nex/docs/api_reference/anthropic/messages.md

Messages

Create

$ ant messages create

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

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.

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

• --message: 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:

  [{"role": "user", "content": "Hello, Claude"}]
  

  Example with multiple conversational turns:

  [
    {"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:

  [
    {"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:

  {"role": "user", "content": "Hello, Claude"}
  

  {"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.

• --model: "claude-opus-4-7" or "claude-mythos-preview" or "claude-opus-4-6" or 14 more or string

  The model that will complete your prompt.

  See models for additional details and options.

• --cache-control: optional object { type, ttl }

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

• --container: optional string

  Container identifier for reuse across requests.

• --inference-geo: optional string

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

• --metadata: optional object { user_id }

  An object describing metadata about the request.

• --output-config: optional object { effort, format }

  Configuration options for the model's output, such as the output format.

• --service-tier: optional "auto" or "standard_only"

  Determines whether to use priority capacity (if available) or standard capacity for this request.

  Anthropic offers different levels of service for your API requests. See service-tiers for details.

• --stop-sequence: 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.

• --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.

• --temperature: optional number

  Amount of randomness injected into the response.

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

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

• --thinking: optional 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.

• --tool-choice: optional 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.

• --tool: 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:

  [
    {
      "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:

  [
    {
      "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:

  [
    {
      "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.

• --top-k: optional number

  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. You usually only need to use temperature.

• --top-p: optional number

  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. You should either alter temperature or top_p, but not both.

  Recommended for advanced use cases only. You usually only need to use temperature.

Returns

• message: object { id, container, content, 7 more }

  • id: string

    Unique object identifier.

    The format and length of IDs may change over time.

  • container: object { id, expires_at }

    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.

  • 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:

    [{"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:

    [
      {"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:

    [{"type": "text", "text": "B)"}]
    

    • text_block: object { citations, text, type }

      • citations: array of TextCitation

        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.

        • citation_char_location: object { cited_text, document_index, document_title, 4 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_char_index: number

          • file_id: string

          • start_char_index: number

          • type: "char_location"

        • citation_page_location: object { cited_text, document_index, document_title, 4 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_page_number: number

          • file_id: string

          • start_page_number: number

          • type: "page_location"

        • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_block_index: number

          • file_id: string

          • start_block_index: number

          • type: "content_block_location"

        • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

          • cited_text: string

          • encrypted_index: string

          • title: string

          • type: "web_search_result_location"

          • url: string

        • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

          • cited_text: string

          • end_block_index: number

          • search_result_index: number

          • source: string

          • start_block_index: number

          • title: string

          • type: "search_result_location"

      • text: string

      • type: "text"

    • thinking_block: object { signature, thinking, type }

      • signature: string

      • thinking: string

      • type: "thinking"

    • redacted_thinking_block: object { data, type }

      • data: string

      • type: "redacted_thinking"

    • tool_use_block: object { id, caller, input, 2 more }

      • id: string

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

      • input: map[unknown]

      • name: string

      • type: "tool_use"

    • server_tool_use_block: object { id, caller, input, 2 more }

      • id: string

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

      • 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"

      • type: "server_tool_use"

    • web_search_tool_result_block: object { caller, content, tool_use_id, type }

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

      • content: WebSearchToolResultError or array of WebSearchResultBlock

        • web_search_tool_result_error: object { error_code, type }

          • error_code: "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"

          • type: "web_search_tool_result_error"

        • union_member_1: array of WebSearchResultBlock

          • encrypted_content: string

          • page_age: string

          • title: string

          • type: "web_search_result"

          • url: string

      • tool_use_id: string

      • type: "web_search_tool_result"

    • web_fetch_tool_result_block: object { caller, content, tool_use_id, type }

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

      • content: WebFetchToolResultErrorBlock or WebFetchBlock

        • web_fetch_tool_result_error_block: object { error_code, type }

          • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

            • "invalid_tool_input"

            • "url_too_long"

            • "url_not_allowed"

            • "url_not_accessible"

            • "unsupported_content_type"

            • "too_many_requests"

            • "max_uses_exceeded"

            • "unavailable"

          • type: "web_fetch_tool_result_error"

        • web_fetch_block: object { content, retrieved_at, type, url }

          • content: object { citations, source, title, type }

            • citations: object { enabled }

              Citation configuration for the document

              • enabled: boolean

            • source: Base64PDFSource or PlainTextSource

              • base64_pdf_source: object { data, media_type, type }

                • data: string

                • media_type: "application/pdf"

                • type: "base64"

              • plain_text_source: object { data, media_type, type }

                • data: string

                • media_type: "text/plain"

                • type: "text"

            • title: string

              The title of the document

            • type: "document"

          • retrieved_at: string

            ISO 8601 timestamp when the content was retrieved

          • type: "web_fetch_result"

          • url: string

            Fetched content URL

      • tool_use_id: string

      • type: "web_fetch_tool_result"

    • code_execution_tool_result_block: object { content, tool_use_id, type }

      • content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

        • code_execution_tool_result_error: object { error_code, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

          • type: "code_execution_tool_result_error"

        • code_execution_result_block: object { content, return_code, stderr, 2 more }

          • content: array of CodeExecutionOutputBlock

            • file_id: string

            • type: "code_execution_output"

          • return_code: number

          • stderr: string

          • stdout: string

          • type: "code_execution_result"

        • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

          • content: array of CodeExecutionOutputBlock

            • file_id: string

            • type: "code_execution_output"

          • encrypted_stdout: string

          • return_code: number

          • stderr: string

          • type: "encrypted_code_execution_result"

      • tool_use_id: string

      • type: "code_execution_tool_result"

    • bash_code_execution_tool_result_block: object { content, tool_use_id, type }

      • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

        • bash_code_execution_tool_result_error: object { error_code, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

            • "output_file_too_large"

          • type: "bash_code_execution_tool_result_error"

        • bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

          • content: array of BashCodeExecutionOutputBlock

            • file_id: string

            • type: "bash_code_execution_output"

          • return_code: number

          • stderr: string

          • stdout: string

          • type: "bash_code_execution_result"

      • tool_use_id: string

      • type: "bash_code_execution_tool_result"

    • text_editor_code_execution_tool_result_block: object { content, tool_use_id, type }

      • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

        • text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

            • "file_not_found"

          • error_message: string

          • type: "text_editor_code_execution_tool_result_error"

        • text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

          • content: string

          • file_type: "text" or "image" or "pdf"

            • "text"

            • "image"

            • "pdf"

          • num_lines: number

          • start_line: number

          • total_lines: number

          • type: "text_editor_code_execution_view_result"

        • text_editor_code_execution_create_result_block: object { is_file_update, type }

          • is_file_update: boolean

          • type: "text_editor_code_execution_create_result"

        • text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

          • lines: array of string

          • new_lines: number

          • new_start: number

          • old_lines: number

          • old_start: number

          • type: "text_editor_code_execution_str_replace_result"

      • tool_use_id: string

      • type: "text_editor_code_execution_tool_result"

    • tool_search_tool_result_block: object { content, tool_use_id, type }

      • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

        • tool_search_tool_result_error: object { error_code, error_message, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

          • error_message: string

          • type: "tool_search_tool_result_error"

        • tool_search_tool_search_result_block: object { tool_references, type }

          • tool_references: array of ToolReferenceBlock

            • tool_name: string

            • type: "tool_reference"

          • type: "tool_search_tool_search_result"

      • tool_use_id: string

      • type: "tool_search_tool_result"

    • container_upload_block: object { file_id, type }

      Response model for a file uploaded to the container.

      • file_id: string

      • type: "container_upload"

  • model: "claude-opus-4-7" or "claude-mythos-preview" or "claude-opus-4-6" or 14 more or string

    The model that will complete your prompt.

    See models for additional details and options.

    • "claude-opus-4-7"

      Frontier intelligence for long-running agents and coding

    • "claude-mythos-preview"

      New class of intelligence, strongest in coding and cybersecurity

    • "claude-opus-4-6"

      Frontier 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"

      Premium model combining maximum intelligence with practical performance

    • "claude-opus-4-5-20251101"

      Premium model combining maximum intelligence with practical performance

    • "claude-sonnet-4-5"

      High-performance model for agents and coding

    • "claude-sonnet-4-5-20250929"

      High-performance model for agents and coding

    • "claude-opus-4-1"

      Exceptional model for specialized complex tasks

    • "claude-opus-4-1-20250805"

      Exceptional model for specialized complex tasks

    • "claude-opus-4-0"

      Powerful model for complex tasks

    • "claude-opus-4-20250514"

      Powerful model for complex tasks

    • "claude-sonnet-4-0"

      High-performance model with extended thinking

    • "claude-sonnet-4-20250514"

      High-performance model with extended thinking

    • "claude-3-haiku-20240307"

      Fast and cost-effective model

  • role: "assistant"

    Conversational role of the generated message.

    This will always be "assistant".

  • stop_details: object { category, explanation, type }

    Structured information about a refusal.

    • category: "cyber" or "bio"

      The policy category that triggered the refusal.

      null when the refusal doesn't map to a named category.

      • "cyber"

      • "bio"

    • explanation: string

      Human-readable explanation of the refusal.

      This text is not guaranteed to be stable. null when no explanation is available for the category.

    • type: "refusal"

  • stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 3 more

    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

    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"

  • stop_sequence: string

    Which custom stop sequence was generated, if any.

    This value will be a non-null string if one of your custom stop sequences was generated.

  • type: "message"

    Object type.

    For Messages, this is always "message".

  • usage: object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 5 more }

    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: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

      Breakdown of cached tokens by TTL

      • ephemeral_1h_input_tokens: number

        The number of input tokens used to create the 1 hour cache entry.

      • ephemeral_5m_input_tokens: number

        The number of input tokens used to create the 5 minute cache entry.

    • cache_creation_input_tokens: number

      The number of input tokens used to create the cache entry.

    • cache_read_input_tokens: number

      The number of input tokens read from the cache.

    • inference_geo: string

      The geographic region where inference was performed for this request.

    • input_tokens: number

      The number of input tokens which were used.

    • output_tokens: number

      The number of output tokens which were used.

    • server_tool_use: object { web_fetch_requests, web_search_requests }

      The number of server tool requests.

      • web_fetch_requests: number

        The number of web fetch tool requests.

      • web_search_requests: number

        The number of web search tool requests.

    • service_tier: "standard" or "priority" or "batch"

      If the request used the priority, standard, or batch tier.

      • "standard"

      • "priority"

      • "batch"

Example

ant messages create \
  --api-key my-anthropic-api-key \
  --max-tokens 1024 \
  --message '{content: [{text: x, type: text}], role: user}' \
  --model claude-opus-4-6

Count Tokens

$ ant messages count-tokens

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

Parameters

• --message: 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:

  [{"role": "user", "content": "Hello, Claude"}]
  

  Example with multiple conversational turns:

  [
    {"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:

  [
    {"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:

  {"role": "user", "content": "Hello, Claude"}
  

  {"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.

• --model: "claude-opus-4-7" or "claude-mythos-preview" or "claude-opus-4-6" or 14 more or string

  The model that will complete your prompt.

  See models for additional details and options.

• --cache-control: optional object { type, ttl }

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

• --output-config: optional object { effort, format }

  Configuration options for the model's output, such as the output 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.

• --thinking: optional 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.

• --tool-choice: optional 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.

• --tool: 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:

  [
    {
      "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:

  [
    {
      "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:

  [
    {
      "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.

Returns

• message_tokens_count: object { input_tokens }

  • input_tokens: number

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

Example

ant messages count-tokens \
  --api-key my-anthropic-api-key \
  --message '{content: [{text: x, type: text}], role: user}' \
  --model claude-opus-4-6

Domain Types

Base64 Image Source

• base64_image_source: object { data, media_type, type }

  • data: string

  • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

    • "image/jpeg"

    • "image/png"

    • "image/gif"

    • "image/webp"

  • type: "base64"

Base64 PDF Source

• base64_pdf_source: object { data, media_type, type }

  • data: string

  • media_type: "application/pdf"

  • type: "base64"

Bash Code Execution Output Block

• bash_code_execution_output_block: object { file_id, type }

  • file_id: string

  • type: "bash_code_execution_output"

Bash Code Execution Output Block Param

• bash_code_execution_output_block_param: object { file_id, type }

  • file_id: string

  • type: "bash_code_execution_output"

Bash Code Execution Result Block

• bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

  • content: array of BashCodeExecutionOutputBlock

    • file_id: string

    • type: "bash_code_execution_output"

  • return_code: number

  • stderr: string

  • stdout: string

  • type: "bash_code_execution_result"

Bash Code Execution Result Block Param

• bash_code_execution_result_block_param: object { content, return_code, stderr, 2 more }

  • content: array of BashCodeExecutionOutputBlockParam

    • file_id: string

    • type: "bash_code_execution_output"

  • return_code: number

  • stderr: string

  • stdout: string

  • type: "bash_code_execution_result"

Bash Code Execution Tool Result Block

• bash_code_execution_tool_result_block: object { content, tool_use_id, type }

  • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

    • bash_code_execution_tool_result_error: object { error_code, type }

      • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

        • "invalid_tool_input"

        • "unavailable"

        • "too_many_requests"

        • "execution_time_exceeded"

        • "output_file_too_large"

      • type: "bash_code_execution_tool_result_error"

    • bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

      • content: array of BashCodeExecutionOutputBlock

        • file_id: string

        • type: "bash_code_execution_output"

      • return_code: number

      • stderr: string

      • stdout: string

      • type: "bash_code_execution_result"

  • tool_use_id: string

  • type: "bash_code_execution_tool_result"

Bash Code Execution Tool Result Block Param

• bash_code_execution_tool_result_block_param: object { content, tool_use_id, type, cache_control }

  • content: BashCodeExecutionToolResultErrorParam or BashCodeExecutionResultBlockParam

    • bash_code_execution_tool_result_error_param: object { error_code, type }

      • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

        • "invalid_tool_input"

        • "unavailable"

        • "too_many_requests"

        • "execution_time_exceeded"

        • "output_file_too_large"

      • type: "bash_code_execution_tool_result_error"

    • bash_code_execution_result_block_param: object { content, return_code, stderr, 2 more }

      • content: array of BashCodeExecutionOutputBlockParam

        • file_id: string

        • type: "bash_code_execution_output"

      • return_code: number

      • stderr: string

      • stdout: string

      • type: "bash_code_execution_result"

  • tool_use_id: string

  • type: "bash_code_execution_tool_result"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

Bash Code Execution Tool Result Error

• bash_code_execution_tool_result_error: object { error_code, type }

  • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

    • "invalid_tool_input"

    • "unavailable"

    • "too_many_requests"

    • "execution_time_exceeded"

    • "output_file_too_large"

  • type: "bash_code_execution_tool_result_error"

Bash Code Execution Tool Result Error Code

• bash_code_execution_tool_result_error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

  • "invalid_tool_input"

  • "unavailable"

  • "too_many_requests"

  • "execution_time_exceeded"

  • "output_file_too_large"

Bash Code Execution Tool Result Error Param

• bash_code_execution_tool_result_error_param: object { error_code, type }

  • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

    • "invalid_tool_input"

    • "unavailable"

    • "too_many_requests"

    • "execution_time_exceeded"

    • "output_file_too_large"

  • type: "bash_code_execution_tool_result_error"

Cache Control Ephemeral

• cache_control_ephemeral: object { type, ttl }

  • 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.

    • "5m"

    • "1h"

Cache Creation

• cache_creation: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

  • ephemeral_1h_input_tokens: number

    The number of input tokens used to create the 1 hour cache entry.

  • ephemeral_5m_input_tokens: number

    The number of input tokens used to create the 5 minute cache entry.

Citation Char Location

• citation_char_location: object { cited_text, document_index, document_title, 4 more }

  • cited_text: string

  • document_index: number

  • document_title: string

  • end_char_index: number

  • file_id: string

  • start_char_index: number

  • type: "char_location"

Citation Char Location Param

• citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

  • cited_text: string

  • document_index: number

  • document_title: string

  • end_char_index: number

  • start_char_index: number

  • type: "char_location"

Citation Content Block Location

• citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

  • cited_text: string

  • document_index: number

  • document_title: string

  • end_block_index: number

  • file_id: string

  • start_block_index: number

  • type: "content_block_location"

Citation Content Block Location Param

• citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

  • cited_text: string

  • document_index: number

  • document_title: string

  • end_block_index: number

  • start_block_index: number

  • type: "content_block_location"

Citation Page Location

• citation_page_location: object { cited_text, document_index, document_title, 4 more }

  • cited_text: string

  • document_index: number

  • document_title: string

  • end_page_number: number

  • file_id: string

  • start_page_number: number

  • type: "page_location"

Citation Page Location Param

• citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

  • cited_text: string

  • document_index: number

  • document_title: string

  • end_page_number: number

  • start_page_number: number

  • type: "page_location"

Citation Search Result Location Param

• citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

  • cited_text: string

  • end_block_index: number

  • search_result_index: number

  • source: string

  • start_block_index: number

  • title: string

  • type: "search_result_location"

Citation Web Search Result Location Param

• citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

  • cited_text: string

  • encrypted_index: string

  • title: string

  • type: "web_search_result_location"

  • url: string

Citations Config

• citations_config: object { enabled }

  • enabled: boolean

Citations Config Param

• citations_config_param: object { enabled }

  • enabled: optional boolean

Citations Delta

• citations_delta: object { citation, type }

  • citation: CitationCharLocation or CitationPageLocation or CitationContentBlockLocation or 2 more

    • citation_char_location: object { cited_text, document_index, document_title, 4 more }

      • cited_text: string

      • document_index: number

      • document_title: string

      • end_char_index: number

      • file_id: string

      • start_char_index: number

      • type: "char_location"

    • citation_page_location: object { cited_text, document_index, document_title, 4 more }

      • cited_text: string

      • document_index: number

      • document_title: string

      • end_page_number: number

      • file_id: string

      • start_page_number: number

      • type: "page_location"

    • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

      • cited_text: string

      • document_index: number

      • document_title: string

      • end_block_index: number

      • file_id: string

      • start_block_index: number

      • type: "content_block_location"

    • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

      • cited_text: string

      • encrypted_index: string

      • title: string

      • type: "web_search_result_location"

      • url: string

    • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

      • cited_text: string

      • end_block_index: number

      • search_result_index: number

      • source: string

      • start_block_index: number

      • title: string

      • type: "search_result_location"

  • type: "citations_delta"

Citations Search Result Location

• citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

  • cited_text: string

  • end_block_index: number

  • search_result_index: number

  • source: string

  • start_block_index: number

  • title: string

  • type: "search_result_location"

Citations Web Search Result Location

• citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

  • cited_text: string

  • encrypted_index: string

  • title: string

  • type: "web_search_result_location"

  • url: string

Code Execution Output Block

• code_execution_output_block: object { file_id, type }

  • file_id: string

  • type: "code_execution_output"

Code Execution Output Block Param

• code_execution_output_block_param: object { file_id, type }

  • file_id: string

  • type: "code_execution_output"

Code Execution Result Block

• code_execution_result_block: object { content, return_code, stderr, 2 more }

  • content: array of CodeExecutionOutputBlock

    • file_id: string

    • type: "code_execution_output"

  • return_code: number

  • stderr: string

  • stdout: string

  • type: "code_execution_result"

Code Execution Result Block Param

• code_execution_result_block_param: object { content, return_code, stderr, 2 more }

  • content: array of CodeExecutionOutputBlockParam

    • file_id: string

    • type: "code_execution_output"

  • return_code: number

  • stderr: string

  • stdout: string

  • type: "code_execution_result"

Code Execution Tool 20250522

• code_execution_tool_20250522: object { name, type, allowed_callers, 3 more }

  • name: "code_execution"

    Name of the tool.

    This is how the tool will be called by the model and in tool_use blocks.

  • type: "code_execution_20250522"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • cache_control: optional object { type, ttl }

    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.

      • "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

• code_execution_tool_20250825: object { name, type, allowed_callers, 3 more }

  • name: "code_execution"

    Name of the tool.

    This is how the tool will be called by the model and in tool_use blocks.

  • type: "code_execution_20250825"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • cache_control: optional object { type, ttl }

    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.

      • "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

• code_execution_tool_20260120: object { name, type, allowed_callers, 3 more }

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

  • name: "code_execution"

    Name of the tool.

    This is how the tool will be called by the model and in tool_use blocks.

  • type: "code_execution_20260120"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • cache_control: optional object { type, ttl }

    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.

      • "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

• code_execution_tool_result_block: object { content, tool_use_id, type }

  • content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

    • code_execution_tool_result_error: object { error_code, type }

      • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

        • "invalid_tool_input"

        • "unavailable"

        • "too_many_requests"

        • "execution_time_exceeded"

      • type: "code_execution_tool_result_error"

    • code_execution_result_block: object { content, return_code, stderr, 2 more }

      • content: array of CodeExecutionOutputBlock

        • file_id: string

        • type: "code_execution_output"

      • return_code: number

      • stderr: string

      • stdout: string

      • type: "code_execution_result"

    • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

      • content: array of CodeExecutionOutputBlock

        • file_id: string

        • type: "code_execution_output"

      • encrypted_stdout: string

      • return_code: number

      • stderr: string

      • type: "encrypted_code_execution_result"

  • tool_use_id: string

  • type: "code_execution_tool_result"

Code Execution Tool Result Block Content

• code_execution_tool_result_block_content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

  • code_execution_tool_result_error: object { error_code, type }

    • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

      • "invalid_tool_input"

      • "unavailable"

      • "too_many_requests"

      • "execution_time_exceeded"

    • type: "code_execution_tool_result_error"

  • code_execution_result_block: object { content, return_code, stderr, 2 more }

    • content: array of CodeExecutionOutputBlock

      • file_id: string

      • type: "code_execution_output"

    • return_code: number

    • stderr: string

    • stdout: string

    • type: "code_execution_result"

  • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

    • content: array of CodeExecutionOutputBlock

      • file_id: string

      • type: "code_execution_output"

    • encrypted_stdout: string

    • return_code: number

    • stderr: string

    • type: "encrypted_code_execution_result"

Code Execution Tool Result Block Param

• code_execution_tool_result_block_param: object { content, tool_use_id, type, cache_control }

  • content: CodeExecutionToolResultErrorParam or CodeExecutionResultBlockParam or EncryptedCodeExecutionResultBlockParam

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

    • code_execution_tool_result_error_param: object { error_code, type }

      • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

        • "invalid_tool_input"

        • "unavailable"

        • "too_many_requests"

        • "execution_time_exceeded"

      • type: "code_execution_tool_result_error"

    • code_execution_result_block_param: object { content, return_code, stderr, 2 more }

      • content: array of CodeExecutionOutputBlockParam

        • file_id: string

        • type: "code_execution_output"

      • return_code: number

      • stderr: string

      • stdout: string

      • type: "code_execution_result"

    • encrypted_code_execution_result_block_param: object { content, encrypted_stdout, return_code, 2 more }

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

      • content: array of CodeExecutionOutputBlockParam

        • file_id: string

        • type: "code_execution_output"

      • encrypted_stdout: string

      • return_code: number

      • stderr: string

      • type: "encrypted_code_execution_result"

  • tool_use_id: string

  • type: "code_execution_tool_result"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

Code Execution Tool Result Block Param Content

• code_execution_tool_result_block_param_content: CodeExecutionToolResultErrorParam or CodeExecutionResultBlockParam or EncryptedCodeExecutionResultBlockParam

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

  • code_execution_tool_result_error_param: object { error_code, type }

    • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

      • "invalid_tool_input"

      • "unavailable"

      • "too_many_requests"

      • "execution_time_exceeded"

    • type: "code_execution_tool_result_error"

  • code_execution_result_block_param: object { content, return_code, stderr, 2 more }

    • content: array of CodeExecutionOutputBlockParam

      • file_id: string

      • type: "code_execution_output"

    • return_code: number

    • stderr: string

    • stdout: string

    • type: "code_execution_result"

  • encrypted_code_execution_result_block_param: object { content, encrypted_stdout, return_code, 2 more }

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

    • content: array of CodeExecutionOutputBlockParam

      • file_id: string

      • type: "code_execution_output"

    • encrypted_stdout: string

    • return_code: number

    • stderr: string

    • type: "encrypted_code_execution_result"

Code Execution Tool Result Error

• code_execution_tool_result_error: object { error_code, type }

  • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

    • "invalid_tool_input"

    • "unavailable"

    • "too_many_requests"

    • "execution_time_exceeded"

  • type: "code_execution_tool_result_error"

Code Execution Tool Result Error Code

• code_execution_tool_result_error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

  • "invalid_tool_input"

  • "unavailable"

  • "too_many_requests"

  • "execution_time_exceeded"

Code Execution Tool Result Error Param

• code_execution_tool_result_error_param: object { error_code, type }

  • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

    • "invalid_tool_input"

    • "unavailable"

    • "too_many_requests"

    • "execution_time_exceeded"

  • type: "code_execution_tool_result_error"

Container

• container: object { id, expires_at }

  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.

Container Upload Block

• container_upload_block: object { file_id, type }

  Response model for a file uploaded to the container.

  • file_id: string

  • type: "container_upload"

Container Upload Block Param

• container_upload_block_param: object { file_id, type, cache_control }

  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.

  • file_id: string

  • type: "container_upload"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

Content Block

• content_block: TextBlock or ThinkingBlock or RedactedThinkingBlock or 9 more

  Response model for a file uploaded to the container.

  • text_block: object { citations, text, type }

    • citations: array of TextCitation

      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.

      • citation_char_location: object { cited_text, document_index, document_title, 4 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_char_index: number

        • file_id: string

        • start_char_index: number

        • type: "char_location"

      • citation_page_location: object { cited_text, document_index, document_title, 4 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_page_number: number

        • file_id: string

        • start_page_number: number

        • type: "page_location"

      • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_block_index: number

        • file_id: string

        • start_block_index: number

        • type: "content_block_location"

      • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

        • cited_text: string

        • encrypted_index: string

        • title: string

        • type: "web_search_result_location"

        • url: string

      • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

        • cited_text: string

        • end_block_index: number

        • search_result_index: number

        • source: string

        • start_block_index: number

        • title: string

        • type: "search_result_location"

    • text: string

    • type: "text"

  • thinking_block: object { signature, thinking, type }

    • signature: string

    • thinking: string

    • type: "thinking"

  • redacted_thinking_block: object { data, type }

    • data: string

    • type: "redacted_thinking"

  • tool_use_block: object { id, caller, input, 2 more }

    • id: string

    • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

      Tool invocation directly from the model.

