

      • file_id: string

# Content Block Param

  • ContentBlockParam = TextBlockParam or ImageBlockParam or DocumentBlockParam or 13 more

    • TextBlockParam object

      • type: "text"

      • text: string

        minLength: 1

      • cache_control: optional CacheControlEphemeral 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 for details.

          • "5m"

          • "1h"

      • citations: optional array of TextCitationParam or null

        • CitationCharLocationParam 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

        • CitationPageLocationParam 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

        • CitationContentBlockLocationParam 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

        • CitationWebSearchResultLocationParam object

          • type: "web_search_result_location"

          • cited_text: string

          • encrypted_index: string

          • title: string or null

            maxLength: 512, minLength: 1

          • url: string

            minLength: 1

        • CitationSearchResultLocationParam 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

    • ImageBlockParam object

      • type: "image"

      • source: Base64ImageSource or URLImageSource or FileImageSource

        • Base64ImageSource 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"

        • URLImageSource object

          • type: "url"

          • url: string

        • FileImageSource object

          • type: "file"

          • file_id: string

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • transformations: optional ImageTransformationsParam 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"

    • DocumentBlockParam object

      • type: "document"

      • source: Base64PDFSource or PlainTextSource or ContentBlockSource or 2 more

        • Base64PDFSource object

          • type: "base64"

          • data: string

            format: byte

          • media_type: "application/pdf"

        • PlainTextSource object

          • type: "text"

          • data: string

          • media_type: "text/plain"

        • ContentBlockSource object

          • type: "content"

          • content: string or array of ContentBlockSourceContent

            • string

            • ContentBlockSourceContent = array of ContentBlockSourceContent

              • TextBlockParam object

              • ImageBlockParam object

        • URLPDFSource object

          • type: "url"

          • url: string

        • FileDocumentSource object

          • type: "file"

          • file_id: string

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam or null

        • enabled: optional boolean
      • context: optional string or null

        minLength: 1

      • title: optional string or null

        maxLength: 500, minLength: 1

    • SearchResultBlockParam object

      • type: "search_result"

      • content: array of TextBlockParam

        • type: "text"

        • text: string

          minLength: 1

        • cache_control: optional CacheControlEphemeral or null

          Create a cache control breakpoint at this content block.

        • citations: optional array of TextCitationParam or null

      • source: string

      • title: string

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam

    • ThinkingBlockParam 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.

    • RedactedThinkingBlockParam 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.

    • ToolUseBlockParam object

      • type: "tool_use"

      • id: string

        pattern: [78]+$

      • input: map[unknown]

      • name: string

        maxLength: 200, minLength: 1

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

        • DirectCaller object

          Tool invocation directly from the model.

          • type: "direct"
        • ServerToolCaller object

          Tool invocation generated by a server-side tool.

          • type: "code_execution_20250825"

          • tool_id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

        • ServerToolCaller20260120 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: [79]+$

    • ToolResultBlockParam object

      • type: "tool_result"

      • tool_use_id: string

        pattern: [80]+$

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • content: optional string or array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more

        • string

        • array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more

          • TextBlockParam object

          • ImageBlockParam object

          • SearchResultBlockParam object

          • DocumentBlockParam object

          • ToolReferenceBlockParam object

            Tool reference block that can be included in tool_result content.

            • type: "tool_reference"

            • tool_name: string

              maxLength: 256, minLength: 1, pattern: [81]{1,256}$

            • cache_control: optional CacheControlEphemeral or null

              Create a cache control breakpoint at this content block.

          • BrowserStateBlockParam object

            The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side 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 BrowserStateTabEntry

              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: [82]*$

              • title: string

                The title of the page the tab is showing. May be empty.

                maxLength: 4096, pattern: [83]*$

              • url: string

                The URL of the page the tab is showing. May be empty.

                maxLength: 4096, pattern: [84]*$

              • 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 CacheControlEphemeral or null

              Create a cache control breakpoint at this content block.

            • state_changes: optional array of BrowserStateChange 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

              • BrowserStateChangeTabOpened object

                A tab this call's execution opened that remains open at its end — the creation delta of the tabs inventory, not an event log.

                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: [85]*$

              • BrowserStateChangeDownloadStarted 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: [86]*$

                • url: string

                  The final post-redirect URL the download was served from.

                  maxLength: 4096, pattern: [87]*$

              • BrowserStateChangeDownloadCompleted 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: [88]*$

                • url: string

                  The final post-redirect URL the download was served from.

                  maxLength: 4096, pattern: [89]*$

                • 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: [90]*$, maxLength: 4096

                • size_bytes: optional number or null

                  The completed download's size.

                  minimum: 0

              • BrowserStateChangeDownloadFailed 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: [91]*$

                • url: string

                  The final post-redirect URL the download was served from.

                  maxLength: 4096, pattern: [92]*$

                • error: optional string or null

                  The failure or cancellation detail, when known.

                  pattern: [93]*$, 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: [94]+$

    • ServerToolUseBlockParam object

      • type: "server_tool_use"

      • id: string

        pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • input: map[unknown]

      • name: "web_search" or "web_fetch" or "code_execution" or 4 more

        • "web_search"

        • "web_fetch"

        • "code_execution"

        • "bash_code_execution"

        • "text_editor_code_execution"

        • "tool_search_tool_regex"

        • "tool_search_tool_bm25"

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

        • DirectCaller object

          Tool invocation directly from the model.

        • ServerToolCaller object

          Tool invocation generated by a server-side tool.

        • ServerToolCaller20260120 object

    • WebSearchToolResultBlockParam object

      • type: "web_search_tool_result"

      • content: WebSearchToolResultBlockParamContent

        • WebSearchToolResultBlockItem = array of WebSearchResultBlockParam

          • type: "web_search_result"

          • encrypted_content: string

          • title: string

          • url: string

          • page_age: optional string or null

        • WebSearchToolRequestError object

          • type: "web_search_tool_result_error"

          • error_code: WebSearchToolResultErrorCode

            • "invalid_tool_input"

            • "unavailable"

            • "max_uses_exceeded"

            • "too_many_requests"

            • "query_too_long"

            • "request_too_large"

      • tool_use_id: string

        pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

        • DirectCaller object

          Tool invocation directly from the model.

        • ServerToolCaller object

          Tool invocation generated by a server-side tool.

        • ServerToolCaller20260120 object

    • WebFetchToolResultBlockParam object

      • type: "web_fetch_tool_result"

      • content: WebFetchToolResultErrorBlockParam or WebFetchBlockParam

        • WebFetchToolResultErrorBlockParam object

          • type: "web_fetch_tool_result_error"

          • error_code: WebFetchToolResultErrorCode

            • "invalid_tool_input"

            • "url_too_long"

            • "url_not_allowed"

            • "url_not_in_prior_context"

            • "url_not_accessible"

            • "unsupported_content_type"

            • "too_many_requests"

            • "max_uses_exceeded"

            • "unavailable"

            • "content_too_large"

        • WebFetchBlockParam object

          • type: "web_fetch_result"

          • content: DocumentBlockParam

          • 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

        • DirectCaller object

          Tool invocation directly from the model.

        • ServerToolCaller object

          Tool invocation generated by a server-side tool.

        • ServerToolCaller20260120 object

    • CodeExecutionToolResultBlockParam object

      • type: "code_execution_tool_result"

      • content: CodeExecutionToolResultBlockParamContent

        • CodeExecutionToolResultErrorParam object

          • type: "code_execution_tool_result_error"

          • error_code: CodeExecutionToolResultErrorCode

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

        • CodeExecutionResultBlockParam object

          • type: "code_execution_result"

          • content: array of CodeExecutionOutputBlockParam

            • type: "code_execution_output"

            • file_id: string

          • return_code: number

          • stderr: string

          • stdout: string

        • EncryptedCodeExecutionResultBlockParam object

          Code execution result with encrypted stdout for PFC + web_search results.

          • type: "encrypted_code_execution_result"

          • content: array of CodeExecutionOutputBlockParam

            • 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

    • BashCodeExecutionToolResultBlockParam object

      • type: "bash_code_execution_tool_result"

      • content: BashCodeExecutionToolResultErrorParam or BashCodeExecutionResultBlockParam

        • BashCodeExecutionToolResultErrorParam object

          • type: "bash_code_execution_tool_result_error"

          • error_code: BashCodeExecutionToolResultErrorCode

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

            • "output_file_too_large"

        • BashCodeExecutionResultBlockParam object

          • type: "bash_code_execution_result"

          • content: array of BashCodeExecutionOutputBlockParam

            • 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

    • TextEditorCodeExecutionToolResultBlockParam object

      • type: "text_editor_code_execution_tool_result"

      • content: TextEditorCodeExecutionToolResultErrorParam or TextEditorCodeExecutionViewResultBlockParam or TextEditorCodeExecutionCreateResultBlockParam or TextEditorCodeExecutionStrReplaceResultBlockParam

        • TextEditorCodeExecutionToolResultErrorParam object

          • type: "text_editor_code_execution_tool_result_error"

          • error_code: TextEditorCodeExecutionToolResultErrorCode

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

            • "file_not_found"

          • error_message: optional string or null

        • TextEditorCodeExecutionViewResultBlockParam 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

        • TextEditorCodeExecutionCreateResultBlockParam object

          • type: "text_editor_code_execution_create_result"

          • is_file_update: boolean

        • TextEditorCodeExecutionStrReplaceResultBlockParam 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

    • ToolSearchToolResultBlockParam object

      • type: "tool_search_tool_result"

      • content: ToolSearchToolResultErrorParam or ToolSearchToolSearchResultBlockParam

        • ToolSearchToolResultErrorParam object

          • type: "tool_search_tool_result_error"

          • error_code: ToolSearchToolResultErrorCode

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

          • error_message: optional string or null

        • ToolSearchToolSearchResultBlockParam object

          • type: "tool_search_tool_search_result"

          • tool_references: array of ToolReferenceBlockParam

            • type: "tool_reference"

            • tool_name: string

              maxLength: 256, minLength: 1, pattern: [95]{1,256}$

            • cache_control: optional CacheControlEphemeral or null

              Create a cache control breakpoint at this content block.

      • tool_use_id: string

        pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

    • ContainerUploadBlockParam object

      A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory.

      • type: "container_upload"

      • file_id: string

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

# Content Block Source

  • ContentBlockSource object

    • type: "content"

    • content: string or array of ContentBlockSourceContent

      • string

      • ContentBlockSourceContent = array of ContentBlockSourceContent

        • TextBlockParam object

          • type: "text"

          • text: string

            minLength: 1

          • cache_control: optional CacheControlEphemeral 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 for details.

              • "5m"

              • "1h"

          • citations: optional array of TextCitationParam or null

            • CitationCharLocationParam 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

            • CitationPageLocationParam 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

            • CitationContentBlockLocationParam 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

            • CitationWebSearchResultLocationParam object

              • type: "web_search_result_location"

              • cited_text: string

              • encrypted_index: string

              • title: string or null

                maxLength: 512, minLength: 1

              • url: string

                minLength: 1

            • CitationSearchResultLocationParam 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

        • ImageBlockParam object

          • type: "image"

          • source: Base64ImageSource or URLImageSource or FileImageSource

            • Base64ImageSource 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"

            • URLImageSource object

              • type: "url"

              • url: string

            • FileImageSource object

              • type: "file"

              • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • transformations: optional ImageTransformationsParam 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"

# Content Block Source Content

  • ContentBlockSourceContent = TextBlockParam or ImageBlockParam

    • TextBlockParam object

      • type: "text"

      • text: string

        minLength: 1

      • cache_control: optional CacheControlEphemeral 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 for details.

          • "5m"

          • "1h"

      • citations: optional array of TextCitationParam or null

        • CitationCharLocationParam 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

        • CitationPageLocationParam 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

        • CitationContentBlockLocationParam 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

        • CitationWebSearchResultLocationParam object

          • type: "web_search_result_location"

          • cited_text: string

          • encrypted_index: string

          • title: string or null

            maxLength: 512, minLength: 1

          • url: string

            minLength: 1

        • CitationSearchResultLocationParam 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

    • ImageBlockParam object

      • type: "image"

      • source: Base64ImageSource or URLImageSource or FileImageSource

        • Base64ImageSource 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"

        • URLImageSource object

          • type: "url"

          • url: string

        • FileImageSource object

          • type: "file"

          • file_id: string

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • transformations: optional ImageTransformationsParam 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"

# Direct Caller

  • DirectCaller object

    Tool invocation directly from the model.

    • type: "direct"

# Document Block

  • DocumentBlock object

    • type: "document"

      default: document

    • citations: CitationsConfig or null

      Citation configuration for the document

      • enabled: boolean

        default: false

    • source: Base64PDFSource or PlainTextSource

      • Base64PDFSource object

        • type: "base64"

        • data: string

          format: byte

        • media_type: "application/pdf"

      • PlainTextSource object

        • type: "text"

        • data: string

        • media_type: "text/plain"

    • title: string or null

      The title of the document

# Document Block Param

  • DocumentBlockParam object

    • type: "document"

    • source: Base64PDFSource or PlainTextSource or ContentBlockSource or 2 more

      • Base64PDFSource object

        • type: "base64"

        • data: string

          format: byte

        • media_type: "application/pdf"

      • PlainTextSource object

        • type: "text"

        • data: string

        • media_type: "text/plain"

      • ContentBlockSource object

        • type: "content"

        • content: string or array of ContentBlockSourceContent

          • string

          • ContentBlockSourceContent = array of ContentBlockSourceContent

            • TextBlockParam object

              • type: "text"

              • text: string

                minLength: 1

              • cache_control: optional CacheControlEphemeral 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 for details.

                  • "5m"

                  • "1h"

              • citations: optional array of TextCitationParam or null

                • CitationCharLocationParam 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

                • CitationPageLocationParam 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

                • CitationContentBlockLocationParam 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

                • CitationWebSearchResultLocationParam object

                  • type: "web_search_result_location"

                  • cited_text: string

                  • encrypted_index: string

                  • title: string or null

                    maxLength: 512, minLength: 1

                  • url: string

                    minLength: 1

                • CitationSearchResultLocationParam 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

            • ImageBlockParam object

              • type: "image"

              • source: Base64ImageSource or URLImageSource or FileImageSource

                • Base64ImageSource 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"

                • URLImageSource object

                  • type: "url"

                  • url: string

                • FileImageSource object

                  • type: "file"

                  • file_id: string

              • cache_control: optional CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

              • transformations: optional ImageTransformationsParam 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"

      • URLPDFSource object

        • type: "url"

        • url: string

      • FileDocumentSource object

        • type: "file"

        • file_id: string

    • cache_control: optional CacheControlEphemeral or null

      Create a cache control breakpoint at this content block.

    • citations: optional CitationsConfigParam or null

      • enabled: optional boolean
    • context: optional string or null

      minLength: 1

    • title: optional string or null

      maxLength: 500, minLength: 1

# Encrypted Code Execution Result Block

  • EncryptedCodeExecutionResultBlock 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 CodeExecutionOutputBlock

      • type: "code_execution_output"

        default: code_execution_output

      • file_id: string

    • encrypted_stdout: string

    • return_code: number

    • stderr: string

# Encrypted Code Execution Result Block Param

  • EncryptedCodeExecutionResultBlockParam object

    Code execution result with encrypted stdout for PFC + web_search results.

    • type: "encrypted_code_execution_result"

    • content: array of CodeExecutionOutputBlockParam

      • type: "code_execution_output"

      • file_id: string

    • encrypted_stdout: string

    • return_code: number

    • stderr: string

# File Document Source

  • FileDocumentSource object

    • type: "file"

    • file_id: string

# File Image Source

  • FileImageSource object

    • type: "file"

    • file_id: string

# Image Block Param

  • ImageBlockParam object

    • type: "image"

    • source: Base64ImageSource or URLImageSource or FileImageSource

      • Base64ImageSource 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"

      • URLImageSource object

        • type: "url"

        • url: string

      • FileImageSource object

        • type: "file"

        • file_id: string

    • cache_control: optional CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • transformations: optional ImageTransformationsParam 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"

# Image Transformations Param

  • ImageTransformationsParam 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"

# Input JSON Delta

  • InputJSONDelta object

    • type: "input_json_delta"

      default: input_json_delta

    • partial_json: string

# JSON Output Format

  • JSONOutputFormat object

    • type: "json_schema"

    • schema: map[unknown]

      The JSON schema of the format

# Memory Tool 20250818

  • MemoryTool20250818 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 CacheControlEphemeral 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 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

# Message

  • Message 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: Container 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 ContainerSkill 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 ContentBlock

      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)"}]
      • TextBlock object

        • type: "text"

          default: text

        • citations: array of TextCitation 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.

          • CitationCharLocation 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

          • CitationPageLocation 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

          • CitationContentBlockLocation 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

          • CitationsWebSearchResultLocation 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

          • CitationsSearchResultLocation 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

      • ThinkingBlock 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 for details.

        • thinking: string

          The text of Claude's thinking process for this block.

      • RedactedThinkingBlock 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 for details.

      • ToolUseBlock object

        • type: "tool_use"

          default: tool_use

        • id: string

          pattern: [96]+$

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          default: {"type":"direct"}

          • DirectCaller object

            Tool invocation directly from the model.

            • type: "direct"
          • ServerToolCaller object

            Tool invocation generated by a server-side tool.

            • type: "code_execution_20250825"

            • tool_id: string

              pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • ServerToolCaller20260120 object

            • type: "code_execution_20260120"

            • tool_id: string

              pattern: ^srvtoolu_[a-zA-Z0-9_]+$

        • input: map[unknown]

        • name: string

          minLength: 1

        • toolset_name: optional string or null

          For a toolset member tool_use, the toolset family.

          maxLength: 64, minLength: 1, pattern: [97]+$

      • ServerToolUseBlock object

        • type: "server_tool_use"

          default: server_tool_use

        • id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          default: {"type":"direct"}

          • DirectCaller object

            Tool invocation directly from the model.

          • ServerToolCaller object

            Tool invocation generated by a server-side tool.

          • ServerToolCaller20260120 object

        • input: map[unknown]

        • name: "web_search" or "web_fetch" or "code_execution" or 4 more

          • "web_search"

          • "web_fetch"

          • "code_execution"

          • "bash_code_execution"

          • "text_editor_code_execution"

          • "tool_search_tool_regex"

          • "tool_search_tool_bm25"

      • WebSearchToolResultBlock object

        • type: "web_search_tool_result"

          default: web_search_tool_result

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          default: {"type":"direct"}

          • DirectCaller object

            Tool invocation directly from the model.

          • ServerToolCaller object

            Tool invocation generated by a server-side tool.

          • ServerToolCaller20260120 object

        • content: WebSearchToolResultBlockContent

          • WebSearchToolResultError object

            • type: "web_search_tool_result_error"

              default: web_search_tool_result_error

            • error_code: WebSearchToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "max_uses_exceeded"

              • "too_many_requests"

              • "query_too_long"

              • "request_too_large"

          • array of WebSearchResultBlock

            • 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_]+$

      • WebFetchToolResultBlock object

        • type: "web_fetch_tool_result"

          default: web_fetch_tool_result

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          default: {"type":"direct"}

          • DirectCaller object

            Tool invocation directly from the model.