      • direct_caller: object { type }

        Tool invocation directly from the model.

        • type: "direct"

      • server_tool_caller: object { tool_id, type }

        Tool invocation generated by a server-side tool.

        • tool_id: string

        • type: "code_execution_20250825"

      • server_tool_caller_20260120: object { tool_id, type }

        • tool_id: string

        • type: "code_execution_20260120"

    • input: map[unknown]

    • name: string

    • type: "tool_use"

  • server_tool_use_block: object { id, caller, input, 2 more }

    • id: string

    • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

      Tool invocation directly from the model.

      • direct_caller: object { type }

        Tool invocation directly from the model.

        • type: "direct"

      • server_tool_caller: object { tool_id, type }

        Tool invocation generated by a server-side tool.

        • tool_id: string

        • type: "code_execution_20250825"

      • server_tool_caller_20260120: object { tool_id, type }

        • tool_id: string

        • type: "code_execution_20260120"

    • 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"

    • type: "server_tool_use"

  • web_search_tool_result_block: object { caller, content, tool_use_id, type }

    • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

      Tool invocation directly from the model.

      • direct_caller: object { type }

        Tool invocation directly from the model.

        • type: "direct"

      • server_tool_caller: object { tool_id, type }

        Tool invocation generated by a server-side tool.

        • tool_id: string

        • type: "code_execution_20250825"

      • server_tool_caller_20260120: object { tool_id, type }

        • tool_id: string

        • type: "code_execution_20260120"

    • content: WebSearchToolResultError or array of WebSearchResultBlock

      • web_search_tool_result_error: object { error_code, type }

        • error_code: "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"

        • type: "web_search_tool_result_error"

      • union_member_1: array of WebSearchResultBlock

        • encrypted_content: string

        • page_age: string

        • title: string

        • type: "web_search_result"

        • url: string

    • tool_use_id: string

    • type: "web_search_tool_result"

  • web_fetch_tool_result_block: object { caller, content, tool_use_id, type }

    • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

      Tool invocation directly from the model.

      • direct_caller: object { type }

        Tool invocation directly from the model.

        • type: "direct"

      • server_tool_caller: object { tool_id, type }

        Tool invocation generated by a server-side tool.

        • tool_id: string

        • type: "code_execution_20250825"

      • server_tool_caller_20260120: object { tool_id, type }

        • tool_id: string

        • type: "code_execution_20260120"

    • content: WebFetchToolResultErrorBlock or WebFetchBlock

      • web_fetch_tool_result_error_block: object { error_code, type }

        • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

          • "invalid_tool_input"

          • "url_too_long"

          • "url_not_allowed"

          • "url_not_accessible"

          • "unsupported_content_type"

          • "too_many_requests"

          • "max_uses_exceeded"

          • "unavailable"

        • type: "web_fetch_tool_result_error"

      • web_fetch_block: object { content, retrieved_at, type, url }

        • content: object { citations, source, title, type }

          • citations: object { enabled }

            Citation configuration for the document

            • enabled: boolean

          • source: Base64PDFSource or PlainTextSource

            • base64_pdf_source: object { data, media_type, type }

              • data: string

              • media_type: "application/pdf"

              • type: "base64"

            • plain_text_source: object { data, media_type, type }

              • data: string

              • media_type: "text/plain"

              • type: "text"

          • title: string

            The title of the document

          • type: "document"

        • retrieved_at: string

          ISO 8601 timestamp when the content was retrieved

        • type: "web_fetch_result"

        • url: string

          Fetched content URL

    • tool_use_id: string

    • type: "web_fetch_tool_result"

  • code_execution_tool_result_block: object { content, tool_use_id, type }

    • content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

      • code_execution_tool_result_error: object { error_code, type }

        • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

        • type: "code_execution_tool_result_error"

      • code_execution_result_block: object { content, return_code, stderr, 2 more }

        • content: array of CodeExecutionOutputBlock

          • file_id: string

          • type: "code_execution_output"

        • return_code: number

        • stderr: string

        • stdout: string

        • type: "code_execution_result"

      • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

        • content: array of CodeExecutionOutputBlock

          • file_id: string

          • type: "code_execution_output"

        • encrypted_stdout: string

        • return_code: number

        • stderr: string

        • type: "encrypted_code_execution_result"

    • tool_use_id: string

    • type: "code_execution_tool_result"

  • bash_code_execution_tool_result_block: object { content, tool_use_id, type }

    • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

      • bash_code_execution_tool_result_error: object { error_code, type }

        • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

          • "output_file_too_large"

        • type: "bash_code_execution_tool_result_error"

      • bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

        • content: array of BashCodeExecutionOutputBlock

          • file_id: string

          • type: "bash_code_execution_output"

        • return_code: number

        • stderr: string

        • stdout: string

        • type: "bash_code_execution_result"

    • tool_use_id: string

    • type: "bash_code_execution_tool_result"

  • text_editor_code_execution_tool_result_block: object { content, tool_use_id, type }

    • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

      • text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

        • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

          • "file_not_found"

        • error_message: string

        • type: "text_editor_code_execution_tool_result_error"

      • text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

        • content: string

        • file_type: "text" or "image" or "pdf"

          • "text"

          • "image"

          • "pdf"

        • num_lines: number

        • start_line: number

        • total_lines: number

        • type: "text_editor_code_execution_view_result"

      • text_editor_code_execution_create_result_block: object { is_file_update, type }

        • is_file_update: boolean

        • type: "text_editor_code_execution_create_result"

      • text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

        • lines: array of string

        • new_lines: number

        • new_start: number

        • old_lines: number

        • old_start: number

        • type: "text_editor_code_execution_str_replace_result"

    • tool_use_id: string

    • type: "text_editor_code_execution_tool_result"

  • tool_search_tool_result_block: object { content, tool_use_id, type }

    • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

      • tool_search_tool_result_error: object { error_code, error_message, type }

        • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

        • error_message: string

        • type: "tool_search_tool_result_error"

      • tool_search_tool_search_result_block: object { tool_references, type }

        • tool_references: array of ToolReferenceBlock

          • tool_name: string

          • type: "tool_reference"

        • type: "tool_search_tool_search_result"

    • tool_use_id: string

    • type: "tool_search_tool_result"

  • container_upload_block: object { file_id, type }

    Response model for a file uploaded to the container.

    • file_id: string

    • type: "container_upload"

Content Block Param

• content_block_param: TextBlockParam or ImageBlockParam or DocumentBlockParam or 13 more

  Regular text content.

  • text_block_param: object { text, type, cache_control, citations }

    • text: string

    • type: "text"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • citations: optional array of TextCitationParam

      • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_char_index: number

        • start_char_index: number

        • type: "char_location"

      • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_page_number: number

        • start_page_number: number

        • type: "page_location"

      • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_block_index: number

        • start_block_index: number

        • type: "content_block_location"

      • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

        • cited_text: string

        • encrypted_index: string

        • title: string

        • type: "web_search_result_location"

        • url: string

      • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

        • cited_text: string

        • end_block_index: number

        • search_result_index: number

        • source: string

        • start_block_index: number

        • title: string

        • type: "search_result_location"

  • image_block_param: object { source, type, cache_control }

    • source: Base64ImageSource or URLImageSource

      • base64_image_source: object { data, media_type, type }

        • data: string

        • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

          • "image/jpeg"

          • "image/png"

          • "image/gif"

          • "image/webp"

        • type: "base64"

      • url_image_source: object { type, url }

        • type: "url"

        • url: string

    • type: "image"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

  • document_block_param: object { source, type, cache_control, 3 more }

    • source: Base64PDFSource or PlainTextSource or ContentBlockSource or URLPDFSource

      • base64_pdf_source: object { data, media_type, type }

        • data: string

        • media_type: "application/pdf"

        • type: "base64"

      • plain_text_source: object { data, media_type, type }

        • data: string

        • media_type: "text/plain"

        • type: "text"

      • content_block_source: object { content, type }

        • content: string or array of ContentBlockSourceContent

          • union_member_0: string

          • content_block_source_content: array of ContentBlockSourceContent

            • text_block_param: object { text, type, cache_control, citations }

              • text: string

              • type: "text"

              • cache_control: optional object { type, ttl }

                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.

                  • "5m"

                  • "1h"

              • citations: optional array of TextCitationParam

                • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

                  • cited_text: string

                  • document_index: number

                  • document_title: string

                  • end_char_index: number

                  • start_char_index: number

                  • type: "char_location"

                • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

                  • cited_text: string

                  • document_index: number

                  • document_title: string

                  • end_page_number: number

                  • start_page_number: number

                  • type: "page_location"

                • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

                  • cited_text: string

                  • document_index: number

                  • document_title: string

                  • end_block_index: number

                  • start_block_index: number

                  • type: "content_block_location"

                • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

                  • cited_text: string

                  • encrypted_index: string

                  • title: string

                  • type: "web_search_result_location"

                  • url: string

                • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

                  • cited_text: string

                  • end_block_index: number

                  • search_result_index: number

                  • source: string

                  • start_block_index: number

                  • title: string

                  • type: "search_result_location"

            • image_block_param: object { source, type, cache_control }

              • source: Base64ImageSource or URLImageSource

                • base64_image_source: object { data, media_type, type }

                  • data: string

                  • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

                    • "image/jpeg"

                    • "image/png"

                    • "image/gif"

                    • "image/webp"

                  • type: "base64"

                • url_image_source: object { type, url }

                  • type: "url"

                  • url: string

              • type: "image"

              • cache_control: optional object { type, ttl }

                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.

                  • "5m"

                  • "1h"

        • type: "content"

      • url_pdf_source: object { type, url }

        • type: "url"

        • url: string

    • type: "document"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • citations: optional object { enabled }

      • enabled: optional boolean

    • context: optional string

    • title: optional string

  • search_result_block_param: object { content, source, title, 3 more }

    • content: array of TextBlockParam

      • text: string

      • type: "text"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

      • citations: optional array of TextCitationParam

        • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_char_index: number

          • start_char_index: number

          • type: "char_location"

        • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_page_number: number

          • start_page_number: number

          • type: "page_location"

        • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_block_index: number

          • start_block_index: number

          • type: "content_block_location"

        • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

          • cited_text: string

          • encrypted_index: string

          • title: string

          • type: "web_search_result_location"

          • url: string

        • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

          • cited_text: string

          • end_block_index: number

          • search_result_index: number

          • source: string

          • start_block_index: number

          • title: string

          • type: "search_result_location"

    • source: string

    • title: string

    • type: "search_result"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • citations: optional object { enabled }

      • enabled: optional boolean

  • thinking_block_param: object { signature, thinking, type }

    • signature: string

    • thinking: string

    • type: "thinking"

  • redacted_thinking_block_param: object { data, type }

    • data: string

    • type: "redacted_thinking"

  • tool_use_block_param: object { id, input, name, 3 more }

    • id: string

    • input: map[unknown]

    • name: string

    • type: "tool_use"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

      Tool invocation directly from the model.

      • direct_caller: object { type }

        Tool invocation directly from the model.

        • type: "direct"

      • server_tool_caller: object { tool_id, type }

        Tool invocation generated by a server-side tool.

        • tool_id: string

        • type: "code_execution_20250825"

      • server_tool_caller_20260120: object { tool_id, type }

        • tool_id: string

        • type: "code_execution_20260120"

  • tool_result_block_param: object { tool_use_id, type, cache_control, 2 more }

    • tool_use_id: string

    • type: "tool_result"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • content: optional array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 2 more

      • text_block_param: object { text, type, cache_control, citations }

        • text: string

        • type: "text"

        • cache_control: optional object { type, ttl }

          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.

            • "5m"

            • "1h"

        • citations: optional array of TextCitationParam

          • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_char_index: number

            • start_char_index: number

            • type: "char_location"

          • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_page_number: number

            • start_page_number: number

            • type: "page_location"

          • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_block_index: number

            • start_block_index: number

            • type: "content_block_location"

          • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

            • cited_text: string

            • encrypted_index: string

            • title: string

            • type: "web_search_result_location"

            • url: string

          • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

            • cited_text: string

            • end_block_index: number

            • search_result_index: number

            • source: string

            • start_block_index: number

            • title: string

            • type: "search_result_location"

      • image_block_param: object { source, type, cache_control }

        • source: Base64ImageSource or URLImageSource

          • base64_image_source: object { data, media_type, type }

            • data: string

            • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

              • "image/jpeg"

              • "image/png"

              • "image/gif"

              • "image/webp"

            • type: "base64"

          • url_image_source: object { type, url }

            • type: "url"

            • url: string

        • type: "image"

        • cache_control: optional object { type, ttl }

          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.

            • "5m"

            • "1h"

      • search_result_block_param: object { content, source, title, 3 more }

        • content: array of TextBlockParam

          • text: string

          • type: "text"

          • cache_control: optional object { type, ttl }

            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.

              • "5m"

              • "1h"

          • citations: optional array of TextCitationParam

            • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

              • cited_text: string

              • document_index: number

              • document_title: string

              • end_char_index: number

              • start_char_index: number

              • type: "char_location"

            • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

              • cited_text: string

              • document_index: number

              • document_title: string

              • end_page_number: number

              • start_page_number: number

              • type: "page_location"

            • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

              • cited_text: string

              • document_index: number

              • document_title: string

              • end_block_index: number

              • start_block_index: number

              • type: "content_block_location"

            • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

              • cited_text: string

              • encrypted_index: string

              • title: string

              • type: "web_search_result_location"

              • url: string

            • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

              • cited_text: string

              • end_block_index: number

              • search_result_index: number

              • source: string

              • start_block_index: number

              • title: string

              • type: "search_result_location"

        • source: string

        • title: string

        • type: "search_result"

        • cache_control: optional object { type, ttl }

          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.

            • "5m"

            • "1h"

        • citations: optional object { enabled }

          • enabled: optional boolean

      • document_block_param: object { source, type, cache_control, 3 more }

        • source: Base64PDFSource or PlainTextSource or ContentBlockSource or URLPDFSource

          • base64_pdf_source: object { data, media_type, type }

            • data: string

            • media_type: "application/pdf"

            • type: "base64"

          • plain_text_source: object { data, media_type, type }

            • data: string

            • media_type: "text/plain"

            • type: "text"

          • content_block_source: object { content, type }

            • content: string or array of ContentBlockSourceContent

              • union_member_0: string

              • content_block_source_content: array of ContentBlockSourceContent

                • text_block_param: object { text, type, cache_control, citations }

                  • text: string

                  • type: "text"

                  • cache_control: optional object { type, ttl }

                    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.

                      • "5m"

                      • "1h"

                  • citations: optional array of TextCitationParam

                    • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

                      • cited_text: string

                      • document_index: number

                      • document_title: string

                      • end_char_index: number

                      • start_char_index: number

                      • type: "char_location"

                    • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

                      • cited_text: string

                      • document_index: number

                      • document_title: string

                      • end_page_number: number

                      • start_page_number: number

                      • type: "page_location"

                    • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

                      • cited_text: string

                      • document_index: number

                      • document_title: string

                      • end_block_index: number

                      • start_block_index: number

                      • type: "content_block_location"

                    • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

                      • cited_text: string

                      • encrypted_index: string

                      • title: string

                      • type: "web_search_result_location"

                      • url: string

                    • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

                      • cited_text: string

                      • end_block_index: number

                      • search_result_index: number

                      • source: string

                      • start_block_index: number

                      • title: string

                      • type: "search_result_location"

                • image_block_param: object { source, type, cache_control }

                  • source: Base64ImageSource or URLImageSource

                    • base64_image_source: object { data, media_type, type }

                      • data: string

                      • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

                        • "image/jpeg"

                        • "image/png"

                        • "image/gif"

                        • "image/webp"

                      • type: "base64"

                    • url_image_source: object { type, url }

                      • type: "url"

                      • url: string

                  • type: "image"

                  • cache_control: optional object { type, ttl }

                    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.

                      • "5m"

                      • "1h"

            • type: "content"

          • url_pdf_source: object { type, url }

            • type: "url"

            • url: string

        • type: "document"

        • cache_control: optional object { type, ttl }

          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.

            • "5m"

            • "1h"

        • citations: optional object { enabled }

          • enabled: optional boolean

        • context: optional string

        • title: optional string

      • tool_reference_block_param: object { tool_name, type, cache_control }

        Tool reference block that can be included in tool_result content.

        • tool_name: string

        • type: "tool_reference"

        • cache_control: optional object { type, ttl }

          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.

            • "5m"

            • "1h"

    • is_error: optional boolean

  • server_tool_use_block_param: object { id, input, name, 3 more }

    • id: string

    • 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"

    • type: "server_tool_use"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

      Tool invocation directly from the model.

      • direct_caller: object { type }

        Tool invocation directly from the model.

        • type: "direct"

      • server_tool_caller: object { tool_id, type }

        Tool invocation generated by a server-side tool.

        • tool_id: string

        • type: "code_execution_20250825"

      • server_tool_caller_20260120: object { tool_id, type }

        • tool_id: string

        • type: "code_execution_20260120"

  • web_search_tool_result_block_param: object { content, tool_use_id, type, 2 more }

    • content: array of WebSearchResultBlockParam or WebSearchToolRequestError

      • web_search_tool_result_block_item: array of WebSearchResultBlockParam

        • encrypted_content: string

        • title: string

        • type: "web_search_result"

        • url: string

        • page_age: optional string

      • web_search_tool_request_error: object { error_code, type }

        • error_code: "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"

        • type: "web_search_tool_result_error"

    • tool_use_id: string

    • type: "web_search_tool_result"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

      Tool invocation directly from the model.

      • direct_caller: object { type }

        Tool invocation directly from the model.

        • type: "direct"

      • server_tool_caller: object { tool_id, type }

        Tool invocation generated by a server-side tool.

        • tool_id: string

        • type: "code_execution_20250825"

      • server_tool_caller_20260120: object { tool_id, type }

        • tool_id: string

        • type: "code_execution_20260120"

  • web_fetch_tool_result_block_param: object { content, tool_use_id, type, 2 more }

    • content: WebFetchToolResultErrorBlockParam or WebFetchBlockParam

      • web_fetch_tool_result_error_block_param: object { error_code, type }

        • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

          • "invalid_tool_input"

          • "url_too_long"

          • "url_not_allowed"

          • "url_not_accessible"

          • "unsupported_content_type"

          • "too_many_requests"

          • "max_uses_exceeded"

          • "unavailable"

        • type: "web_fetch_tool_result_error"

      • web_fetch_block_param: object { content, type, url, retrieved_at }

        • content: object { source, type, cache_control, 3 more }

          • source: Base64PDFSource or PlainTextSource or ContentBlockSource or URLPDFSource

            • base64_pdf_source: object { data, media_type, type }

              • data: string

              • media_type: "application/pdf"

              • type: "base64"

            • plain_text_source: object { data, media_type, type }

              • data: string

              • media_type: "text/plain"

              • type: "text"

            • content_block_source: object { content, type }

              • content: string or array of ContentBlockSourceContent

                • union_member_0: string

                • content_block_source_content: array of ContentBlockSourceContent

                  • text_block_param: object { text, type, cache_control, citations }

                    • text: string

                    • type: "text"

                    • cache_control: optional object { type, ttl }

                      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.

                        • "5m"

                        • "1h"

                    • citations: optional array of TextCitationParam

                      • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

                        • cited_text: string

                        • document_index: number

                        • document_title: string

                        • end_char_index: number

                        • start_char_index: number

                        • type: "char_location"

                      • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

                        • cited_text: string

                        • document_index: number

                        • document_title: string

                        • end_page_number: number

                        • start_page_number: number

                        • type: "page_location"

                      • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

                        • cited_text: string

                        • document_index: number

                        • document_title: string

                        • end_block_index: number

                        • start_block_index: number

                        • type: "content_block_location"

                      • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

                        • cited_text: string

                        • encrypted_index: string

                        • title: string

                        • type: "web_search_result_location"

                        • url: string

                      • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

                        • cited_text: string

                        • end_block_index: number

                        • search_result_index: number

                        • source: string

                        • start_block_index: number

                        • title: string

                        • type: "search_result_location"

                  • image_block_param: object { source, type, cache_control }

                    • source: Base64ImageSource or URLImageSource

                      • base64_image_source: object { data, media_type, type }

                        • data: string

                        • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

                          • "image/jpeg"

                          • "image/png"

                          • "image/gif"

                          • "image/webp"

                        • type: "base64"

                      • url_image_source: object { type, url }

                        • type: "url"

                        • url: string

                    • type: "image"

                    • cache_control: optional object { type, ttl }

                      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.

                        • "5m"

                        • "1h"

              • type: "content"

            • url_pdf_source: object { type, url }

              • type: "url"

              • url: string

          • type: "document"

          • cache_control: optional object { type, ttl }

            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.

              • "5m"

              • "1h"

          • citations: optional object { enabled }

            • enabled: optional boolean

          • context: optional string

          • title: optional string

        • type: "web_fetch_result"

        • url: string

          Fetched content URL

        • retrieved_at: optional string

          ISO 8601 timestamp when the content was retrieved

    • tool_use_id: string

    • type: "web_fetch_tool_result"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

      Tool invocation directly from the model.

      • direct_caller: object { type }

        Tool invocation directly from the model.

        • type: "direct"

      • server_tool_caller: object { tool_id, type }

        Tool invocation generated by a server-side tool.

        • tool_id: string

        • type: "code_execution_20250825"

      • server_tool_caller_20260120: object { tool_id, type }

        • tool_id: string

        • type: "code_execution_20260120"

  • code_execution_tool_result_block_param: object { content, tool_use_id, type, cache_control }

    • content: CodeExecutionToolResultErrorParam or CodeExecutionResultBlockParam or EncryptedCodeExecutionResultBlockParam

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

      • code_execution_tool_result_error_param: object { error_code, type }

        • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

        • type: "code_execution_tool_result_error"

      • code_execution_result_block_param: object { content, return_code, stderr, 2 more }

        • content: array of CodeExecutionOutputBlockParam

          • file_id: string

          • type: "code_execution_output"

        • return_code: number

        • stderr: string

        • stdout: string

        • type: "code_execution_result"

      • encrypted_code_execution_result_block_param: object { content, encrypted_stdout, return_code, 2 more }

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

        • content: array of CodeExecutionOutputBlockParam

          • file_id: string

          • type: "code_execution_output"

        • encrypted_stdout: string

        • return_code: number

        • stderr: string

        • type: "encrypted_code_execution_result"

    • tool_use_id: string

    • type: "code_execution_tool_result"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

  • bash_code_execution_tool_result_block_param: object { content, tool_use_id, type, cache_control }

    • content: BashCodeExecutionToolResultErrorParam or BashCodeExecutionResultBlockParam

      • bash_code_execution_tool_result_error_param: object { error_code, type }

        • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

          • "output_file_too_large"

        • type: "bash_code_execution_tool_result_error"

      • bash_code_execution_result_block_param: object { content, return_code, stderr, 2 more }

        • content: array of BashCodeExecutionOutputBlockParam

          • file_id: string

          • type: "bash_code_execution_output"

        • return_code: number

        • stderr: string

        • stdout: string

        • type: "bash_code_execution_result"

    • tool_use_id: string

    • type: "bash_code_execution_tool_result"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

  • text_editor_code_execution_tool_result_block_param: object { content, tool_use_id, type, cache_control }

    • content: TextEditorCodeExecutionToolResultErrorParam or TextEditorCodeExecutionViewResultBlockParam or TextEditorCodeExecutionCreateResultBlockParam or TextEditorCodeExecutionStrReplaceResultBlockParam

      • text_editor_code_execution_tool_result_error_param: object { error_code, type, error_message }

        • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

          • "file_not_found"

        • type: "text_editor_code_execution_tool_result_error"

        • error_message: optional string

      • text_editor_code_execution_view_result_block_param: object { content, file_type, type, 3 more }

        • content: string

        • file_type: "text" or "image" or "pdf"

          • "text"

          • "image"

          • "pdf"

        • type: "text_editor_code_execution_view_result"

        • num_lines: optional number

        • start_line: optional number

        • total_lines: optional number

      • text_editor_code_execution_create_result_block_param: object { is_file_update, type }

        • is_file_update: boolean

        • type: "text_editor_code_execution_create_result"

      • text_editor_code_execution_str_replace_result_block_param: object { type, lines, new_lines, 3 more }

        • type: "text_editor_code_execution_str_replace_result"

        • lines: optional array of string

        • new_lines: optional number

        • new_start: optional number

        • old_lines: optional number

        • old_start: optional number

    • tool_use_id: string

    • type: "text_editor_code_execution_tool_result"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

  • tool_search_tool_result_block_param: object { content, tool_use_id, type, cache_control }

    • content: ToolSearchToolResultErrorParam or ToolSearchToolSearchResultBlockParam

      • tool_search_tool_result_error_param: object { error_code, type }

        • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

          • "invalid_tool_input"

          • "unavailable"

          • "too_many_requests"

          • "execution_time_exceeded"

        • type: "tool_search_tool_result_error"

      • tool_search_tool_search_result_block_param: object { tool_references, type }

        • tool_references: array of ToolReferenceBlockParam

          • tool_name: string

          • type: "tool_reference"

          • cache_control: optional object { type, ttl }

            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.

              • "5m"

              • "1h"

        • type: "tool_search_tool_search_result"

    • tool_use_id: string

    • type: "tool_search_tool_result"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

  • container_upload_block_param: object { file_id, type, cache_control }

    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.

    • file_id: string

    • type: "container_upload"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

Content Block Source

• content_block_source: object { content, type }

  • content: string or array of ContentBlockSourceContent

    • union_member_0: string

    • content_block_source_content: array of ContentBlockSourceContent

      • text_block_param: object { text, type, cache_control, citations }

        • text: string

        • type: "text"

        • cache_control: optional object { type, ttl }

          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.

            • "5m"

            • "1h"

        • citations: optional array of TextCitationParam

          • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_char_index: number

            • start_char_index: number

            • type: "char_location"

          • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_page_number: number

            • start_page_number: number

            • type: "page_location"

          • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_block_index: number

            • start_block_index: number

            • type: "content_block_location"

          • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

            • cited_text: string

            • encrypted_index: string

            • title: string

            • type: "web_search_result_location"

            • url: string

          • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

            • cited_text: string

            • end_block_index: number

            • search_result_index: number

            • source: string

            • start_block_index: number

            • title: string

            • type: "search_result_location"

      • image_block_param: object { source, type, cache_control }

        • source: Base64ImageSource or URLImageSource

          • base64_image_source: object { data, media_type, type }

            • data: string

            • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

              • "image/jpeg"

              • "image/png"

              • "image/gif"

              • "image/webp"

            • type: "base64"

          • url_image_source: object { type, url }

            • type: "url"

            • url: string

        • type: "image"

        • cache_control: optional object { type, ttl }

          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.

            • "5m"

            • "1h"

  • type: "content"

Content Block Source Content

• content_block_source_content: TextBlockParam or ImageBlockParam

  • text_block_param: object { text, type, cache_control, citations }

    • text: string

    • type: "text"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • citations: optional array of TextCitationParam

      • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_char_index: number

        • start_char_index: number

        • type: "char_location"

      • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_page_number: number

        • start_page_number: number

        • type: "page_location"

      • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_block_index: number

        • start_block_index: number

        • type: "content_block_location"

      • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

        • cited_text: string

        • encrypted_index: string

        • title: string

        • type: "web_search_result_location"

        • url: string

      • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

        • cited_text: string

        • end_block_index: number

        • search_result_index: number

        • source: string

        • start_block_index: number

        • title: string

        • type: "search_result_location"

  • image_block_param: object { source, type, cache_control }

    • source: Base64ImageSource or URLImageSource

      • base64_image_source: object { data, media_type, type }

        • data: string

        • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

          • "image/jpeg"

          • "image/png"

          • "image/gif"

          • "image/webp"

        • type: "base64"

      • url_image_source: object { type, url }

        • type: "url"

        • url: string

    • type: "image"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

Direct Caller

• direct_caller: object { type }

  Tool invocation directly from the model.

  • type: "direct"

Document Block

• document_block: object { citations, source, title, type }

  • citations: object { enabled }

    Citation configuration for the document

    • enabled: boolean

  • source: Base64PDFSource or PlainTextSource

    • base64_pdf_source: object { data, media_type, type }

      • data: string

      • media_type: "application/pdf"

      • type: "base64"

    • plain_text_source: object { data, media_type, type }

      • data: string

      • media_type: "text/plain"

      • type: "text"

  • title: string

    The title of the document

  • type: "document"

Document Block Param

• document_block_param: object { source, type, cache_control, 3 more }

  • source: Base64PDFSource or PlainTextSource or ContentBlockSource or URLPDFSource

    • base64_pdf_source: object { data, media_type, type }

      • data: string

      • media_type: "application/pdf"

      • type: "base64"

    • plain_text_source: object { data, media_type, type }

      • data: string

      • media_type: "text/plain"

      • type: "text"

    • content_block_source: object { content, type }

      • content: string or array of ContentBlockSourceContent

        • union_member_0: string

        • content_block_source_content: array of ContentBlockSourceContent

          • text_block_param: object { text, type, cache_control, citations }

            • text: string

            • type: "text"

            • cache_control: optional object { type, ttl }

              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.

                • "5m"

                • "1h"

            • citations: optional array of TextCitationParam

              • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

                • cited_text: string

                • document_index: number

                • document_title: string

                • end_char_index: number

                • start_char_index: number

                • type: "char_location"

              • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

                • cited_text: string

                • document_index: number

                • document_title: string

                • end_page_number: number

                • start_page_number: number

                • type: "page_location"

              • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

                • cited_text: string

                • document_index: number

                • document_title: string

                • end_block_index: number

                • start_block_index: number

                • type: "content_block_location"

              • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

                • cited_text: string

                • encrypted_index: string

                • title: string

                • type: "web_search_result_location"

                • url: string

              • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

                • cited_text: string

                • end_block_index: number

                • search_result_index: number

                • source: string

                • start_block_index: number

                • title: string

                • type: "search_result_location"

          • image_block_param: object { source, type, cache_control }

            • source: Base64ImageSource or URLImageSource

              • base64_image_source: object { data, media_type, type }

                • data: string

                • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

                  • "image/jpeg"

                  • "image/png"

                  • "image/gif"

                  • "image/webp"

                • type: "base64"

              • url_image_source: object { type, url }

                • type: "url"

                • url: string

            • type: "image"

            • cache_control: optional object { type, ttl }

              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.

                • "5m"

                • "1h"

      • type: "content"

    • url_pdf_source: object { type, url }

      • type: "url"

      • url: string

  • type: "document"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

  • citations: optional object { enabled }

    • enabled: optional boolean

  • context: optional string

  • title: optional string

Encrypted Code Execution Result Block

• encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

  • content: array of CodeExecutionOutputBlock

    • file_id: string

    • type: "code_execution_output"

  • encrypted_stdout: string

  • return_code: number

  • stderr: string

  • type: "encrypted_code_execution_result"

Encrypted Code Execution Result Block Param

• encrypted_code_execution_result_block_param: object { content, encrypted_stdout, return_code, 2 more }

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

  • content: array of CodeExecutionOutputBlockParam

    • file_id: string

    • type: "code_execution_output"

  • encrypted_stdout: string

  • return_code: number

  • stderr: string

  • type: "encrypted_code_execution_result"

Image Block Param

• image_block_param: object { source, type, cache_control }

  • source: Base64ImageSource or URLImageSource

    • base64_image_source: object { data, media_type, type }

      • data: string

      • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

        • "image/jpeg"

        • "image/png"

        • "image/gif"

        • "image/webp"

      • type: "base64"

    • url_image_source: object { type, url }

      • type: "url"

      • url: string

  • type: "image"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

Input JSON Delta

• input_json_delta: object { partial_json, type }

  • partial_json: string

  • type: "input_json_delta"

JSON Output Format

• json_output_format: object { schema, type }

  • schema: map[unknown]

    The JSON schema of the format

  • type: "json_schema"

Memory Tool 20250818

• memory_tool_20250818: object { name, type, allowed_callers, 4 more }

  • name: "memory"

    Name of the tool.

    This is how the tool will be called by the model and in tool_use blocks.

  • type: "memory_20250818"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • cache_control: optional object { type, ttl }

    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.

      • "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 { id, container, content, 7 more }

  • id: string

    Unique object identifier.

    The format and length of IDs may change over time.

  • container: object { id, expires_at }

    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.

  • 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:

    [{"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:

    [
      {"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:

    [{"type": "text", "text": "B)"}]
    

    • text_block: object { citations, text, type }

      • citations: array of TextCitation

        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.

        • citation_char_location: object { cited_text, document_index, document_title, 4 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_char_index: number

          • file_id: string

          • start_char_index: number

          • type: "char_location"

        • citation_page_location: object { cited_text, document_index, document_title, 4 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_page_number: number

          • file_id: string

          • start_page_number: number

          • type: "page_location"

        • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_block_index: number

          • file_id: string

          • start_block_index: number

          • type: "content_block_location"

        • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

          • cited_text: string

          • encrypted_index: string

          • title: string

          • type: "web_search_result_location"

          • url: string

        • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

          • cited_text: string

          • end_block_index: number

          • search_result_index: number

          • source: string

          • start_block_index: number

          • title: string

          • type: "search_result_location"

      • text: string

      • type: "text"

    • thinking_block: object { signature, thinking, type }

      • signature: string

      • thinking: string

      • type: "thinking"

    • redacted_thinking_block: object { data, type }

      • data: string

      • type: "redacted_thinking"

    • tool_use_block: object { id, caller, input, 2 more }

      • id: string

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

      • input: map[unknown]

      • name: string

      • type: "tool_use"

    • server_tool_use_block: object { id, caller, input, 2 more }

      • id: string

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

      • 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"

      • type: "server_tool_use"

    • web_search_tool_result_block: object { caller, content, tool_use_id, type }

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

      • content: WebSearchToolResultError or array of WebSearchResultBlock

        • web_search_tool_result_error: object { error_code, type }

          • error_code: "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"

          • type: "web_search_tool_result_error"

        • union_member_1: array of WebSearchResultBlock

          • encrypted_content: string

          • page_age: string

          • title: string

          • type: "web_search_result"

          • url: string

      • tool_use_id: string

      • type: "web_search_tool_result"

    • web_fetch_tool_result_block: object { caller, content, tool_use_id, type }

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

      • content: WebFetchToolResultErrorBlock or WebFetchBlock

        • web_fetch_tool_result_error_block: object { error_code, type }

          • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

            • "invalid_tool_input"

            • "url_too_long"

            • "url_not_allowed"

            • "url_not_accessible"

            • "unsupported_content_type"

            • "too_many_requests"

            • "max_uses_exceeded"

            • "unavailable"

          • type: "web_fetch_tool_result_error"

        • web_fetch_block: object { content, retrieved_at, type, url }

          • content: object { citations, source, title, type }

            • citations: object { enabled }

              Citation configuration for the document

              • enabled: boolean

            • source: Base64PDFSource or PlainTextSource

              • base64_pdf_source: object { data, media_type, type }

                • data: string

                • media_type: "application/pdf"

                • type: "base64"

              • plain_text_source: object { data, media_type, type }

                • data: string

                • media_type: "text/plain"

                • type: "text"

            • title: string

              The title of the document

            • type: "document"

          • retrieved_at: string

            ISO 8601 timestamp when the content was retrieved

          • type: "web_fetch_result"

          • url: string

            Fetched content URL

      • tool_use_id: string

      • type: "web_fetch_tool_result"

    • code_execution_tool_result_block: object { content, tool_use_id, type }

      • content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

        • code_execution_tool_result_error: object { error_code, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

          • type: "code_execution_tool_result_error"

        • code_execution_result_block: object { content, return_code, stderr, 2 more }

          • content: array of CodeExecutionOutputBlock

            • file_id: string

            • type: "code_execution_output"

          • return_code: number

          • stderr: string

          • stdout: string

          • type: "code_execution_result"

        • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

          • content: array of CodeExecutionOutputBlock

            • file_id: string

            • type: "code_execution_output"

          • encrypted_stdout: string

          • return_code: number

          • stderr: string

          • type: "encrypted_code_execution_result"

      • tool_use_id: string

      • type: "code_execution_tool_result"

    • bash_code_execution_tool_result_block: object { content, tool_use_id, type }

      • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

        • bash_code_execution_tool_result_error: object { error_code, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

            • "output_file_too_large"

          • type: "bash_code_execution_tool_result_error"

        • bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

          • content: array of BashCodeExecutionOutputBlock

            • file_id: string

            • type: "bash_code_execution_output"

          • return_code: number

          • stderr: string

          • stdout: string

          • type: "bash_code_execution_result"

      • tool_use_id: string

      • type: "bash_code_execution_tool_result"

    • text_editor_code_execution_tool_result_block: object { content, tool_use_id, type }

      • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

        • text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

            • "file_not_found"

          • error_message: string

          • type: "text_editor_code_execution_tool_result_error"

        • text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

          • content: string

          • file_type: "text" or "image" or "pdf"

            • "text"

            • "image"

            • "pdf"

          • num_lines: number

          • start_line: number

          • total_lines: number

          • type: "text_editor_code_execution_view_result"

        • text_editor_code_execution_create_result_block: object { is_file_update, type }

          • is_file_update: boolean

          • type: "text_editor_code_execution_create_result"

        • text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

          • lines: array of string

          • new_lines: number

          • new_start: number

          • old_lines: number

          • old_start: number

          • type: "text_editor_code_execution_str_replace_result"

      • tool_use_id: string

      • type: "text_editor_code_execution_tool_result"

    • tool_search_tool_result_block: object { content, tool_use_id, type }

      • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

        • tool_search_tool_result_error: object { error_code, error_message, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

          • error_message: string

          • type: "tool_search_tool_result_error"

        • tool_search_tool_search_result_block: object { tool_references, type }

          • tool_references: array of ToolReferenceBlock

            • tool_name: string

            • type: "tool_reference"

          • type: "tool_search_tool_search_result"

      • tool_use_id: string

      • type: "tool_search_tool_result"

    • container_upload_block: object { file_id, type }

      Response model for a file uploaded to the container.

      • file_id: string

      • type: "container_upload"

  • model: "claude-opus-4-7" or "claude-mythos-preview" or "claude-opus-4-6" or 14 more or string

    The model that will complete your prompt.

    See models for additional details and options.

    • "claude-opus-4-7"

      Frontier intelligence for long-running agents and coding

    • "claude-mythos-preview"

      New class of intelligence, strongest in coding and cybersecurity

    • "claude-opus-4-6"

      Frontier 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"

      Premium model combining maximum intelligence with practical performance

    • "claude-opus-4-5-20251101"

      Premium model combining maximum intelligence with practical performance

    • "claude-sonnet-4-5"

      High-performance model for agents and coding

    • "claude-sonnet-4-5-20250929"

      High-performance model for agents and coding

    • "claude-opus-4-1"

      Exceptional model for specialized complex tasks

    • "claude-opus-4-1-20250805"

      Exceptional model for specialized complex tasks

    • "claude-opus-4-0"

      Powerful model for complex tasks

    • "claude-opus-4-20250514"

      Powerful model for complex tasks

    • "claude-sonnet-4-0"

      High-performance model with extended thinking

    • "claude-sonnet-4-20250514"

      High-performance model with extended thinking

    • "claude-3-haiku-20240307"

      Fast and cost-effective model

  • role: "assistant"

    Conversational role of the generated message.

    This will always be "assistant".

  • stop_details: object { category, explanation, type }

    Structured information about a refusal.

    • category: "cyber" or "bio"

      The policy category that triggered the refusal.

      null when the refusal doesn't map to a named category.

      • "cyber"

      • "bio"

    • explanation: string

      Human-readable explanation of the refusal.

      This text is not guaranteed to be stable. null when no explanation is available for the category.

    • type: "refusal"

  • stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 3 more

    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

    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"

  • stop_sequence: string

    Which custom stop sequence was generated, if any.

    This value will be a non-null string if one of your custom stop sequences was generated.

  • type: "message"

    Object type.

    For Messages, this is always "message".

  • usage: object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 5 more }

    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: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

      Breakdown of cached tokens by TTL

      • ephemeral_1h_input_tokens: number

        The number of input tokens used to create the 1 hour cache entry.

      • ephemeral_5m_input_tokens: number

        The number of input tokens used to create the 5 minute cache entry.

    • cache_creation_input_tokens: number

      The number of input tokens used to create the cache entry.

    • cache_read_input_tokens: number

      The number of input tokens read from the cache.

    • inference_geo: string

      The geographic region where inference was performed for this request.

    • input_tokens: number

      The number of input tokens which were used.

    • output_tokens: number

      The number of output tokens which were used.

    • server_tool_use: object { web_fetch_requests, web_search_requests }

      The number of server tool requests.

      • web_fetch_requests: number

        The number of web fetch tool requests.

      • web_search_requests: number

        The number of web search tool requests.

    • service_tier: "standard" or "priority" or "batch"

      If the request used the priority, standard, or batch tier.

      • "standard"

      • "priority"

      • "batch"

Message Count Tokens Tool

• message_count_tokens_tool: Tool or ToolBash20250124 or CodeExecutionTool20250522 or 13 more

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

  • tool: object { input_schema, name, allowed_callers, 7 more }

    • input_schema: object { type, properties, required }

      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]

      • required: optional array of string

    • name: string

      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"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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

      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

    • type: optional "custom"

      • "custom"

  • tool_bash_20250124: object { name, type, allowed_callers, 4 more }

    • name: "bash"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "bash_20250124"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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

  • code_execution_tool_20250522: object { name, type, allowed_callers, 3 more }

    • name: "code_execution"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "code_execution_20250522"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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: object { name, type, allowed_callers, 3 more }

    • name: "code_execution"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "code_execution_20250825"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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: object { name, type, allowed_callers, 3 more }

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

    • name: "code_execution"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "code_execution_20260120"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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

  • memory_tool_20250818: object { name, type, allowed_callers, 4 more }

    • name: "memory"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "memory_20250818"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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_20250124: object { name, type, allowed_callers, 4 more }

    • name: "str_replace_editor"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "text_editor_20250124"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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: object { name, type, allowed_callers, 4 more }

    • 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.

    • type: "text_editor_20250429"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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: object { name, type, allowed_callers, 5 more }

    • 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.

    • type: "text_editor_20250728"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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

      Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file.

    • strict: optional boolean

      When true, guarantees schema validation on tool names and inputs

  • web_search_tool_20250305: object { name, type, allowed_callers, 7 more }

    • name: "web_search"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "web_search_20250305"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • allowed_domains: optional array of string

      If provided, only these domains will be included in results. Cannot be used alongside blocked_domains.

    • blocked_domains: optional array of string

      If provided, these domains will never appear in results. Cannot be used alongside allowed_domains.

    • cache_control: optional object { type, ttl }

      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.

        • "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

      Maximum number of times the tool can be used in the API request.

    • strict: optional boolean

      When true, guarantees schema validation on tool names and inputs

    • user_location: optional object { type, city, country, 2 more }

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

      • type: "approximate"

      • city: optional string

        The city of the user.

      • country: optional string

        The two letter ISO country code of the user.

      • region: optional string

        The region of the user.

      • timezone: optional string

        The IANA timezone of the user.

  • web_fetch_tool_20250910: object { name, type, allowed_callers, 8 more }

    • name: "web_fetch"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "web_fetch_20250910"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • allowed_domains: optional array of string

      List of domains to allow fetching from

    • blocked_domains: optional array of string

      List of domains to block fetching from

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • citations: optional object { enabled }

      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

      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.

    • max_uses: optional number

      Maximum number of times the tool can be used in the API request.

    • strict: optional boolean

      When true, guarantees schema validation on tool names and inputs

  • web_search_tool_20260209: object { name, type, allowed_callers, 7 more }

    • name: "web_search"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "web_search_20260209"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • allowed_domains: optional array of string

      If provided, only these domains will be included in results. Cannot be used alongside blocked_domains.

    • blocked_domains: optional array of string

      If provided, these domains will never appear in results. Cannot be used alongside allowed_domains.

    • cache_control: optional object { type, ttl }

      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.

        • "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

      Maximum number of times the tool can be used in the API request.

    • strict: optional boolean

      When true, guarantees schema validation on tool names and inputs

    • user_location: optional object { type, city, country, 2 more }

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

      • type: "approximate"

      • city: optional string

        The city of the user.

      • country: optional string

        The two letter ISO country code of the user.

      • region: optional string

        The region of the user.

      • timezone: optional string

        The IANA timezone of the user.

  • web_fetch_tool_20260209: object { name, type, allowed_callers, 8 more }

    • name: "web_fetch"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "web_fetch_20260209"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • allowed_domains: optional array of string

      List of domains to allow fetching from

    • blocked_domains: optional array of string

      List of domains to block fetching from

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • citations: optional object { enabled }

      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

      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.

    • max_uses: optional number

      Maximum number of times the tool can be used in the API request.

    • strict: optional boolean

      When true, guarantees schema validation on tool names and inputs

  • web_fetch_tool_20260309: object { name, type, allowed_callers, 9 more }

    Web fetch tool with use_cache parameter for bypassing cached content.

    • name: "web_fetch"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "web_fetch_20260309"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • allowed_domains: optional array of string

      List of domains to allow fetching from

    • blocked_domains: optional array of string

      List of domains to block fetching from

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • citations: optional object { enabled }

      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

      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.

    • max_uses: optional number

      Maximum number of times the tool can be used in the API request.

    • strict: optional boolean

      When true, guarantees schema validation on tool names and inputs

    • use_cache: optional boolean

      Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.

  • tool_search_tool_bm25_20251119: object { name, type, allowed_callers, 3 more }

    • 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.

    • type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"

      • "tool_search_tool_bm25_20251119"

      • "tool_search_tool_bm25"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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: object { name, type, allowed_callers, 3 more }

    • 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.

    • type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"

      • "tool_search_tool_regex_20251119"

      • "tool_search_tool_regex"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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

Message Delta Usage

• message_delta_usage: object { cache_creation_input_tokens, cache_read_input_tokens, input_tokens, 2 more }

  • cache_creation_input_tokens: number

    The cumulative number of input tokens used to create the cache entry.

  • cache_read_input_tokens: number

    The cumulative number of input tokens read from the cache.

  • input_tokens: number

    The cumulative number of input tokens which were used.

  • output_tokens: number

    The cumulative number of output tokens which were used.

  • server_tool_use: object { web_fetch_requests, web_search_requests }

    The number of server tool requests.

    • web_fetch_requests: number

      The number of web fetch tool requests.

    • web_search_requests: number

      The number of web search tool requests.

Message Param

• message_param: object { content, role }

  • content: array of ContentBlockParam

    • text_block_param: object { text, type, cache_control, citations }

      • text: string

      • type: "text"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

      • citations: optional array of TextCitationParam

        • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_char_index: number

          • start_char_index: number

          • type: "char_location"

        • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_page_number: number

          • start_page_number: number

          • type: "page_location"

        • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_block_index: number

          • start_block_index: number

          • type: "content_block_location"

        • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

          • cited_text: string

          • encrypted_index: string

          • title: string

          • type: "web_search_result_location"

          • url: string

        • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

          • cited_text: string

          • end_block_index: number

          • search_result_index: number

          • source: string

          • start_block_index: number

          • title: string

          • type: "search_result_location"

    • image_block_param: object { source, type, cache_control }

      • source: Base64ImageSource or URLImageSource

        • base64_image_source: object { data, media_type, type }

          • data: string

          • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

            • "image/jpeg"

            • "image/png"

            • "image/gif"

            • "image/webp"

          • type: "base64"

        • url_image_source: object { type, url }

          • type: "url"

          • url: string

      • type: "image"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

    • document_block_param: object { source, type, cache_control, 3 more }

      • source: Base64PDFSource or PlainTextSource or ContentBlockSource or URLPDFSource

        • base64_pdf_source: object { data, media_type, type }

          • data: string

          • media_type: "application/pdf"

          • type: "base64"

        • plain_text_source: object { data, media_type, type }

          • data: string

          • media_type: "text/plain"

          • type: "text"

        • content_block_source: object { content, type }

          • content: string or array of ContentBlockSourceContent

            • union_member_0: string

            • content_block_source_content: array of ContentBlockSourceContent

              • text_block_param: object { text, type, cache_control, citations }

                • text: string

                • type: "text"

                • cache_control: optional object { type, ttl }

                  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.

                    • "5m"

                    • "1h"

                • citations: optional array of TextCitationParam

                  • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

                    • cited_text: string

                    • document_index: number

                    • document_title: string

                    • end_char_index: number

                    • start_char_index: number

                    • type: "char_location"

                  • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

                    • cited_text: string

                    • document_index: number

                    • document_title: string

                    • end_page_number: number

                    • start_page_number: number

                    • type: "page_location"

                  • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

                    • cited_text: string

                    • document_index: number

                    • document_title: string

                    • end_block_index: number

                    • start_block_index: number

                    • type: "content_block_location"

                  • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

                    • cited_text: string

                    • encrypted_index: string

                    • title: string

                    • type: "web_search_result_location"

                    • url: string

                  • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

                    • cited_text: string

                    • end_block_index: number

                    • search_result_index: number

                    • source: string

                    • start_block_index: number

                    • title: string

                    • type: "search_result_location"

              • image_block_param: object { source, type, cache_control }

                • source: Base64ImageSource or URLImageSource

                  • base64_image_source: object { data, media_type, type }

                    • data: string

                    • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

                      • "image/jpeg"

                      • "image/png"

                      • "image/gif"

                      • "image/webp"

                    • type: "base64"

                  • url_image_source: object { type, url }

                    • type: "url"

                    • url: string

                • type: "image"

                • cache_control: optional object { type, ttl }

                  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.

                    • "5m"

                    • "1h"

          • type: "content"

        • url_pdf_source: object { type, url }

          • type: "url"

          • url: string

      • type: "document"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

      • citations: optional object { enabled }

        • enabled: optional boolean

      • context: optional string

      • title: optional string

    • search_result_block_param: object { content, source, title, 3 more }

      • content: array of TextBlockParam

        • text: string

        • type: "text"

        • cache_control: optional object { type, ttl }

          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.

            • "5m"

            • "1h"

        • citations: optional array of TextCitationParam

          • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_char_index: number

            • start_char_index: number

            • type: "char_location"

          • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_page_number: number

            • start_page_number: number

            • type: "page_location"

          • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_block_index: number

            • start_block_index: number

            • type: "content_block_location"

          • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

            • cited_text: string

            • encrypted_index: string

            • title: string

            • type: "web_search_result_location"

            • url: string

          • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

            • cited_text: string

            • end_block_index: number

            • search_result_index: number

            • source: string

            • start_block_index: number

            • title: string

            • type: "search_result_location"

      • source: string

      • title: string

      • type: "search_result"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

      • citations: optional object { enabled }

        • enabled: optional boolean

    • thinking_block_param: object { signature, thinking, type }

      • signature: string

      • thinking: string

      • type: "thinking"

    • redacted_thinking_block_param: object { data, type }

      • data: string

      • type: "redacted_thinking"

    • tool_use_block_param: object { id, input, name, 3 more }

      • id: string

      • input: map[unknown]

      • name: string

      • type: "tool_use"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

      • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

    • tool_result_block_param: object { tool_use_id, type, cache_control, 2 more }

      • tool_use_id: string

      • type: "tool_result"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

      • content: optional array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 2 more

        • text_block_param: object { text, type, cache_control, citations }

          • text: string

          • type: "text"

          • cache_control: optional object { type, ttl }

            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.