          • ServerToolCaller object

            Tool invocation generated by a server-side tool.

          • ServerToolCaller20260120 object

        • content: WebFetchToolResultErrorBlock or WebFetchBlock

          • WebFetchToolResultErrorBlock object

            • type: "web_fetch_tool_result_error"

              default: web_fetch_tool_result_error

            • error_code: WebFetchToolResultErrorCode

              • "invalid_tool_input"

              • "url_too_long"

              • "url_not_allowed"

              • "url_not_in_prior_context"

              • "url_not_accessible"

              • "unsupported_content_type"

              • "too_many_requests"

              • "max_uses_exceeded"

              • "unavailable"

              • "content_too_large"

          • WebFetchBlock object

            • type: "web_fetch_result"

              default: web_fetch_result

            • content: DocumentBlock

              • type: "document"

                default: document

              • citations: CitationsConfig or null

                Citation configuration for the document

                • enabled: boolean

                  default: false

              • source: Base64PDFSource or PlainTextSource

                • Base64PDFSource object

                  • type: "base64"

                  • data: string

                    format: byte

                  • media_type: "application/pdf"

                • PlainTextSource 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_]+$

      • CodeExecutionToolResultBlock object

        • type: "code_execution_tool_result"

          default: code_execution_tool_result

        • content: CodeExecutionToolResultBlockContent

          • CodeExecutionToolResultError object

            • type: "code_execution_tool_result_error"

              default: code_execution_tool_result_error

            • error_code: CodeExecutionToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

          • CodeExecutionResultBlock object

            • type: "code_execution_result"

              default: code_execution_result

            • content: array of CodeExecutionOutputBlock

              • type: "code_execution_output"

                default: code_execution_output

              • file_id: string

            • return_code: number

            • stderr: string

            • stdout: string

          • EncryptedCodeExecutionResultBlock 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 CodeExecutionOutputBlock

              • 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_]+$

      • BashCodeExecutionToolResultBlock object

        • type: "bash_code_execution_tool_result"

          default: bash_code_execution_tool_result

        • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

          • BashCodeExecutionToolResultError object

            • type: "bash_code_execution_tool_result_error"

              default: bash_code_execution_tool_result_error

            • error_code: BashCodeExecutionToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

              • "output_file_too_large"

          • BashCodeExecutionResultBlock object

            • type: "bash_code_execution_result"

              default: bash_code_execution_result

            • content: array of BashCodeExecutionOutputBlock

              • 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_]+$

      • TextEditorCodeExecutionToolResultBlock object

        • type: "text_editor_code_execution_tool_result"

          default: text_editor_code_execution_tool_result

        • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

          • TextEditorCodeExecutionToolResultError object

            • type: "text_editor_code_execution_tool_result_error"

              default: text_editor_code_execution_tool_result_error

            • error_code: TextEditorCodeExecutionToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

              • "file_not_found"

            • error_message: string or null

          • TextEditorCodeExecutionViewResultBlock 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

          • TextEditorCodeExecutionCreateResultBlock object

            • type: "text_editor_code_execution_create_result"

              default: text_editor_code_execution_create_result

            • is_file_update: boolean

          • TextEditorCodeExecutionStrReplaceResultBlock 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_]+$

      • ToolSearchToolResultBlock object

        • type: "tool_search_tool_result"

          default: tool_search_tool_result

        • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

          • ToolSearchToolResultError object

            • type: "tool_search_tool_result_error"

              default: tool_search_tool_result_error

            • error_code: ToolSearchToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

            • error_message: string or null

          • ToolSearchToolSearchResultBlock object

            • type: "tool_search_tool_search_result"

              default: tool_search_tool_search_result

            • tool_references: array of ToolReferenceBlock

              • type: "tool_reference"

                default: tool_reference

              • tool_name: string

                maxLength: 256, minLength: 1, pattern: [98]{1,256}$

        • tool_use_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • ContainerUploadBlock object

        Response model for a file uploaded to the container.

        • type: "container_upload"

          default: container_upload

        • file_id: string

    • model: Model

      The model that will complete your prompt.

      See models 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 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

    • role: "assistant"

      Conversational role of the generated message.

      This will always be "assistant".

      default: assistant

    • stop_details: RefusalStopDetails 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. 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.

        • "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.

    • stop_reason: StopReason 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"

      • "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: Usage

      Billing and rate-limit usage.

      Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.

      Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.

      For example, output_tokens will be non-zero, even for an empty string response from Claude.

      Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.

      • cache_creation: CacheCreation 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

      • 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

      • output_tokens: number

        The number of output tokens which were used.

        minimum: 0

      • output_tokens_details: OutputTokensDetails 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: ServerToolUsage 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"

# Message Count Tokens Tool

  • MessageCountTokensTool = Tool or ToolBash20250124 or CodeExecutionTool20250522 or 18 more

    • Tool object

      • type: optional "custom" or null

      • input_schema: object

        JSON schema 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: [99]{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 CacheControlEphemeral 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 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

    • ToolBash20250124 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20250522 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20250825 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20260120 object

      Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint).

      • 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20260521 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • BrowserToolset20260801 object

      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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • configs: optional BrowserToolsetConfigs 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 BrowserTypeConfig 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 BrowserCloseTabConfig 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 BrowserDoubleClickConfig 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 BrowserFileUploadConfig 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 BrowserFindConfig 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 BrowserFormInputConfig 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 BrowserGetPageTextConfig 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 BrowserHoldKeyConfig 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 BrowserHoverConfig 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 BrowserJavascriptExecConfig 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 BrowserKeyConfig 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 BrowserLeftClickConfig 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 BrowserLeftClickDragConfig 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 BrowserLeftMouseDownConfig 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 BrowserLeftMouseUpConfig 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 BrowserListTabsConfig 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 BrowserMiddleClickConfig 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 BrowserMouseMoveConfig 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 BrowserNavigateConfig 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 BrowserNewTabConfig 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 BrowserReadConsoleConfig 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 BrowserReadNetworkConfig 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 BrowserReadPageConfig 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 BrowserRightClickConfig 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 BrowserScreenshotConfig 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 BrowserScrollConfig 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 BrowserScrollToConfig 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 BrowserSwitchTabConfig 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 BrowserTripleClickConfig 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 BrowserWaitConfig 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 BrowserZoomConfig 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.

    • MemoryTool20250818 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ComputerToolset20260801 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • configs: optional ComputerToolsetConfigs 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 ComputerTypeConfig 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 ComputerCursorPositionConfig 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 ComputerDoubleClickConfig 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 ComputerHoldKeyConfig 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 ComputerKeyConfig 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 ComputerLeftClickConfig 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 ComputerLeftClickDragConfig 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 ComputerLeftMouseDownConfig 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 ComputerLeftMouseUpConfig 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 ComputerMiddleClickConfig 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 ComputerMouseMoveConfig 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 ComputerRightClickConfig 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 ComputerScreenshotConfig 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 ComputerScrollConfig 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 ComputerTripleClickConfig 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 ComputerWaitConfig 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 ComputerZoomConfig 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.

    • ToolTextEditor20250124 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ToolTextEditor20250429 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ToolTextEditor20250728 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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

    • WebSearchTool20250305 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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 UserLocation 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 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 of the user.

          maxLength: 255, minLength: 1

    • WebFetchTool20250910 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

        • client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

          Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].

          • WebFetchURLSourceAll object

            The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

            • type: "all"
          • WebFetchURLSourceNone object

            The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

            • type: "none"
          • WebFetchURLSourceOnly object

            The tool filter variant under which only the named tools' results contribute.

            • type: "only"

            • tools: array of WebFetchURLSourceToolReference

              • type: "tool_reference"

              • name: string

          • WebFetchURLSourceExcept object

            The tool filter variant under which every result but the named tools' contributes.

            • type: "except"

            • tools: array of WebFetchURLSourceToolReference

              • type: "tool_reference"

              • name: string

        • server_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

          Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute.

          • WebFetchURLSourceAll object

            The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

          • WebFetchURLSourceNone object

            The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

          • WebFetchURLSourceOnly object

            The tool filter variant under which only the named tools' results contribute.

          • WebFetchURLSourceExcept object

            The tool filter variant under which every result but the named tools' contributes.

        • user_input: optional WebFetchURLSourceAll or WebFetchURLSourceNone

          Whether URLs in user messages are fetchable: "all" or "none".

          • WebFetchURLSourceAll object

            The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

          • WebFetchURLSourceNone object

            The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

    • WebSearchTool20260209 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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 UserLocation or null

        Parameters for the user's location. Used to provide more relevant search results.

    • WebFetchTool20260209 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

    • WebFetchTool20260309 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

      • 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.

    • WebSearchTool20260318 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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 UserLocation or null

        Parameters for the user's location. Used to provide more relevant search results.

    • WebFetchTool20260318 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

      • 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.

    • ToolSearchToolBm25_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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ToolSearchToolRegex20251119 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

# Message Create Params Container

  • MessageCreateParamsContainer = ContainerParams or string

    Container identifier for reuse across requests.

    • ContainerParams object

      Container parameters with skills to be loaded.

      • id: optional string or null

        Container id

      • skills: optional array of SkillParams 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

# Message Delta Usage

  • MessageDeltaUsage 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

    • input_tokens: number or null

      The cumulative number of input tokens which were used.

      minimum: 0

    • output_tokens: number

      The cumulative number of output tokens which were used.

    • output_tokens_details: OutputTokensDetails 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: ServerToolUsage 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

# Message Param

  • MessageParam object

    • content: string or array of ContentBlockParam

      • string

      • array of ContentBlockParam

        • TextBlockParam object

          • type: "text"

          • text: string

            minLength: 1

          • cache_control: optional CacheControlEphemeral 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 for details.

              • "5m"

              • "1h"

          • citations: optional array of TextCitationParam or null

            • CitationCharLocationParam 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

            • CitationPageLocationParam 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

            • CitationContentBlockLocationParam 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

            • CitationWebSearchResultLocationParam object

              • type: "web_search_result_location"

              • cited_text: string

              • encrypted_index: string

              • title: string or null

                maxLength: 512, minLength: 1

              • url: string

                minLength: 1

            • CitationSearchResultLocationParam 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

        • ImageBlockParam object

          • type: "image"

          • source: Base64ImageSource or URLImageSource or FileImageSource

            • Base64ImageSource 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"

            • URLImageSource object

              • type: "url"

              • url: string

            • FileImageSource object

              • type: "file"

              • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • transformations: optional ImageTransformationsParam 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"

        • DocumentBlockParam object

          • type: "document"

          • source: Base64PDFSource or PlainTextSource or ContentBlockSource or 2 more

            • Base64PDFSource object

              • type: "base64"

              • data: string

                format: byte

              • media_type: "application/pdf"

            • PlainTextSource object

              • type: "text"

              • data: string

              • media_type: "text/plain"

            • ContentBlockSource object

              • type: "content"

              • content: string or array of ContentBlockSourceContent

                • string

                • ContentBlockSourceContent = array of ContentBlockSourceContent

                  • TextBlockParam object

                  • ImageBlockParam object

            • URLPDFSource object

              • type: "url"

              • url: string

            • FileDocumentSource object

              • type: "file"

              • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam or null

            • enabled: optional boolean
          • context: optional string or null

            minLength: 1

          • title: optional string or null

            maxLength: 500, minLength: 1

        • SearchResultBlockParam object

          • type: "search_result"

          • content: array of TextBlockParam

            • type: "text"

            • text: string

              minLength: 1

            • cache_control: optional CacheControlEphemeral or null

              Create a cache control breakpoint at this content block.

            • citations: optional array of TextCitationParam or null

          • source: string

          • title: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam

        • ThinkingBlockParam 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.

        • RedactedThinkingBlockParam 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.

        • ToolUseBlockParam object

          • type: "tool_use"

          • id: string

            pattern: [100]+$

          • input: map[unknown]

          • name: string

            maxLength: 200, minLength: 1

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

            • DirectCaller object

              Tool invocation directly from the model.

              • type: "direct"
            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

              • type: "code_execution_20250825"

              • tool_id: string

                pattern: ^srvtoolu_[a-zA-Z0-9_]+$

            • ServerToolCaller20260120 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: [101]+$

        • ToolResultBlockParam object

          • type: "tool_result"

          • tool_use_id: string

            pattern: [102]+$

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • content: optional string or array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more

            • string

            • array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more

              • TextBlockParam object

              • ImageBlockParam object

              • SearchResultBlockParam object

              • DocumentBlockParam object

              • ToolReferenceBlockParam object

                Tool reference block that can be included in tool_result content.

                • type: "tool_reference"

                • tool_name: string

                  maxLength: 256, minLength: 1, pattern: [103]{1,256}$

                • cache_control: optional CacheControlEphemeral or null

                  Create a cache control breakpoint at this content block.

              • BrowserStateBlockParam object

                The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side 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 BrowserStateTabEntry

                  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: [104]*$

                  • title: string

                    The title of the page the tab is showing. May be empty.

                    maxLength: 4096, pattern: [105]*$

                  • url: string

                    The URL of the page the tab is showing. May be empty.

                    maxLength: 4096, pattern: [106]*$

                  • 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 CacheControlEphemeral or null

                  Create a cache control breakpoint at this content block.

                • state_changes: optional array of BrowserStateChange 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

                  • BrowserStateChangeTabOpened object

                    A tab this call's execution opened that remains open at its end — the creation delta of the tabs inventory, not an event log.

                    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: [107]*$

                  • BrowserStateChangeDownloadStarted 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: [108]*$

                    • url: string

                      The final post-redirect URL the download was served from.

                      maxLength: 4096, pattern: [109]*$

                  • BrowserStateChangeDownloadCompleted 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: [110]*$

                    • url: string

                      The final post-redirect URL the download was served from.

                      maxLength: 4096, pattern: [111]*$

                    • 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: [112]*$, maxLength: 4096

                    • size_bytes: optional number or null

                      The completed download's size.

                      minimum: 0

                  • BrowserStateChangeDownloadFailed 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: [113]*$

                    • url: string

                      The final post-redirect URL the download was served from.

                      maxLength: 4096, pattern: [114]*$

                    • error: optional string or null

                      The failure or cancellation detail, when known.

                      pattern: [115]*$, 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: [116]+$

        • ServerToolUseBlockParam object

          • type: "server_tool_use"

          • id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • input: map[unknown]

          • name: "web_search" or "web_fetch" or "code_execution" or 4 more

            • "web_search"

            • "web_fetch"

            • "code_execution"

            • "bash_code_execution"

            • "text_editor_code_execution"

            • "tool_search_tool_regex"

            • "tool_search_tool_bm25"

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

            • DirectCaller object

              Tool invocation directly from the model.

            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

            • ServerToolCaller20260120 object

        • WebSearchToolResultBlockParam object

          • type: "web_search_tool_result"

          • content: WebSearchToolResultBlockParamContent

            • WebSearchToolResultBlockItem = array of WebSearchResultBlockParam

              • type: "web_search_result"

              • encrypted_content: string

              • title: string

              • url: string

              • page_age: optional string or null

            • WebSearchToolRequestError object

              • type: "web_search_tool_result_error"

              • error_code: WebSearchToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "max_uses_exceeded"

                • "too_many_requests"

                • "query_too_long"

                • "request_too_large"

          • tool_use_id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

            • DirectCaller object

              Tool invocation directly from the model.

            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

            • ServerToolCaller20260120 object

        • WebFetchToolResultBlockParam object

          • type: "web_fetch_tool_result"

          • content: WebFetchToolResultErrorBlockParam or WebFetchBlockParam

            • WebFetchToolResultErrorBlockParam object

              • type: "web_fetch_tool_result_error"

              • error_code: WebFetchToolResultErrorCode

                • "invalid_tool_input"

                • "url_too_long"

                • "url_not_allowed"

                • "url_not_in_prior_context"

                • "url_not_accessible"

                • "unsupported_content_type"

                • "too_many_requests"

                • "max_uses_exceeded"

                • "unavailable"

                • "content_too_large"

            • WebFetchBlockParam object

              • type: "web_fetch_result"

              • content: DocumentBlockParam

              • 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

            • DirectCaller object

              Tool invocation directly from the model.

            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

            • ServerToolCaller20260120 object

        • CodeExecutionToolResultBlockParam object

          • type: "code_execution_tool_result"

          • content: CodeExecutionToolResultBlockParamContent

            • CodeExecutionToolResultErrorParam object

              • type: "code_execution_tool_result_error"

              • error_code: CodeExecutionToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

            • CodeExecutionResultBlockParam object

              • type: "code_execution_result"

              • content: array of CodeExecutionOutputBlockParam

                • type: "code_execution_output"

                • file_id: string

              • return_code: number

              • stderr: string

              • stdout: string

            • EncryptedCodeExecutionResultBlockParam object

              Code execution result with encrypted stdout for PFC + web_search results.

              • type: "encrypted_code_execution_result"

              • content: array of CodeExecutionOutputBlockParam

                • 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • BashCodeExecutionToolResultBlockParam object

          • type: "bash_code_execution_tool_result"

          • content: BashCodeExecutionToolResultErrorParam or BashCodeExecutionResultBlockParam

            • BashCodeExecutionToolResultErrorParam object

              • type: "bash_code_execution_tool_result_error"

              • error_code: BashCodeExecutionToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

                • "output_file_too_large"

            • BashCodeExecutionResultBlockParam object

              • type: "bash_code_execution_result"

              • content: array of BashCodeExecutionOutputBlockParam

                • 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • TextEditorCodeExecutionToolResultBlockParam object

          • type: "text_editor_code_execution_tool_result"

          • content: TextEditorCodeExecutionToolResultErrorParam or TextEditorCodeExecutionViewResultBlockParam or TextEditorCodeExecutionCreateResultBlockParam or TextEditorCodeExecutionStrReplaceResultBlockParam

            • TextEditorCodeExecutionToolResultErrorParam object

              • type: "text_editor_code_execution_tool_result_error"

              • error_code: TextEditorCodeExecutionToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

                • "file_not_found"

              • error_message: optional string or null

            • TextEditorCodeExecutionViewResultBlockParam 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

            • TextEditorCodeExecutionCreateResultBlockParam object

              • type: "text_editor_code_execution_create_result"

              • is_file_update: boolean

            • TextEditorCodeExecutionStrReplaceResultBlockParam 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • ToolSearchToolResultBlockParam object

          • type: "tool_search_tool_result"

          • content: ToolSearchToolResultErrorParam or ToolSearchToolSearchResultBlockParam

            • ToolSearchToolResultErrorParam object

              • type: "tool_search_tool_result_error"

              • error_code: ToolSearchToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

              • error_message: optional string or null

            • ToolSearchToolSearchResultBlockParam object

              • type: "tool_search_tool_search_result"

              • tool_references: array of ToolReferenceBlockParam

                • type: "tool_reference"

                • tool_name: string

                  maxLength: 256, minLength: 1, pattern: [117]{1,256}$

                • cache_control: optional CacheControlEphemeral or null

                  Create a cache control breakpoint at this content block.