              • "5m"

              • "1h"

          • citations: optional array of TextCitationParam

            • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

              • cited_text: string

              • document_index: number

              • document_title: string

              • end_char_index: number

              • start_char_index: number

              • type: "char_location"

            • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

              • cited_text: string

              • document_index: number

              • document_title: string

              • end_page_number: number

              • start_page_number: number

              • type: "page_location"

            • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

              • cited_text: string

              • document_index: number

              • document_title: string

              • end_block_index: number

              • start_block_index: number

              • type: "content_block_location"

            • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

              • cited_text: string

              • encrypted_index: string

              • title: string

              • type: "web_search_result_location"

              • url: string

            • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

              • cited_text: string

              • end_block_index: number

              • search_result_index: number

              • source: string

              • start_block_index: number

              • title: string

              • type: "search_result_location"

        • image_block_param: object { source, type, cache_control }

          • source: Base64ImageSource or URLImageSource

            • base64_image_source: object { data, media_type, type }

              • data: string

              • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

                • "image/jpeg"

                • "image/png"

                • "image/gif"

                • "image/webp"

              • type: "base64"

            • url_image_source: object { type, url }

              • type: "url"

              • url: string

          • type: "image"

          • cache_control: optional object { type, ttl }

            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.

              • "5m"

              • "1h"

        • search_result_block_param: object { content, source, title, 3 more }

          • content: array of TextBlockParam

            • text: string

            • type: "text"

            • cache_control: optional object { type, ttl }

              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.

                • "5m"

                • "1h"

            • citations: optional array of TextCitationParam

              • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

                • cited_text: string

                • document_index: number

                • document_title: string

                • end_char_index: number

                • start_char_index: number

                • type: "char_location"

              • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

                • cited_text: string

                • document_index: number

                • document_title: string

                • end_page_number: number

                • start_page_number: number

                • type: "page_location"

              • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

                • cited_text: string

                • document_index: number

                • document_title: string

                • end_block_index: number

                • start_block_index: number

                • type: "content_block_location"

              • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

                • cited_text: string

                • encrypted_index: string

                • title: string

                • type: "web_search_result_location"

                • url: string

              • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

                • cited_text: string

                • end_block_index: number

                • search_result_index: number

                • source: string

                • start_block_index: number

                • title: string

                • type: "search_result_location"

          • source: string

          • title: string

          • type: "search_result"

          • cache_control: optional object { type, ttl }

            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.

              • "5m"

              • "1h"

          • citations: optional object { enabled }

            • enabled: optional boolean

        • document_block_param: object { source, type, cache_control, 3 more }

          • source: Base64PDFSource or PlainTextSource or ContentBlockSource or URLPDFSource

            • base64_pdf_source: object { data, media_type, type }

              • data: string

              • media_type: "application/pdf"

              • type: "base64"

            • plain_text_source: object { data, media_type, type }

              • data: string

              • media_type: "text/plain"

              • type: "text"

            • content_block_source: object { content, type }

              • content: string or array of ContentBlockSourceContent

                • union_member_0: string

                • content_block_source_content: array of ContentBlockSourceContent

                  • text_block_param: object { text, type, cache_control, citations }

                    • text: string

                    • type: "text"

                    • cache_control: optional object { type, ttl }

                      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.

                        • "5m"

                        • "1h"

                    • citations: optional array of TextCitationParam

                      • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

                        • cited_text: string

                        • document_index: number

                        • document_title: string

                        • end_char_index: number

                        • start_char_index: number

                        • type: "char_location"

                      • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

                        • cited_text: string

                        • document_index: number

                        • document_title: string

                        • end_page_number: number

                        • start_page_number: number

                        • type: "page_location"

                      • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

                        • cited_text: string

                        • document_index: number

                        • document_title: string

                        • end_block_index: number

                        • start_block_index: number

                        • type: "content_block_location"

                      • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

                        • cited_text: string

                        • encrypted_index: string

                        • title: string

                        • type: "web_search_result_location"

                        • url: string

                      • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

                        • cited_text: string

                        • end_block_index: number

                        • search_result_index: number

                        • source: string

                        • start_block_index: number

                        • title: string

                        • type: "search_result_location"

                  • image_block_param: object { source, type, cache_control }

                    • source: Base64ImageSource or URLImageSource

                      • base64_image_source: object { data, media_type, type }

                        • data: string

                        • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

                          • "image/jpeg"

                          • "image/png"

                          • "image/gif"

                          • "image/webp"

                        • type: "base64"

                      • url_image_source: object { type, url }

                        • type: "url"

                        • url: string

                    • type: "image"

                    • cache_control: optional object { type, ttl }

                      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.

                        • "5m"

                        • "1h"

              • type: "content"

            • url_pdf_source: object { type, url }

              • type: "url"

              • url: string

          • type: "document"

          • cache_control: optional object { type, ttl }

            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.

              • "5m"

              • "1h"

          • citations: optional object { enabled }

            • enabled: optional boolean

          • context: optional string

          • title: optional string

        • tool_reference_block_param: object { tool_name, type, cache_control }

          Tool reference block that can be included in tool_result content.

          • tool_name: string

          • type: "tool_reference"

          • cache_control: optional object { type, ttl }

            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.

              • "5m"

              • "1h"

      • is_error: optional boolean

    • server_tool_use_block_param: object { id, input, name, 3 more }

      • id: string

      • 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"

      • type: "server_tool_use"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

      • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

    • web_search_tool_result_block_param: object { content, tool_use_id, type, 2 more }

      • content: array of WebSearchResultBlockParam or WebSearchToolRequestError

        • web_search_tool_result_block_item: array of WebSearchResultBlockParam

          • encrypted_content: string

          • title: string

          • type: "web_search_result"

          • url: string

          • page_age: optional string

        • web_search_tool_request_error: object { error_code, type }

          • error_code: "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"

          • type: "web_search_tool_result_error"

      • tool_use_id: string

      • type: "web_search_tool_result"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

      • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

    • web_fetch_tool_result_block_param: object { content, tool_use_id, type, 2 more }

      • content: WebFetchToolResultErrorBlockParam or WebFetchBlockParam

        • web_fetch_tool_result_error_block_param: object { error_code, type }

          • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

            • "invalid_tool_input"

            • "url_too_long"

            • "url_not_allowed"

            • "url_not_accessible"

            • "unsupported_content_type"

            • "too_many_requests"

            • "max_uses_exceeded"

            • "unavailable"

          • type: "web_fetch_tool_result_error"

        • web_fetch_block_param: object { content, type, url, retrieved_at }

          • content: object { source, type, cache_control, 3 more }

            • source: Base64PDFSource or PlainTextSource or ContentBlockSource or URLPDFSource

              • base64_pdf_source: object { data, media_type, type }

                • data: string

                • media_type: "application/pdf"

                • type: "base64"

              • plain_text_source: object { data, media_type, type }

                • data: string

                • media_type: "text/plain"

                • type: "text"

              • content_block_source: object { content, type }

                • content: string or array of ContentBlockSourceContent

                  • union_member_0: string

                  • content_block_source_content: array of ContentBlockSourceContent

                    • text_block_param: object { text, type, cache_control, citations }

                      • text: string

                      • type: "text"

                      • cache_control: optional object { type, ttl }

                        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.

                          • "5m"

                          • "1h"

                      • citations: optional array of TextCitationParam

                        • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

                          • cited_text: string

                          • document_index: number

                          • document_title: string

                          • end_char_index: number

                          • start_char_index: number

                          • type: "char_location"

                        • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

                          • cited_text: string

                          • document_index: number

                          • document_title: string

                          • end_page_number: number

                          • start_page_number: number

                          • type: "page_location"

                        • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

                          • cited_text: string

                          • document_index: number

                          • document_title: string

                          • end_block_index: number

                          • start_block_index: number

                          • type: "content_block_location"

                        • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

                          • cited_text: string

                          • encrypted_index: string

                          • title: string

                          • type: "web_search_result_location"

                          • url: string

                        • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

                          • cited_text: string

                          • end_block_index: number

                          • search_result_index: number

                          • source: string

                          • start_block_index: number

                          • title: string

                          • type: "search_result_location"

                    • image_block_param: object { source, type, cache_control }

                      • source: Base64ImageSource or URLImageSource

                        • base64_image_source: object { data, media_type, type }

                          • data: string

                          • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

                            • "image/jpeg"

                            • "image/png"

                            • "image/gif"

                            • "image/webp"

                          • type: "base64"

                        • url_image_source: object { type, url }

                          • type: "url"

                          • url: string

                      • type: "image"

                      • cache_control: optional object { type, ttl }

                        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.

                          • "5m"

                          • "1h"

                • type: "content"

              • url_pdf_source: object { type, url }

                • type: "url"

                • url: string

            • type: "document"

            • cache_control: optional object { type, ttl }

              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.

                • "5m"

                • "1h"

            • citations: optional object { enabled }

              • enabled: optional boolean

            • context: optional string

            • title: optional string

          • type: "web_fetch_result"

          • url: string

            Fetched content URL

          • retrieved_at: optional string

            ISO 8601 timestamp when the content was retrieved

      • tool_use_id: string

      • type: "web_fetch_tool_result"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

      • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

    • code_execution_tool_result_block_param: object { content, tool_use_id, type, cache_control }

      • content: CodeExecutionToolResultErrorParam or CodeExecutionResultBlockParam or EncryptedCodeExecutionResultBlockParam

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

        • code_execution_tool_result_error_param: object { error_code, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

          • type: "code_execution_tool_result_error"

        • code_execution_result_block_param: object { content, return_code, stderr, 2 more }

          • content: array of CodeExecutionOutputBlockParam

            • file_id: string

            • type: "code_execution_output"

          • return_code: number

          • stderr: string

          • stdout: string

          • type: "code_execution_result"

        • encrypted_code_execution_result_block_param: object { content, encrypted_stdout, return_code, 2 more }

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

          • content: array of CodeExecutionOutputBlockParam

            • file_id: string

            • type: "code_execution_output"

          • encrypted_stdout: string

          • return_code: number

          • stderr: string

          • type: "encrypted_code_execution_result"

      • tool_use_id: string

      • type: "code_execution_tool_result"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

    • bash_code_execution_tool_result_block_param: object { content, tool_use_id, type, cache_control }

      • content: BashCodeExecutionToolResultErrorParam or BashCodeExecutionResultBlockParam

        • bash_code_execution_tool_result_error_param: object { error_code, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

            • "output_file_too_large"

          • type: "bash_code_execution_tool_result_error"

        • bash_code_execution_result_block_param: object { content, return_code, stderr, 2 more }

          • content: array of BashCodeExecutionOutputBlockParam

            • file_id: string

            • type: "bash_code_execution_output"

          • return_code: number

          • stderr: string

          • stdout: string

          • type: "bash_code_execution_result"

      • tool_use_id: string

      • type: "bash_code_execution_tool_result"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

    • text_editor_code_execution_tool_result_block_param: object { content, tool_use_id, type, cache_control }

      • content: TextEditorCodeExecutionToolResultErrorParam or TextEditorCodeExecutionViewResultBlockParam or TextEditorCodeExecutionCreateResultBlockParam or TextEditorCodeExecutionStrReplaceResultBlockParam

        • text_editor_code_execution_tool_result_error_param: object { error_code, type, error_message }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

            • "file_not_found"

          • type: "text_editor_code_execution_tool_result_error"

          • error_message: optional string

        • text_editor_code_execution_view_result_block_param: object { content, file_type, type, 3 more }

          • content: string

          • file_type: "text" or "image" or "pdf"

            • "text"

            • "image"

            • "pdf"

          • type: "text_editor_code_execution_view_result"

          • num_lines: optional number

          • start_line: optional number

          • total_lines: optional number

        • text_editor_code_execution_create_result_block_param: object { is_file_update, type }

          • is_file_update: boolean

          • type: "text_editor_code_execution_create_result"

        • text_editor_code_execution_str_replace_result_block_param: object { type, lines, new_lines, 3 more }

          • type: "text_editor_code_execution_str_replace_result"

          • lines: optional array of string

          • new_lines: optional number

          • new_start: optional number

          • old_lines: optional number

          • old_start: optional number

      • tool_use_id: string

      • type: "text_editor_code_execution_tool_result"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

    • tool_search_tool_result_block_param: object { content, tool_use_id, type, cache_control }

      • content: ToolSearchToolResultErrorParam or ToolSearchToolSearchResultBlockParam

        • tool_search_tool_result_error_param: object { error_code, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

          • type: "tool_search_tool_result_error"

        • tool_search_tool_search_result_block_param: object { tool_references, type }

          • tool_references: array of ToolReferenceBlockParam

            • tool_name: string

            • type: "tool_reference"

            • cache_control: optional object { type, ttl }

              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.

                • "5m"

                • "1h"

          • type: "tool_search_tool_search_result"

      • tool_use_id: string

      • type: "tool_search_tool_result"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

    • container_upload_block_param: object { file_id, type, cache_control }

      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.

      • file_id: string

      • type: "container_upload"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

  • role: "user" or "assistant"

    • "user"

    • "assistant"

Message Tokens Count

• message_tokens_count: object { input_tokens }

  • input_tokens: number

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

Metadata

• metadata: object { user_id }

  • user_id: optional string

    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.

Output Config

• output_config: object { effort, format }

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

    All possible effort levels.

    • "low"

    • "medium"

    • "high"

    • "xhigh"

    • "max"

  • format: optional object { schema, type }

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

    • schema: map[unknown]

      The JSON schema of the format

    • type: "json_schema"

Plain Text Source

• plain_text_source: object { data, media_type, type }

  • data: string

  • media_type: "text/plain"

  • type: "text"

Raw Content Block Delta

• raw_content_block_delta: TextDelta or InputJSONDelta or CitationsDelta or 2 more

  • text_delta: object { text, type }

    • text: string

    • type: "text_delta"

  • input_json_delta: object { partial_json, type }

    • partial_json: string

    • type: "input_json_delta"

  • citations_delta: object { citation, type }

    • citation: CitationCharLocation or CitationPageLocation or CitationContentBlockLocation or 2 more

      • citation_char_location: object { cited_text, document_index, document_title, 4 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_char_index: number

        • file_id: string

        • start_char_index: number

        • type: "char_location"

      • citation_page_location: object { cited_text, document_index, document_title, 4 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_page_number: number

        • file_id: string

        • start_page_number: number

        • type: "page_location"

      • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_block_index: number

        • file_id: string

        • start_block_index: number

        • type: "content_block_location"

      • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

        • cited_text: string

        • encrypted_index: string

        • title: string

        • type: "web_search_result_location"

        • url: string

      • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

        • cited_text: string

        • end_block_index: number

        • search_result_index: number

        • source: string

        • start_block_index: number

        • title: string

        • type: "search_result_location"

    • type: "citations_delta"

  • thinking_delta: object { thinking, type }

    • thinking: string

    • type: "thinking_delta"

  • signature_delta: object { signature, type }

    • signature: string

    • type: "signature_delta"

Raw Content Block Delta Event

• raw_content_block_delta_event: object { delta, index, type }

  • delta: TextDelta or InputJSONDelta or CitationsDelta or 2 more

    • text_delta: object { text, type }

      • text: string

      • type: "text_delta"

    • input_json_delta: object { partial_json, type }

      • partial_json: string

      • type: "input_json_delta"

    • citations_delta: object { citation, type }

      • citation: CitationCharLocation or CitationPageLocation or CitationContentBlockLocation or 2 more

        • citation_char_location: object { cited_text, document_index, document_title, 4 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_char_index: number

          • file_id: string

          • start_char_index: number

          • type: "char_location"

        • citation_page_location: object { cited_text, document_index, document_title, 4 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_page_number: number

          • file_id: string

          • start_page_number: number

          • type: "page_location"

        • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_block_index: number

          • file_id: string

          • start_block_index: number

          • type: "content_block_location"

        • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

          • cited_text: string

          • encrypted_index: string

          • title: string

          • type: "web_search_result_location"

          • url: string

        • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

          • cited_text: string

          • end_block_index: number

          • search_result_index: number

          • source: string

          • start_block_index: number

          • title: string

          • type: "search_result_location"

      • type: "citations_delta"

    • thinking_delta: object { thinking, type }

      • thinking: string

      • type: "thinking_delta"

    • signature_delta: object { signature, type }

      • signature: string

      • type: "signature_delta"

  • index: number

  • type: "content_block_delta"

Raw Content Block Start Event

• raw_content_block_start_event: object { content_block, index, type }

  • content_block: TextBlock or ThinkingBlock or RedactedThinkingBlock or 9 more

    Response model for a file uploaded to the container.

    • text_block: object { citations, text, type }

      • citations: array of TextCitation

        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.

        • citation_char_location: object { cited_text, document_index, document_title, 4 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_char_index: number

          • file_id: string

          • start_char_index: number

          • type: "char_location"

        • citation_page_location: object { cited_text, document_index, document_title, 4 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_page_number: number

          • file_id: string

          • start_page_number: number

          • type: "page_location"

        • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_block_index: number

          • file_id: string

          • start_block_index: number

          • type: "content_block_location"

        • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

          • cited_text: string

          • encrypted_index: string

          • title: string

          • type: "web_search_result_location"

          • url: string

        • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

          • cited_text: string

          • end_block_index: number

          • search_result_index: number

          • source: string

          • start_block_index: number

          • title: string

          • type: "search_result_location"

      • text: string

      • type: "text"

    • thinking_block: object { signature, thinking, type }

      • signature: string

      • thinking: string

      • type: "thinking"

    • redacted_thinking_block: object { data, type }

      • data: string

      • type: "redacted_thinking"

    • tool_use_block: object { id, caller, input, 2 more }

      • id: string

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

      • input: map[unknown]

      • name: string

      • type: "tool_use"

    • server_tool_use_block: object { id, caller, input, 2 more }

      • id: string

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

      • 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"

      • type: "server_tool_use"

    • web_search_tool_result_block: object { caller, content, tool_use_id, type }

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

      • content: WebSearchToolResultError or array of WebSearchResultBlock

        • web_search_tool_result_error: object { error_code, type }

          • error_code: "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"

          • type: "web_search_tool_result_error"

        • union_member_1: array of WebSearchResultBlock

          • encrypted_content: string

          • page_age: string

          • title: string

          • type: "web_search_result"

          • url: string

      • tool_use_id: string

      • type: "web_search_tool_result"

    • web_fetch_tool_result_block: object { caller, content, tool_use_id, type }

      • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

        Tool invocation directly from the model.

        • direct_caller: object { type }

          Tool invocation directly from the model.

          • type: "direct"

        • server_tool_caller: object { tool_id, type }

          Tool invocation generated by a server-side tool.

          • tool_id: string

          • type: "code_execution_20250825"

        • server_tool_caller_20260120: object { tool_id, type }

          • tool_id: string

          • type: "code_execution_20260120"

      • content: WebFetchToolResultErrorBlock or WebFetchBlock

        • web_fetch_tool_result_error_block: object { error_code, type }

          • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

            • "invalid_tool_input"

            • "url_too_long"

            • "url_not_allowed"

            • "url_not_accessible"

            • "unsupported_content_type"

            • "too_many_requests"

            • "max_uses_exceeded"

            • "unavailable"

          • type: "web_fetch_tool_result_error"

        • web_fetch_block: object { content, retrieved_at, type, url }

          • content: object { citations, source, title, type }

            • citations: object { enabled }

              Citation configuration for the document

              • enabled: boolean

            • source: Base64PDFSource or PlainTextSource

              • base64_pdf_source: object { data, media_type, type }

                • data: string

                • media_type: "application/pdf"

                • type: "base64"

              • plain_text_source: object { data, media_type, type }

                • data: string

                • media_type: "text/plain"

                • type: "text"

            • title: string

              The title of the document

            • type: "document"

          • retrieved_at: string

            ISO 8601 timestamp when the content was retrieved

          • type: "web_fetch_result"

          • url: string

            Fetched content URL

      • tool_use_id: string

      • type: "web_fetch_tool_result"

    • code_execution_tool_result_block: object { content, tool_use_id, type }

      • content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

        • code_execution_tool_result_error: object { error_code, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

          • type: "code_execution_tool_result_error"

        • code_execution_result_block: object { content, return_code, stderr, 2 more }

          • content: array of CodeExecutionOutputBlock

            • file_id: string

            • type: "code_execution_output"

          • return_code: number

          • stderr: string

          • stdout: string

          • type: "code_execution_result"

        • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

          • content: array of CodeExecutionOutputBlock

            • file_id: string

            • type: "code_execution_output"

          • encrypted_stdout: string

          • return_code: number

          • stderr: string

          • type: "encrypted_code_execution_result"

      • tool_use_id: string

      • type: "code_execution_tool_result"

    • bash_code_execution_tool_result_block: object { content, tool_use_id, type }

      • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

        • bash_code_execution_tool_result_error: object { error_code, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

            • "output_file_too_large"

          • type: "bash_code_execution_tool_result_error"

        • bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

          • content: array of BashCodeExecutionOutputBlock

            • file_id: string

            • type: "bash_code_execution_output"

          • return_code: number

          • stderr: string

          • stdout: string

          • type: "bash_code_execution_result"

      • tool_use_id: string

      • type: "bash_code_execution_tool_result"

    • text_editor_code_execution_tool_result_block: object { content, tool_use_id, type }

      • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

        • text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

            • "file_not_found"

          • error_message: string

          • type: "text_editor_code_execution_tool_result_error"

        • text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

          • content: string

          • file_type: "text" or "image" or "pdf"

            • "text"

            • "image"

            • "pdf"

          • num_lines: number

          • start_line: number

          • total_lines: number

          • type: "text_editor_code_execution_view_result"

        • text_editor_code_execution_create_result_block: object { is_file_update, type }

          • is_file_update: boolean

          • type: "text_editor_code_execution_create_result"

        • text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

          • lines: array of string

          • new_lines: number

          • new_start: number

          • old_lines: number

          • old_start: number

          • type: "text_editor_code_execution_str_replace_result"

      • tool_use_id: string

      • type: "text_editor_code_execution_tool_result"

    • tool_search_tool_result_block: object { content, tool_use_id, type }

      • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

        • tool_search_tool_result_error: object { error_code, error_message, type }

          • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

            • "invalid_tool_input"

            • "unavailable"

            • "too_many_requests"

            • "execution_time_exceeded"

          • error_message: string

          • type: "tool_search_tool_result_error"

        • tool_search_tool_search_result_block: object { tool_references, type }

          • tool_references: array of ToolReferenceBlock

            • tool_name: string

            • type: "tool_reference"

          • type: "tool_search_tool_search_result"

      • tool_use_id: string

      • type: "tool_search_tool_result"

    • container_upload_block: object { file_id, type }

      Response model for a file uploaded to the container.

      • file_id: string

      • type: "container_upload"

  • index: number

  • type: "content_block_start"

Raw Content Block Stop Event

• raw_content_block_stop_event: object { index, type }

  • index: number

  • type: "content_block_stop"

Raw Message Delta Event

• raw_message_delta_event: object { delta, type, usage }

  • delta: object { container, stop_details, stop_reason, stop_sequence }

    • container: object { id, expires_at }

      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.

    • stop_details: object { category, explanation, type }

      Structured information about a refusal.

      • category: "cyber" or "bio"

        The policy category that triggered the refusal.

        null when the refusal doesn't map to a named category.

        • "cyber"

        • "bio"

      • explanation: string

        Human-readable explanation of the refusal.

        This text is not guaranteed to be stable. null when no explanation is available for the category.

      • type: "refusal"

    • stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 3 more

      • "end_turn"

      • "max_tokens"

      • "stop_sequence"

      • "tool_use"

      • "pause_turn"

      • "refusal"

    • stop_sequence: string

  • type: "message_delta"

  • usage: object { cache_creation_input_tokens, cache_read_input_tokens, input_tokens, 2 more }

    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

      The cumulative number of input tokens used to create the cache entry.

    • cache_read_input_tokens: number

      The cumulative number of input tokens read from the cache.

    • input_tokens: number

      The cumulative number of input tokens which were used.

    • output_tokens: number

      The cumulative number of output tokens which were used.

    • server_tool_use: object { web_fetch_requests, web_search_requests }

      The number of server tool requests.

      • web_fetch_requests: number

        The number of web fetch tool requests.

      • web_search_requests: number

        The number of web search tool requests.

Raw Message Start Event

• raw_message_start_event: object { message, type }

  • message: object { id, container, content, 7 more }

    • id: string

      Unique object identifier.

      The format and length of IDs may change over time.

    • container: object { id, expires_at }

      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.

    • 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:

      [{"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:

      [
        {"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:

      [{"type": "text", "text": "B)"}]
      

      • text_block: object { citations, text, type }

        • citations: array of TextCitation

          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.

          • citation_char_location: object { cited_text, document_index, document_title, 4 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_char_index: number

            • file_id: string

            • start_char_index: number

            • type: "char_location"

          • citation_page_location: object { cited_text, document_index, document_title, 4 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_page_number: number

            • file_id: string

            • start_page_number: number

            • type: "page_location"

          • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_block_index: number

            • file_id: string

            • start_block_index: number

            • type: "content_block_location"

          • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

            • cited_text: string

            • encrypted_index: string

            • title: string

            • type: "web_search_result_location"

            • url: string

          • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

            • cited_text: string

            • end_block_index: number

            • search_result_index: number

            • source: string

            • start_block_index: number

            • title: string

            • type: "search_result_location"

        • text: string

        • type: "text"

      • thinking_block: object { signature, thinking, type }

        • signature: string

        • thinking: string

        • type: "thinking"

      • redacted_thinking_block: object { data, type }

        • data: string

        • type: "redacted_thinking"

      • tool_use_block: object { id, caller, input, 2 more }

        • id: string

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          Tool invocation directly from the model.

          • direct_caller: object { type }

            Tool invocation directly from the model.

            • type: "direct"

          • server_tool_caller: object { tool_id, type }

            Tool invocation generated by a server-side tool.

            • tool_id: string

            • type: "code_execution_20250825"

          • server_tool_caller_20260120: object { tool_id, type }

            • tool_id: string

            • type: "code_execution_20260120"

        • input: map[unknown]

        • name: string

        • type: "tool_use"

      • server_tool_use_block: object { id, caller, input, 2 more }

        • id: string

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          Tool invocation directly from the model.

          • direct_caller: object { type }

            Tool invocation directly from the model.

            • type: "direct"

          • server_tool_caller: object { tool_id, type }

            Tool invocation generated by a server-side tool.

            • tool_id: string

            • type: "code_execution_20250825"

          • server_tool_caller_20260120: object { tool_id, type }

            • tool_id: string

            • type: "code_execution_20260120"

        • 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"

        • type: "server_tool_use"

      • web_search_tool_result_block: object { caller, content, tool_use_id, type }

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          Tool invocation directly from the model.

          • direct_caller: object { type }

            Tool invocation directly from the model.

            • type: "direct"

          • server_tool_caller: object { tool_id, type }

            Tool invocation generated by a server-side tool.

            • tool_id: string

            • type: "code_execution_20250825"

          • server_tool_caller_20260120: object { tool_id, type }

            • tool_id: string

            • type: "code_execution_20260120"

        • content: WebSearchToolResultError or array of WebSearchResultBlock

          • web_search_tool_result_error: object { error_code, type }

            • error_code: "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"

            • type: "web_search_tool_result_error"

          • union_member_1: array of WebSearchResultBlock

            • encrypted_content: string

            • page_age: string

            • title: string

            • type: "web_search_result"

            • url: string

        • tool_use_id: string

        • type: "web_search_tool_result"

      • web_fetch_tool_result_block: object { caller, content, tool_use_id, type }

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          Tool invocation directly from the model.

          • direct_caller: object { type }

            Tool invocation directly from the model.

            • type: "direct"

          • server_tool_caller: object { tool_id, type }

            Tool invocation generated by a server-side tool.

            • tool_id: string

            • type: "code_execution_20250825"

          • server_tool_caller_20260120: object { tool_id, type }

            • tool_id: string

            • type: "code_execution_20260120"

        • content: WebFetchToolResultErrorBlock or WebFetchBlock

          • web_fetch_tool_result_error_block: object { error_code, type }

            • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

              • "invalid_tool_input"

              • "url_too_long"

              • "url_not_allowed"

              • "url_not_accessible"

              • "unsupported_content_type"

              • "too_many_requests"

              • "max_uses_exceeded"

              • "unavailable"

            • type: "web_fetch_tool_result_error"

          • web_fetch_block: object { content, retrieved_at, type, url }

            • content: object { citations, source, title, type }

              • citations: object { enabled }

                Citation configuration for the document

                • enabled: boolean

              • source: Base64PDFSource or PlainTextSource

                • base64_pdf_source: object { data, media_type, type }

                  • data: string

                  • media_type: "application/pdf"

                  • type: "base64"

                • plain_text_source: object { data, media_type, type }

                  • data: string

                  • media_type: "text/plain"

                  • type: "text"

              • title: string

                The title of the document

              • type: "document"

            • retrieved_at: string

              ISO 8601 timestamp when the content was retrieved

            • type: "web_fetch_result"

            • url: string

              Fetched content URL

        • tool_use_id: string

        • type: "web_fetch_tool_result"

      • code_execution_tool_result_block: object { content, tool_use_id, type }

        • content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

          • code_execution_tool_result_error: object { error_code, type }

            • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

            • type: "code_execution_tool_result_error"

          • code_execution_result_block: object { content, return_code, stderr, 2 more }

            • content: array of CodeExecutionOutputBlock

              • file_id: string

              • type: "code_execution_output"

            • return_code: number

            • stderr: string

            • stdout: string

            • type: "code_execution_result"

          • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

            • content: array of CodeExecutionOutputBlock

              • file_id: string

              • type: "code_execution_output"

            • encrypted_stdout: string

            • return_code: number

            • stderr: string

            • type: "encrypted_code_execution_result"

        • tool_use_id: string

        • type: "code_execution_tool_result"

      • bash_code_execution_tool_result_block: object { content, tool_use_id, type }

        • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

          • bash_code_execution_tool_result_error: object { error_code, type }

            • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

              • "output_file_too_large"

            • type: "bash_code_execution_tool_result_error"

          • bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

            • content: array of BashCodeExecutionOutputBlock

              • file_id: string

              • type: "bash_code_execution_output"

            • return_code: number

            • stderr: string

            • stdout: string

            • type: "bash_code_execution_result"

        • tool_use_id: string

        • type: "bash_code_execution_tool_result"

      • text_editor_code_execution_tool_result_block: object { content, tool_use_id, type }

        • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

          • text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

            • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

              • "file_not_found"

            • error_message: string

            • type: "text_editor_code_execution_tool_result_error"

          • text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

            • content: string

            • file_type: "text" or "image" or "pdf"

              • "text"

              • "image"

              • "pdf"

            • num_lines: number

            • start_line: number

            • total_lines: number

            • type: "text_editor_code_execution_view_result"

          • text_editor_code_execution_create_result_block: object { is_file_update, type }

            • is_file_update: boolean

            • type: "text_editor_code_execution_create_result"

          • text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

            • lines: array of string

            • new_lines: number

            • new_start: number

            • old_lines: number

            • old_start: number

            • type: "text_editor_code_execution_str_replace_result"

        • tool_use_id: string

        • type: "text_editor_code_execution_tool_result"

      • tool_search_tool_result_block: object { content, tool_use_id, type }

        • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

          • tool_search_tool_result_error: object { error_code, error_message, type }

            • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

            • error_message: string

            • type: "tool_search_tool_result_error"

          • tool_search_tool_search_result_block: object { tool_references, type }

            • tool_references: array of ToolReferenceBlock

              • tool_name: string

              • type: "tool_reference"

            • type: "tool_search_tool_search_result"

        • tool_use_id: string

        • type: "tool_search_tool_result"

      • container_upload_block: object { file_id, type }

        Response model for a file uploaded to the container.

        • file_id: string

        • type: "container_upload"

    • model: "claude-opus-4-7" or "claude-mythos-preview" or "claude-opus-4-6" or 14 more or string

      The model that will complete your prompt.

      See models for additional details and options.

      • "claude-opus-4-7"

        Frontier intelligence for long-running agents and coding

      • "claude-mythos-preview"

        New class of intelligence, strongest in coding and cybersecurity

      • "claude-opus-4-6"

        Frontier 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"

        Premium model combining maximum intelligence with practical performance

      • "claude-opus-4-5-20251101"

        Premium model combining maximum intelligence with practical performance

      • "claude-sonnet-4-5"

        High-performance model for agents and coding

      • "claude-sonnet-4-5-20250929"

        High-performance model for agents and coding

      • "claude-opus-4-1"

        Exceptional model for specialized complex tasks

      • "claude-opus-4-1-20250805"

        Exceptional model for specialized complex tasks

      • "claude-opus-4-0"

        Powerful model for complex tasks

      • "claude-opus-4-20250514"

        Powerful model for complex tasks

      • "claude-sonnet-4-0"

        High-performance model with extended thinking

      • "claude-sonnet-4-20250514"

        High-performance model with extended thinking

      • "claude-3-haiku-20240307"

        Fast and cost-effective model

    • role: "assistant"

      Conversational role of the generated message.

      This will always be "assistant".

    • stop_details: object { category, explanation, type }

      Structured information about a refusal.

      • category: "cyber" or "bio"

        The policy category that triggered the refusal.

        null when the refusal doesn't map to a named category.

        • "cyber"

        • "bio"

      • explanation: string

        Human-readable explanation of the refusal.

        This text is not guaranteed to be stable. null when no explanation is available for the category.

      • type: "refusal"

    • stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 3 more

      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

      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"

    • stop_sequence: string

      Which custom stop sequence was generated, if any.

      This value will be a non-null string if one of your custom stop sequences was generated.

    • type: "message"

      Object type.

      For Messages, this is always "message".

    • usage: object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 5 more }

      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: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

        Breakdown of cached tokens by TTL

        • ephemeral_1h_input_tokens: number

          The number of input tokens used to create the 1 hour cache entry.

        • ephemeral_5m_input_tokens: number

          The number of input tokens used to create the 5 minute cache entry.

      • cache_creation_input_tokens: number

        The number of input tokens used to create the cache entry.

      • cache_read_input_tokens: number

        The number of input tokens read from the cache.

      • inference_geo: string

        The geographic region where inference was performed for this request.

      • input_tokens: number

        The number of input tokens which were used.

      • output_tokens: number

        The number of output tokens which were used.

      • server_tool_use: object { web_fetch_requests, web_search_requests }

        The number of server tool requests.

        • web_fetch_requests: number

          The number of web fetch tool requests.

        • web_search_requests: number

          The number of web search tool requests.

      • service_tier: "standard" or "priority" or "batch"

        If the request used the priority, standard, or batch tier.

        • "standard"

        • "priority"

        • "batch"

  • type: "message_start"

Raw Message Stop Event

• raw_message_stop_event: object { type }

  • type: "message_stop"

Raw Message Stream Event

• raw_message_stream_event: RawMessageStartEvent or RawMessageDeltaEvent or RawMessageStopEvent or 3 more

  • raw_message_start_event: object { message, type }

    • message: object { id, container, content, 7 more }

      • id: string

        Unique object identifier.

        The format and length of IDs may change over time.

      • container: object { id, expires_at }

        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.

      • 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:

        [{"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:

        [
          {"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:

        [{"type": "text", "text": "B)"}]
        

        • text_block: object { citations, text, type }

          • citations: array of TextCitation

            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.

            • citation_char_location: object { cited_text, document_index, document_title, 4 more }

              • cited_text: string

              • document_index: number

              • document_title: string

              • end_char_index: number

              • file_id: string

              • start_char_index: number

              • type: "char_location"

            • citation_page_location: object { cited_text, document_index, document_title, 4 more }

              • cited_text: string

              • document_index: number

              • document_title: string

              • end_page_number: number

              • file_id: string

              • start_page_number: number

              • type: "page_location"

            • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

              • cited_text: string

              • document_index: number

              • document_title: string

              • end_block_index: number

              • file_id: string

              • start_block_index: number

              • type: "content_block_location"

            • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

              • cited_text: string

              • encrypted_index: string

              • title: string

              • type: "web_search_result_location"

              • url: string

            • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

              • cited_text: string

              • end_block_index: number

              • search_result_index: number

              • source: string

              • start_block_index: number

              • title: string

              • type: "search_result_location"

          • text: string

          • type: "text"

        • thinking_block: object { signature, thinking, type }

          • signature: string

          • thinking: string

          • type: "thinking"

        • redacted_thinking_block: object { data, type }

          • data: string

          • type: "redacted_thinking"

        • tool_use_block: object { id, caller, input, 2 more }

          • id: string

          • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

            Tool invocation directly from the model.

            • direct_caller: object { type }

              Tool invocation directly from the model.

              • type: "direct"

            • server_tool_caller: object { tool_id, type }

              Tool invocation generated by a server-side tool.

              • tool_id: string

              • type: "code_execution_20250825"

            • server_tool_caller_20260120: object { tool_id, type }

              • tool_id: string

              • type: "code_execution_20260120"

          • input: map[unknown]

          • name: string

          • type: "tool_use"

        • server_tool_use_block: object { id, caller, input, 2 more }

          • id: string

          • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

            Tool invocation directly from the model.

            • direct_caller: object { type }

              Tool invocation directly from the model.

              • type: "direct"

            • server_tool_caller: object { tool_id, type }

              Tool invocation generated by a server-side tool.

              • tool_id: string

              • type: "code_execution_20250825"

            • server_tool_caller_20260120: object { tool_id, type }

              • tool_id: string

              • type: "code_execution_20260120"

          • 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"

          • type: "server_tool_use"

        • web_search_tool_result_block: object { caller, content, tool_use_id, type }

          • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

            Tool invocation directly from the model.

            • direct_caller: object { type }

              Tool invocation directly from the model.

              • type: "direct"

            • server_tool_caller: object { tool_id, type }

              Tool invocation generated by a server-side tool.

              • tool_id: string

              • type: "code_execution_20250825"

            • server_tool_caller_20260120: object { tool_id, type }

              • tool_id: string

              • type: "code_execution_20260120"

          • content: WebSearchToolResultError or array of WebSearchResultBlock

            • web_search_tool_result_error: object { error_code, type }

              • error_code: "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"

              • type: "web_search_tool_result_error"

            • union_member_1: array of WebSearchResultBlock

              • encrypted_content: string

              • page_age: string

              • title: string

              • type: "web_search_result"

              • url: string

          • tool_use_id: string

          • type: "web_search_tool_result"

        • web_fetch_tool_result_block: object { caller, content, tool_use_id, type }

          • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

            Tool invocation directly from the model.

            • direct_caller: object { type }

              Tool invocation directly from the model.

              • type: "direct"

            • server_tool_caller: object { tool_id, type }

              Tool invocation generated by a server-side tool.

              • tool_id: string

              • type: "code_execution_20250825"

            • server_tool_caller_20260120: object { tool_id, type }

              • tool_id: string

              • type: "code_execution_20260120"

          • content: WebFetchToolResultErrorBlock or WebFetchBlock

            • web_fetch_tool_result_error_block: object { error_code, type }

              • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

                • "invalid_tool_input"

                • "url_too_long"

                • "url_not_allowed"

                • "url_not_accessible"

                • "unsupported_content_type"

                • "too_many_requests"

                • "max_uses_exceeded"

                • "unavailable"

              • type: "web_fetch_tool_result_error"

            • web_fetch_block: object { content, retrieved_at, type, url }

              • content: object { citations, source, title, type }

                • citations: object { enabled }

                  Citation configuration for the document

                  • enabled: boolean

                • source: Base64PDFSource or PlainTextSource

                  • base64_pdf_source: object { data, media_type, type }

                    • data: string

                    • media_type: "application/pdf"

                    • type: "base64"

                  • plain_text_source: object { data, media_type, type }

                    • data: string

                    • media_type: "text/plain"

                    • type: "text"

                • title: string

                  The title of the document

                • type: "document"

              • retrieved_at: string

                ISO 8601 timestamp when the content was retrieved

              • type: "web_fetch_result"

              • url: string

                Fetched content URL

          • tool_use_id: string

          • type: "web_fetch_tool_result"

        • code_execution_tool_result_block: object { content, tool_use_id, type }

          • content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

            • code_execution_tool_result_error: object { error_code, type }

              • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

              • type: "code_execution_tool_result_error"

            • code_execution_result_block: object { content, return_code, stderr, 2 more }

              • content: array of CodeExecutionOutputBlock

                • file_id: string

                • type: "code_execution_output"

              • return_code: number

              • stderr: string

              • stdout: string

              • type: "code_execution_result"

            • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

              • content: array of CodeExecutionOutputBlock

                • file_id: string

                • type: "code_execution_output"

              • encrypted_stdout: string

              • return_code: number

              • stderr: string

              • type: "encrypted_code_execution_result"

          • tool_use_id: string

          • type: "code_execution_tool_result"

        • bash_code_execution_tool_result_block: object { content, tool_use_id, type }

          • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

            • bash_code_execution_tool_result_error: object { error_code, type }

              • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

                • "output_file_too_large"

              • type: "bash_code_execution_tool_result_error"

            • bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

              • content: array of BashCodeExecutionOutputBlock

                • file_id: string

                • type: "bash_code_execution_output"

              • return_code: number

              • stderr: string

              • stdout: string

              • type: "bash_code_execution_result"

          • tool_use_id: string

          • type: "bash_code_execution_tool_result"

        • text_editor_code_execution_tool_result_block: object { content, tool_use_id, type }

          • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

            • text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

              • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

                • "file_not_found"

              • error_message: string

              • type: "text_editor_code_execution_tool_result_error"

            • text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

              • content: string

              • file_type: "text" or "image" or "pdf"

                • "text"

                • "image"

                • "pdf"

              • num_lines: number

              • start_line: number

              • total_lines: number

              • type: "text_editor_code_execution_view_result"

            • text_editor_code_execution_create_result_block: object { is_file_update, type }

              • is_file_update: boolean

              • type: "text_editor_code_execution_create_result"

            • text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

              • lines: array of string

              • new_lines: number

              • new_start: number

              • old_lines: number

              • old_start: number

              • type: "text_editor_code_execution_str_replace_result"

          • tool_use_id: string

          • type: "text_editor_code_execution_tool_result"

        • tool_search_tool_result_block: object { content, tool_use_id, type }

          • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

            • tool_search_tool_result_error: object { error_code, error_message, type }

              • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

              • error_message: string

              • type: "tool_search_tool_result_error"

            • tool_search_tool_search_result_block: object { tool_references, type }

              • tool_references: array of ToolReferenceBlock

                • tool_name: string

                • type: "tool_reference"

              • type: "tool_search_tool_search_result"

          • tool_use_id: string

          • type: "tool_search_tool_result"

        • container_upload_block: object { file_id, type }

          Response model for a file uploaded to the container.

          • file_id: string

          • type: "container_upload"

      • model: "claude-opus-4-7" or "claude-mythos-preview" or "claude-opus-4-6" or 14 more or string

        The model that will complete your prompt.

        See models for additional details and options.

        • "claude-opus-4-7"

          Frontier intelligence for long-running agents and coding

        • "claude-mythos-preview"

          New class of intelligence, strongest in coding and cybersecurity

        • "claude-opus-4-6"

          Frontier 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"

          Premium model combining maximum intelligence with practical performance

        • "claude-opus-4-5-20251101"

          Premium model combining maximum intelligence with practical performance

        • "claude-sonnet-4-5"

          High-performance model for agents and coding

        • "claude-sonnet-4-5-20250929"

          High-performance model for agents and coding

        • "claude-opus-4-1"

          Exceptional model for specialized complex tasks

        • "claude-opus-4-1-20250805"

          Exceptional model for specialized complex tasks

        • "claude-opus-4-0"

          Powerful model for complex tasks

        • "claude-opus-4-20250514"

          Powerful model for complex tasks

        • "claude-sonnet-4-0"

          High-performance model with extended thinking

        • "claude-sonnet-4-20250514"

          High-performance model with extended thinking

        • "claude-3-haiku-20240307"

          Fast and cost-effective model

      • role: "assistant"

        Conversational role of the generated message.

        This will always be "assistant".

      • stop_details: object { category, explanation, type }

        Structured information about a refusal.

        • category: "cyber" or "bio"

          The policy category that triggered the refusal.

          null when the refusal doesn't map to a named category.

          • "cyber"

          • "bio"

        • explanation: string

          Human-readable explanation of the refusal.

          This text is not guaranteed to be stable. null when no explanation is available for the category.

        • type: "refusal"

      • stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 3 more

        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

        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"

      • stop_sequence: string

        Which custom stop sequence was generated, if any.

        This value will be a non-null string if one of your custom stop sequences was generated.

      • type: "message"

        Object type.

        For Messages, this is always "message".

      • usage: object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 5 more }

        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: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

          Breakdown of cached tokens by TTL

          • ephemeral_1h_input_tokens: number

            The number of input tokens used to create the 1 hour cache entry.

          • ephemeral_5m_input_tokens: number

            The number of input tokens used to create the 5 minute cache entry.

        • cache_creation_input_tokens: number

          The number of input tokens used to create the cache entry.

        • cache_read_input_tokens: number

          The number of input tokens read from the cache.

        • inference_geo: string

          The geographic region where inference was performed for this request.

        • input_tokens: number

          The number of input tokens which were used.

        • output_tokens: number

          The number of output tokens which were used.

        • server_tool_use: object { web_fetch_requests, web_search_requests }

          The number of server tool requests.

          • web_fetch_requests: number

            The number of web fetch tool requests.

          • web_search_requests: number

            The number of web search tool requests.

        • service_tier: "standard" or "priority" or "batch"

          If the request used the priority, standard, or batch tier.

          • "standard"

          • "priority"

          • "batch"

    • type: "message_start"

  • raw_message_delta_event: object { delta, type, usage }

    • delta: object { container, stop_details, stop_reason, stop_sequence }

      • container: object { id, expires_at }

        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.

      • stop_details: object { category, explanation, type }

        Structured information about a refusal.

        • category: "cyber" or "bio"

          The policy category that triggered the refusal.

          null when the refusal doesn't map to a named category.

          • "cyber"

          • "bio"

        • explanation: string

          Human-readable explanation of the refusal.

          This text is not guaranteed to be stable. null when no explanation is available for the category.

        • type: "refusal"

      • stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 3 more

        • "end_turn"

        • "max_tokens"

        • "stop_sequence"

        • "tool_use"

        • "pause_turn"

        • "refusal"

      • stop_sequence: string

    • type: "message_delta"

    • usage: object { cache_creation_input_tokens, cache_read_input_tokens, input_tokens, 2 more }

      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

        The cumulative number of input tokens used to create the cache entry.

      • cache_read_input_tokens: number

        The cumulative number of input tokens read from the cache.

      • input_tokens: number

        The cumulative number of input tokens which were used.

      • output_tokens: number

        The cumulative number of output tokens which were used.

      • server_tool_use: object { web_fetch_requests, web_search_requests }

        The number of server tool requests.

        • web_fetch_requests: number

          The number of web fetch tool requests.

        • web_search_requests: number

          The number of web search tool requests.

  • raw_message_stop_event: object { type }

    • type: "message_stop"

  • raw_content_block_start_event: object { content_block, index, type }

    • content_block: TextBlock or ThinkingBlock or RedactedThinkingBlock or 9 more

      Response model for a file uploaded to the container.

      • text_block: object { citations, text, type }

        • citations: array of TextCitation

          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.

          • citation_char_location: object { cited_text, document_index, document_title, 4 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_char_index: number

            • file_id: string

            • start_char_index: number

            • type: "char_location"

          • citation_page_location: object { cited_text, document_index, document_title, 4 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_page_number: number

            • file_id: string

            • start_page_number: number

            • type: "page_location"

          • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_block_index: number

            • file_id: string

            • start_block_index: number

            • type: "content_block_location"

          • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

            • cited_text: string

            • encrypted_index: string

            • title: string

            • type: "web_search_result_location"

            • url: string

          • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

            • cited_text: string

            • end_block_index: number

            • search_result_index: number

            • source: string

            • start_block_index: number

            • title: string

            • type: "search_result_location"

        • text: string

        • type: "text"

      • thinking_block: object { signature, thinking, type }

        • signature: string

        • thinking: string

        • type: "thinking"

      • redacted_thinking_block: object { data, type }

        • data: string

        • type: "redacted_thinking"

      • tool_use_block: object { id, caller, input, 2 more }

        • id: string

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          Tool invocation directly from the model.

          • direct_caller: object { type }

            Tool invocation directly from the model.

            • type: "direct"

          • server_tool_caller: object { tool_id, type }

            Tool invocation generated by a server-side tool.

            • tool_id: string

            • type: "code_execution_20250825"

          • server_tool_caller_20260120: object { tool_id, type }

            • tool_id: string

            • type: "code_execution_20260120"

        • input: map[unknown]

        • name: string

        • type: "tool_use"

      • server_tool_use_block: object { id, caller, input, 2 more }

        • id: string

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          Tool invocation directly from the model.

          • direct_caller: object { type }

            Tool invocation directly from the model.

            • type: "direct"

          • server_tool_caller: object { tool_id, type }

            Tool invocation generated by a server-side tool.

            • tool_id: string

            • type: "code_execution_20250825"

          • server_tool_caller_20260120: object { tool_id, type }

            • tool_id: string

            • type: "code_execution_20260120"

        • 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"

        • type: "server_tool_use"

      • web_search_tool_result_block: object { caller, content, tool_use_id, type }

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          Tool invocation directly from the model.

          • direct_caller: object { type }

            Tool invocation directly from the model.

            • type: "direct"

          • server_tool_caller: object { tool_id, type }

            Tool invocation generated by a server-side tool.

            • tool_id: string

            • type: "code_execution_20250825"

          • server_tool_caller_20260120: object { tool_id, type }

            • tool_id: string

            • type: "code_execution_20260120"

        • content: WebSearchToolResultError or array of WebSearchResultBlock

          • web_search_tool_result_error: object { error_code, type }

            • error_code: "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"

            • type: "web_search_tool_result_error"

          • union_member_1: array of WebSearchResultBlock

            • encrypted_content: string

            • page_age: string

            • title: string

            • type: "web_search_result"

            • url: string

        • tool_use_id: string

        • type: "web_search_tool_result"

      • web_fetch_tool_result_block: object { caller, content, tool_use_id, type }

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          Tool invocation directly from the model.

          • direct_caller: object { type }

            Tool invocation directly from the model.

            • type: "direct"

          • server_tool_caller: object { tool_id, type }

            Tool invocation generated by a server-side tool.