          • tool_use_id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • ContainerUploadBlockParam object

          A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory.

          • type: "container_upload"

          • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

    • role: "user" or "assistant" or "system"

      • "user"

      • "assistant"

      • "system"

# Message Tokens Count

  • MessageTokensCount object

    • input_tokens: number

      The total number of tokens across the provided list of messages, system prompt, and tools.

# Metadata

  • Metadata 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

# Model

  • Model = "claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more or string

    The model that will complete your prompt.

    See models 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 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 Config

  • OutputConfig object

    • effort: optional "low" or "medium" or "high" or 2 more or null

      All possible effort levels.

      • "low"

      • "medium"

      • "high"

      • "xhigh"

      • "max"

    • format: optional JSONOutputFormat or null

      A schema to specify Claude's output format in responses. See structured outputs

      • type: "json_schema"

      • schema: map[unknown]

        The JSON schema of the format

# Output Tokens Details

  • OutputTokensDetails 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

# Plain Text Source

  • PlainTextSource object

    • type: "text"

    • data: string

    • media_type: "text/plain"

# Raw Content Block Delta

  • RawContentBlockDelta = TextDelta or InputJSONDelta or CitationsDelta or 2 more

    • TextDelta object

      • type: "text_delta"

        default: text_delta

      • text: string

    • InputJSONDelta object

      • type: "input_json_delta"

        default: input_json_delta

      • partial_json: string

    • CitationsDelta object

      • type: "citations_delta"

        default: citations_delta

      • citation: CitationCharLocation or CitationPageLocation or CitationContentBlockLocation or 2 more

        • CitationCharLocation 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

        • CitationPageLocation 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

        • CitationContentBlockLocation 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

        • CitationsWebSearchResultLocation 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

        • CitationsSearchResultLocation 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

    • ThinkingDelta object

      • type: "thinking_delta"

        default: thinking_delta

      • thinking: string

        The incremental thinking text for this content block. Concatenate the thinking values of successive thinking_delta events to assemble the block's full thinking value.

    • SignatureDelta 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.

# Raw Content Block Delta Event

  • RawContentBlockDeltaEvent object

    • type: "content_block_delta"

      default: content_block_delta

    • delta: RawContentBlockDelta

      • TextDelta object

        • type: "text_delta"

          default: text_delta

        • text: string

      • InputJSONDelta object

        • type: "input_json_delta"

          default: input_json_delta

        • partial_json: string

      • CitationsDelta object

        • type: "citations_delta"

          default: citations_delta

        • citation: CitationCharLocation or CitationPageLocation or CitationContentBlockLocation or 2 more

          • CitationCharLocation 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

          • CitationPageLocation 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

          • CitationContentBlockLocation 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

          • CitationsWebSearchResultLocation 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

          • CitationsSearchResultLocation 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

      • ThinkingDelta object

        • type: "thinking_delta"

          default: thinking_delta

        • thinking: string

          The incremental thinking text for this content block. Concatenate the thinking values of successive thinking_delta events to assemble the block's full thinking value.

      • SignatureDelta 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.

    • index: number

# Raw Content Block Start Event

  • RawContentBlockStartEvent object

    • type: "content_block_start"

      default: content_block_start

    • content_block: TextBlock or ThinkingBlock or RedactedThinkingBlock or 9 more

      • TextBlock object

        • type: "text"

          default: text

        • citations: array of TextCitation 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.

          • CitationCharLocation 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

          • CitationPageLocation 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

          • CitationContentBlockLocation 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

          • CitationsWebSearchResultLocation 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

          • CitationsSearchResultLocation 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

      • ThinkingBlock 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 for details.

        • thinking: string

          The text of Claude's thinking process for this block.

      • RedactedThinkingBlock 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 for details.

      • ToolUseBlock object

        • type: "tool_use"

          default: tool_use

        • id: string

          pattern: [118]+$

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          default: {"type":"direct"}

          • DirectCaller object

            Tool invocation directly from the model.

            • type: "direct"
          • ServerToolCaller object

            Tool invocation generated by a server-side tool.

            • type: "code_execution_20250825"

            • tool_id: string

              pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • ServerToolCaller20260120 object

            • type: "code_execution_20260120"

            • tool_id: string

              pattern: ^srvtoolu_[a-zA-Z0-9_]+$

        • input: map[unknown]

        • name: string

          minLength: 1

        • toolset_name: optional string or null

          For a toolset member tool_use, the toolset family.

          maxLength: 64, minLength: 1, pattern: [119]+$

      • ServerToolUseBlock object

        • type: "server_tool_use"

          default: server_tool_use

        • id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          default: {"type":"direct"}

          • DirectCaller object

            Tool invocation directly from the model.

          • ServerToolCaller object

            Tool invocation generated by a server-side tool.

          • ServerToolCaller20260120 object

        • input: map[unknown]

        • name: "web_search" or "web_fetch" or "code_execution" or 4 more

          • "web_search"

          • "web_fetch"

          • "code_execution"

          • "bash_code_execution"

          • "text_editor_code_execution"

          • "tool_search_tool_regex"

          • "tool_search_tool_bm25"

      • WebSearchToolResultBlock object

        • type: "web_search_tool_result"

          default: web_search_tool_result

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          default: {"type":"direct"}

          • DirectCaller object

            Tool invocation directly from the model.

          • ServerToolCaller object

            Tool invocation generated by a server-side tool.

          • ServerToolCaller20260120 object

        • content: WebSearchToolResultBlockContent

          • WebSearchToolResultError object

            • type: "web_search_tool_result_error"

              default: web_search_tool_result_error

            • error_code: WebSearchToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "max_uses_exceeded"

              • "too_many_requests"

              • "query_too_long"

              • "request_too_large"

          • array of WebSearchResultBlock

            • 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_]+$

      • WebFetchToolResultBlock object

        • type: "web_fetch_tool_result"

          default: web_fetch_tool_result

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          default: {"type":"direct"}

          • DirectCaller object

            Tool invocation directly from the model.

          • ServerToolCaller object

            Tool invocation generated by a server-side tool.

          • ServerToolCaller20260120 object

        • content: WebFetchToolResultErrorBlock or WebFetchBlock

          • WebFetchToolResultErrorBlock object

            • type: "web_fetch_tool_result_error"

              default: web_fetch_tool_result_error

            • error_code: WebFetchToolResultErrorCode

              • "invalid_tool_input"

              • "url_too_long"

              • "url_not_allowed"

              • "url_not_in_prior_context"

              • "url_not_accessible"

              • "unsupported_content_type"

              • "too_many_requests"

              • "max_uses_exceeded"

              • "unavailable"

              • "content_too_large"

          • WebFetchBlock object

            • type: "web_fetch_result"

              default: web_fetch_result

            • content: DocumentBlock

              • type: "document"

                default: document

              • citations: CitationsConfig or null

                Citation configuration for the document

                • enabled: boolean

                  default: false

              • source: Base64PDFSource or PlainTextSource

                • Base64PDFSource object

                  • type: "base64"

                  • data: string

                    format: byte

                  • media_type: "application/pdf"

                • PlainTextSource 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_]+$

      • CodeExecutionToolResultBlock object

        • type: "code_execution_tool_result"

          default: code_execution_tool_result

        • content: CodeExecutionToolResultBlockContent

          • CodeExecutionToolResultError object

            • type: "code_execution_tool_result_error"

              default: code_execution_tool_result_error

            • error_code: CodeExecutionToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

          • CodeExecutionResultBlock object

            • type: "code_execution_result"

              default: code_execution_result

            • content: array of CodeExecutionOutputBlock

              • type: "code_execution_output"

                default: code_execution_output

              • file_id: string

            • return_code: number

            • stderr: string

            • stdout: string

          • EncryptedCodeExecutionResultBlock 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 CodeExecutionOutputBlock

              • 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_]+$

      • BashCodeExecutionToolResultBlock object

        • type: "bash_code_execution_tool_result"

          default: bash_code_execution_tool_result

        • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

          • BashCodeExecutionToolResultError object

            • type: "bash_code_execution_tool_result_error"

              default: bash_code_execution_tool_result_error

            • error_code: BashCodeExecutionToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

              • "output_file_too_large"

          • BashCodeExecutionResultBlock object

            • type: "bash_code_execution_result"

              default: bash_code_execution_result

            • content: array of BashCodeExecutionOutputBlock

              • 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_]+$

      • TextEditorCodeExecutionToolResultBlock object

        • type: "text_editor_code_execution_tool_result"

          default: text_editor_code_execution_tool_result

        • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

          • TextEditorCodeExecutionToolResultError object

            • type: "text_editor_code_execution_tool_result_error"

              default: text_editor_code_execution_tool_result_error

            • error_code: TextEditorCodeExecutionToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

              • "file_not_found"

            • error_message: string or null

          • TextEditorCodeExecutionViewResultBlock 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

          • TextEditorCodeExecutionCreateResultBlock object

            • type: "text_editor_code_execution_create_result"

              default: text_editor_code_execution_create_result

            • is_file_update: boolean

          • TextEditorCodeExecutionStrReplaceResultBlock 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_]+$

      • ToolSearchToolResultBlock object

        • type: "tool_search_tool_result"

          default: tool_search_tool_result

        • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

          • ToolSearchToolResultError object

            • type: "tool_search_tool_result_error"

              default: tool_search_tool_result_error

            • error_code: ToolSearchToolResultErrorCode

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

            • error_message: string or null

          • ToolSearchToolSearchResultBlock object

            • type: "tool_search_tool_search_result"

              default: tool_search_tool_search_result

            • tool_references: array of ToolReferenceBlock

              • type: "tool_reference"

                default: tool_reference

              • tool_name: string

                maxLength: 256, minLength: 1, pattern: [120]{1,256}$

        • tool_use_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • ContainerUploadBlock object

        Response model for a file uploaded to the container.

        • type: "container_upload"

          default: container_upload

        • file_id: string

    • index: number

# Raw Content Block Stop Event

  • RawContentBlockStopEvent object

    • type: "content_block_stop"

      default: content_block_stop

    • index: number

# Raw Message Delta Event

  • RawMessageDeltaEvent object

    • type: "message_delta"

      default: message_delta

    • delta: object

      • container: Container 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 ContainerSkill 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: RefusalStopDetails 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. 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.

          • "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.

      • stop_reason: StopReason or null

        • "end_turn"

        • "max_tokens"

        • "stop_sequence"

        • "tool_use"

        • "pause_turn"

        • "refusal"

        • "model_context_window_exceeded"

      • stop_sequence: string or null

    • usage: MessageDeltaUsage

      Billing and rate-limit usage.

      Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.

      Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.

      For example, output_tokens will be non-zero, even for an empty string response from Claude.

      Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.

      • cache_creation_input_tokens: number 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

      • input_tokens: number or null

        The cumulative number of input tokens which were used.

        minimum: 0

      • output_tokens: number

        The cumulative number of output tokens which were used.

      • output_tokens_details: OutputTokensDetails 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: ServerToolUsage 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

# Raw Message Start Event

  • RawMessageStartEvent object

    • type: "message_start"

      default: message_start

    • message: Message

      • type: "message"

        Object type.

        For Messages, this is always "message".

        default: message

      • id: string

        Unique object identifier.

        The format and length of IDs may change over time.

      • container: Container 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 ContainerSkill 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 ContentBlock

        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)"}]
        • TextBlock object

          • type: "text"

            default: text

          • citations: array of TextCitation 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.

            • CitationCharLocation 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

            • CitationPageLocation 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

            • CitationContentBlockLocation 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

            • CitationsWebSearchResultLocation 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

            • CitationsSearchResultLocation 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

        • ThinkingBlock 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 for details.

          • thinking: string

            The text of Claude's thinking process for this block.

        • RedactedThinkingBlock 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 for details.

        • ToolUseBlock object

          • type: "tool_use"

            default: tool_use

          • id: string

            pattern: [121]+$

          • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

            default: {"type":"direct"}

            • DirectCaller object

              Tool invocation directly from the model.

              • type: "direct"
            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

              • type: "code_execution_20250825"

              • tool_id: string

                pattern: ^srvtoolu_[a-zA-Z0-9_]+$

            • ServerToolCaller20260120 object

              • type: "code_execution_20260120"

              • tool_id: string

                pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • input: map[unknown]

          • name: string

            minLength: 1

          • toolset_name: optional string or null

            For a toolset member tool_use, the toolset family.

            maxLength: 64, minLength: 1, pattern: [122]+$

        • ServerToolUseBlock object

          • type: "server_tool_use"

            default: server_tool_use

          • id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

            default: {"type":"direct"}

            • DirectCaller object

              Tool invocation directly from the model.

            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

            • ServerToolCaller20260120 object

          • input: map[unknown]

          • name: "web_search" or "web_fetch" or "code_execution" or 4 more

            • "web_search"

            • "web_fetch"

            • "code_execution"

            • "bash_code_execution"

            • "text_editor_code_execution"

            • "tool_search_tool_regex"

            • "tool_search_tool_bm25"

        • WebSearchToolResultBlock object

          • type: "web_search_tool_result"

            default: web_search_tool_result

          • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

            default: {"type":"direct"}

            • DirectCaller object

              Tool invocation directly from the model.

            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

            • ServerToolCaller20260120 object

          • content: WebSearchToolResultBlockContent

            • WebSearchToolResultError object

              • type: "web_search_tool_result_error"

                default: web_search_tool_result_error

              • error_code: WebSearchToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "max_uses_exceeded"

                • "too_many_requests"

                • "query_too_long"

                • "request_too_large"

            • array of WebSearchResultBlock

              • 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_]+$

        • WebFetchToolResultBlock object

          • type: "web_fetch_tool_result"

            default: web_fetch_tool_result

          • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

            default: {"type":"direct"}

            • DirectCaller object

              Tool invocation directly from the model.

            • ServerToolCaller object

              Tool invocation generated by a server-side tool.

            • ServerToolCaller20260120 object

          • content: WebFetchToolResultErrorBlock or WebFetchBlock

            • WebFetchToolResultErrorBlock object

              • type: "web_fetch_tool_result_error"

                default: web_fetch_tool_result_error

              • error_code: WebFetchToolResultErrorCode

                • "invalid_tool_input"

                • "url_too_long"

                • "url_not_allowed"

                • "url_not_in_prior_context"

                • "url_not_accessible"

                • "unsupported_content_type"

                • "too_many_requests"

                • "max_uses_exceeded"

                • "unavailable"

                • "content_too_large"

            • WebFetchBlock object

              • type: "web_fetch_result"

                default: web_fetch_result

              • content: DocumentBlock

                • type: "document"

                  default: document

                • citations: CitationsConfig or null

                  Citation configuration for the document

                  • enabled: boolean

                    default: false

                • source: Base64PDFSource or PlainTextSource

                  • Base64PDFSource object

                    • type: "base64"

                    • data: string

                      format: byte

                    • media_type: "application/pdf"

                  • PlainTextSource 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_]+$

        • CodeExecutionToolResultBlock object

          • type: "code_execution_tool_result"

            default: code_execution_tool_result

          • content: CodeExecutionToolResultBlockContent

            • CodeExecutionToolResultError object

              • type: "code_execution_tool_result_error"

                default: code_execution_tool_result_error

              • error_code: CodeExecutionToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

            • CodeExecutionResultBlock object

              • type: "code_execution_result"

                default: code_execution_result

              • content: array of CodeExecutionOutputBlock

                • type: "code_execution_output"

                  default: code_execution_output

                • file_id: string

              • return_code: number

              • stderr: string

              • stdout: string

            • EncryptedCodeExecutionResultBlock 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 CodeExecutionOutputBlock

                • 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_]+$

        • BashCodeExecutionToolResultBlock object

          • type: "bash_code_execution_tool_result"

            default: bash_code_execution_tool_result

          • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

            • BashCodeExecutionToolResultError object

              • type: "bash_code_execution_tool_result_error"

                default: bash_code_execution_tool_result_error

              • error_code: BashCodeExecutionToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

                • "output_file_too_large"

            • BashCodeExecutionResultBlock object

              • type: "bash_code_execution_result"

                default: bash_code_execution_result

              • content: array of BashCodeExecutionOutputBlock

                • 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_]+$

        • TextEditorCodeExecutionToolResultBlock object

          • type: "text_editor_code_execution_tool_result"

            default: text_editor_code_execution_tool_result

          • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

            • TextEditorCodeExecutionToolResultError object

              • type: "text_editor_code_execution_tool_result_error"

                default: text_editor_code_execution_tool_result_error

              • error_code: TextEditorCodeExecutionToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

                • "file_not_found"

              • error_message: string or null

            • TextEditorCodeExecutionViewResultBlock 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

            • TextEditorCodeExecutionCreateResultBlock object

              • type: "text_editor_code_execution_create_result"

                default: text_editor_code_execution_create_result

              • is_file_update: boolean

            • TextEditorCodeExecutionStrReplaceResultBlock 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_]+$

        • ToolSearchToolResultBlock object

          • type: "tool_search_tool_result"

            default: tool_search_tool_result

          • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

            • ToolSearchToolResultError object

              • type: "tool_search_tool_result_error"

                default: tool_search_tool_result_error

              • error_code: ToolSearchToolResultErrorCode

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

              • error_message: string or null

            • ToolSearchToolSearchResultBlock object

              • type: "tool_search_tool_search_result"

                default: tool_search_tool_search_result

              • tool_references: array of ToolReferenceBlock

                • type: "tool_reference"

                  default: tool_reference

                • tool_name: string

                  maxLength: 256, minLength: 1, pattern: [123]{1,256}$

          • tool_use_id: string

            pattern: ^srvtoolu_[a-zA-Z0-9_]+$

        • ContainerUploadBlock object

          Response model for a file uploaded to the container.

          • type: "container_upload"

            default: container_upload

          • file_id: string

      • model: Model

        The model that will complete your prompt.

        See models 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 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

      • role: "assistant"

        Conversational role of the generated message.

        This will always be "assistant".

        default: assistant

      • stop_details: RefusalStopDetails 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. 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.

          • "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.

      • stop_reason: StopReason 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"

        • "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: Usage

        Billing and rate-limit usage.

        Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.

        Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.

        For example, output_tokens will be non-zero, even for an empty string response from Claude.

        Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.

        • cache_creation: CacheCreation 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

        • 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

        • output_tokens: number

          The number of output tokens which were used.

          minimum: 0

        • output_tokens_details: OutputTokensDetails 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: ServerToolUsage 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"

# Raw Message Stop Event

  • RawMessageStopEvent object

    • type: "message_stop"

      default: message_stop

# Raw Message Stream Event

  • RawMessageStreamEvent = RawMessageStartEvent or RawMessageDeltaEvent or RawMessageStopEvent or 3 more

    • RawMessageStartEvent object

      • type: "message_start"

        default: message_start

      • message: Message

        • type: "message"

          Object type.

          For Messages, this is always "message".

          default: message

        • id: string

          Unique object identifier.

          The format and length of IDs may change over time.

        • container: Container 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 ContainerSkill 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 ContentBlock

          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)"}]
          • TextBlock object

            • type: "text"

              default: text

            • citations: array of TextCitation 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.