            • tool_id: string

            • type: "code_execution_20250825"

          • server_tool_caller_20260120: object { tool_id, type }

            • tool_id: string

            • type: "code_execution_20260120"

        • content: WebFetchToolResultErrorBlock or WebFetchBlock

          • web_fetch_tool_result_error_block: object { error_code, type }

            • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

              • "invalid_tool_input"

              • "url_too_long"

              • "url_not_allowed"

              • "url_not_accessible"

              • "unsupported_content_type"

              • "too_many_requests"

              • "max_uses_exceeded"

              • "unavailable"

            • type: "web_fetch_tool_result_error"

          • web_fetch_block: object { content, retrieved_at, type, url }

            • content: object { citations, source, title, type }

              • citations: object { enabled }

                Citation configuration for the document

                • enabled: boolean

              • source: Base64PDFSource or PlainTextSource

                • base64_pdf_source: object { data, media_type, type }

                  • data: string

                  • media_type: "application/pdf"

                  • type: "base64"

                • plain_text_source: object { data, media_type, type }

                  • data: string

                  • media_type: "text/plain"

                  • type: "text"

              • title: string

                The title of the document

              • type: "document"

            • retrieved_at: string

              ISO 8601 timestamp when the content was retrieved

            • type: "web_fetch_result"

            • url: string

              Fetched content URL

        • tool_use_id: string

        • type: "web_fetch_tool_result"

      • code_execution_tool_result_block: object { content, tool_use_id, type }

        • content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

          • code_execution_tool_result_error: object { error_code, type }

            • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

            • type: "code_execution_tool_result_error"

          • code_execution_result_block: object { content, return_code, stderr, 2 more }

            • content: array of CodeExecutionOutputBlock

              • file_id: string

              • type: "code_execution_output"

            • return_code: number

            • stderr: string

            • stdout: string

            • type: "code_execution_result"

          • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

            • content: array of CodeExecutionOutputBlock

              • file_id: string

              • type: "code_execution_output"

            • encrypted_stdout: string

            • return_code: number

            • stderr: string

            • type: "encrypted_code_execution_result"

        • tool_use_id: string

        • type: "code_execution_tool_result"

      • bash_code_execution_tool_result_block: object { content, tool_use_id, type }

        • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

          • bash_code_execution_tool_result_error: object { error_code, type }

            • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

              • "output_file_too_large"

            • type: "bash_code_execution_tool_result_error"

          • bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

            • content: array of BashCodeExecutionOutputBlock

              • file_id: string

              • type: "bash_code_execution_output"

            • return_code: number

            • stderr: string

            • stdout: string

            • type: "bash_code_execution_result"

        • tool_use_id: string

        • type: "bash_code_execution_tool_result"

      • text_editor_code_execution_tool_result_block: object { content, tool_use_id, type }

        • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

          • text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

            • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

              • "file_not_found"

            • error_message: string

            • type: "text_editor_code_execution_tool_result_error"

          • text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

            • content: string

            • file_type: "text" or "image" or "pdf"

              • "text"

              • "image"

              • "pdf"

            • num_lines: number

            • start_line: number

            • total_lines: number

            • type: "text_editor_code_execution_view_result"

          • text_editor_code_execution_create_result_block: object { is_file_update, type }

            • is_file_update: boolean

            • type: "text_editor_code_execution_create_result"

          • text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

            • lines: array of string

            • new_lines: number

            • new_start: number

            • old_lines: number

            • old_start: number

            • type: "text_editor_code_execution_str_replace_result"

        • tool_use_id: string

        • type: "text_editor_code_execution_tool_result"

      • tool_search_tool_result_block: object { content, tool_use_id, type }

        • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

          • tool_search_tool_result_error: object { error_code, error_message, type }

            • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

            • error_message: string

            • type: "tool_search_tool_result_error"

          • tool_search_tool_search_result_block: object { tool_references, type }

            • tool_references: array of ToolReferenceBlock

              • tool_name: string

              • type: "tool_reference"

            • type: "tool_search_tool_search_result"

        • tool_use_id: string

        • type: "tool_search_tool_result"

      • container_upload_block: object { file_id, type }

        Response model for a file uploaded to the container.

        • file_id: string

        • type: "container_upload"

    • index: number

    • type: "content_block_start"

  • raw_content_block_delta_event: object { delta, index, type }

    • delta: TextDelta or InputJSONDelta or CitationsDelta or 2 more

      • text_delta: object { text, type }

        • text: string

        • type: "text_delta"

      • input_json_delta: object { partial_json, type }

        • partial_json: string

        • type: "input_json_delta"

      • citations_delta: object { citation, type }

        • citation: CitationCharLocation or CitationPageLocation or CitationContentBlockLocation or 2 more

          • citation_char_location: object { cited_text, document_index, document_title, 4 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_char_index: number

            • file_id: string

            • start_char_index: number

            • type: "char_location"

          • citation_page_location: object { cited_text, document_index, document_title, 4 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_page_number: number

            • file_id: string

            • start_page_number: number

            • type: "page_location"

          • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_block_index: number

            • file_id: string

            • start_block_index: number

            • type: "content_block_location"

          • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

            • cited_text: string

            • encrypted_index: string

            • title: string

            • type: "web_search_result_location"

            • url: string

          • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

            • cited_text: string

            • end_block_index: number

            • search_result_index: number

            • source: string

            • start_block_index: number

            • title: string

            • type: "search_result_location"

        • type: "citations_delta"

      • thinking_delta: object { thinking, type }

        • thinking: string

        • type: "thinking_delta"

      • signature_delta: object { signature, type }

        • signature: string

        • type: "signature_delta"

    • index: number

    • type: "content_block_delta"

  • raw_content_block_stop_event: object { index, type }

    • index: number

    • type: "content_block_stop"

Redacted Thinking Block

• redacted_thinking_block: object { data, type }

  • data: string

  • type: "redacted_thinking"

Redacted Thinking Block Param

• redacted_thinking_block_param: object { data, type }

  • data: string

  • type: "redacted_thinking"

Refusal Stop Details

• refusal_stop_details: object { category, explanation, type }

  Structured information about a refusal.

  • category: "cyber" or "bio"

    The policy category that triggered the refusal.

    null when the refusal doesn't map to a named category.

    • "cyber"

    • "bio"

  • explanation: string

    Human-readable explanation of the refusal.

    This text is not guaranteed to be stable. null when no explanation is available for the category.

  • type: "refusal"

Search Result Block Param

• search_result_block_param: object { content, source, title, 3 more }

  • content: array of TextBlockParam

    • text: string

    • type: "text"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • citations: optional array of TextCitationParam

      • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_char_index: number

        • start_char_index: number

        • type: "char_location"

      • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_page_number: number

        • start_page_number: number

        • type: "page_location"

      • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

        • cited_text: string

        • document_index: number

        • document_title: string

        • end_block_index: number

        • start_block_index: number

        • type: "content_block_location"

      • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

        • cited_text: string

        • encrypted_index: string

        • title: string

        • type: "web_search_result_location"

        • url: string

      • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

        • cited_text: string

        • end_block_index: number

        • search_result_index: number

        • source: string

        • start_block_index: number

        • title: string

        • type: "search_result_location"

  • source: string

  • title: string

  • type: "search_result"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

  • citations: optional object { enabled }

    • enabled: optional boolean

Server Tool Caller

• server_tool_caller: object { tool_id, type }

  Tool invocation generated by a server-side tool.

  • tool_id: string

  • type: "code_execution_20250825"

Server Tool Caller 20260120

• server_tool_caller_20260120: object { tool_id, type }

  • tool_id: string

  • type: "code_execution_20260120"

Server Tool Usage

• server_tool_usage: object { web_fetch_requests, web_search_requests }

  • web_fetch_requests: number

    The number of web fetch tool requests.

  • web_search_requests: number

    The number of web search tool requests.

Server Tool Use Block

• server_tool_use_block: object { id, caller, input, 2 more }

  • id: string

  • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

    Tool invocation directly from the model.

    • direct_caller: object { type }

      Tool invocation directly from the model.

      • type: "direct"

    • server_tool_caller: object { tool_id, type }

      Tool invocation generated by a server-side tool.

      • tool_id: string

      • type: "code_execution_20250825"

    • server_tool_caller_20260120: object { tool_id, type }

      • tool_id: string

      • type: "code_execution_20260120"

  • 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"

  • type: "server_tool_use"

Server Tool Use Block Param

• server_tool_use_block_param: object { id, input, name, 3 more }

  • id: string

  • 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"

  • type: "server_tool_use"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

  • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

    Tool invocation directly from the model.

    • direct_caller: object { type }

      Tool invocation directly from the model.

      • type: "direct"

    • server_tool_caller: object { tool_id, type }

      Tool invocation generated by a server-side tool.

      • tool_id: string

      • type: "code_execution_20250825"

    • server_tool_caller_20260120: object { tool_id, type }

      • tool_id: string

      • type: "code_execution_20260120"

Signature Delta

• signature_delta: object { signature, type }

  • signature: string

  • type: "signature_delta"

Stop Reason

• stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 3 more

  • "end_turn"

  • "max_tokens"

  • "stop_sequence"

  • "tool_use"

  • "pause_turn"

  • "refusal"

Text Block

• text_block: object { citations, text, type }

  • citations: array of TextCitation

    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.

    • citation_char_location: object { cited_text, document_index, document_title, 4 more }

      • cited_text: string

      • document_index: number

      • document_title: string

      • end_char_index: number

      • file_id: string

      • start_char_index: number

      • type: "char_location"

    • citation_page_location: object { cited_text, document_index, document_title, 4 more }

      • cited_text: string

      • document_index: number

      • document_title: string

      • end_page_number: number

      • file_id: string

      • start_page_number: number

      • type: "page_location"

    • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

      • cited_text: string

      • document_index: number

      • document_title: string

      • end_block_index: number

      • file_id: string

      • start_block_index: number

      • type: "content_block_location"

    • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

      • cited_text: string

      • encrypted_index: string

      • title: string

      • type: "web_search_result_location"

      • url: string

    • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

      • cited_text: string

      • end_block_index: number

      • search_result_index: number

      • source: string

      • start_block_index: number

      • title: string

      • type: "search_result_location"

  • text: string

  • type: "text"

Text Block Param

• text_block_param: object { text, type, cache_control, citations }

  • text: string

  • type: "text"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

  • citations: optional array of TextCitationParam

    • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

      • cited_text: string

      • document_index: number

      • document_title: string

      • end_char_index: number

      • start_char_index: number

      • type: "char_location"

    • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

      • cited_text: string

      • document_index: number

      • document_title: string

      • end_page_number: number

      • start_page_number: number

      • type: "page_location"

    • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

      • cited_text: string

      • document_index: number

      • document_title: string

      • end_block_index: number

      • start_block_index: number

      • type: "content_block_location"

    • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

      • cited_text: string

      • encrypted_index: string

      • title: string

      • type: "web_search_result_location"

      • url: string

    • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

      • cited_text: string

      • end_block_index: number

      • search_result_index: number

      • source: string

      • start_block_index: number

      • title: string

      • type: "search_result_location"

Text Citation

• text_citation: CitationCharLocation or CitationPageLocation or CitationContentBlockLocation or 2 more

  • citation_char_location: object { cited_text, document_index, document_title, 4 more }

    • cited_text: string

    • document_index: number

    • document_title: string

    • end_char_index: number

    • file_id: string

    • start_char_index: number

    • type: "char_location"

  • citation_page_location: object { cited_text, document_index, document_title, 4 more }

    • cited_text: string

    • document_index: number

    • document_title: string

    • end_page_number: number

    • file_id: string

    • start_page_number: number

    • type: "page_location"

  • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

    • cited_text: string

    • document_index: number

    • document_title: string

    • end_block_index: number

    • file_id: string

    • start_block_index: number

    • type: "content_block_location"

  • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

    • cited_text: string

    • encrypted_index: string

    • title: string

    • type: "web_search_result_location"

    • url: string

  • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

    • cited_text: string

    • end_block_index: number

    • search_result_index: number

    • source: string

    • start_block_index: number

    • title: string

    • type: "search_result_location"

Text Citation Param

• text_citation_param: CitationCharLocationParam or CitationPageLocationParam or CitationContentBlockLocationParam or 2 more

  • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

    • cited_text: string

    • document_index: number

    • document_title: string

    • end_char_index: number

    • start_char_index: number

    • type: "char_location"

  • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

    • cited_text: string

    • document_index: number

    • document_title: string

    • end_page_number: number

    • start_page_number: number

    • type: "page_location"

  • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

    • cited_text: string

    • document_index: number

    • document_title: string

    • end_block_index: number

    • start_block_index: number

    • type: "content_block_location"

  • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

    • cited_text: string

    • encrypted_index: string

    • title: string

    • type: "web_search_result_location"

    • url: string

  • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

    • cited_text: string

    • end_block_index: number

    • search_result_index: number

    • source: string

    • start_block_index: number

    • title: string

    • type: "search_result_location"

Text Delta

• text_delta: object { text, type }

  • text: string

  • type: "text_delta"

Text Editor Code Execution Create Result Block

• text_editor_code_execution_create_result_block: object { is_file_update, type }

  • is_file_update: boolean

  • type: "text_editor_code_execution_create_result"

Text Editor Code Execution Create Result Block Param

• text_editor_code_execution_create_result_block_param: object { is_file_update, type }

  • is_file_update: boolean

  • type: "text_editor_code_execution_create_result"

Text Editor Code Execution Str Replace Result Block

• text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

  • lines: array of string

  • new_lines: number

  • new_start: number

  • old_lines: number

  • old_start: number

  • type: "text_editor_code_execution_str_replace_result"

Text Editor Code Execution Str Replace Result Block Param

• text_editor_code_execution_str_replace_result_block_param: object { type, lines, new_lines, 3 more }

  • type: "text_editor_code_execution_str_replace_result"

  • lines: optional array of string

  • new_lines: optional number

  • new_start: optional number

  • old_lines: optional number

  • old_start: optional number

Text Editor Code Execution Tool Result Block

• text_editor_code_execution_tool_result_block: object { content, tool_use_id, type }

  • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

    • text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

      • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

        • "invalid_tool_input"

        • "unavailable"

        • "too_many_requests"

        • "execution_time_exceeded"

        • "file_not_found"

      • error_message: string

      • type: "text_editor_code_execution_tool_result_error"

    • text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

      • content: string

      • file_type: "text" or "image" or "pdf"

        • "text"

        • "image"

        • "pdf"

      • num_lines: number

      • start_line: number

      • total_lines: number

      • type: "text_editor_code_execution_view_result"

    • text_editor_code_execution_create_result_block: object { is_file_update, type }

      • is_file_update: boolean

      • type: "text_editor_code_execution_create_result"

    • text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

      • lines: array of string

      • new_lines: number

      • new_start: number

      • old_lines: number

      • old_start: number

      • type: "text_editor_code_execution_str_replace_result"

  • tool_use_id: string

  • type: "text_editor_code_execution_tool_result"

Text Editor Code Execution Tool Result Block Param

• text_editor_code_execution_tool_result_block_param: object { content, tool_use_id, type, cache_control }

  • content: TextEditorCodeExecutionToolResultErrorParam or TextEditorCodeExecutionViewResultBlockParam or TextEditorCodeExecutionCreateResultBlockParam or TextEditorCodeExecutionStrReplaceResultBlockParam

    • text_editor_code_execution_tool_result_error_param: object { error_code, type, error_message }

      • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

        • "invalid_tool_input"

        • "unavailable"

        • "too_many_requests"

        • "execution_time_exceeded"

        • "file_not_found"

      • type: "text_editor_code_execution_tool_result_error"

      • error_message: optional string

    • text_editor_code_execution_view_result_block_param: object { content, file_type, type, 3 more }

      • content: string

      • file_type: "text" or "image" or "pdf"

        • "text"

        • "image"

        • "pdf"

      • type: "text_editor_code_execution_view_result"

      • num_lines: optional number

      • start_line: optional number

      • total_lines: optional number

    • text_editor_code_execution_create_result_block_param: object { is_file_update, type }

      • is_file_update: boolean

      • type: "text_editor_code_execution_create_result"

    • text_editor_code_execution_str_replace_result_block_param: object { type, lines, new_lines, 3 more }

      • type: "text_editor_code_execution_str_replace_result"

      • lines: optional array of string

      • new_lines: optional number

      • new_start: optional number

      • old_lines: optional number

      • old_start: optional number

  • tool_use_id: string

  • type: "text_editor_code_execution_tool_result"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

Text Editor Code Execution Tool Result Error

• text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

  • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

    • "invalid_tool_input"

    • "unavailable"

    • "too_many_requests"

    • "execution_time_exceeded"

    • "file_not_found"

  • error_message: string

  • type: "text_editor_code_execution_tool_result_error"

Text Editor Code Execution Tool Result Error Code

• text_editor_code_execution_tool_result_error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

  • "invalid_tool_input"

  • "unavailable"

  • "too_many_requests"

  • "execution_time_exceeded"

  • "file_not_found"

Text Editor Code Execution Tool Result Error Param

• text_editor_code_execution_tool_result_error_param: object { error_code, type, error_message }

  • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

    • "invalid_tool_input"

    • "unavailable"

    • "too_many_requests"

    • "execution_time_exceeded"

    • "file_not_found"

  • type: "text_editor_code_execution_tool_result_error"

  • error_message: optional string

Text Editor Code Execution View Result Block

• text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

  • content: string

  • file_type: "text" or "image" or "pdf"

    • "text"

    • "image"

    • "pdf"

  • num_lines: number

  • start_line: number

  • total_lines: number

  • type: "text_editor_code_execution_view_result"

Text Editor Code Execution View Result Block Param

• text_editor_code_execution_view_result_block_param: object { content, file_type, type, 3 more }

  • content: string

  • file_type: "text" or "image" or "pdf"

    • "text"

    • "image"

    • "pdf"

  • type: "text_editor_code_execution_view_result"

  • num_lines: optional number

  • start_line: optional number

  • total_lines: optional number

Thinking Block

• thinking_block: object { signature, thinking, type }

  • signature: string

  • thinking: string

  • type: "thinking"

Thinking Block Param

• thinking_block_param: object { signature, thinking, type }

  • signature: string

  • thinking: string

  • type: "thinking"

Thinking Config Adaptive

• thinking_config_adaptive: object { type, display }

  • type: "adaptive"

  • display: optional "summarized" or "omitted"

    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

• thinking_config_disabled: object { type }

  • type: "disabled"

Thinking Config Enabled

• thinking_config_enabled: object { budget_tokens, type, display }

  • 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.

  • type: "enabled"

  • display: optional "summarized" or "omitted"

    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

• thinking_config_param: 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.

  • thinking_config_enabled: object { budget_tokens, type, display }

    • 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.

    • type: "enabled"

    • display: optional "summarized" or "omitted"

      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: object { type }

    • type: "disabled"

  • thinking_config_adaptive: object { type, display }

    • type: "adaptive"

    • display: optional "summarized" or "omitted"

      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

• thinking_delta: object { thinking, type }

  • thinking: string

  • type: "thinking_delta"

Tool

• tool: object { input_schema, name, allowed_callers, 7 more }

  • input_schema: object { type, properties, required }

    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]

    • required: optional array of string

  • name: string

    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"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • cache_control: optional object { type, ttl }

    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.

      • "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

    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

  • type: optional "custom"

    • "custom"

Tool Bash 20250124

• tool_bash_20250124: object { name, type, allowed_callers, 4 more }

  • name: "bash"

    Name of the tool.

    This is how the tool will be called by the model and in tool_use blocks.

  • type: "bash_20250124"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • cache_control: optional object { type, ttl }

    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.

      • "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

• tool_choice: 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.

  • tool_choice_auto: object { type, disable_parallel_tool_use }

    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_any: object { type, disable_parallel_tool_use }

    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_tool: object { name, type, disable_parallel_tool_use }

    The model will use the specified tool with tool_choice.name.

    • name: string

      The name of the tool to use.

    • type: "tool"

    • disable_parallel_tool_use: optional boolean

      Whether to disable parallel tool use.

      Defaults to false. If set to true, the model will output exactly one tool use.

  • tool_choice_none: object { type }

    The model will not be allowed to use tools.

    • type: "none"

Tool Choice Any

• tool_choice_any: object { type, disable_parallel_tool_use }

  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

• tool_choice_auto: object { type, disable_parallel_tool_use }

  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

• tool_choice_none: object { type }

  The model will not be allowed to use tools.

  • type: "none"

Tool Choice Tool

• tool_choice_tool: object { name, type, disable_parallel_tool_use }

  The model will use the specified tool with tool_choice.name.

  • name: string

    The name of the tool to use.

  • type: "tool"

  • disable_parallel_tool_use: optional boolean

    Whether to disable parallel tool use.

    Defaults to false. If set to true, the model will output exactly one tool use.

Tool Reference Block

• tool_reference_block: object { tool_name, type }

  • tool_name: string

  • type: "tool_reference"

Tool Reference Block Param

• tool_reference_block_param: object { tool_name, type, cache_control }

  Tool reference block that can be included in tool_result content.

  • tool_name: string

  • type: "tool_reference"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

Tool Result Block Param

• tool_result_block_param: object { tool_use_id, type, cache_control, 2 more }

  • tool_use_id: string

  • type: "tool_result"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

  • content: optional array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 2 more

    • text_block_param: object { text, type, cache_control, citations }

      • text: string

      • type: "text"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

      • citations: optional array of TextCitationParam

        • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_char_index: number

          • start_char_index: number

          • type: "char_location"

        • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_page_number: number

          • start_page_number: number

          • type: "page_location"

        • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

          • cited_text: string

          • document_index: number

          • document_title: string

          • end_block_index: number

          • start_block_index: number

          • type: "content_block_location"

        • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

          • cited_text: string

          • encrypted_index: string

          • title: string

          • type: "web_search_result_location"

          • url: string

        • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

          • cited_text: string

          • end_block_index: number

          • search_result_index: number

          • source: string

          • start_block_index: number

          • title: string

          • type: "search_result_location"

    • image_block_param: object { source, type, cache_control }

      • source: Base64ImageSource or URLImageSource

        • base64_image_source: object { data, media_type, type }

          • data: string

          • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

            • "image/jpeg"

            • "image/png"

            • "image/gif"

            • "image/webp"

          • type: "base64"

        • url_image_source: object { type, url }

          • type: "url"

          • url: string

      • type: "image"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

    • search_result_block_param: object { content, source, title, 3 more }

      • content: array of TextBlockParam

        • text: string

        • type: "text"

        • cache_control: optional object { type, ttl }

          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.

            • "5m"

            • "1h"

        • citations: optional array of TextCitationParam

          • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_char_index: number

            • start_char_index: number

            • type: "char_location"

          • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_page_number: number

            • start_page_number: number

            • type: "page_location"

          • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_block_index: number

            • start_block_index: number

            • type: "content_block_location"

          • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

            • cited_text: string

            • encrypted_index: string

            • title: string

            • type: "web_search_result_location"

            • url: string

          • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

            • cited_text: string

            • end_block_index: number

            • search_result_index: number

            • source: string

            • start_block_index: number

            • title: string

            • type: "search_result_location"

      • source: string

      • title: string

      • type: "search_result"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

      • citations: optional object { enabled }

        • enabled: optional boolean

    • document_block_param: object { source, type, cache_control, 3 more }

      • source: Base64PDFSource or PlainTextSource or ContentBlockSource or URLPDFSource

        • base64_pdf_source: object { data, media_type, type }

          • data: string

          • media_type: "application/pdf"

          • type: "base64"

        • plain_text_source: object { data, media_type, type }

          • data: string

          • media_type: "text/plain"

          • type: "text"

        • content_block_source: object { content, type }

          • content: string or array of ContentBlockSourceContent

            • union_member_0: string

            • content_block_source_content: array of ContentBlockSourceContent

              • text_block_param: object { text, type, cache_control, citations }

                • text: string

                • type: "text"

                • cache_control: optional object { type, ttl }

                  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.

                    • "5m"

                    • "1h"

                • citations: optional array of TextCitationParam

                  • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

                    • cited_text: string

                    • document_index: number

                    • document_title: string

                    • end_char_index: number

                    • start_char_index: number

                    • type: "char_location"

                  • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

                    • cited_text: string

                    • document_index: number

                    • document_title: string

                    • end_page_number: number

                    • start_page_number: number

                    • type: "page_location"

                  • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

                    • cited_text: string

                    • document_index: number

                    • document_title: string

                    • end_block_index: number

                    • start_block_index: number

                    • type: "content_block_location"

                  • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

                    • cited_text: string

                    • encrypted_index: string

                    • title: string

                    • type: "web_search_result_location"

                    • url: string

                  • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

                    • cited_text: string

                    • end_block_index: number

                    • search_result_index: number

                    • source: string

                    • start_block_index: number

                    • title: string

                    • type: "search_result_location"

              • image_block_param: object { source, type, cache_control }

                • source: Base64ImageSource or URLImageSource

                  • base64_image_source: object { data, media_type, type }

                    • data: string

                    • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

                      • "image/jpeg"

                      • "image/png"

                      • "image/gif"

                      • "image/webp"

                    • type: "base64"

                  • url_image_source: object { type, url }

                    • type: "url"

                    • url: string

                • type: "image"

                • cache_control: optional object { type, ttl }

                  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.

                    • "5m"

                    • "1h"

          • type: "content"

        • url_pdf_source: object { type, url }

          • type: "url"

          • url: string

      • type: "document"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

      • citations: optional object { enabled }

        • enabled: optional boolean

      • context: optional string

      • title: optional string

    • tool_reference_block_param: object { tool_name, type, cache_control }

      Tool reference block that can be included in tool_result content.

      • tool_name: string

      • type: "tool_reference"

      • cache_control: optional object { type, ttl }

        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.

          • "5m"

          • "1h"

  • is_error: optional boolean

Tool Search Tool Bm25 20251119

• tool_search_tool_bm25_20251119: object { name, type, allowed_callers, 3 more }

  • 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.

  • type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"

    • "tool_search_tool_bm25_20251119"

    • "tool_search_tool_bm25"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • cache_control: optional object { type, ttl }

    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.

      • "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

• tool_search_tool_regex_20251119: object { name, type, allowed_callers, 3 more }

  • 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.

  • type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"

    • "tool_search_tool_regex_20251119"

    • "tool_search_tool_regex"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • cache_control: optional object { type, ttl }

    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.

      • "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

• tool_search_tool_result_block: object { content, tool_use_id, type }

  • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

    • tool_search_tool_result_error: object { error_code, error_message, type }

      • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

        • "invalid_tool_input"

        • "unavailable"

        • "too_many_requests"

        • "execution_time_exceeded"

      • error_message: string

      • type: "tool_search_tool_result_error"

    • tool_search_tool_search_result_block: object { tool_references, type }

      • tool_references: array of ToolReferenceBlock

        • tool_name: string

        • type: "tool_reference"

      • type: "tool_search_tool_search_result"

  • tool_use_id: string

  • type: "tool_search_tool_result"

Tool Search Tool Result Block Param

• tool_search_tool_result_block_param: object { content, tool_use_id, type, cache_control }

  • content: ToolSearchToolResultErrorParam or ToolSearchToolSearchResultBlockParam

    • tool_search_tool_result_error_param: object { error_code, type }

      • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

        • "invalid_tool_input"

        • "unavailable"

        • "too_many_requests"

        • "execution_time_exceeded"

      • type: "tool_search_tool_result_error"

    • tool_search_tool_search_result_block_param: object { tool_references, type }

      • tool_references: array of ToolReferenceBlockParam

        • tool_name: string

        • type: "tool_reference"

        • cache_control: optional object { type, ttl }

          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.