              • CitationCharLocation 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

              • CitationPageLocation 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

              • CitationContentBlockLocation 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

              • CitationsWebSearchResultLocation 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

              • CitationsSearchResultLocation 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

          • ThinkingBlock 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 for details.

            • thinking: string

              The text of Claude's thinking process for this block.

          • RedactedThinkingBlock 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 for details.

          • ToolUseBlock object

            • type: "tool_use"

              default: tool_use

            • id: string

              pattern: [124]+$

            • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

              default: {"type":"direct"}

              • DirectCaller object

                Tool invocation directly from the model.

                • type: "direct"
              • ServerToolCaller object

                Tool invocation generated by a server-side tool.

                • type: "code_execution_20250825"

                • tool_id: string

                  pattern: ^srvtoolu_[a-zA-Z0-9_]+$

              • ServerToolCaller20260120 object

                • type: "code_execution_20260120"

                • tool_id: string

                  pattern: ^srvtoolu_[a-zA-Z0-9_]+$

            • input: map[unknown]

            • name: string

              minLength: 1

            • toolset_name: optional string or null

              For a toolset member tool_use, the toolset family.

              maxLength: 64, minLength: 1, pattern: [125]+$

          • ServerToolUseBlock object

            • type: "server_tool_use"

              default: server_tool_use

            • id: string

              pattern: ^srvtoolu_[a-zA-Z0-9_]+$

            • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

              default: {"type":"direct"}

              • DirectCaller object

                Tool invocation directly from the model.

              • ServerToolCaller object

                Tool invocation generated by a server-side tool.

              • ServerToolCaller20260120 object

            • input: map[unknown]

            • name: "web_search" or "web_fetch" or "code_execution" or 4 more

              • "web_search"

              • "web_fetch"

              • "code_execution"

              • "bash_code_execution"

              • "text_editor_code_execution"

              • "tool_search_tool_regex"

              • "tool_search_tool_bm25"

          • WebSearchToolResultBlock object

            • type: "web_search_tool_result"

              default: web_search_tool_result

            • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

              default: {"type":"direct"}

              • DirectCaller object

                Tool invocation directly from the model.

              • ServerToolCaller object

                Tool invocation generated by a server-side tool.

              • ServerToolCaller20260120 object

            • content: WebSearchToolResultBlockContent

              • WebSearchToolResultError object

                • type: "web_search_tool_result_error"

                  default: web_search_tool_result_error

                • error_code: WebSearchToolResultErrorCode

                  • "invalid_tool_input"

                  • "unavailable"

                  • "max_uses_exceeded"

                  • "too_many_requests"

                  • "query_too_long"

                  • "request_too_large"

              • array of WebSearchResultBlock

                • 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_]+$

          • WebFetchToolResultBlock object

            • type: "web_fetch_tool_result"

              default: web_fetch_tool_result

            • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

              default: {"type":"direct"}

              • DirectCaller object

                Tool invocation directly from the model.

              • ServerToolCaller object

                Tool invocation generated by a server-side tool.

              • ServerToolCaller20260120 object

            • content: WebFetchToolResultErrorBlock or WebFetchBlock

              • WebFetchToolResultErrorBlock object

                • type: "web_fetch_tool_result_error"

                  default: web_fetch_tool_result_error

                • error_code: WebFetchToolResultErrorCode

                  • "invalid_tool_input"

                  • "url_too_long"

                  • "url_not_allowed"

                  • "url_not_in_prior_context"

                  • "url_not_accessible"

                  • "unsupported_content_type"

                  • "too_many_requests"

                  • "max_uses_exceeded"

                  • "unavailable"

                  • "content_too_large"

              • WebFetchBlock object

                • type: "web_fetch_result"

                  default: web_fetch_result

                • content: DocumentBlock

                  • type: "document"

                    default: document

                  • citations: CitationsConfig or null

                    Citation configuration for the document

                    • enabled: boolean

                      default: false

                  • source: Base64PDFSource or PlainTextSource

                    • Base64PDFSource object

                      • type: "base64"

                      • data: string

                        format: byte

                      • media_type: "application/pdf"

                    • PlainTextSource 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_]+$

          • CodeExecutionToolResultBlock object

            • type: "code_execution_tool_result"

              default: code_execution_tool_result

            • content: CodeExecutionToolResultBlockContent

              • CodeExecutionToolResultError object

                • type: "code_execution_tool_result_error"

                  default: code_execution_tool_result_error

                • error_code: CodeExecutionToolResultErrorCode

                  • "invalid_tool_input"

                  • "unavailable"

                  • "too_many_requests"

                  • "execution_time_exceeded"

              • CodeExecutionResultBlock object

                • type: "code_execution_result"

                  default: code_execution_result

                • content: array of CodeExecutionOutputBlock

                  • type: "code_execution_output"

                    default: code_execution_output

                  • file_id: string

                • return_code: number

                • stderr: string

                • stdout: string

              • EncryptedCodeExecutionResultBlock 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 CodeExecutionOutputBlock

                  • 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_]+$

          • BashCodeExecutionToolResultBlock object

            • type: "bash_code_execution_tool_result"

              default: bash_code_execution_tool_result

            • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

              • BashCodeExecutionToolResultError object

                • type: "bash_code_execution_tool_result_error"

                  default: bash_code_execution_tool_result_error

                • error_code: BashCodeExecutionToolResultErrorCode

                  • "invalid_tool_input"

                  • "unavailable"

                  • "too_many_requests"

                  • "execution_time_exceeded"

                  • "output_file_too_large"

              • BashCodeExecutionResultBlock object

                • type: "bash_code_execution_result"

                  default: bash_code_execution_result

                • content: array of BashCodeExecutionOutputBlock

                  • 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_]+$

          • TextEditorCodeExecutionToolResultBlock object

            • type: "text_editor_code_execution_tool_result"

              default: text_editor_code_execution_tool_result

            • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

              • TextEditorCodeExecutionToolResultError object

                • type: "text_editor_code_execution_tool_result_error"

                  default: text_editor_code_execution_tool_result_error

                • error_code: TextEditorCodeExecutionToolResultErrorCode

                  • "invalid_tool_input"

                  • "unavailable"

                  • "too_many_requests"

                  • "execution_time_exceeded"

                  • "file_not_found"

                • error_message: string or null

              • TextEditorCodeExecutionViewResultBlock 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

              • TextEditorCodeExecutionCreateResultBlock object

                • type: "text_editor_code_execution_create_result"

                  default: text_editor_code_execution_create_result

                • is_file_update: boolean

              • TextEditorCodeExecutionStrReplaceResultBlock 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_]+$

          • ToolSearchToolResultBlock object

            • type: "tool_search_tool_result"

              default: tool_search_tool_result

            • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

              • ToolSearchToolResultError object

                • type: "tool_search_tool_result_error"

                  default: tool_search_tool_result_error

                • error_code: ToolSearchToolResultErrorCode

                  • "invalid_tool_input"

                  • "unavailable"

                  • "too_many_requests"

                  • "execution_time_exceeded"

                • error_message: string or null

              • ToolSearchToolSearchResultBlock object

                • type: "tool_search_tool_search_result"

                  default: tool_search_tool_search_result

                • tool_references: array of ToolReferenceBlock

                  • type: "tool_reference"

                    default: tool_reference

                  • tool_name: string

                    maxLength: 256, minLength: 1, pattern: [126]{1,256}$

            • tool_use_id: string

              pattern: ^srvtoolu_[a-zA-Z0-9_]+$

          • ContainerUploadBlock object

            Response model for a file uploaded to the container.

            • type: "container_upload"

              default: container_upload

            • file_id: string

        • model: Model

          The model that will complete your prompt.

          See models 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 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

        • role: "assistant"

          Conversational role of the generated message.

          This will always be "assistant".

          default: assistant

        • stop_details: RefusalStopDetails 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. 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.

            • "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.

        • stop_reason: StopReason 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"

          • "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: Usage

          Billing and rate-limit usage.

          Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.

          Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.

          For example, output_tokens will be non-zero, even for an empty string response from Claude.

          Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.

          • cache_creation: CacheCreation 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

          • 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

          • output_tokens: number

            The number of output tokens which were used.

            minimum: 0

          • output_tokens_details: OutputTokensDetails 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: ServerToolUsage 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"

    • RawMessageDeltaEvent object

      • type: "message_delta"

        default: message_delta

      • delta: object

        • container: Container or null

          Information about the container used in the request (for the code execution tool)

        • stop_details: RefusalStopDetails or null

          Structured information about a refusal.

        • stop_reason: StopReason or null

        • stop_sequence: string or null

      • usage: MessageDeltaUsage

        Billing and rate-limit usage.

        Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.

        Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.

        For example, output_tokens will be non-zero, even for an empty string response from Claude.

        Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.

        • cache_creation_input_tokens: number 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

        • input_tokens: number or null

          The cumulative number of input tokens which were used.

          minimum: 0

        • output_tokens: number

          The cumulative number of output tokens which were used.

        • output_tokens_details: OutputTokensDetails 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: ServerToolUsage or null

          The number of server tool requests.

    • RawMessageStopEvent object

      • type: "message_stop"

        default: message_stop

    • RawContentBlockStartEvent object

      • type: "content_block_start"

        default: content_block_start

      • content_block: TextBlock or ThinkingBlock or RedactedThinkingBlock or 9 more

        • TextBlock object

        • ThinkingBlock object

        • RedactedThinkingBlock object

        • ToolUseBlock object

        • ServerToolUseBlock object

        • WebSearchToolResultBlock object

        • WebFetchToolResultBlock object

        • CodeExecutionToolResultBlock object

        • BashCodeExecutionToolResultBlock object

        • TextEditorCodeExecutionToolResultBlock object

        • ToolSearchToolResultBlock object

        • ContainerUploadBlock object

          Response model for a file uploaded to the container.

      • index: number

    • RawContentBlockDeltaEvent object

      • type: "content_block_delta"

        default: content_block_delta

      • delta: RawContentBlockDelta

        • TextDelta object

          • type: "text_delta"

            default: text_delta

          • text: string

        • InputJSONDelta object

          • type: "input_json_delta"

            default: input_json_delta

          • partial_json: string

        • CitationsDelta object

          • type: "citations_delta"

            default: citations_delta

          • citation: CitationCharLocation or CitationPageLocation or CitationContentBlockLocation or 2 more

            • CitationCharLocation object

            • CitationPageLocation object

            • CitationContentBlockLocation object

            • CitationsWebSearchResultLocation object

            • CitationsSearchResultLocation object

        • ThinkingDelta object

          • type: "thinking_delta"

            default: thinking_delta

          • thinking: string

            The incremental thinking text for this content block. Concatenate the thinking values of successive thinking_delta events to assemble the block's full thinking value.

        • SignatureDelta 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.

      • index: number

    • RawContentBlockStopEvent object

      • type: "content_block_stop"

        default: content_block_stop

      • index: number

# Redacted Thinking Block

  • RedactedThinkingBlock 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 for details.

# Redacted Thinking Block Param

  • RedactedThinkingBlockParam 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.

# Refusal Stop Details

  • RefusalStopDetails 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. 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.

      • "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.

# Search Result Block Param

  • SearchResultBlockParam object

    • type: "search_result"

    • content: array of TextBlockParam

      • type: "text"

      • text: string

        minLength: 1

      • cache_control: optional CacheControlEphemeral 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 for details.

          • "5m"

          • "1h"

      • citations: optional array of TextCitationParam or null

        • CitationCharLocationParam 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

        • CitationPageLocationParam 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

        • CitationContentBlockLocationParam 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

        • CitationWebSearchResultLocationParam object

          • type: "web_search_result_location"

          • cited_text: string

          • encrypted_index: string

          • title: string or null

            maxLength: 512, minLength: 1

          • url: string

            minLength: 1

        • CitationSearchResultLocationParam 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 CacheControlEphemeral or null

      Create a cache control breakpoint at this content block.

    • citations: optional CitationsConfigParam

      • enabled: optional boolean

# Server Tool Caller

  • ServerToolCaller object

    Tool invocation generated by a server-side tool.

    • type: "code_execution_20250825"

    • tool_id: string

      pattern: ^srvtoolu_[a-zA-Z0-9_]+$

# Server Tool Caller 20260120

  • ServerToolCaller20260120 object

    • type: "code_execution_20260120"

    • tool_id: string

      pattern: ^srvtoolu_[a-zA-Z0-9_]+$

# Server Tool Usage

  • ServerToolUsage 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

# Server Tool Use Block

  • ServerToolUseBlock object

    • type: "server_tool_use"

      default: server_tool_use

    • id: string

      pattern: ^srvtoolu_[a-zA-Z0-9_]+$

    • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

      default: {"type":"direct"}

      • DirectCaller object

        Tool invocation directly from the model.

        • type: "direct"
      • ServerToolCaller object

        Tool invocation generated by a server-side tool.

        • type: "code_execution_20250825"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • ServerToolCaller20260120 object

        • type: "code_execution_20260120"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

    • input: map[unknown]

    • name: "web_search" or "web_fetch" or "code_execution" or 4 more

      • "web_search"

      • "web_fetch"

      • "code_execution"

      • "bash_code_execution"

      • "text_editor_code_execution"

      • "tool_search_tool_regex"

      • "tool_search_tool_bm25"

# Server Tool Use Block Param

  • ServerToolUseBlockParam object

    • type: "server_tool_use"

    • id: string

      pattern: ^srvtoolu_[a-zA-Z0-9_]+$

    • input: map[unknown]

    • name: "web_search" or "web_fetch" or "code_execution" or 4 more

      • "web_search"

      • "web_fetch"

      • "code_execution"

      • "bash_code_execution"

      • "text_editor_code_execution"

      • "tool_search_tool_regex"

      • "tool_search_tool_bm25"

    • cache_control: optional CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

      • DirectCaller object

        Tool invocation directly from the model.

        • type: "direct"
      • ServerToolCaller object

        Tool invocation generated by a server-side tool.

        • type: "code_execution_20250825"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • ServerToolCaller20260120 object

        • type: "code_execution_20260120"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

# Signature Delta

  • SignatureDelta 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.

# Skill Params

  • SkillParams 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

# Stop Reason

  • StopReason = "end_turn" or "max_tokens" or "stop_sequence" or 4 more

    • "end_turn"

    • "max_tokens"

    • "stop_sequence"

    • "tool_use"

    • "pause_turn"

    • "refusal"

    • "model_context_window_exceeded"

# Text Block

  • TextBlock object

    • type: "text"

      default: text

    • citations: array of TextCitation 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.

      • CitationCharLocation 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

      • CitationPageLocation 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

      • CitationContentBlockLocation 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

      • CitationsWebSearchResultLocation 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

      • CitationsSearchResultLocation 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

# Text Block Param

  • TextBlockParam object

    • type: "text"

    • text: string

      minLength: 1

    • cache_control: optional CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • citations: optional array of TextCitationParam or null

      • CitationCharLocationParam 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

      • CitationPageLocationParam 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

      • CitationContentBlockLocationParam 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

      • CitationWebSearchResultLocationParam object

        • type: "web_search_result_location"

        • cited_text: string

        • encrypted_index: string

        • title: string or null

          maxLength: 512, minLength: 1

        • url: string

          minLength: 1

      • CitationSearchResultLocationParam 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

# Text Citation

  • TextCitation = CitationCharLocation or CitationPageLocation or CitationContentBlockLocation or 2 more

    • CitationCharLocation 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

    • CitationPageLocation 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

    • CitationContentBlockLocation 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

    • CitationsWebSearchResultLocation 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

    • CitationsSearchResultLocation 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 Citation Param

  • TextCitationParam = CitationCharLocationParam or CitationPageLocationParam or CitationContentBlockLocationParam or 2 more

    • CitationCharLocationParam 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

    • CitationPageLocationParam 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

    • CitationContentBlockLocationParam 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

    • CitationWebSearchResultLocationParam object

      • type: "web_search_result_location"

      • cited_text: string

      • encrypted_index: string

      • title: string or null

        maxLength: 512, minLength: 1

      • url: string

        minLength: 1

    • CitationSearchResultLocationParam 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

# Text Delta

  • TextDelta object

    • type: "text_delta"

      default: text_delta

    • text: string

# Text Editor Code Execution Create Result Block

  • TextEditorCodeExecutionCreateResultBlock object

    • type: "text_editor_code_execution_create_result"

      default: text_editor_code_execution_create_result

    • is_file_update: boolean

# Text Editor Code Execution Create Result Block Param

  • TextEditorCodeExecutionCreateResultBlockParam object

    • type: "text_editor_code_execution_create_result"

    • is_file_update: boolean

# Text Editor Code Execution Str Replace Result Block

  • TextEditorCodeExecutionStrReplaceResultBlock 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

# Text Editor Code Execution Str Replace Result Block Param

  • TextEditorCodeExecutionStrReplaceResultBlockParam 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

# Text Editor Code Execution Tool Result Block

  • TextEditorCodeExecutionToolResultBlock object

    • type: "text_editor_code_execution_tool_result"

      default: text_editor_code_execution_tool_result

    • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

      • TextEditorCodeExecutionToolResultError object

        • type: "text_editor_code_execution_tool_result_error"

          default: text_editor_code_execution_tool_result_error

        • error_code: TextEditorCodeExecutionToolResultErrorCode

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

          • "file_not_found"

        • error_message: string or null

      • TextEditorCodeExecutionViewResultBlock 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

      • TextEditorCodeExecutionCreateResultBlock object

        • type: "text_editor_code_execution_create_result"

          default: text_editor_code_execution_create_result

        • is_file_update: boolean

      • TextEditorCodeExecutionStrReplaceResultBlock 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_]+$

# Text Editor Code Execution Tool Result Block Param

  • TextEditorCodeExecutionToolResultBlockParam object

    • type: "text_editor_code_execution_tool_result"

    • content: TextEditorCodeExecutionToolResultErrorParam or TextEditorCodeExecutionViewResultBlockParam or TextEditorCodeExecutionCreateResultBlockParam or TextEditorCodeExecutionStrReplaceResultBlockParam

      • TextEditorCodeExecutionToolResultErrorParam object

        • type: "text_editor_code_execution_tool_result_error"

        • error_code: TextEditorCodeExecutionToolResultErrorCode

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

          • "file_not_found"

        • error_message: optional string or null

      • TextEditorCodeExecutionViewResultBlockParam 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

      • TextEditorCodeExecutionCreateResultBlockParam object

        • type: "text_editor_code_execution_create_result"

        • is_file_update: boolean

      • TextEditorCodeExecutionStrReplaceResultBlockParam 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 CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

# Text Editor Code Execution Tool Result Error

  • TextEditorCodeExecutionToolResultError object

    • type: "text_editor_code_execution_tool_result_error"

      default: text_editor_code_execution_tool_result_error

    • error_code: TextEditorCodeExecutionToolResultErrorCode

      • "invalid_tool_input"

      • "unavailable"

      • "too_many_requests"

      • "execution_time_exceeded"

      • "file_not_found"

    • error_message: string or null

# Text Editor Code Execution Tool Result Error Code

  • TextEditorCodeExecutionToolResultErrorCode = "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"

# Text Editor Code Execution Tool Result Error Param

  • TextEditorCodeExecutionToolResultErrorParam object

    • type: "text_editor_code_execution_tool_result_error"

    • error_code: TextEditorCodeExecutionToolResultErrorCode

      • "invalid_tool_input"

      • "unavailable"

      • "too_many_requests"

      • "execution_time_exceeded"

      • "file_not_found"

    • error_message: optional string or null

# Text Editor Code Execution View Result Block

  • TextEditorCodeExecutionViewResultBlock 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

# Text Editor Code Execution View Result Block Param

  • TextEditorCodeExecutionViewResultBlockParam 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

# Thinking Block

  • ThinkingBlock 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 for details.