            • "5m"

            • "1h"

      • type: "tool_search_tool_search_result"

  • tool_use_id: string

  • type: "tool_search_tool_result"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

Tool Search Tool Result Error

• tool_search_tool_result_error: object { error_code, error_message, type }

  • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

    • "invalid_tool_input"

    • "unavailable"

    • "too_many_requests"

    • "execution_time_exceeded"

  • error_message: string

  • type: "tool_search_tool_result_error"

Tool Search Tool Result Error Code

• tool_search_tool_result_error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

  • "invalid_tool_input"

  • "unavailable"

  • "too_many_requests"

  • "execution_time_exceeded"

Tool Search Tool Result Error Param

• tool_search_tool_result_error_param: object { error_code, type }

  • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

    • "invalid_tool_input"

    • "unavailable"

    • "too_many_requests"

    • "execution_time_exceeded"

  • type: "tool_search_tool_result_error"

Tool Search Tool Search Result Block

• tool_search_tool_search_result_block: object { tool_references, type }

  • tool_references: array of ToolReferenceBlock

    • tool_name: string

    • type: "tool_reference"

  • type: "tool_search_tool_search_result"

Tool Search Tool Search Result Block Param

• tool_search_tool_search_result_block_param: object { tool_references, type }

  • tool_references: array of ToolReferenceBlockParam

    • tool_name: string

    • type: "tool_reference"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

  • type: "tool_search_tool_search_result"

Tool Text Editor 20250124

• tool_text_editor_20250124: object { name, type, allowed_callers, 4 more }

  • name: "str_replace_editor"

    Name of the tool.

    This is how the tool will be called by the model and in tool_use blocks.

  • type: "text_editor_20250124"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • cache_control: optional object { type, ttl }

    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.

      • "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

• tool_text_editor_20250429: object { name, type, allowed_callers, 4 more }

  • 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.

  • type: "text_editor_20250429"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • cache_control: optional object { type, ttl }

    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.

      • "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

• tool_text_editor_20250728: object { name, type, allowed_callers, 5 more }

  • 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.

  • type: "text_editor_20250728"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • cache_control: optional object { type, ttl }

    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.

      • "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

    Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file.

  • strict: optional boolean

    When true, guarantees schema validation on tool names and inputs

Tool Union

• tool_union: Tool or ToolBash20250124 or CodeExecutionTool20250522 or 13 more

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

  • tool: object { input_schema, name, allowed_callers, 7 more }

    • input_schema: object { type, properties, required }

      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]

      • required: optional array of string

    • name: string

      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"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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

      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

    • type: optional "custom"

      • "custom"

  • tool_bash_20250124: object { name, type, allowed_callers, 4 more }

    • name: "bash"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "bash_20250124"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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

  • code_execution_tool_20250522: object { name, type, allowed_callers, 3 more }

    • name: "code_execution"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "code_execution_20250522"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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: object { name, type, allowed_callers, 3 more }

    • name: "code_execution"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "code_execution_20250825"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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: object { name, type, allowed_callers, 3 more }

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

    • name: "code_execution"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "code_execution_20260120"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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

  • memory_tool_20250818: object { name, type, allowed_callers, 4 more }

    • name: "memory"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "memory_20250818"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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_20250124: object { name, type, allowed_callers, 4 more }

    • name: "str_replace_editor"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "text_editor_20250124"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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: object { name, type, allowed_callers, 4 more }

    • 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.

    • type: "text_editor_20250429"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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: object { name, type, allowed_callers, 5 more }

    • 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.

    • type: "text_editor_20250728"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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

      Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file.

    • strict: optional boolean

      When true, guarantees schema validation on tool names and inputs

  • web_search_tool_20250305: object { name, type, allowed_callers, 7 more }

    • name: "web_search"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "web_search_20250305"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • allowed_domains: optional array of string

      If provided, only these domains will be included in results. Cannot be used alongside blocked_domains.

    • blocked_domains: optional array of string

      If provided, these domains will never appear in results. Cannot be used alongside allowed_domains.

    • cache_control: optional object { type, ttl }

      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.

        • "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

      Maximum number of times the tool can be used in the API request.

    • strict: optional boolean

      When true, guarantees schema validation on tool names and inputs

    • user_location: optional object { type, city, country, 2 more }

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

      • type: "approximate"

      • city: optional string

        The city of the user.

      • country: optional string

        The two letter ISO country code of the user.

      • region: optional string

        The region of the user.

      • timezone: optional string

        The IANA timezone of the user.

  • web_fetch_tool_20250910: object { name, type, allowed_callers, 8 more }

    • name: "web_fetch"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "web_fetch_20250910"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • allowed_domains: optional array of string

      List of domains to allow fetching from

    • blocked_domains: optional array of string

      List of domains to block fetching from

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • citations: optional object { enabled }

      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

      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.

    • max_uses: optional number

      Maximum number of times the tool can be used in the API request.

    • strict: optional boolean

      When true, guarantees schema validation on tool names and inputs

  • web_search_tool_20260209: object { name, type, allowed_callers, 7 more }

    • name: "web_search"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "web_search_20260209"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • allowed_domains: optional array of string

      If provided, only these domains will be included in results. Cannot be used alongside blocked_domains.

    • blocked_domains: optional array of string

      If provided, these domains will never appear in results. Cannot be used alongside allowed_domains.

    • cache_control: optional object { type, ttl }

      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.

        • "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

      Maximum number of times the tool can be used in the API request.

    • strict: optional boolean

      When true, guarantees schema validation on tool names and inputs

    • user_location: optional object { type, city, country, 2 more }

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

      • type: "approximate"

      • city: optional string

        The city of the user.

      • country: optional string

        The two letter ISO country code of the user.

      • region: optional string

        The region of the user.

      • timezone: optional string

        The IANA timezone of the user.

  • web_fetch_tool_20260209: object { name, type, allowed_callers, 8 more }

    • name: "web_fetch"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "web_fetch_20260209"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • allowed_domains: optional array of string

      List of domains to allow fetching from

    • blocked_domains: optional array of string

      List of domains to block fetching from

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • citations: optional object { enabled }

      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

      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.

    • max_uses: optional number

      Maximum number of times the tool can be used in the API request.

    • strict: optional boolean

      When true, guarantees schema validation on tool names and inputs

  • web_fetch_tool_20260309: object { name, type, allowed_callers, 9 more }

    Web fetch tool with use_cache parameter for bypassing cached content.

    • name: "web_fetch"

      Name of the tool.

      This is how the tool will be called by the model and in tool_use blocks.

    • type: "web_fetch_20260309"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • allowed_domains: optional array of string

      List of domains to allow fetching from

    • blocked_domains: optional array of string

      List of domains to block fetching from

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • citations: optional object { enabled }

      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

      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.

    • max_uses: optional number

      Maximum number of times the tool can be used in the API request.

    • strict: optional boolean

      When true, guarantees schema validation on tool names and inputs

    • use_cache: optional boolean

      Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.

  • tool_search_tool_bm25_20251119: object { name, type, allowed_callers, 3 more }

    • 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.

    • type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"

      • "tool_search_tool_bm25_20251119"

      • "tool_search_tool_bm25"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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: object { name, type, allowed_callers, 3 more }

    • 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.

    • type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"

      • "tool_search_tool_regex_20251119"

      • "tool_search_tool_regex"

    • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

      • "direct"

      • "code_execution_20250825"

      • "code_execution_20260120"

    • cache_control: optional object { type, ttl }

      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.

        • "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 Use Block

• tool_use_block: object { id, caller, input, 2 more }

  • id: string

  • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

    Tool invocation directly from the model.

    • direct_caller: object { type }

      Tool invocation directly from the model.

      • type: "direct"

    • server_tool_caller: object { tool_id, type }

      Tool invocation generated by a server-side tool.

      • tool_id: string

      • type: "code_execution_20250825"

    • server_tool_caller_20260120: object { tool_id, type }

      • tool_id: string

      • type: "code_execution_20260120"

  • input: map[unknown]

  • name: string

  • type: "tool_use"

Tool Use Block Param

• tool_use_block_param: object { id, input, name, 3 more }

  • id: string

  • input: map[unknown]

  • name: string

  • type: "tool_use"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

  • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

    Tool invocation directly from the model.

    • direct_caller: object { type }

      Tool invocation directly from the model.

      • type: "direct"

    • server_tool_caller: object { tool_id, type }

      Tool invocation generated by a server-side tool.

      • tool_id: string

      • type: "code_execution_20250825"

    • server_tool_caller_20260120: object { tool_id, type }

      • tool_id: string

      • type: "code_execution_20260120"

URL Image Source

• url_image_source: object { type, url }

  • type: "url"

  • url: string

URL PDF Source

• url_pdf_source: object { type, url }

  • type: "url"

  • url: string

Usage

• usage: object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 5 more }

  • cache_creation: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

    Breakdown of cached tokens by TTL

    • ephemeral_1h_input_tokens: number

      The number of input tokens used to create the 1 hour cache entry.

    • ephemeral_5m_input_tokens: number

      The number of input tokens used to create the 5 minute cache entry.

  • cache_creation_input_tokens: number

    The number of input tokens used to create the cache entry.

  • cache_read_input_tokens: number

    The number of input tokens read from the cache.

  • inference_geo: string

    The geographic region where inference was performed for this request.

  • input_tokens: number

    The number of input tokens which were used.

  • output_tokens: number

    The number of output tokens which were used.

  • server_tool_use: object { web_fetch_requests, web_search_requests }

    The number of server tool requests.

    • web_fetch_requests: number

      The number of web fetch tool requests.

    • web_search_requests: number

      The number of web search tool requests.

  • service_tier: "standard" or "priority" or "batch"

    If the request used the priority, standard, or batch tier.

    • "standard"

    • "priority"

    • "batch"

User Location

• user_location: object { type, city, country, 2 more }

  • type: "approximate"

  • city: optional string

    The city of the user.

  • country: optional string

    The two letter ISO country code of the user.

  • region: optional string

    The region of the user.

  • timezone: optional string

    The IANA timezone of the user.

Web Fetch Block

• web_fetch_block: object { content, retrieved_at, type, url }

  • content: object { citations, source, title, type }

    • citations: object { enabled }

      Citation configuration for the document

      • enabled: boolean

    • source: Base64PDFSource or PlainTextSource

      • base64_pdf_source: object { data, media_type, type }

        • data: string

        • media_type: "application/pdf"

        • type: "base64"

      • plain_text_source: object { data, media_type, type }

        • data: string

        • media_type: "text/plain"

        • type: "text"

    • title: string

      The title of the document

    • type: "document"

  • retrieved_at: string

    ISO 8601 timestamp when the content was retrieved

  • type: "web_fetch_result"

  • url: string

    Fetched content URL

Web Fetch Block Param

• web_fetch_block_param: object { content, type, url, retrieved_at }

  • content: object { source, type, cache_control, 3 more }

    • source: Base64PDFSource or PlainTextSource or ContentBlockSource or URLPDFSource

      • base64_pdf_source: object { data, media_type, type }

        • data: string

        • media_type: "application/pdf"

        • type: "base64"

      • plain_text_source: object { data, media_type, type }

        • data: string

        • media_type: "text/plain"

        • type: "text"

      • content_block_source: object { content, type }

        • content: string or array of ContentBlockSourceContent

          • union_member_0: string

          • content_block_source_content: array of ContentBlockSourceContent

            • text_block_param: object { text, type, cache_control, citations }

              • text: string

              • type: "text"

              • cache_control: optional object { type, ttl }

                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.

                  • "5m"

                  • "1h"

              • citations: optional array of TextCitationParam

                • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

                  • cited_text: string

                  • document_index: number

                  • document_title: string

                  • end_char_index: number

                  • start_char_index: number

                  • type: "char_location"

                • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

                  • cited_text: string

                  • document_index: number

                  • document_title: string

                  • end_page_number: number

                  • start_page_number: number

                  • type: "page_location"

                • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

                  • cited_text: string

                  • document_index: number

                  • document_title: string

                  • end_block_index: number

                  • start_block_index: number

                  • type: "content_block_location"

                • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

                  • cited_text: string

                  • encrypted_index: string

                  • title: string

                  • type: "web_search_result_location"

                  • url: string

                • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

                  • cited_text: string

                  • end_block_index: number

                  • search_result_index: number

                  • source: string

                  • start_block_index: number

                  • title: string

                  • type: "search_result_location"

            • image_block_param: object { source, type, cache_control }

              • source: Base64ImageSource or URLImageSource

                • base64_image_source: object { data, media_type, type }

                  • data: string

                  • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

                    • "image/jpeg"

                    • "image/png"

                    • "image/gif"

                    • "image/webp"

                  • type: "base64"

                • url_image_source: object { type, url }

                  • type: "url"

                  • url: string

              • type: "image"

              • cache_control: optional object { type, ttl }

                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.

                  • "5m"

                  • "1h"

        • type: "content"

      • url_pdf_source: object { type, url }

        • type: "url"

        • url: string

    • type: "document"

    • cache_control: optional object { type, ttl }

      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.

        • "5m"

        • "1h"

    • citations: optional object { enabled }

      • enabled: optional boolean

    • context: optional string

    • title: optional string

  • type: "web_fetch_result"

  • url: string

    Fetched content URL

  • retrieved_at: optional string

    ISO 8601 timestamp when the content was retrieved

Web Fetch Tool 20250910

• web_fetch_tool_20250910: object { name, type, allowed_callers, 8 more }

  • name: "web_fetch"

    Name of the tool.

    This is how the tool will be called by the model and in tool_use blocks.

  • type: "web_fetch_20250910"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • allowed_domains: optional array of string

    List of domains to allow fetching from

  • blocked_domains: optional array of string

    List of domains to block fetching from

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

  • citations: optional object { enabled }

    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

    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.

  • max_uses: optional number

    Maximum number of times the tool can be used in the API request.

  • strict: optional boolean

    When true, guarantees schema validation on tool names and inputs

Web Fetch Tool 20260209

• web_fetch_tool_20260209: object { name, type, allowed_callers, 8 more }

  • name: "web_fetch"

    Name of the tool.

    This is how the tool will be called by the model and in tool_use blocks.

  • type: "web_fetch_20260209"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • allowed_domains: optional array of string

    List of domains to allow fetching from

  • blocked_domains: optional array of string

    List of domains to block fetching from

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

  • citations: optional object { enabled }

    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

    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.

  • max_uses: optional number

    Maximum number of times the tool can be used in the API request.

  • strict: optional boolean

    When true, guarantees schema validation on tool names and inputs

Web Fetch Tool 20260309

• web_fetch_tool_20260309: object { name, type, allowed_callers, 9 more }

  Web fetch tool with use_cache parameter for bypassing cached content.

  • name: "web_fetch"

    Name of the tool.

    This is how the tool will be called by the model and in tool_use blocks.

  • type: "web_fetch_20260309"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • allowed_domains: optional array of string

    List of domains to allow fetching from

  • blocked_domains: optional array of string

    List of domains to block fetching from

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

  • citations: optional object { enabled }

    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

    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.

  • max_uses: optional number

    Maximum number of times the tool can be used in the API request.

  • strict: optional boolean

    When true, guarantees schema validation on tool names and inputs

  • use_cache: optional boolean

    Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.

Web Fetch Tool Result Block

• web_fetch_tool_result_block: object { caller, content, tool_use_id, type }

  • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

    Tool invocation directly from the model.

    • direct_caller: object { type }

      Tool invocation directly from the model.

      • type: "direct"

    • server_tool_caller: object { tool_id, type }

      Tool invocation generated by a server-side tool.

      • tool_id: string

      • type: "code_execution_20250825"

    • server_tool_caller_20260120: object { tool_id, type }

      • tool_id: string

      • type: "code_execution_20260120"

  • content: WebFetchToolResultErrorBlock or WebFetchBlock

    • web_fetch_tool_result_error_block: object { error_code, type }

      • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

        • "invalid_tool_input"

        • "url_too_long"

        • "url_not_allowed"

        • "url_not_accessible"

        • "unsupported_content_type"

        • "too_many_requests"

        • "max_uses_exceeded"

        • "unavailable"

      • type: "web_fetch_tool_result_error"

    • web_fetch_block: object { content, retrieved_at, type, url }

      • content: object { citations, source, title, type }

        • citations: object { enabled }

          Citation configuration for the document

          • enabled: boolean

        • source: Base64PDFSource or PlainTextSource

          • base64_pdf_source: object { data, media_type, type }

            • data: string

            • media_type: "application/pdf"

            • type: "base64"

          • plain_text_source: object { data, media_type, type }

            • data: string

            • media_type: "text/plain"

            • type: "text"

        • title: string

          The title of the document

        • type: "document"

      • retrieved_at: string

        ISO 8601 timestamp when the content was retrieved

      • type: "web_fetch_result"

      • url: string

        Fetched content URL

  • tool_use_id: string

  • type: "web_fetch_tool_result"

Web Fetch Tool Result Block Param

• web_fetch_tool_result_block_param: object { content, tool_use_id, type, 2 more }

  • content: WebFetchToolResultErrorBlockParam or WebFetchBlockParam

    • web_fetch_tool_result_error_block_param: object { error_code, type }

      • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

        • "invalid_tool_input"

        • "url_too_long"

        • "url_not_allowed"

        • "url_not_accessible"

        • "unsupported_content_type"

        • "too_many_requests"

        • "max_uses_exceeded"

        • "unavailable"

      • type: "web_fetch_tool_result_error"

    • web_fetch_block_param: object { content, type, url, retrieved_at }

      • content: object { source, type, cache_control, 3 more }

        • source: Base64PDFSource or PlainTextSource or ContentBlockSource or URLPDFSource

          • base64_pdf_source: object { data, media_type, type }

            • data: string

            • media_type: "application/pdf"

            • type: "base64"

          • plain_text_source: object { data, media_type, type }

            • data: string

            • media_type: "text/plain"

            • type: "text"

          • content_block_source: object { content, type }

            • content: string or array of ContentBlockSourceContent

              • union_member_0: string

              • content_block_source_content: array of ContentBlockSourceContent

                • text_block_param: object { text, type, cache_control, citations }

                  • text: string

                  • type: "text"

                  • cache_control: optional object { type, ttl }

                    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.

                      • "5m"

                      • "1h"

                  • citations: optional array of TextCitationParam

                    • citation_char_location_param: object { cited_text, document_index, document_title, 3 more }

                      • cited_text: string

                      • document_index: number

                      • document_title: string

                      • end_char_index: number

                      • start_char_index: number

                      • type: "char_location"

                    • citation_page_location_param: object { cited_text, document_index, document_title, 3 more }

                      • cited_text: string

                      • document_index: number

                      • document_title: string

                      • end_page_number: number

                      • start_page_number: number

                      • type: "page_location"

                    • citation_content_block_location_param: object { cited_text, document_index, document_title, 3 more }

                      • cited_text: string

                      • document_index: number

                      • document_title: string

                      • end_block_index: number

                      • start_block_index: number

                      • type: "content_block_location"

                    • citation_web_search_result_location_param: object { cited_text, encrypted_index, title, 2 more }

                      • cited_text: string

                      • encrypted_index: string

                      • title: string

                      • type: "web_search_result_location"

                      • url: string

                    • citation_search_result_location_param: object { cited_text, end_block_index, search_result_index, 4 more }

                      • cited_text: string

                      • end_block_index: number

                      • search_result_index: number

                      • source: string

                      • start_block_index: number

                      • title: string

                      • type: "search_result_location"

                • image_block_param: object { source, type, cache_control }

                  • source: Base64ImageSource or URLImageSource

                    • base64_image_source: object { data, media_type, type }

                      • data: string

                      • media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"

                        • "image/jpeg"

                        • "image/png"

                        • "image/gif"

                        • "image/webp"

                      • type: "base64"

                    • url_image_source: object { type, url }

                      • type: "url"

                      • url: string

                  • type: "image"

                  • cache_control: optional object { type, ttl }

                    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.

                      • "5m"

                      • "1h"

            • type: "content"

          • url_pdf_source: object { type, url }

            • type: "url"

            • url: string

        • type: "document"

        • cache_control: optional object { type, ttl }

          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.

            • "5m"

            • "1h"

        • citations: optional object { enabled }

          • enabled: optional boolean

        • context: optional string

        • title: optional string

      • type: "web_fetch_result"

      • url: string

        Fetched content URL

      • retrieved_at: optional string

        ISO 8601 timestamp when the content was retrieved

  • tool_use_id: string

  • type: "web_fetch_tool_result"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

  • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

    Tool invocation directly from the model.

    • direct_caller: object { type }

      Tool invocation directly from the model.

      • type: "direct"

    • server_tool_caller: object { tool_id, type }

      Tool invocation generated by a server-side tool.

      • tool_id: string

      • type: "code_execution_20250825"

    • server_tool_caller_20260120: object { tool_id, type }

      • tool_id: string

      • type: "code_execution_20260120"

Web Fetch Tool Result Error Block

• web_fetch_tool_result_error_block: object { error_code, type }

  • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

    • "invalid_tool_input"

    • "url_too_long"

    • "url_not_allowed"

    • "url_not_accessible"

    • "unsupported_content_type"

    • "too_many_requests"

    • "max_uses_exceeded"

    • "unavailable"

  • type: "web_fetch_tool_result_error"

Web Fetch Tool Result Error Block Param

• web_fetch_tool_result_error_block_param: object { error_code, type }

  • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

    • "invalid_tool_input"

    • "url_too_long"

    • "url_not_allowed"

    • "url_not_accessible"

    • "unsupported_content_type"

    • "too_many_requests"

    • "max_uses_exceeded"

    • "unavailable"

  • type: "web_fetch_tool_result_error"

Web Fetch Tool Result Error Code

• web_fetch_tool_result_error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

  • "invalid_tool_input"

  • "url_too_long"

  • "url_not_allowed"

  • "url_not_accessible"

  • "unsupported_content_type"

  • "too_many_requests"

  • "max_uses_exceeded"

  • "unavailable"

Web Search Result Block

• web_search_result_block: object { encrypted_content, page_age, title, 2 more }

  • encrypted_content: string

  • page_age: string

  • title: string

  • type: "web_search_result"

  • url: string

Web Search Result Block Param

• web_search_result_block_param: object { encrypted_content, title, type, 2 more }

  • encrypted_content: string

  • title: string

  • type: "web_search_result"

  • url: string

  • page_age: optional string

Web Search Tool 20250305

• web_search_tool_20250305: object { name, type, allowed_callers, 7 more }

  • name: "web_search"

    Name of the tool.

    This is how the tool will be called by the model and in tool_use blocks.

  • type: "web_search_20250305"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • allowed_domains: optional array of string

    If provided, only these domains will be included in results. Cannot be used alongside blocked_domains.

  • blocked_domains: optional array of string

    If provided, these domains will never appear in results. Cannot be used alongside allowed_domains.

  • cache_control: optional object { type, ttl }

    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.

      • "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

    Maximum number of times the tool can be used in the API request.

  • strict: optional boolean

    When true, guarantees schema validation on tool names and inputs

  • user_location: optional object { type, city, country, 2 more }

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

    • type: "approximate"

    • city: optional string

      The city of the user.

    • country: optional string

      The two letter ISO country code of the user.

    • region: optional string

      The region of the user.

    • timezone: optional string

      The IANA timezone of the user.

Web Search Tool 20260209

• web_search_tool_20260209: object { name, type, allowed_callers, 7 more }

  • name: "web_search"

    Name of the tool.

    This is how the tool will be called by the model and in tool_use blocks.

  • type: "web_search_20260209"

  • allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120"

    • "direct"

    • "code_execution_20250825"

    • "code_execution_20260120"

  • allowed_domains: optional array of string

    If provided, only these domains will be included in results. Cannot be used alongside blocked_domains.

  • blocked_domains: optional array of string

    If provided, these domains will never appear in results. Cannot be used alongside allowed_domains.

  • cache_control: optional object { type, ttl }

    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.

      • "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

    Maximum number of times the tool can be used in the API request.

  • strict: optional boolean

    When true, guarantees schema validation on tool names and inputs

  • user_location: optional object { type, city, country, 2 more }

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

    • type: "approximate"

    • city: optional string

      The city of the user.

    • country: optional string

      The two letter ISO country code of the user.

    • region: optional string

      The region of the user.

    • timezone: optional string

      The IANA timezone of the user.

Web Search Tool Request Error

• web_search_tool_request_error: object { error_code, type }

  • error_code: "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"

  • type: "web_search_tool_result_error"

Web Search Tool Result Block

• web_search_tool_result_block: object { caller, content, tool_use_id, type }

  • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

    Tool invocation directly from the model.

    • direct_caller: object { type }

      Tool invocation directly from the model.

      • type: "direct"

    • server_tool_caller: object { tool_id, type }

      Tool invocation generated by a server-side tool.

      • tool_id: string

      • type: "code_execution_20250825"

    • server_tool_caller_20260120: object { tool_id, type }

      • tool_id: string

      • type: "code_execution_20260120"

  • content: WebSearchToolResultError or array of WebSearchResultBlock

    • web_search_tool_result_error: object { error_code, type }

      • error_code: "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"

      • type: "web_search_tool_result_error"

    • union_member_1: array of WebSearchResultBlock

      • encrypted_content: string

      • page_age: string

      • title: string

      • type: "web_search_result"

      • url: string

  • tool_use_id: string

  • type: "web_search_tool_result"

Web Search Tool Result Block Content

• web_search_tool_result_block_content: WebSearchToolResultError or array of WebSearchResultBlock

  • web_search_tool_result_error: object { error_code, type }

    • error_code: "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"

    • type: "web_search_tool_result_error"

  • union_member_1: array of WebSearchResultBlock

    • encrypted_content: string

    • page_age: string

    • title: string

    • type: "web_search_result"

    • url: string

Web Search Tool Result Block Param

• web_search_tool_result_block_param: object { content, tool_use_id, type, 2 more }

  • content: array of WebSearchResultBlockParam or WebSearchToolRequestError

    • web_search_tool_result_block_item: array of WebSearchResultBlockParam

      • encrypted_content: string

      • title: string

      • type: "web_search_result"

      • url: string

      • page_age: optional string

    • web_search_tool_request_error: object { error_code, type }

      • error_code: "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"

      • type: "web_search_tool_result_error"

  • tool_use_id: string

  • type: "web_search_tool_result"

  • cache_control: optional object { type, ttl }

    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.

      • "5m"

      • "1h"

  • caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120

    Tool invocation directly from the model.

    • direct_caller: object { type }

      Tool invocation directly from the model.

      • type: "direct"

    • server_tool_caller: object { tool_id, type }

      Tool invocation generated by a server-side tool.