    • thinking: string

      The text of Claude's thinking process for this block.

# Thinking Block Param

  • ThinkingBlockParam 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.

# Thinking Config Adaptive

  • ThinkingConfigAdaptive object

    • type: "adaptive"

    • display: optional "summarized" or "omitted" or null

      Controls how thinking content appears in the response. When set to summarized, thinking is returned normally. When set to omitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to summarized.

      • "summarized"

      • "omitted"

# Thinking Config Disabled

  • ThinkingConfigDisabled object

    • type: "disabled"

# Thinking Config Enabled

  • ThinkingConfigEnabled 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 for details.

      minimum: 1024

    • display: optional "summarized" or "omitted" or null

      Controls how thinking content appears in the response. When set to summarized, thinking is returned normally. When set to omitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to summarized.

      • "summarized"

      • "omitted"

# Thinking Config Param

  • ThinkingConfigParam = ThinkingConfigEnabled or ThinkingConfigDisabled or ThinkingConfigAdaptive

    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 for details.

    • ThinkingConfigEnabled 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 for details.

        minimum: 1024

      • display: optional "summarized" or "omitted" or null

        Controls how thinking content appears in the response. When set to summarized, thinking is returned normally. When set to omitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to summarized.

        • "summarized"

        • "omitted"

    • ThinkingConfigDisabled object

      • type: "disabled"
    • ThinkingConfigAdaptive object

      • type: "adaptive"

      • display: optional "summarized" or "omitted" or null

        Controls how thinking content appears in the response. When set to summarized, thinking is returned normally. When set to omitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to summarized.

        • "summarized"

        • "omitted"

# Thinking Delta

  • ThinkingDelta object

    • type: "thinking_delta"

      default: thinking_delta

    • thinking: string

      The incremental thinking text for this content block. Concatenate the thinking values of successive thinking_delta events to assemble the block's full thinking value.

# Tool

  • Tool object

    • type: optional "custom" or null

    • input_schema: object

      JSON schema 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: [127]{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 CacheControlEphemeral 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 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

# Tool Bash 20250124

  • ToolBash20250124 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 CacheControlEphemeral 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 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

# Tool Choice

  • ToolChoice = ToolChoiceAuto or ToolChoiceAny or ToolChoiceTool or ToolChoiceNone

    How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.

    • ToolChoiceAuto object

      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.

    • ToolChoiceAny 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.

    • ToolChoiceTool 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.

    • ToolChoiceNone object

      The model will not be allowed to use tools.

      • type: "none"

# Tool Choice Any

  • ToolChoiceAny 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.

# Tool Choice Auto

  • ToolChoiceAuto 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.

# Tool Choice None

  • ToolChoiceNone object

    The model will not be allowed to use tools.

    • type: "none"

# Tool Choice Tool

  • ToolChoiceTool 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.

# Tool Reference Block

  • ToolReferenceBlock object

    • type: "tool_reference"

      default: tool_reference

    • tool_name: string

      maxLength: 256, minLength: 1, pattern: [128]{1,256}$

# Tool Reference Block Param

  • ToolReferenceBlockParam object

    Tool reference block that can be included in tool_result content.

    • type: "tool_reference"

    • tool_name: string

      maxLength: 256, minLength: 1, pattern: [129]{1,256}$

    • cache_control: optional CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

# Tool Result Block Param

  • ToolResultBlockParam object

    • type: "tool_result"

    • tool_use_id: string

      pattern: [130]+$

    • cache_control: optional CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • content: optional string or array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more

      • string

      • array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more

        • TextBlockParam object

          • type: "text"

          • text: string

            minLength: 1

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional array of TextCitationParam or null

            • CitationCharLocationParam 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

            • CitationPageLocationParam 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

            • CitationContentBlockLocationParam 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

            • CitationWebSearchResultLocationParam object

              • type: "web_search_result_location"

              • cited_text: string

              • encrypted_index: string

              • title: string or null

                maxLength: 512, minLength: 1

              • url: string

                minLength: 1

            • CitationSearchResultLocationParam 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

        • ImageBlockParam object

          • type: "image"

          • source: Base64ImageSource or URLImageSource or FileImageSource

            • Base64ImageSource 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"

            • URLImageSource object

              • type: "url"

              • url: string

            • FileImageSource object

              • type: "file"

              • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • transformations: optional ImageTransformationsParam 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"

        • SearchResultBlockParam object

          • type: "search_result"

          • content: array of TextBlockParam

            • type: "text"

            • text: string

              minLength: 1

            • cache_control: optional CacheControlEphemeral or null

              Create a cache control breakpoint at this content block.

            • citations: optional array of TextCitationParam or null

          • source: string

          • title: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam

            • enabled: optional boolean
        • DocumentBlockParam object

          • type: "document"

          • source: Base64PDFSource or PlainTextSource or ContentBlockSource or 2 more

            • Base64PDFSource object

              • type: "base64"

              • data: string

                format: byte

              • media_type: "application/pdf"

            • PlainTextSource object

              • type: "text"

              • data: string

              • media_type: "text/plain"

            • ContentBlockSource object

              • type: "content"

              • content: string or array of ContentBlockSourceContent

                • string

                • ContentBlockSourceContent = array of ContentBlockSourceContent

                  • TextBlockParam object

                  • ImageBlockParam object

            • URLPDFSource object

              • type: "url"

              • url: string

            • FileDocumentSource object

              • type: "file"

              • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam or null

          • context: optional string or null

            minLength: 1

          • title: optional string or null

            maxLength: 500, minLength: 1

        • ToolReferenceBlockParam object

          Tool reference block that can be included in tool_result content.

          • type: "tool_reference"

          • tool_name: string

            maxLength: 256, minLength: 1, pattern: [131]{1,256}$

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

        • BrowserStateBlockParam object

          The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side 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 BrowserStateTabEntry

            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: [132]*$

            • title: string

              The title of the page the tab is showing. May be empty.

              maxLength: 4096, pattern: [133]*$

            • url: string

              The URL of the page the tab is showing. May be empty.

              maxLength: 4096, pattern: [134]*$

            • 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • state_changes: optional array of BrowserStateChange 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

            • BrowserStateChangeTabOpened object

              A tab this call's execution opened that remains open at its end — the creation delta of the tabs inventory, not an event log.

              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: [135]*$

            • BrowserStateChangeDownloadStarted 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: [136]*$

              • url: string

                The final post-redirect URL the download was served from.

                maxLength: 4096, pattern: [137]*$

            • BrowserStateChangeDownloadCompleted 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: [138]*$

              • url: string

                The final post-redirect URL the download was served from.

                maxLength: 4096, pattern: [139]*$

              • 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: [140]*$, maxLength: 4096

              • size_bytes: optional number or null

                The completed download's size.

                minimum: 0

            • BrowserStateChangeDownloadFailed 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: [141]*$

              • url: string

                The final post-redirect URL the download was served from.

                maxLength: 4096, pattern: [142]*$

              • error: optional string or null

                The failure or cancellation detail, when known.

                pattern: [143]*$, 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: [144]+$

# Tool Search Tool Bm25 20251119

  • ToolSearchToolBm25_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 CacheControlEphemeral 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 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

# Tool Search Tool Regex 20251119

  • ToolSearchToolRegex20251119 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 CacheControlEphemeral 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 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

# Tool Search Tool Result Block

  • ToolSearchToolResultBlock object

    • type: "tool_search_tool_result"

      default: tool_search_tool_result

    • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

      • ToolSearchToolResultError object

        • type: "tool_search_tool_result_error"

          default: tool_search_tool_result_error

        • error_code: ToolSearchToolResultErrorCode

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

        • error_message: string or null

      • ToolSearchToolSearchResultBlock object

        • type: "tool_search_tool_search_result"

          default: tool_search_tool_search_result

        • tool_references: array of ToolReferenceBlock

          • type: "tool_reference"

            default: tool_reference

          • tool_name: string

            maxLength: 256, minLength: 1, pattern: [145]{1,256}$

    • tool_use_id: string

      pattern: ^srvtoolu_[a-zA-Z0-9_]+$

# Tool Search Tool Result Block Param

  • ToolSearchToolResultBlockParam object

    • type: "tool_search_tool_result"

    • content: ToolSearchToolResultErrorParam or ToolSearchToolSearchResultBlockParam

      • ToolSearchToolResultErrorParam object

        • type: "tool_search_tool_result_error"

        • error_code: ToolSearchToolResultErrorCode

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

        • error_message: optional string or null

      • ToolSearchToolSearchResultBlockParam object

        • type: "tool_search_tool_search_result"

        • tool_references: array of ToolReferenceBlockParam

          • type: "tool_reference"

          • tool_name: string

            maxLength: 256, minLength: 1, pattern: [146]{1,256}$

          • cache_control: optional CacheControlEphemeral 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 for details.

              • "5m"

              • "1h"

    • tool_use_id: string

      pattern: ^srvtoolu_[a-zA-Z0-9_]+$

    • cache_control: optional CacheControlEphemeral or null

      Create a cache control breakpoint at this content block.

# Tool Search Tool Result Error

  • ToolSearchToolResultError object

    • type: "tool_search_tool_result_error"

      default: tool_search_tool_result_error

    • error_code: ToolSearchToolResultErrorCode

      • "invalid_tool_input"

      • "unavailable"

      • "too_many_requests"

      • "execution_time_exceeded"

    • error_message: string or null

# Tool Search Tool Result Error Code

  • ToolSearchToolResultErrorCode = "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

    • "invalid_tool_input"

    • "unavailable"

    • "too_many_requests"

    • "execution_time_exceeded"

# Tool Search Tool Result Error Param

  • ToolSearchToolResultErrorParam object

    • type: "tool_search_tool_result_error"

    • error_code: ToolSearchToolResultErrorCode

      • "invalid_tool_input"

      • "unavailable"

      • "too_many_requests"

      • "execution_time_exceeded"

    • error_message: optional string or null

# Tool Search Tool Search Result Block

  • ToolSearchToolSearchResultBlock object

    • type: "tool_search_tool_search_result"

      default: tool_search_tool_search_result

    • tool_references: array of ToolReferenceBlock

      • type: "tool_reference"

        default: tool_reference

      • tool_name: string

        maxLength: 256, minLength: 1, pattern: [147]{1,256}$

# Tool Search Tool Search Result Block Param

  • ToolSearchToolSearchResultBlockParam object

    • type: "tool_search_tool_search_result"

    • tool_references: array of ToolReferenceBlockParam

      • type: "tool_reference"

      • tool_name: string

        maxLength: 256, minLength: 1, pattern: [148]{1,256}$

      • cache_control: optional CacheControlEphemeral 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 for details.

          • "5m"

          • "1h"

# Tool Text Editor 20250124

  • ToolTextEditor20250124 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 CacheControlEphemeral 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 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

# Tool Text Editor 20250429

  • ToolTextEditor20250429 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 CacheControlEphemeral 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 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

# Tool Text Editor 20250728

  • ToolTextEditor20250728 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 CacheControlEphemeral 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 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

# Tool Union

  • ToolUnion = Tool or ToolBash20250124 or CodeExecutionTool20250522 or 18 more

    • Tool object

      • type: optional "custom" or null

      • input_schema: object

        JSON schema 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: [149]{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 CacheControlEphemeral 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 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

    • ToolBash20250124 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20250522 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20250825 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20260120 object

      Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint).

      • 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • CodeExecutionTool20260521 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • BrowserToolset20260801 object

      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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • configs: optional BrowserToolsetConfigs 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 BrowserTypeConfig 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 BrowserCloseTabConfig 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 BrowserDoubleClickConfig 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 BrowserFileUploadConfig 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 BrowserFindConfig 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 BrowserFormInputConfig 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 BrowserGetPageTextConfig 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 BrowserHoldKeyConfig 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 BrowserHoverConfig 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 BrowserJavascriptExecConfig 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 BrowserKeyConfig 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 BrowserLeftClickConfig 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 BrowserLeftClickDragConfig 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 BrowserLeftMouseDownConfig 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 BrowserLeftMouseUpConfig 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 BrowserListTabsConfig 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 BrowserMiddleClickConfig 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 BrowserMouseMoveConfig 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 BrowserNavigateConfig 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 BrowserNewTabConfig 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 BrowserReadConsoleConfig 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 BrowserReadNetworkConfig 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 BrowserReadPageConfig 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 BrowserRightClickConfig 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 BrowserScreenshotConfig 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 BrowserScrollConfig 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 BrowserScrollToConfig 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 BrowserSwitchTabConfig 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 BrowserTripleClickConfig 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 BrowserWaitConfig 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 BrowserZoomConfig 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.

    • MemoryTool20250818 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ComputerToolset20260801 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • configs: optional ComputerToolsetConfigs 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 ComputerTypeConfig 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 ComputerCursorPositionConfig 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 ComputerDoubleClickConfig 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 ComputerHoldKeyConfig 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 ComputerKeyConfig 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 ComputerLeftClickConfig 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 ComputerLeftClickDragConfig 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 ComputerLeftMouseDownConfig 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 ComputerLeftMouseUpConfig 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 ComputerMiddleClickConfig 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 ComputerMouseMoveConfig 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 ComputerRightClickConfig 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 ComputerScreenshotConfig 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 ComputerScrollConfig 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 ComputerTripleClickConfig 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 ComputerWaitConfig 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 ComputerZoomConfig 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.

    • ToolTextEditor20250124 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ToolTextEditor20250429 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • input_examples: optional array of map[unknown]

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ToolTextEditor20250728 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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

    • WebSearchTool20250305 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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 UserLocation 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 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 of the user.

          maxLength: 255, minLength: 1

    • WebFetchTool20250910 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

        • client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

          Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].

          • WebFetchURLSourceAll object

            The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

            • type: "all"
          • WebFetchURLSourceNone object

            The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

            • type: "none"
          • WebFetchURLSourceOnly object

            The tool filter variant under which only the named tools' results contribute.

            • type: "only"

            • tools: array of WebFetchURLSourceToolReference

              • type: "tool_reference"

              • name: string

          • WebFetchURLSourceExcept object

            The tool filter variant under which every result but the named tools' contributes.

            • type: "except"

            • tools: array of WebFetchURLSourceToolReference

              • type: "tool_reference"

              • name: string

        • server_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

          Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute.

          • WebFetchURLSourceAll object

            The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

          • WebFetchURLSourceNone object

            The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

          • WebFetchURLSourceOnly object

            The tool filter variant under which only the named tools' results contribute.

          • WebFetchURLSourceExcept object

            The tool filter variant under which every result but the named tools' contributes.

        • user_input: optional WebFetchURLSourceAll or WebFetchURLSourceNone

          Whether URLs in user messages are fetchable: "all" or "none".

          • WebFetchURLSourceAll object

            The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

          • WebFetchURLSourceNone object

            The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

    • WebSearchTool20260209 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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 UserLocation or null

        Parameters for the user's location. Used to provide more relevant search results.

    • WebFetchTool20260209 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

    • WebFetchTool20260309 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

      • 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.

    • WebSearchTool20260318 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • 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 UserLocation or null

        Parameters for the user's location. Used to provide more relevant search results.

    • WebFetchTool20260318 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

      • url_sources: optional WebFetchURLSources or null

        Which sources contribute to the set of URLs web fetch may fetch.

        Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

      • 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.

    • ToolSearchToolBm25_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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

    • ToolSearchToolRegex20251119 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 CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • defer_loading: optional boolean

        If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

      • strict: optional boolean

        When true, guarantees schema validation on tool names and inputs

# Tool Use Block

  • ToolUseBlock object

    • type: "tool_use"

      default: tool_use

    • id: string

      pattern: [150]+$

    • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

      default: {"type":"direct"}

      • DirectCaller object

        Tool invocation directly from the model.

        • type: "direct"
      • ServerToolCaller object

        Tool invocation generated by a server-side tool.

        • type: "code_execution_20250825"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • ServerToolCaller20260120 object

        • type: "code_execution_20260120"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

    • input: map[unknown]

    • name: string

      minLength: 1

    • toolset_name: optional string or null

      For a toolset member tool_use, the toolset family.

      maxLength: 64, minLength: 1, pattern: [151]+$

# Tool Use Block Param

  • ToolUseBlockParam object

    • type: "tool_use"

    • id: string

      pattern: [152]+$

    • input: map[unknown]

    • name: string

      maxLength: 200, minLength: 1

    • cache_control: optional CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

      • DirectCaller object

        Tool invocation directly from the model.

        • type: "direct"
      • ServerToolCaller object

        Tool invocation generated by a server-side tool.

        • type: "code_execution_20250825"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • ServerToolCaller20260120 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: [153]+$

# URL Image Source

  • URLImageSource object

    • type: "url"

    • url: string

# URL PDF Source

  • URLPDFSource object

    • type: "url"

    • url: string

# Usage

  • Usage object

    • cache_creation: CacheCreation 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

    • 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

    • output_tokens: number

      The number of output tokens which were used.

      minimum: 0

    • output_tokens_details: OutputTokensDetails 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: ServerToolUsage 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"

# User Location

  • UserLocation 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 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 of the user.

      maxLength: 255, minLength: 1

# Web Fetch Block

  • WebFetchBlock object

    • type: "web_fetch_result"

      default: web_fetch_result

    • content: DocumentBlock

      • type: "document"

        default: document

      • citations: CitationsConfig or null

        Citation configuration for the document

        • enabled: boolean

          default: false

      • source: Base64PDFSource or PlainTextSource

        • Base64PDFSource object

          • type: "base64"

          • data: string

            format: byte

          • media_type: "application/pdf"

        • PlainTextSource 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

# Web Fetch Block Param

  • WebFetchBlockParam object

    • type: "web_fetch_result"

    • content: DocumentBlockParam

      • type: "document"

      • source: Base64PDFSource or PlainTextSource or ContentBlockSource or 2 more

        • Base64PDFSource object

          • type: "base64"

          • data: string

            format: byte

          • media_type: "application/pdf"

        • PlainTextSource object

          • type: "text"

          • data: string

          • media_type: "text/plain"

        • ContentBlockSource object

          • type: "content"

          • content: string or array of ContentBlockSourceContent

            • string

            • ContentBlockSourceContent = array of ContentBlockSourceContent

              • TextBlockParam object

                • type: "text"

                • text: string

                  minLength: 1

                • cache_control: optional CacheControlEphemeral 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 for details.

                    • "5m"

                    • "1h"

                • citations: optional array of TextCitationParam or null

                  • CitationCharLocationParam 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

                  • CitationPageLocationParam 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

                  • CitationContentBlockLocationParam 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

                  • CitationWebSearchResultLocationParam object

                    • type: "web_search_result_location"

                    • cited_text: string

                    • encrypted_index: string

                    • title: string or null

                      maxLength: 512, minLength: 1

                    • url: string

                      minLength: 1

                  • CitationSearchResultLocationParam 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

              • ImageBlockParam object

                • type: "image"

                • source: Base64ImageSource or URLImageSource or FileImageSource

                  • Base64ImageSource 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"

                  • URLImageSource object

                    • type: "url"

                    • url: string

                  • FileImageSource object

                    • type: "file"

                    • file_id: string

                • cache_control: optional CacheControlEphemeral or null

                  Create a cache control breakpoint at this content block.

                • transformations: optional ImageTransformationsParam 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"

        • URLPDFSource object

          • type: "url"

          • url: string

        • FileDocumentSource object

          • type: "file"

          • file_id: string

      • cache_control: optional CacheControlEphemeral or null

        Create a cache control breakpoint at this content block.

      • citations: optional CitationsConfigParam 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

# Web Fetch Tool 20250910

  • WebFetchTool20250910 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 CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • citations: optional CitationsConfigParam 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

    • url_sources: optional WebFetchURLSources or null

      Which sources contribute to the set of URLs web fetch may fetch.

      Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

      • client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

        Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].

        • WebFetchURLSourceAll object

          The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

          • type: "all"
        • WebFetchURLSourceNone object

          The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

          • type: "none"
        • WebFetchURLSourceOnly object

          The tool filter variant under which only the named tools' results contribute.

          • type: "only"

          • tools: array of WebFetchURLSourceToolReference

            • type: "tool_reference"

            • name: string

        • WebFetchURLSourceExcept object

          The tool filter variant under which every result but the named tools' contributes.

          • type: "except"

          • tools: array of WebFetchURLSourceToolReference

            • type: "tool_reference"

            • name: string

      • server_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

        Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute.

        • WebFetchURLSourceAll object

          The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

        • WebFetchURLSourceNone object

          The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

        • WebFetchURLSourceOnly object

          The tool filter variant under which only the named tools' results contribute.

        • WebFetchURLSourceExcept object

          The tool filter variant under which every result but the named tools' contributes.

      • user_input: optional WebFetchURLSourceAll or WebFetchURLSourceNone

        Whether URLs in user messages are fetchable: "all" or "none".

        • WebFetchURLSourceAll object

          The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

        • WebFetchURLSourceNone object

          The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

# Web Fetch Tool 20260209

  • WebFetchTool20260209 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 CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • citations: optional CitationsConfigParam 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

    • url_sources: optional WebFetchURLSources or null

      Which sources contribute to the set of URLs web fetch may fetch.

      Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

      • client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

        Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].

        • WebFetchURLSourceAll object

          The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

          • type: "all"
        • WebFetchURLSourceNone object

          The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

          • type: "none"
        • WebFetchURLSourceOnly object

          The tool filter variant under which only the named tools' results contribute.

          • type: "only"

          • tools: array of WebFetchURLSourceToolReference

            • type: "tool_reference"

            • name: string

        • WebFetchURLSourceExcept object

          The tool filter variant under which every result but the named tools' contributes.

          • type: "except"

          • tools: array of WebFetchURLSourceToolReference

            • type: "tool_reference"

            • name: string

      • server_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

        Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute.

        • WebFetchURLSourceAll object

          The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

        • WebFetchURLSourceNone object

          The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

        • WebFetchURLSourceOnly object

          The tool filter variant under which only the named tools' results contribute.

        • WebFetchURLSourceExcept object

          The tool filter variant under which every result but the named tools' contributes.

      • user_input: optional WebFetchURLSourceAll or WebFetchURLSourceNone

        Whether URLs in user messages are fetchable: "all" or "none".

        • WebFetchURLSourceAll object

          The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

        • WebFetchURLSourceNone object

          The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

# Web Fetch Tool 20260309

  • WebFetchTool20260309 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 CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • citations: optional CitationsConfigParam 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

    • url_sources: optional WebFetchURLSources or null

      Which sources contribute to the set of URLs web fetch may fetch.

      Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

      • client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

        Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].

        • WebFetchURLSourceAll object

          The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

          • type: "all"
        • WebFetchURLSourceNone object

          The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

          • type: "none"
        • WebFetchURLSourceOnly object

          The tool filter variant under which only the named tools' results contribute.

          • type: "only"

          • tools: array of WebFetchURLSourceToolReference

            • type: "tool_reference"

            • name: string

        • WebFetchURLSourceExcept object

          The tool filter variant under which every result but the named tools' contributes.

          • type: "except"

          • tools: array of WebFetchURLSourceToolReference

            • type: "tool_reference"

            • name: string

      • server_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

        Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute.

        • WebFetchURLSourceAll object

          The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

        • WebFetchURLSourceNone object

          The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

        • WebFetchURLSourceOnly object

          The tool filter variant under which only the named tools' results contribute.

        • WebFetchURLSourceExcept object

          The tool filter variant under which every result but the named tools' contributes.

      • user_input: optional WebFetchURLSourceAll or WebFetchURLSourceNone

        Whether URLs in user messages are fetchable: "all" or "none".

        • WebFetchURLSourceAll object

          The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

        • WebFetchURLSourceNone object

          The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

    • 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.

# Web Fetch Tool 20260318

  • WebFetchTool20260318 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 CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • citations: optional CitationsConfigParam 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

    • url_sources: optional WebFetchURLSources or null

      Which sources contribute to the set of URLs web fetch may fetch.

      Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

      • client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

        Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].

        • WebFetchURLSourceAll object

          The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

          • type: "all"
        • WebFetchURLSourceNone object

          The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

          • type: "none"
        • WebFetchURLSourceOnly object

          The tool filter variant under which only the named tools' results contribute.

          • type: "only"

          • tools: array of WebFetchURLSourceToolReference

            • type: "tool_reference"

            • name: string

        • WebFetchURLSourceExcept object

          The tool filter variant under which every result but the named tools' contributes.

          • type: "except"

          • tools: array of WebFetchURLSourceToolReference

            • type: "tool_reference"

            • name: string

      • server_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

        Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute.

        • WebFetchURLSourceAll object

          The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

        • WebFetchURLSourceNone object

          The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

        • WebFetchURLSourceOnly object

          The tool filter variant under which only the named tools' results contribute.

        • WebFetchURLSourceExcept object

          The tool filter variant under which every result but the named tools' contributes.

      • user_input: optional WebFetchURLSourceAll or WebFetchURLSourceNone

        Whether URLs in user messages are fetchable: "all" or "none".

        • WebFetchURLSourceAll object

          The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

        • WebFetchURLSourceNone object

          The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

    • 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.

# Web Fetch Tool Result Block

  • WebFetchToolResultBlock object

    • type: "web_fetch_tool_result"

      default: web_fetch_tool_result

    • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

      default: {"type":"direct"}

      • DirectCaller object

        Tool invocation directly from the model.

        • type: "direct"
      • ServerToolCaller object

        Tool invocation generated by a server-side tool.

        • type: "code_execution_20250825"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • ServerToolCaller20260120 object

        • type: "code_execution_20260120"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

    • content: WebFetchToolResultErrorBlock or WebFetchBlock

      • WebFetchToolResultErrorBlock object

        • type: "web_fetch_tool_result_error"

          default: web_fetch_tool_result_error

        • error_code: WebFetchToolResultErrorCode

          • "invalid_tool_input"

          • "url_too_long"

          • "url_not_allowed"

          • "url_not_in_prior_context"

          • "url_not_accessible"

          • "unsupported_content_type"

          • "too_many_requests"

          • "max_uses_exceeded"

          • "unavailable"

          • "content_too_large"

      • WebFetchBlock object

        • type: "web_fetch_result"

          default: web_fetch_result

        • content: DocumentBlock

          • type: "document"

            default: document

          • citations: CitationsConfig or null

            Citation configuration for the document

            • enabled: boolean

              default: false

          • source: Base64PDFSource or PlainTextSource

            • Base64PDFSource object

              • type: "base64"

              • data: string

                format: byte

              • media_type: "application/pdf"

            • PlainTextSource 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_]+$

# Web Fetch Tool Result Block Param

  • WebFetchToolResultBlockParam object

    • type: "web_fetch_tool_result"

    • content: WebFetchToolResultErrorBlockParam or WebFetchBlockParam

      • WebFetchToolResultErrorBlockParam object

        • type: "web_fetch_tool_result_error"

        • error_code: WebFetchToolResultErrorCode

          • "invalid_tool_input"

          • "url_too_long"

          • "url_not_allowed"

          • "url_not_in_prior_context"

          • "url_not_accessible"

          • "unsupported_content_type"

          • "too_many_requests"

          • "max_uses_exceeded"

          • "unavailable"

          • "content_too_large"

      • WebFetchBlockParam object

        • type: "web_fetch_result"

        • content: DocumentBlockParam

          • type: "document"

          • source: Base64PDFSource or PlainTextSource or ContentBlockSource or 2 more

            • Base64PDFSource object

              • type: "base64"

              • data: string

                format: byte

              • media_type: "application/pdf"

            • PlainTextSource object

              • type: "text"

              • data: string

              • media_type: "text/plain"

            • ContentBlockSource object

              • type: "content"

              • content: string or array of ContentBlockSourceContent

                • string

                • ContentBlockSourceContent = array of ContentBlockSourceContent

                  • TextBlockParam object

                    • type: "text"

                    • text: string

                      minLength: 1

                    • cache_control: optional CacheControlEphemeral 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 for details.

                        • "5m"

                        • "1h"

                    • citations: optional array of TextCitationParam or null

                      • CitationCharLocationParam 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

                      • CitationPageLocationParam 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

                      • CitationContentBlockLocationParam 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

                      • CitationWebSearchResultLocationParam object

                        • type: "web_search_result_location"

                        • cited_text: string

                        • encrypted_index: string

                        • title: string or null

                          maxLength: 512, minLength: 1

                        • url: string

                          minLength: 1

                      • CitationSearchResultLocationParam 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

                  • ImageBlockParam object

                    • type: "image"

                    • source: Base64ImageSource or URLImageSource or FileImageSource

                      • Base64ImageSource 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"

                      • URLImageSource object

                        • type: "url"

                        • url: string

                      • FileImageSource object

                        • type: "file"

                        • file_id: string

                    • cache_control: optional CacheControlEphemeral or null

                      Create a cache control breakpoint at this content block.

                    • transformations: optional ImageTransformationsParam 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"

            • URLPDFSource object

              • type: "url"

              • url: string

            • FileDocumentSource object

              • type: "file"

              • file_id: string

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam 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 CacheControlEphemeral or null

      Create a cache control breakpoint at this content block.

    • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

      • DirectCaller object

        Tool invocation directly from the model.

        • type: "direct"
      • ServerToolCaller object

        Tool invocation generated by a server-side tool.

        • type: "code_execution_20250825"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • ServerToolCaller20260120 object

        • type: "code_execution_20260120"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

# Web Fetch Tool Result Error Block

  • WebFetchToolResultErrorBlock object

    • type: "web_fetch_tool_result_error"

      default: web_fetch_tool_result_error

    • error_code: WebFetchToolResultErrorCode

      • "invalid_tool_input"

      • "url_too_long"

      • "url_not_allowed"

      • "url_not_in_prior_context"

      • "url_not_accessible"

      • "unsupported_content_type"

      • "too_many_requests"

      • "max_uses_exceeded"

      • "unavailable"

      • "content_too_large"

# Web Fetch Tool Result Error Block Param

  • WebFetchToolResultErrorBlockParam object

    • type: "web_fetch_tool_result_error"

    • error_code: WebFetchToolResultErrorCode

      • "invalid_tool_input"

      • "url_too_long"

      • "url_not_allowed"

      • "url_not_in_prior_context"

      • "url_not_accessible"

      • "unsupported_content_type"

      • "too_many_requests"

      • "max_uses_exceeded"

      • "unavailable"

      • "content_too_large"

# Web Fetch Tool Result Error Code

  • WebFetchToolResultErrorCode = "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"

# Web Fetch URL Source All

  • WebFetchURLSourceAll object

    The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

    • type: "all"

# Web Fetch URL Source Except

  • WebFetchURLSourceExcept object

    The tool filter variant under which every result but the named tools' contributes.

    • type: "except"

    • tools: array of WebFetchURLSourceToolReference

      • type: "tool_reference"

      • name: string

# Web Fetch URL Source None

  • WebFetchURLSourceNone object

    The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

    • type: "none"

# Web Fetch URL Source Only

  • WebFetchURLSourceOnly object

    The tool filter variant under which only the named tools' results contribute.

    • type: "only"

    • tools: array of WebFetchURLSourceToolReference

      • type: "tool_reference"

      • name: string

# Web Fetch URL Source Tool Reference

  • WebFetchURLSourceToolReference object

    One entry of a tool filter's tools: it must name a tool declared in this request's tools[].

    • type: "tool_reference"

    • name: string

# Web Fetch URL Sources

  • WebFetchURLSources object

    Which sources contribute to the set of URLs web fetch may fetch.

    Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

    • client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

      Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].

      • WebFetchURLSourceAll object

        The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

        • type: "all"
      • WebFetchURLSourceNone object

        The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

        • type: "none"
      • WebFetchURLSourceOnly object

        The tool filter variant under which only the named tools' results contribute.

        • type: "only"

        • tools: array of WebFetchURLSourceToolReference

          • type: "tool_reference"

          • name: string

      • WebFetchURLSourceExcept object

        The tool filter variant under which every result but the named tools' contributes.

        • type: "except"

        • tools: array of WebFetchURLSourceToolReference

          • type: "tool_reference"

          • name: string

    • server_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

      Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute.

      • WebFetchURLSourceAll object

        The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

      • WebFetchURLSourceNone object

        The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

      • WebFetchURLSourceOnly object

        The tool filter variant under which only the named tools' results contribute.

      • WebFetchURLSourceExcept object

        The tool filter variant under which every result but the named tools' contributes.

    • user_input: optional WebFetchURLSourceAll or WebFetchURLSourceNone

      Whether URLs in user messages are fetchable: "all" or "none".

      • WebFetchURLSourceAll object

        The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

      • WebFetchURLSourceNone object

        The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

# Web Search Result Block

  • WebSearchResultBlock object

    • type: "web_search_result"

      default: web_search_result

    • encrypted_content: string

    • page_age: string or null

    • title: string

    • url: string

# Web Search Result Block Param

  • WebSearchResultBlockParam object

    • type: "web_search_result"

    • encrypted_content: string

    • title: string

    • url: string

    • page_age: optional string or null

# Web Search Tool 20250305

  • WebSearchTool20250305 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 CacheControlEphemeral 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 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 UserLocation 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 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 of the user.

        maxLength: 255, minLength: 1

# Web Search Tool 20260209

  • WebSearchTool20260209 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 CacheControlEphemeral 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 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 UserLocation 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 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 of the user.

        maxLength: 255, minLength: 1

# Web Search Tool 20260318

  • WebSearchTool20260318 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 CacheControlEphemeral 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 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 UserLocation 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 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 of the user.

        maxLength: 255, minLength: 1

# Web Search Tool Request Error

  • WebSearchToolRequestError object

    • type: "web_search_tool_result_error"

    • error_code: WebSearchToolResultErrorCode

      • "invalid_tool_input"

      • "unavailable"

      • "max_uses_exceeded"

      • "too_many_requests"

      • "query_too_long"

      • "request_too_large"

# Web Search Tool Result Block

  • WebSearchToolResultBlock object

    • type: "web_search_tool_result"

      default: web_search_tool_result

    • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

      default: {"type":"direct"}

      • DirectCaller object

        Tool invocation directly from the model.

        • type: "direct"
      • ServerToolCaller object

        Tool invocation generated by a server-side tool.

        • type: "code_execution_20250825"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • ServerToolCaller20260120 object

        • type: "code_execution_20260120"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

    • content: WebSearchToolResultBlockContent

      • WebSearchToolResultError object

        • type: "web_search_tool_result_error"

          default: web_search_tool_result_error

        • error_code: WebSearchToolResultErrorCode

          • "invalid_tool_input"

          • "unavailable"

          • "max_uses_exceeded"

          • "too_many_requests"

          • "query_too_long"

          • "request_too_large"

      • array of WebSearchResultBlock

        • 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_]+$

# Web Search Tool Result Block Content

  • WebSearchToolResultBlockContent = WebSearchToolResultError or array of WebSearchResultBlock

    • WebSearchToolResultError object

      • type: "web_search_tool_result_error"

        default: web_search_tool_result_error

      • error_code: WebSearchToolResultErrorCode

        • "invalid_tool_input"

        • "unavailable"

        • "max_uses_exceeded"

        • "too_many_requests"

        • "query_too_long"

        • "request_too_large"

    • array of WebSearchResultBlock

      • type: "web_search_result"

        default: web_search_result

      • encrypted_content: string

      • page_age: string or null

      • title: string

      • url: string

# Web Search Tool Result Block Param

  • WebSearchToolResultBlockParam object

    • type: "web_search_tool_result"

    • content: WebSearchToolResultBlockParamContent

      • WebSearchToolResultBlockItem = array of WebSearchResultBlockParam

        • type: "web_search_result"

        • encrypted_content: string

        • title: string

        • url: string

        • page_age: optional string or null

      • WebSearchToolRequestError object

        • type: "web_search_tool_result_error"

        • error_code: WebSearchToolResultErrorCode

          • "invalid_tool_input"

          • "unavailable"

          • "max_uses_exceeded"

          • "too_many_requests"

          • "query_too_long"

          • "request_too_large"

    • tool_use_id: string

      pattern: ^srvtoolu_[a-zA-Z0-9_]+$

    • cache_control: optional CacheControlEphemeral 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 for details.

        • "5m"

        • "1h"

    • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

      • DirectCaller object

        Tool invocation directly from the model.

        • type: "direct"
      • ServerToolCaller object

        Tool invocation generated by a server-side tool.

        • type: "code_execution_20250825"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

      • ServerToolCaller20260120 object

        • type: "code_execution_20260120"

        • tool_id: string

          pattern: ^srvtoolu_[a-zA-Z0-9_]+$

# Web Search Tool Result Block Param Content

  • WebSearchToolResultBlockParamContent = array of WebSearchResultBlockParam or WebSearchToolRequestError

    • WebSearchToolResultBlockItem = array of WebSearchResultBlockParam

      • type: "web_search_result"

      • encrypted_content: string

      • title: string

      • url: string

      • page_age: optional string or null

    • WebSearchToolRequestError object

      • type: "web_search_tool_result_error"

      • error_code: WebSearchToolResultErrorCode

        • "invalid_tool_input"

        • "unavailable"

        • "max_uses_exceeded"

        • "too_many_requests"

        • "query_too_long"

        • "request_too_large"

# Web Search Tool Result Error

  • WebSearchToolResultError object

    • type: "web_search_tool_result_error"

      default: web_search_tool_result_error

    • error_code: WebSearchToolResultErrorCode

      • "invalid_tool_input"

      • "unavailable"

      • "max_uses_exceeded"

      • "too_many_requests"

      • "query_too_long"

      • "request_too_large"

# Web Search Tool Result Error Code

  • WebSearchToolResultErrorCode = "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

# Headers

  • "anthropic-user-profile-id": optional string

    The user profile ID to attribute the requests in this batch to. Use when acting on behalf of a party other than your organization. Requires the user-profiles beta header. Applies to every request in the batch; an individual request whose user_profile_id body field conflicts with this header is errored.

  • "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: [154]{1,64}$

    • params: object

      Messages API creation parameters for the individual request.

      See the Messages API reference 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 without generating a response.

        Different models have different maximum values for this parameter. See models for details.

        minimum: 0

      • messages: array of MessageParam

        Input messages.

        Our models are trained to operate on alternating user and assistant conversational turns. When creating a new Message, you specify the prior conversational turns with the messages parameter, and the model then generates the next Message in the conversation. Consecutive user or assistant turns in your request will be combined into a single turn.

        Each input message must be an object with a role and content. You can specify a single user-role message, or you can include multiple user and assistant messages.

        If the final message uses the assistant role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response.

        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.

        Note that if you want to include a system prompt, 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 ContentBlockParam

          • string

          • array of ContentBlockParam

            • TextBlockParam object

              • type: "text"

              • text: string

                minLength: 1

              • cache_control: optional CacheControlEphemeral 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 for details.

                  • "5m"

                  • "1h"

              • citations: optional array of TextCitationParam or null

                • CitationCharLocationParam 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

                • CitationPageLocationParam 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

                • CitationContentBlockLocationParam 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

                • CitationWebSearchResultLocationParam object

                  • type: "web_search_result_location"

                  • cited_text: string

                  • encrypted_index: string

                  • title: string or null

                    maxLength: 512, minLength: 1

                  • url: string

                    minLength: 1

                • CitationSearchResultLocationParam 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

            • ImageBlockParam object

              • type: "image"

              • source: Base64ImageSource or URLImageSource or FileImageSource

                • Base64ImageSource 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"

                • URLImageSource object

                  • type: "url"

                  • url: string

                • FileImageSource object

                  • type: "file"

                  • file_id: string

              • cache_control: optional CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

              • transformations: optional ImageTransformationsParam 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"

            • DocumentBlockParam object

              • type: "document"

              • source: Base64PDFSource or PlainTextSource or ContentBlockSource or 2 more

                • Base64PDFSource object

                  • type: "base64"

                  • data: string

                    format: byte

                  • media_type: "application/pdf"

                • PlainTextSource object

                  • type: "text"

                  • data: string

                  • media_type: "text/plain"

                • ContentBlockSource object

                  • type: "content"

                  • content: string or array of ContentBlockSourceContent

                    • string

                    • ContentBlockSourceContent = array of ContentBlockSourceContent

                      • TextBlockParam object

                      • ImageBlockParam object

                • URLPDFSource object

                  • type: "url"

                  • url: string

                • FileDocumentSource object

                  • type: "file"

                  • file_id: string

              • cache_control: optional CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

              • citations: optional CitationsConfigParam or null

                • enabled: optional boolean
              • context: optional string or null

                minLength: 1

              • title: optional string or null

                maxLength: 500, minLength: 1

            • SearchResultBlockParam object

              • type: "search_result"

              • content: array of TextBlockParam

                • type: "text"

                • text: string

                  minLength: 1

                • cache_control: optional CacheControlEphemeral or null

                  Create a cache control breakpoint at this content block.

                • citations: optional array of TextCitationParam or null

              • source: string

              • title: string

              • cache_control: optional CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

              • citations: optional CitationsConfigParam

            • ThinkingBlockParam 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.

            • RedactedThinkingBlockParam 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.

            • ToolUseBlockParam object

              • type: "tool_use"

              • id: string

                pattern: [155]+$

              • input: map[unknown]

              • name: string

                maxLength: 200, minLength: 1

              • cache_control: optional CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

              • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

                • DirectCaller object

                  Tool invocation directly from the model.

                  • type: "direct"
                • ServerToolCaller object

                  Tool invocation generated by a server-side tool.

                  • type: "code_execution_20250825"

                  • tool_id: string

                    pattern: ^srvtoolu_[a-zA-Z0-9_]+$

                • ServerToolCaller20260120 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: [156]+$

            • ToolResultBlockParam object

              • type: "tool_result"

              • tool_use_id: string

                pattern: [157]+$

              • cache_control: optional CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

              • content: optional string or array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more

                • string

                • array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 more

                  • TextBlockParam object

                  • ImageBlockParam object

                  • SearchResultBlockParam object

                  • DocumentBlockParam object

                  • ToolReferenceBlockParam object

                    Tool reference block that can be included in tool_result content.

                    • type: "tool_reference"

                    • tool_name: string

                      maxLength: 256, minLength: 1, pattern: [158]{1,256}$

                    • cache_control: optional CacheControlEphemeral or null

                      Create a cache control breakpoint at this content block.

                  • BrowserStateBlockParam object

                    The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side 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 BrowserStateTabEntry

                      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: [159]*$

                      • title: string

                        The title of the page the tab is showing. May be empty.

                        maxLength: 4096, pattern: [160]*$

                      • url: string

                        The URL of the page the tab is showing. May be empty.

                        maxLength: 4096, pattern: [161]*$

                      • 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 CacheControlEphemeral or null

                      Create a cache control breakpoint at this content block.

                    • state_changes: optional array of BrowserStateChange 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

                      • BrowserStateChangeTabOpened object

                        A tab this call's execution opened that remains open at its end — the creation delta of the tabs inventory, not an event log.

                        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: [162]*$

                      • BrowserStateChangeDownloadStarted 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: [163]*$

                        • url: string

                          The final post-redirect URL the download was served from.

                          maxLength: 4096, pattern: [164]*$

                      • BrowserStateChangeDownloadCompleted 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: [165]*$

                        • url: string

                          The final post-redirect URL the download was served from.

                          maxLength: 4096, pattern: [166]*$

                        • 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: [167]*$, maxLength: 4096

                        • size_bytes: optional number or null

                          The completed download's size.

                          minimum: 0

                      • BrowserStateChangeDownloadFailed 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: [168]*$

                        • url: string

                          The final post-redirect URL the download was served from.

                          maxLength: 4096, pattern: [169]*$

                        • error: optional string or null

                          The failure or cancellation detail, when known.

                          pattern: [170]*$, 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: [171]+$

            • ServerToolUseBlockParam object

              • type: "server_tool_use"

              • id: string

                pattern: ^srvtoolu_[a-zA-Z0-9_]+$

              • input: map[unknown]

              • name: "web_search" or "web_fetch" or "code_execution" or 4 more

                • "web_search"

                • "web_fetch"

                • "code_execution"

                • "bash_code_execution"

                • "text_editor_code_execution"

                • "tool_search_tool_regex"

                • "tool_search_tool_bm25"

              • cache_control: optional CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

              • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

                • DirectCaller object

                  Tool invocation directly from the model.

                • ServerToolCaller object

                  Tool invocation generated by a server-side tool.

                • ServerToolCaller20260120 object

            • WebSearchToolResultBlockParam object

              • type: "web_search_tool_result"

              • content: WebSearchToolResultBlockParamContent

                • WebSearchToolResultBlockItem = array of WebSearchResultBlockParam

                  • type: "web_search_result"

                  • encrypted_content: string

                  • title: string

                  • url: string

                  • page_age: optional string or null

                • WebSearchToolRequestError object

                  • type: "web_search_tool_result_error"

                  • error_code: WebSearchToolResultErrorCode

                    • "invalid_tool_input"

                    • "unavailable"

                    • "max_uses_exceeded"

                    • "too_many_requests"

                    • "query_too_long"

                    • "request_too_large"

              • tool_use_id: string

                pattern: ^srvtoolu_[a-zA-Z0-9_]+$

              • cache_control: optional CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

              • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

                • DirectCaller object

                  Tool invocation directly from the model.

                • ServerToolCaller object

                  Tool invocation generated by a server-side tool.

                • ServerToolCaller20260120 object

            • WebFetchToolResultBlockParam object

              • type: "web_fetch_tool_result"

              • content: WebFetchToolResultErrorBlockParam or WebFetchBlockParam

                • WebFetchToolResultErrorBlockParam object

                  • type: "web_fetch_tool_result_error"

                  • error_code: WebFetchToolResultErrorCode

                    • "invalid_tool_input"

                    • "url_too_long"

                    • "url_not_allowed"

                    • "url_not_in_prior_context"

                    • "url_not_accessible"

                    • "unsupported_content_type"

                    • "too_many_requests"

                    • "max_uses_exceeded"

                    • "unavailable"

                    • "content_too_large"

                • WebFetchBlockParam object

                  • type: "web_fetch_result"

                  • content: DocumentBlockParam

                  • 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 CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

              • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

                • DirectCaller object

                  Tool invocation directly from the model.

                • ServerToolCaller object

                  Tool invocation generated by a server-side tool.

                • ServerToolCaller20260120 object

            • CodeExecutionToolResultBlockParam object

              • type: "code_execution_tool_result"

              • content: CodeExecutionToolResultBlockParamContent

                • CodeExecutionToolResultErrorParam object

                  • type: "code_execution_tool_result_error"

                  • error_code: CodeExecutionToolResultErrorCode

                    • "invalid_tool_input"

                    • "unavailable"

                    • "too_many_requests"

                    • "execution_time_exceeded"

                • CodeExecutionResultBlockParam object

                  • type: "code_execution_result"

                  • content: array of CodeExecutionOutputBlockParam

                    • type: "code_execution_output"

                    • file_id: string

                  • return_code: number

                  • stderr: string

                  • stdout: string

                • EncryptedCodeExecutionResultBlockParam object

                  Code execution result with encrypted stdout for PFC + web_search results.

                  • type: "encrypted_code_execution_result"

                  • content: array of CodeExecutionOutputBlockParam

                    • 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 CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

            • BashCodeExecutionToolResultBlockParam object

              • type: "bash_code_execution_tool_result"

              • content: BashCodeExecutionToolResultErrorParam or BashCodeExecutionResultBlockParam

                • BashCodeExecutionToolResultErrorParam object

                  • type: "bash_code_execution_tool_result_error"

                  • error_code: BashCodeExecutionToolResultErrorCode

                    • "invalid_tool_input"

                    • "unavailable"

                    • "too_many_requests"

                    • "execution_time_exceeded"

                    • "output_file_too_large"

                • BashCodeExecutionResultBlockParam object

                  • type: "bash_code_execution_result"

                  • content: array of BashCodeExecutionOutputBlockParam

                    • 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 CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

            • TextEditorCodeExecutionToolResultBlockParam object

              • type: "text_editor_code_execution_tool_result"

              • content: TextEditorCodeExecutionToolResultErrorParam or TextEditorCodeExecutionViewResultBlockParam or TextEditorCodeExecutionCreateResultBlockParam or TextEditorCodeExecutionStrReplaceResultBlockParam

                • TextEditorCodeExecutionToolResultErrorParam object

                  • type: "text_editor_code_execution_tool_result_error"

                  • error_code: TextEditorCodeExecutionToolResultErrorCode

                    • "invalid_tool_input"

                    • "unavailable"

                    • "too_many_requests"

                    • "execution_time_exceeded"

                    • "file_not_found"

                  • error_message: optional string or null

                • TextEditorCodeExecutionViewResultBlockParam 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

                • TextEditorCodeExecutionCreateResultBlockParam object

                  • type: "text_editor_code_execution_create_result"

                  • is_file_update: boolean

                • TextEditorCodeExecutionStrReplaceResultBlockParam 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 CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

            • ToolSearchToolResultBlockParam object

              • type: "tool_search_tool_result"

              • content: ToolSearchToolResultErrorParam or ToolSearchToolSearchResultBlockParam

                • ToolSearchToolResultErrorParam object

                  • type: "tool_search_tool_result_error"

                  • error_code: ToolSearchToolResultErrorCode

                    • "invalid_tool_input"

                    • "unavailable"

                    • "too_many_requests"

                    • "execution_time_exceeded"

                  • error_message: optional string or null

                • ToolSearchToolSearchResultBlockParam object

                  • type: "tool_search_tool_search_result"

                  • tool_references: array of ToolReferenceBlockParam

                    • type: "tool_reference"

                    • tool_name: string

                      maxLength: 256, minLength: 1, pattern: [172]{1,256}$

                    • cache_control: optional CacheControlEphemeral or null

                      Create a cache control breakpoint at this content block.

              • tool_use_id: string

                pattern: ^srvtoolu_[a-zA-Z0-9_]+$

              • cache_control: optional CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

            • ContainerUploadBlockParam object

              A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory.

              • type: "container_upload"

              • file_id: string

              • cache_control: optional CacheControlEphemeral or null

                Create a cache control breakpoint at this content block.

        • role: "user" or "assistant" or "system"

          • "user"

          • "assistant"

          • "system"

      • model: Model

        The model that will complete your prompt.

        See models 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 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

      • cache_control: optional CacheControlEphemeral or null

        Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request.

      • container: optional MessageCreateParamsContainer or null

        Container identifier for reuse across requests.

        • ContainerParams object

          Container parameters with skills to be loaded.

          • id: optional string or null

            Container id

          • skills: optional array of SkillParams 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

      • inference_geo: optional string or null

        Specifies the geographic region for inference processing. If not specified, the workspace's default_inference_geo is used.

      • metadata: optional Metadata

        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 OutputConfig

        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 JSONOutputFormat or null

          A schema to specify Claude's output format in responses. See structured outputs

          • type: "json_schema"

          • schema: map[unknown]

            The JSON schema of the 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 for details.

        • "auto"

        • "standard_only"

      • 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 for details.

      • system: optional string or array of TextBlockParam

        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.

        • string

        • array of TextBlockParam

          • type: "text"

          • text: string

            minLength: 1

          • cache_control: optional CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional array of TextCitationParam or null

      • thinking: optional ThinkingConfigParam

        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 for details.

        • ThinkingConfigEnabled 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 for details.

            minimum: 1024

          • display: optional "summarized" or "omitted" or null

            Controls how thinking content appears in the response. When set to summarized, thinking is returned normally. When set to omitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to summarized.

            • "summarized"

            • "omitted"

        • ThinkingConfigDisabled object

          • type: "disabled"
        • ThinkingConfigAdaptive object

          • type: "adaptive"

          • display: optional "summarized" or "omitted" or null

            Controls how thinking content appears in the response. When set to summarized, thinking is returned normally. When set to omitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to summarized.

            • "summarized"

            • "omitted"

      • tool_choice: optional ToolChoice

        How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.

        • ToolChoiceAuto 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.

        • ToolChoiceAny 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.

        • ToolChoiceTool 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.

        • ToolChoiceNone object

          The model will not be allowed to use tools.

          • type: "none"
      • tools: optional array of ToolUnion

        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, see their individual documentation as each has its own behavior (e.g., the 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 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 for more details.

        • Tool object

          • type: optional "custom" or null

          • input_schema: object

            JSON schema 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: [173]{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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • 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

        • ToolBash20250124 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • input_examples: optional array of map[unknown]

          • strict: optional boolean

            When true, guarantees schema validation on tool names and inputs

        • CodeExecutionTool20250522 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • strict: optional boolean

            When true, guarantees schema validation on tool names and inputs

        • CodeExecutionTool20250825 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • strict: optional boolean

            When true, guarantees schema validation on tool names and inputs

        • CodeExecutionTool20260120 object

          Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint).

          • 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • strict: optional boolean

            When true, guarantees schema validation on tool names and inputs

        • CodeExecutionTool20260521 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • strict: optional boolean

            When true, guarantees schema validation on tool names and inputs

        • BrowserToolset20260801 object

          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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • configs: optional BrowserToolsetConfigs 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 BrowserTypeConfig 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 BrowserCloseTabConfig 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 BrowserDoubleClickConfig 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 BrowserFileUploadConfig 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 BrowserFindConfig 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 BrowserFormInputConfig 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 BrowserGetPageTextConfig 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 BrowserHoldKeyConfig 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 BrowserHoverConfig 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 BrowserJavascriptExecConfig 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 BrowserKeyConfig 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 BrowserLeftClickConfig 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 BrowserLeftClickDragConfig 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 BrowserLeftMouseDownConfig 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 BrowserLeftMouseUpConfig 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 BrowserListTabsConfig 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 BrowserMiddleClickConfig 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 BrowserMouseMoveConfig 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 BrowserNavigateConfig 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 BrowserNewTabConfig 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 BrowserReadConsoleConfig 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 BrowserReadNetworkConfig 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 BrowserReadPageConfig 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 BrowserRightClickConfig 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 BrowserScreenshotConfig 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 BrowserScrollConfig 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 BrowserScrollToConfig 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 BrowserSwitchTabConfig 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 BrowserTripleClickConfig 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 BrowserWaitConfig 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 BrowserZoomConfig 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.

        • MemoryTool20250818 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • input_examples: optional array of map[unknown]

          • strict: optional boolean

            When true, guarantees schema validation on tool names and inputs

        • ComputerToolset20260801 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • configs: optional ComputerToolsetConfigs 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 ComputerTypeConfig 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 ComputerCursorPositionConfig 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 ComputerDoubleClickConfig 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 ComputerHoldKeyConfig 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 ComputerKeyConfig 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 ComputerLeftClickConfig 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 ComputerLeftClickDragConfig 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 ComputerLeftMouseDownConfig 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 ComputerLeftMouseUpConfig 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 ComputerMiddleClickConfig 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 ComputerMouseMoveConfig 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 ComputerRightClickConfig 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 ComputerScreenshotConfig 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 ComputerScrollConfig 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 ComputerTripleClickConfig 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 ComputerWaitConfig 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 ComputerZoomConfig 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.

        • ToolTextEditor20250124 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • input_examples: optional array of map[unknown]

          • strict: optional boolean

            When true, guarantees schema validation on tool names and inputs

        • ToolTextEditor20250429 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • input_examples: optional array of map[unknown]

          • strict: optional boolean

            When true, guarantees schema validation on tool names and inputs

        • ToolTextEditor20250728 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • 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

        • WebSearchTool20250305 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • 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 UserLocation 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 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 of the user.

              maxLength: 255, minLength: 1

        • WebFetchTool20250910 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam 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

          • url_sources: optional WebFetchURLSources or null

            Which sources contribute to the set of URLs web fetch may fetch.

            Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

            • client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

              Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].

              • WebFetchURLSourceAll object

                The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

                • type: "all"
              • WebFetchURLSourceNone object

                The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

                • type: "none"
              • WebFetchURLSourceOnly object

                The tool filter variant under which only the named tools' results contribute.

                • type: "only"

                • tools: array of WebFetchURLSourceToolReference

                  • type: "tool_reference"

                  • name: string

              • WebFetchURLSourceExcept object

                The tool filter variant under which every result but the named tools' contributes.

                • type: "except"

                • tools: array of WebFetchURLSourceToolReference

                  • type: "tool_reference"

                  • name: string

            • server_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept

              Which server tools' results contribute fetchable URLs: "all", "none", or an only or except list of server tool names from tools[]; only web_search and web_fetch results ever contribute.

              • WebFetchURLSourceAll object

                The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

              • WebFetchURLSourceNone object

                The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

              • WebFetchURLSourceOnly object

                The tool filter variant under which only the named tools' results contribute.

              • WebFetchURLSourceExcept object

                The tool filter variant under which every result but the named tools' contributes.

            • user_input: optional WebFetchURLSourceAll or WebFetchURLSourceNone

              Whether URLs in user messages are fetchable: "all" or "none".

              • WebFetchURLSourceAll object

                The url_sources variant under which a source contributes in full: every result of the tool filter's source, or all user input.

              • WebFetchURLSourceNone object

                The url_sources variant under which a source contributes nothing: no result of the tool filter's source, or no user input.

        • WebSearchTool20260209 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • 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 UserLocation or null

            Parameters for the user's location. Used to provide more relevant search results.

        • WebFetchTool20260209 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam 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

          • url_sources: optional WebFetchURLSources or null

            Which sources contribute to the set of URLs web fetch may fetch.

            Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

        • WebFetchTool20260309 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam 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

          • url_sources: optional WebFetchURLSources or null

            Which sources contribute to the set of URLs web fetch may fetch.

            Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

          • 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.

        • WebSearchTool20260318 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • 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 UserLocation or null

            Parameters for the user's location. Used to provide more relevant search results.

        • WebFetchTool20260318 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • citations: optional CitationsConfigParam 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

          • url_sources: optional WebFetchURLSources or null

            Which sources contribute to the set of URLs web fetch may fetch.

            Each key is a tagged variant: user_input is all or none; the two tool filters are all, none, only (only the named tools' results) or except (every result but the named tools'). A named tool must be declared in this request's tools[].

          • 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.

        • ToolSearchToolBm25_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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • strict: optional boolean

            When true, guarantees schema validation on tool names and inputs

        • ToolSearchToolRegex20251119 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 CacheControlEphemeral or null

            Create a cache control breakpoint at this content block.

          • defer_loading: optional boolean

            If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.

          • strict: optional boolean

            When true, guarantees schema validation on tool names and inputs

      • temperature: optional number

        Deprecated: Deprecated. Models released after Claude Opus 4.6 do not support setting temperature. A value of 1.0 will be accepted for backwards compatibility, all other values will be rejected with a 400 error.

        Amount of randomness injected into the response.

        Defaults to 1.0. Ranges from 0.0 to 1.0. Use temperature closer to 0.0 for analytical / multiple choice, and closer to 1.0 for creative and generative tasks.

        Note that even with temperature of 0.0, the results will not be fully deterministic.

        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.

        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

  • MessageBatch 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: MessageBatchRequestCounts

      Tallies requests within the Message Batch, categorized by their status.

      Requests start as processing and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch.

      • canceled: 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 "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

# Path parameters

  • message_batch_id: string

    ID of the Message Batch.

# Headers

  • "anthropic-workspace-id": optional string

# Returns

  • MessageBatch 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: MessageBatchRequestCounts

      Tallies requests within the Message Batch, categorized by their status.

      Requests start as processing and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch.

      • canceled: 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 "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

# 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-workspace-id": optional string

# Returns

  • data: array of MessageBatch

    • 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: MessageBatchRequestCounts

      Tallies requests within the Message Batch, categorized by their status.

      Requests start as processing and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch.

      • canceled: 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 "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

# Path parameters

  • message_batch_id: string

    ID of the Message Batch.

# Headers

  • "anthropic-workspace-id": optional string

# Returns

  • MessageBatch 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: MessageBatchRequestCounts

      Tallies requests within the Message Batch, categorized by their status.

      Requests start as processing and move to one of the other statuses only once processing of the entire batch ends. The sum of all values always matches the total number of requests in the batch.

      • canceled: 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 "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

# Path parameters

  • message_batch_id: string

    ID of the Message Batch.

# Headers

  • "anthropic-workspace-id": optional string

# Returns

  • DeletedMessageBatch 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 "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

# Path parameters

  • message_batch_id: string

    ID of the Message Batch.

# Headers

  • "anthropic-workspace-id": optional string

# Returns

  • MessageBatchIndividualResponse 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: MessageBatchResult

      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.

      • MessageBatchSucceededResult object

        • type: "succeeded"

          default: succeeded

        • message: Message

          • type: "message"

            Object type.

            For Messages, this is always "message".

            default: message

          • id: string

            Unique object identifier.

            The format and length of IDs may change over time.

          • container: Container 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 ContainerSkill 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 ContentBlock

            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)"}]
            • TextBlock object

              • type: "text"

                default: text

              • citations: array of TextCitation 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.

                • CitationCharLocation 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

                • CitationPageLocation 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

                • CitationContentBlockLocation 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

                • CitationsWebSearchResultLocation 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

                • CitationsSearchResultLocation 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

            • ThinkingBlock 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 for details.

              • thinking: string

                The text of Claude's thinking process for this block.

            • RedactedThinkingBlock 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 for details.

            • ToolUseBlock object

              • type: "tool_use"

                default: tool_use

              • id: string

                pattern: [174]+$

              • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

                default: {"type":"direct"}

                • DirectCaller object

                  Tool invocation directly from the model.

                  • type: "direct"
                • ServerToolCaller object

                  Tool invocation generated by a server-side tool.

                  • type: "code_execution_20250825"

                  • tool_id: string

                    pattern: ^srvtoolu_[a-zA-Z0-9_]+$

                • ServerToolCaller20260120 object

                  • type: "code_execution_20260120"

                  • tool_id: string

                    pattern: ^srvtoolu_[a-zA-Z0-9_]+$

              • input: map[unknown]

              • name: string

                minLength: 1

              • toolset_name: optional string or null

                For a toolset member tool_use, the toolset family.

                maxLength: 64, minLength: 1, pattern: [175]+$

            • ServerToolUseBlock object

              • type: "server_tool_use"

                default: server_tool_use

              • id: string

                pattern: ^srvtoolu_[a-zA-Z0-9_]+$

              • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

                default: {"type":"direct"}

                • DirectCaller object

                  Tool invocation directly from the model.

                • ServerToolCaller object

                  Tool invocation generated by a server-side tool.

                • ServerToolCaller20260120 object

              • input: map[unknown]

              • name: "web_search" or "web_fetch" or "code_execution" or 4 more

                • "web_search"

                • "web_fetch"

                • "code_execution"

                • "bash_code_execution"

                • "text_editor_code_execution"

                • "tool_search_tool_regex"

                • "tool_search_tool_bm25"

            • WebSearchToolResultBlock object

              • type: "web_search_tool_result"

                default: web_search_tool_result

              • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

                default: {"type":"direct"}

                • DirectCaller object

                  Tool invocation directly from the model.

                • ServerToolCaller object

                  Tool invocation generated by a server-side tool.

                • ServerToolCaller20260120 object

              • content: WebSearchToolResultBlockContent

                • WebSearchToolResultError object

                  • type: "web_search_tool_result_error"

                    default: web_search_tool_result_error

                  • error_code: WebSearchToolResultErrorCode

                    • "invalid_tool_input"

                    • "unavailable"

                    • "max_uses_exceeded"

                    • "too_many_requests"

                    • "query_too_long"

                    • "request_too_large"

                • array of WebSearchResultBlock

                  • 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_]+$

            • WebFetchToolResultBlock object

              • type: "web_fetch_tool_result"

                default: web_fetch_tool_result

              • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

                default: {"type":"direct"}

                • DirectCaller object

                  Tool invocation directly from the model.

                • ServerToolCaller object

                  Tool invocation generated by a server-side tool.

                • ServerToolCaller20260120 object

              • content: WebFetchToolResultErrorBlock or WebFetchBlock

                • WebFetchToolResultErrorBlock object

                  • type: "web_fetch_tool_result_error"

                    default: web_fetch_tool_result_error

                  • error_code: WebFetchToolResultErrorCode

                    • "invalid_tool_input"

                    • "url_too_long"

                    • "url_not_allowed"

                    • "url_not_in_prior_context"

                    • "url_not_accessible"

                    • "unsupported_content_type"

                    • "too_many_requests"

                    • "max_uses_exceeded"

                    • "unavailable"

                    • "content_too_large"

                • WebFetchBlock object

                  • type: "web_fetch_result"

                    default: web_fetch_result

                  • content: DocumentBlock

                    • type: "document"

                      default: document

                    • citations: CitationsConfig or null

                      Citation configuration for the document

                      • enabled: boolean

                        default: false

                    • source: Base64PDFSource or PlainTextSource

                      • Base64PDFSource object

                        • type: "base64"

                        • data: string

                          format: byte

                        • media_type: "application/pdf"

                      • PlainTextSource 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_]+$

            • CodeExecutionToolResultBlock object

              • type: "code_execution_tool_result"

                default: code_execution_tool_result

              • content: CodeExecutionToolResultBlockContent

                • CodeExecutionToolResultError object

                  • type: "code_execution_tool_result_error"

                    default: code_execution_tool_result_error

                  • error_code: CodeExecutionToolResultErrorCode

                    • "invalid_tool_input"

                    • "unavailable"

                    • "too_many_requests"

                    • "execution_time_exceeded"

                • CodeExecutionResultBlock object

                  • type: "code_execution_result"

                    default: code_execution_result

                  • content: array of CodeExecutionOutputBlock

                    • type: "code_execution_output"

                      default: code_execution_output

                    • file_id: string

                  • return_code: number

                  • stderr: string

                  • stdout: string

                • EncryptedCodeExecutionResultBlock 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 CodeExecutionOutputBlock

                    • 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_]+$

            • BashCodeExecutionToolResultBlock object

              • type: "bash_code_execution_tool_result"

                default: bash_code_execution_tool_result

              • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

                • BashCodeExecutionToolResultError object

                  • type: "bash_code_execution_tool_result_error"

                    default: bash_code_execution_tool_result_error

                  • error_code: BashCodeExecutionToolResultErrorCode

                    • "invalid_tool_input"

                    • "unavailable"

                    • "too_many_requests"

                    • "execution_time_exceeded"

                    • "output_file_too_large"

                • BashCodeExecutionResultBlock object

                  • type: "bash_code_execution_result"

                    default: bash_code_execution_result

                  • content: array of BashCodeExecutionOutputBlock

                    • 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_]+$

            • TextEditorCodeExecutionToolResultBlock object

              • type: "text_editor_code_execution_tool_result"

                default: text_editor_code_execution_tool_result

              • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

                • TextEditorCodeExecutionToolResultError object

                  • type: "text_editor_code_execution_tool_result_error"

                    default: text_editor_code_execution_tool_result_error

                  • error_code: TextEditorCodeExecutionToolResultErrorCode

                    • "invalid_tool_input"

                    • "unavailable"

                    • "too_many_requests"

                    • "execution_time_exceeded"

                    • "file_not_found"

                  • error_message: string or null

                • TextEditorCodeExecutionViewResultBlock 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

                • TextEditorCodeExecutionCreateResultBlock object

                  • type: "text_editor_code_execution_create_result"

                    default: text_editor_code_execution_create_result

                  • is_file_update: boolean

                • TextEditorCodeExecutionStrReplaceResultBlock 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_]+$

            • ToolSearchToolResultBlock object

              • type: "tool_search_tool_result"

                default: tool_search_tool_result

              • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

                • ToolSearchToolResultError object

                  • type: "tool_search_tool_result_error"

                    default: tool_search_tool_result_error

                  • error_code: ToolSearchToolResultErrorCode

                    • "invalid_tool_input"

                    • "unavailable"

                    • "too_many_requests"

                    • "execution_time_exceeded"

                  • error_message: string or null

                • ToolSearchToolSearchResultBlock object

                  • type: "tool_search_tool_search_result"

                    default: tool_search_tool_search_result

                  • tool_references: array of ToolReferenceBlock

                    • type: "tool_reference"

                      default: tool_reference

                    • tool_name: string

                      maxLength: 256, minLength: 1, pattern: [176]{1,256}$

              • tool_use_id: string

                pattern: ^srvtoolu_[a-zA-Z0-9_]+$

            • ContainerUploadBlock object

              Response model for a file uploaded to the container.

              • type: "container_upload"

                default: container_upload

              • file_id: string

          • model: Model

            The model that will complete your prompt.

            See models 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 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

          • role: "assistant"

            Conversational role of the generated message.

            This will always be "assistant".

            default: assistant

          • stop_details: RefusalStopDetails 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. 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.

              • "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.

          • stop_reason: StopReason 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"

            • "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: Usage

            Billing and rate-limit usage.

            Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems.

            Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in usage will not match one-to-one with the exact visible content of an API request or response.

            For example, output_tokens will be non-zero, even for an empty string response from Claude.

            Total input tokens in a request is the summation of input_tokens, cache_creation_input_tokens, and cache_read_input_tokens.

            • cache_creation: CacheCreation 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

            • 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

            • output_tokens: number

              The number of output tokens which were used.

              minimum: 0

            • output_tokens_details: OutputTokensDetails 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: ServerToolUsage 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"

      • MessageBatchErroredResult object

        • type: "errored"

          default: errored

        • error: ErrorResponse

          • type: "error"

            default: error

          • error: ErrorObject

            • InvalidRequestError object

              • type: "invalid_request_error"

                default: invalid_request_error

              • message: string

                default: Invalid request

            • AuthenticationError object

              • type: "authentication_error"

                default: authentication_error

              • message: string

                default: Authentication error

            • BillingError object

              • type: "billing_error"

                default: billing_error

              • message: string

                default: Billing error

            • PermissionError object

              • type: "permission_error"

                default: permission_error

              • message: string

                default: Permission denied

            • NotFoundError object

              • type: "not_found_error"

                default: not_found_error

              • message: string

                default: Not found

            • RateLimitError object

              • type: "rate_limit_error"

                default: rate_limit_error

              • message: string

                default: Rate limited

            • GatewayTimeoutError object

              • type: "timeout_error"

                default: timeout_error

              • message: string

                default: Request timeout

            • APIErrorObject object

              • type: "api_error"

                default: api_error

              • message: string

                default: Internal server error

            • OverloadedError object

              • type: "overloaded_error"

                default: overloaded_error

              • message: string

                default: Overloaded

          • request_id: string or null

      • MessageBatchCanceledResult object

        • type: "canceled"

          default: canceled

      • MessageBatchExpiredResult 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 "X-Api-Key: $ANTHROPIC_API_KEY"

  1. a-zA-Z0-9_- ↩︎

  2. a-zA-Z0-9_- ↩︎

  3. a-zA-Z0-9_- ↩︎

  4. a-zA-Z0-9_- ↩︎

  5. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  6. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  7. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  8. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  9. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  10. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  11. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  12. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  13. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  14. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  15. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  16. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  17. a-zA-Z0-9_- ↩︎

  18. a-zA-Z0-9_- ↩︎

  19. a-zA-Z0-9_- ↩︎

  20. a-zA-Z0-9_- ↩︎

  21. a-zA-Z0-9_- ↩︎

  22. a-zA-Z0-9_- ↩︎

  23. a-zA-Z0-9_- ↩︎

  24. a-zA-Z0-9_- ↩︎

  25. a-zA-Z0-9_- ↩︎

  26. a-zA-Z0-9_- ↩︎

  27. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  28. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  29. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  30. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  31. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  32. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  33. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  34. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  35. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  36. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  37. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  38. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  39. a-zA-Z0-9_- ↩︎

  40. a-zA-Z0-9_- ↩︎

  41. a-zA-Z0-9_- ↩︎

  42. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  43. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  44. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  45. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  46. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  47. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  48. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  49. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  50. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  51. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  52. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  53. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  54. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  55. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  56. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  57. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  58. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  59. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  60. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  61. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  62. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  63. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  64. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  65. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  66. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  67. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  68. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  69. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  70. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  71. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  72. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  73. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  74. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  75. a-zA-Z0-9_- ↩︎

  76. a-zA-Z0-9_- ↩︎

  77. a-zA-Z0-9_- ↩︎

  78. a-zA-Z0-9_- ↩︎

  79. a-zA-Z0-9_- ↩︎

  80. a-zA-Z0-9_- ↩︎

  81. a-zA-Z0-9_- ↩︎

  82. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  83. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  84. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  85. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  86. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  87. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  88. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  89. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  90. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  91. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  92. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  93. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  94. a-zA-Z0-9_- ↩︎

  95. a-zA-Z0-9_- ↩︎

  96. a-zA-Z0-9_- ↩︎

  97. a-zA-Z0-9_- ↩︎

  98. a-zA-Z0-9_- ↩︎

  99. a-zA-Z0-9_- ↩︎

  100. a-zA-Z0-9_- ↩︎

  101. a-zA-Z0-9_- ↩︎

  102. a-zA-Z0-9_- ↩︎

  103. a-zA-Z0-9_- ↩︎

  104. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  105. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  106. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  107. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  108. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  109. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  110. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  111. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  112. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  113. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  114. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  115. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  116. a-zA-Z0-9_- ↩︎

  117. a-zA-Z0-9_- ↩︎

  118. a-zA-Z0-9_- ↩︎

  119. a-zA-Z0-9_- ↩︎

  120. a-zA-Z0-9_- ↩︎

  121. a-zA-Z0-9_- ↩︎

  122. a-zA-Z0-9_- ↩︎

  123. a-zA-Z0-9_- ↩︎

  124. a-zA-Z0-9_- ↩︎

  125. a-zA-Z0-9_- ↩︎

  126. a-zA-Z0-9_- ↩︎

  127. a-zA-Z0-9_- ↩︎

  128. a-zA-Z0-9_- ↩︎

  129. a-zA-Z0-9_- ↩︎

  130. a-zA-Z0-9_- ↩︎

  131. a-zA-Z0-9_- ↩︎

  132. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  133. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  134. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  135. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  136. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  137. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  138. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  139. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  140. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  141. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  142. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  143. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  144. a-zA-Z0-9_- ↩︎

  145. a-zA-Z0-9_- ↩︎

  146. a-zA-Z0-9_- ↩︎

  147. a-zA-Z0-9_- ↩︎

  148. a-zA-Z0-9_- ↩︎

  149. a-zA-Z0-9_- ↩︎

  150. a-zA-Z0-9_- ↩︎

  151. a-zA-Z0-9_- ↩︎

  152. a-zA-Z0-9_- ↩︎

  153. a-zA-Z0-9_- ↩︎

  154. a-zA-Z0-9_- ↩︎

  155. a-zA-Z0-9_- ↩︎

  156. a-zA-Z0-9_- ↩︎

  157. a-zA-Z0-9_- ↩︎

  158. a-zA-Z0-9_- ↩︎

  159. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  160. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  161. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  162. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  163. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  164. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  165. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  166. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  167. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  168. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  169. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  170. ^\x00-\x1f\x7f-\x9f\u2028\u2029 ↩︎

  171. a-zA-Z0-9_- ↩︎

  172. a-zA-Z0-9_- ↩︎

  173. a-zA-Z0-9_- ↩︎

  174. a-zA-Z0-9_- ↩︎

  175. a-zA-Z0-9_- ↩︎

  176. a-zA-Z0-9_- ↩︎

Files main
Menu

Theme