      • tool_id: string

      • type: "code_execution_20250825"

    • server_tool_caller_20260120: object { tool_id, type }

      • tool_id: string

      • type: "code_execution_20260120"

Web Search Tool Result Block Param Content

• web_search_tool_result_block_param_content: array of WebSearchResultBlockParam or WebSearchToolRequestError

  • web_search_tool_result_block_item: array of WebSearchResultBlockParam

    • encrypted_content: string

    • title: string

    • type: "web_search_result"

    • url: string

    • page_age: optional string

  • web_search_tool_request_error: object { error_code, type }

    • error_code: "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"

    • type: "web_search_tool_result_error"

Web Search Tool Result Error

• web_search_tool_result_error: object { error_code, type }

  • error_code: "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"

  • type: "web_search_tool_result_error"

Web Search Tool Result Error Code

• web_search_tool_result_error_code: "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"

Batches

Create

$ ant messages:batches create

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

Parameters

• --request: array of object { custom_id, params }

  List of requests for prompt completion. Each is an individual request to create a Message.

Returns

• message_batch: object { id, archived_at, cancel_initiated_at, 7 more }

  • id: string

    Unique object identifier.

    The format and length of IDs may change over time.

  • archived_at: string

    RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable.

  • cancel_initiated_at: string

    RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated.

  • created_at: string

    RFC 3339 datetime string representing the time at which the Message Batch was created.

  • ended_at: string

    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.

  • 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.

  • processing_status: "in_progress" or "canceling" or "ended"

    Processing status of the Message Batch.

    • "in_progress"

    • "canceling"

    • "ended"

  • request_counts: object { canceled, errored, expired, 2 more }

    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.

    • 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.

    • expired: number

      Number of requests in the Message Batch that have expired.

      This is zero until processing of the entire Message Batch has ended.

    • processing: number

      Number of requests in the Message Batch that are processing.

    • 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.

  • results_url: string

    URL to a .jsonl file containing the results of the Message Batch requests. Specified only once processing ends.

    Results in the file are not guaranteed to be in the same order as requests. Use the custom_id field to match results to requests.

  • type: "message_batch"

    Object type.

    For Message Batches, this is always "message_batch".

Example

ant messages:batches create \
  --api-key my-anthropic-api-key \
  --request '{custom_id: my-custom-id-1, params: {max_tokens: 1024, messages: [{content: [{text: x, type: text}], role: user}], model: claude-opus-4-6}}'

Retrieve

$ ant messages:batches retrieve

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

Parameters

• --message-batch-id: string

  ID of the Message Batch.

Returns

• message_batch: object { id, archived_at, cancel_initiated_at, 7 more }

  • id: string

    Unique object identifier.

    The format and length of IDs may change over time.

  • archived_at: string

    RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable.

  • cancel_initiated_at: string

    RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated.

  • created_at: string

    RFC 3339 datetime string representing the time at which the Message Batch was created.

  • ended_at: string

    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.

  • 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.

  • processing_status: "in_progress" or "canceling" or "ended"

    Processing status of the Message Batch.

    • "in_progress"

    • "canceling"

    • "ended"

  • request_counts: object { canceled, errored, expired, 2 more }

    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.

    • 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.

    • expired: number

      Number of requests in the Message Batch that have expired.

      This is zero until processing of the entire Message Batch has ended.

    • processing: number

      Number of requests in the Message Batch that are processing.

    • 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.

  • results_url: string

    URL to a .jsonl file containing the results of the Message Batch requests. Specified only once processing ends.

    Results in the file are not guaranteed to be in the same order as requests. Use the custom_id field to match results to requests.

  • type: "message_batch"

    Object type.

    For Message Batches, this is always "message_batch".

Example

ant messages:batches retrieve \
  --api-key my-anthropic-api-key \
  --message-batch-id message_batch_id

List

$ ant messages:batches list

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

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.

Returns

• ListResponse_MessageBatch_: object { data, first_id, has_more, last_id }

  • data: array of MessageBatch

    • id: string

      Unique object identifier.

      The format and length of IDs may change over time.

    • archived_at: string

      RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable.

    • cancel_initiated_at: string

      RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated.

    • created_at: string

      RFC 3339 datetime string representing the time at which the Message Batch was created.

    • ended_at: string

      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.

    • 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.

    • processing_status: "in_progress" or "canceling" or "ended"

      Processing status of the Message Batch.

      • "in_progress"

      • "canceling"

      • "ended"

    • request_counts: object { canceled, errored, expired, 2 more }

      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.

      • 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.

      • expired: number

        Number of requests in the Message Batch that have expired.

        This is zero until processing of the entire Message Batch has ended.

      • processing: number

        Number of requests in the Message Batch that are processing.

      • 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.

    • results_url: string

      URL to a .jsonl file containing the results of the Message Batch requests. Specified only once processing ends.

      Results in the file are not guaranteed to be in the same order as requests. Use the custom_id field to match results to requests.

    • type: "message_batch"

      Object type.

      For Message Batches, this is always "message_batch".

  • first_id: string

    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

    Last ID in the data list. Can be used as the after_id for the next page.

Example

ant messages:batches list \
  --api-key my-anthropic-api-key

Cancel

$ ant messages:batches cancel

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

Parameters

• --message-batch-id: string

  ID of the Message Batch.

Returns

• message_batch: object { id, archived_at, cancel_initiated_at, 7 more }

  • id: string

    Unique object identifier.

    The format and length of IDs may change over time.

  • archived_at: string

    RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable.

  • cancel_initiated_at: string

    RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated.

  • created_at: string

    RFC 3339 datetime string representing the time at which the Message Batch was created.

  • ended_at: string

    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.

  • 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.

  • processing_status: "in_progress" or "canceling" or "ended"

    Processing status of the Message Batch.

    • "in_progress"

    • "canceling"

    • "ended"

  • request_counts: object { canceled, errored, expired, 2 more }

    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.

    • 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.

    • expired: number

      Number of requests in the Message Batch that have expired.

      This is zero until processing of the entire Message Batch has ended.

    • processing: number

      Number of requests in the Message Batch that are processing.

    • 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.

  • results_url: string

    URL to a .jsonl file containing the results of the Message Batch requests. Specified only once processing ends.

    Results in the file are not guaranteed to be in the same order as requests. Use the custom_id field to match results to requests.

  • type: "message_batch"

    Object type.

    For Message Batches, this is always "message_batch".

Example

ant messages:batches cancel \
  --api-key my-anthropic-api-key \
  --message-batch-id message_batch_id

Delete

$ ant messages:batches delete

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

Parameters

• --message-batch-id: string

  ID of the Message Batch.

Returns

• deleted_message_batch: object { id, type }

  • id: string

    ID of the Message Batch.

  • type: "message_batch_deleted"

    Deleted object type.

    For Message Batches, this is always "message_batch_deleted".

Example

ant messages:batches delete \
  --api-key my-anthropic-api-key \
  --message-batch-id message_batch_id

Results

$ ant messages:batches 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

Parameters

• --message-batch-id: string

  ID of the Message Batch.

Returns

• message_batch_individual_response: object { custom_id, result }

  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: MessageBatchSucceededResult or MessageBatchErroredResult or MessageBatchCanceledResult or MessageBatchExpiredResult

    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.

    • message_batch_succeeded_result: object { message, type }

      • message: object { id, container, content, 7 more }

        • id: string

          Unique object identifier.

          The format and length of IDs may change over time.

        • container: object { id, expires_at }

          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.

        • 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:

          [{"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:

          [
            {"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:

          [{"type": "text", "text": "B)"}]
          

          • text_block: object { citations, text, type }

            • citations: array of TextCitation

              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.

              • citation_char_location: object { cited_text, document_index, document_title, 4 more }

                • cited_text: string

                • document_index: number

                • document_title: string

                • end_char_index: number

                • file_id: string

                • start_char_index: number

                • type: "char_location"

              • citation_page_location: object { cited_text, document_index, document_title, 4 more }

                • cited_text: string

                • document_index: number

                • document_title: string

                • end_page_number: number

                • file_id: string

                • start_page_number: number

                • type: "page_location"

              • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

                • cited_text: string

                • document_index: number

                • document_title: string

                • end_block_index: number

                • file_id: string

                • start_block_index: number

                • type: "content_block_location"

              • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

                • cited_text: string

                • encrypted_index: string

                • title: string

                • type: "web_search_result_location"

                • url: string

              • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

                • cited_text: string

                • end_block_index: number

                • search_result_index: number

                • source: string

                • start_block_index: number

                • title: string

                • type: "search_result_location"

            • text: string

            • type: "text"

          • thinking_block: object { signature, thinking, type }

            • signature: string

            • thinking: string

            • type: "thinking"

          • redacted_thinking_block: object { data, type }

            • data: string

            • type: "redacted_thinking"

          • tool_use_block: object { id, caller, input, 2 more }

            • id: string

            • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

              Tool invocation directly from the model.

              • direct_caller: object { type }

                Tool invocation directly from the model.

                • type: "direct"

              • server_tool_caller: object { tool_id, type }

                Tool invocation generated by a server-side tool.

                • tool_id: string

                • type: "code_execution_20250825"

              • server_tool_caller_20260120: object { tool_id, type }

                • tool_id: string

                • type: "code_execution_20260120"

            • input: map[unknown]

            • name: string

            • type: "tool_use"

          • server_tool_use_block: object { id, caller, input, 2 more }

            • id: string

            • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

              Tool invocation directly from the model.

              • direct_caller: object { type }

                Tool invocation directly from the model.

                • type: "direct"

              • server_tool_caller: object { tool_id, type }

                Tool invocation generated by a server-side tool.

                • tool_id: string

                • type: "code_execution_20250825"

              • server_tool_caller_20260120: object { tool_id, type }

                • tool_id: string

                • type: "code_execution_20260120"

            • 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"

            • type: "server_tool_use"

          • web_search_tool_result_block: object { caller, content, tool_use_id, type }

            • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

              Tool invocation directly from the model.

              • direct_caller: object { type }

                Tool invocation directly from the model.

                • type: "direct"

              • server_tool_caller: object { tool_id, type }

                Tool invocation generated by a server-side tool.

                • tool_id: string

                • type: "code_execution_20250825"

              • server_tool_caller_20260120: object { tool_id, type }

                • tool_id: string

                • type: "code_execution_20260120"

            • content: WebSearchToolResultError or array of WebSearchResultBlock

              • web_search_tool_result_error: object { error_code, type }

                • error_code: "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"

                • type: "web_search_tool_result_error"

              • union_member_1: array of WebSearchResultBlock

                • encrypted_content: string

                • page_age: string

                • title: string

                • type: "web_search_result"

                • url: string

            • tool_use_id: string

            • type: "web_search_tool_result"

          • web_fetch_tool_result_block: object { caller, content, tool_use_id, type }

            • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

              Tool invocation directly from the model.

              • direct_caller: object { type }

                Tool invocation directly from the model.

                • type: "direct"

              • server_tool_caller: object { tool_id, type }

                Tool invocation generated by a server-side tool.

                • tool_id: string

                • type: "code_execution_20250825"

              • server_tool_caller_20260120: object { tool_id, type }

                • tool_id: string

                • type: "code_execution_20260120"

            • content: WebFetchToolResultErrorBlock or WebFetchBlock

              • web_fetch_tool_result_error_block: object { error_code, type }

                • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

                  • "invalid_tool_input"

                  • "url_too_long"

                  • "url_not_allowed"

                  • "url_not_accessible"

                  • "unsupported_content_type"

                  • "too_many_requests"

                  • "max_uses_exceeded"

                  • "unavailable"

                • type: "web_fetch_tool_result_error"

              • web_fetch_block: object { content, retrieved_at, type, url }

                • content: object { citations, source, title, type }

                  • citations: object { enabled }

                    Citation configuration for the document

                    • enabled: boolean

                  • source: Base64PDFSource or PlainTextSource

                    • base64_pdf_source: object { data, media_type, type }

                      • data: string

                      • media_type: "application/pdf"

                      • type: "base64"

                    • plain_text_source: object { data, media_type, type }

                      • data: string

                      • media_type: "text/plain"

                      • type: "text"

                  • title: string

                    The title of the document

                  • type: "document"

                • retrieved_at: string

                  ISO 8601 timestamp when the content was retrieved

                • type: "web_fetch_result"

                • url: string

                  Fetched content URL

            • tool_use_id: string

            • type: "web_fetch_tool_result"

          • code_execution_tool_result_block: object { content, tool_use_id, type }

            • content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

              • code_execution_tool_result_error: object { error_code, type }

                • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

                  • "invalid_tool_input"

                  • "unavailable"

                  • "too_many_requests"

                  • "execution_time_exceeded"

                • type: "code_execution_tool_result_error"

              • code_execution_result_block: object { content, return_code, stderr, 2 more }

                • content: array of CodeExecutionOutputBlock

                  • file_id: string

                  • type: "code_execution_output"

                • return_code: number

                • stderr: string

                • stdout: string

                • type: "code_execution_result"

              • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

                • content: array of CodeExecutionOutputBlock

                  • file_id: string

                  • type: "code_execution_output"

                • encrypted_stdout: string

                • return_code: number

                • stderr: string

                • type: "encrypted_code_execution_result"

            • tool_use_id: string

            • type: "code_execution_tool_result"

          • bash_code_execution_tool_result_block: object { content, tool_use_id, type }

            • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

              • bash_code_execution_tool_result_error: object { error_code, type }

                • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

                  • "invalid_tool_input"

                  • "unavailable"

                  • "too_many_requests"

                  • "execution_time_exceeded"

                  • "output_file_too_large"

                • type: "bash_code_execution_tool_result_error"

              • bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

                • content: array of BashCodeExecutionOutputBlock

                  • file_id: string

                  • type: "bash_code_execution_output"

                • return_code: number

                • stderr: string

                • stdout: string

                • type: "bash_code_execution_result"

            • tool_use_id: string

            • type: "bash_code_execution_tool_result"

          • text_editor_code_execution_tool_result_block: object { content, tool_use_id, type }

            • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

              • text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

                • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

                  • "invalid_tool_input"

                  • "unavailable"

                  • "too_many_requests"

                  • "execution_time_exceeded"

                  • "file_not_found"

                • error_message: string

                • type: "text_editor_code_execution_tool_result_error"

              • text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

                • content: string

                • file_type: "text" or "image" or "pdf"

                  • "text"

                  • "image"

                  • "pdf"

                • num_lines: number

                • start_line: number

                • total_lines: number

                • type: "text_editor_code_execution_view_result"

              • text_editor_code_execution_create_result_block: object { is_file_update, type }

                • is_file_update: boolean

                • type: "text_editor_code_execution_create_result"

              • text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

                • lines: array of string

                • new_lines: number

                • new_start: number

                • old_lines: number

                • old_start: number

                • type: "text_editor_code_execution_str_replace_result"

            • tool_use_id: string

            • type: "text_editor_code_execution_tool_result"

          • tool_search_tool_result_block: object { content, tool_use_id, type }

            • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

              • tool_search_tool_result_error: object { error_code, error_message, type }

                • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

                  • "invalid_tool_input"

                  • "unavailable"

                  • "too_many_requests"

                  • "execution_time_exceeded"

                • error_message: string

                • type: "tool_search_tool_result_error"

              • tool_search_tool_search_result_block: object { tool_references, type }

                • tool_references: array of ToolReferenceBlock

                  • tool_name: string

                  • type: "tool_reference"

                • type: "tool_search_tool_search_result"

            • tool_use_id: string

            • type: "tool_search_tool_result"

          • container_upload_block: object { file_id, type }

            Response model for a file uploaded to the container.

            • file_id: string

            • type: "container_upload"

        • model: "claude-opus-4-7" or "claude-mythos-preview" or "claude-opus-4-6" or 14 more or string

          The model that will complete your prompt.

          See models for additional details and options.

          • "claude-opus-4-7"

            Frontier intelligence for long-running agents and coding

          • "claude-mythos-preview"

            New class of intelligence, strongest in coding and cybersecurity

          • "claude-opus-4-6"

            Frontier 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"

            Premium model combining maximum intelligence with practical performance

          • "claude-opus-4-5-20251101"

            Premium model combining maximum intelligence with practical performance

          • "claude-sonnet-4-5"

            High-performance model for agents and coding

          • "claude-sonnet-4-5-20250929"

            High-performance model for agents and coding

          • "claude-opus-4-1"

            Exceptional model for specialized complex tasks

          • "claude-opus-4-1-20250805"

            Exceptional model for specialized complex tasks

          • "claude-opus-4-0"

            Powerful model for complex tasks

          • "claude-opus-4-20250514"

            Powerful model for complex tasks

          • "claude-sonnet-4-0"

            High-performance model with extended thinking

          • "claude-sonnet-4-20250514"

            High-performance model with extended thinking

          • "claude-3-haiku-20240307"

            Fast and cost-effective model

        • role: "assistant"

          Conversational role of the generated message.

          This will always be "assistant".

        • stop_details: object { category, explanation, type }

          Structured information about a refusal.

          • category: "cyber" or "bio"

            The policy category that triggered the refusal.

            null when the refusal doesn't map to a named category.

            • "cyber"

            • "bio"

          • explanation: string

            Human-readable explanation of the refusal.

            This text is not guaranteed to be stable. null when no explanation is available for the category.

          • type: "refusal"

        • stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 3 more

          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

          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"

        • stop_sequence: string

          Which custom stop sequence was generated, if any.

          This value will be a non-null string if one of your custom stop sequences was generated.

        • type: "message"

          Object type.

          For Messages, this is always "message".

        • usage: object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 5 more }

          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: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

            Breakdown of cached tokens by TTL

            • ephemeral_1h_input_tokens: number

              The number of input tokens used to create the 1 hour cache entry.

            • ephemeral_5m_input_tokens: number

              The number of input tokens used to create the 5 minute cache entry.

          • cache_creation_input_tokens: number

            The number of input tokens used to create the cache entry.

          • cache_read_input_tokens: number

            The number of input tokens read from the cache.

          • inference_geo: string

            The geographic region where inference was performed for this request.

          • input_tokens: number

            The number of input tokens which were used.

          • output_tokens: number

            The number of output tokens which were used.

          • server_tool_use: object { web_fetch_requests, web_search_requests }

            The number of server tool requests.

            • web_fetch_requests: number

              The number of web fetch tool requests.

            • web_search_requests: number

              The number of web search tool requests.

          • service_tier: "standard" or "priority" or "batch"

            If the request used the priority, standard, or batch tier.

            • "standard"

            • "priority"

            • "batch"

      • type: "succeeded"

    • message_batch_errored_result: object { error, type }

      • error: object { error, request_id, type }

        • error: InvalidRequestError or AuthenticationError or BillingError or 6 more

          • invalid_request_error: object { message, type }

            • message: string

            • type: "invalid_request_error"

          • authentication_error: object { message, type }

            • message: string

            • type: "authentication_error"

          • billing_error: object { message, type }

            • message: string

            • type: "billing_error"

          • permission_error: object { message, type }

            • message: string

            • type: "permission_error"

          • not_found_error: object { message, type }

            • message: string

            • type: "not_found_error"

          • rate_limit_error: object { message, type }

            • message: string

            • type: "rate_limit_error"

          • gateway_timeout_error: object { message, type }

            • message: string

            • type: "timeout_error"

          • api_error_object: object { message, type }

            • message: string

            • type: "api_error"

          • overloaded_error: object { message, type }

            • message: string

            • type: "overloaded_error"

        • request_id: string

        • type: "error"

      • type: "errored"

    • message_batch_canceled_result: object { type }

      • type: "canceled"

    • message_batch_expired_result: object { type }

      • type: "expired"

Example

ant messages:batches results \
  --api-key my-anthropic-api-key \
  --message-batch-id message_batch_id

Domain Types

Deleted Message Batch

• deleted_message_batch: object { id, type }

  • id: string

    ID of the Message Batch.

  • type: "message_batch_deleted"

    Deleted object type.

    For Message Batches, this is always "message_batch_deleted".

Message Batch

• message_batch: object { id, archived_at, cancel_initiated_at, 7 more }

  • id: string

    Unique object identifier.

    The format and length of IDs may change over time.

  • archived_at: string

    RFC 3339 datetime string representing the time at which the Message Batch was archived and its results became unavailable.

  • cancel_initiated_at: string

    RFC 3339 datetime string representing the time at which cancellation was initiated for the Message Batch. Specified only if cancellation was initiated.

  • created_at: string

    RFC 3339 datetime string representing the time at which the Message Batch was created.

  • ended_at: string

    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.

  • 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.

  • processing_status: "in_progress" or "canceling" or "ended"

    Processing status of the Message Batch.

    • "in_progress"

    • "canceling"

    • "ended"

  • request_counts: object { canceled, errored, expired, 2 more }

    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.

    • 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.

    • expired: number

      Number of requests in the Message Batch that have expired.

      This is zero until processing of the entire Message Batch has ended.

    • processing: number

      Number of requests in the Message Batch that are processing.

    • 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.

  • results_url: string

    URL to a .jsonl file containing the results of the Message Batch requests. Specified only once processing ends.

    Results in the file are not guaranteed to be in the same order as requests. Use the custom_id field to match results to requests.

  • type: "message_batch"

    Object type.

    For Message Batches, this is always "message_batch".

Message Batch Canceled Result

• message_batch_canceled_result: object { type }

  • type: "canceled"

Message Batch Errored Result

• message_batch_errored_result: object { error, type }

  • error: object { error, request_id, type }

    • error: InvalidRequestError or AuthenticationError or BillingError or 6 more

      • invalid_request_error: object { message, type }

        • message: string

        • type: "invalid_request_error"

      • authentication_error: object { message, type }

        • message: string

        • type: "authentication_error"

      • billing_error: object { message, type }

        • message: string

        • type: "billing_error"

      • permission_error: object { message, type }

        • message: string

        • type: "permission_error"

      • not_found_error: object { message, type }

        • message: string

        • type: "not_found_error"

      • rate_limit_error: object { message, type }

        • message: string

        • type: "rate_limit_error"

      • gateway_timeout_error: object { message, type }

        • message: string

        • type: "timeout_error"

      • api_error_object: object { message, type }

        • message: string

        • type: "api_error"

      • overloaded_error: object { message, type }

        • message: string

        • type: "overloaded_error"

    • request_id: string

    • type: "error"

  • type: "errored"

Message Batch Expired Result

• message_batch_expired_result: object { type }

  • type: "expired"

Message Batch Individual Response

• message_batch_individual_response: object { custom_id, result }

  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: MessageBatchSucceededResult or MessageBatchErroredResult or MessageBatchCanceledResult or MessageBatchExpiredResult

    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.

    • message_batch_succeeded_result: object { message, type }

      • message: object { id, container, content, 7 more }

        • id: string

          Unique object identifier.

          The format and length of IDs may change over time.

        • container: object { id, expires_at }

          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.

        • 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:

          [{"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:

          [
            {"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:

          [{"type": "text", "text": "B)"}]
          

          • text_block: object { citations, text, type }

            • citations: array of TextCitation

              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.

              • citation_char_location: object { cited_text, document_index, document_title, 4 more }

                • cited_text: string

                • document_index: number

                • document_title: string

                • end_char_index: number

                • file_id: string

                • start_char_index: number

                • type: "char_location"

              • citation_page_location: object { cited_text, document_index, document_title, 4 more }

                • cited_text: string

                • document_index: number

                • document_title: string

                • end_page_number: number

                • file_id: string

                • start_page_number: number

                • type: "page_location"

              • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

                • cited_text: string

                • document_index: number

                • document_title: string

                • end_block_index: number

                • file_id: string

                • start_block_index: number

                • type: "content_block_location"

              • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

                • cited_text: string

                • encrypted_index: string

                • title: string

                • type: "web_search_result_location"

                • url: string

              • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

                • cited_text: string

                • end_block_index: number

                • search_result_index: number

                • source: string

                • start_block_index: number

                • title: string

                • type: "search_result_location"

            • text: string

            • type: "text"

          • thinking_block: object { signature, thinking, type }

            • signature: string

            • thinking: string

            • type: "thinking"

          • redacted_thinking_block: object { data, type }

            • data: string

            • type: "redacted_thinking"

          • tool_use_block: object { id, caller, input, 2 more }

            • id: string

            • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

              Tool invocation directly from the model.

              • direct_caller: object { type }

                Tool invocation directly from the model.

                • type: "direct"

              • server_tool_caller: object { tool_id, type }

                Tool invocation generated by a server-side tool.

                • tool_id: string

                • type: "code_execution_20250825"

              • server_tool_caller_20260120: object { tool_id, type }

                • tool_id: string

                • type: "code_execution_20260120"

            • input: map[unknown]

            • name: string

            • type: "tool_use"

          • server_tool_use_block: object { id, caller, input, 2 more }

            • id: string

            • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

              Tool invocation directly from the model.

              • direct_caller: object { type }

                Tool invocation directly from the model.

                • type: "direct"

              • server_tool_caller: object { tool_id, type }

                Tool invocation generated by a server-side tool.

                • tool_id: string

                • type: "code_execution_20250825"

              • server_tool_caller_20260120: object { tool_id, type }

                • tool_id: string

                • type: "code_execution_20260120"

            • 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"

            • type: "server_tool_use"

          • web_search_tool_result_block: object { caller, content, tool_use_id, type }

            • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

              Tool invocation directly from the model.

              • direct_caller: object { type }

                Tool invocation directly from the model.

                • type: "direct"

              • server_tool_caller: object { tool_id, type }

                Tool invocation generated by a server-side tool.

                • tool_id: string

                • type: "code_execution_20250825"

              • server_tool_caller_20260120: object { tool_id, type }

                • tool_id: string

                • type: "code_execution_20260120"

            • content: WebSearchToolResultError or array of WebSearchResultBlock

              • web_search_tool_result_error: object { error_code, type }

                • error_code: "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"

                • type: "web_search_tool_result_error"

              • union_member_1: array of WebSearchResultBlock

                • encrypted_content: string

                • page_age: string

                • title: string

                • type: "web_search_result"

                • url: string

            • tool_use_id: string

            • type: "web_search_tool_result"

          • web_fetch_tool_result_block: object { caller, content, tool_use_id, type }

            • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

              Tool invocation directly from the model.

              • direct_caller: object { type }

                Tool invocation directly from the model.

                • type: "direct"

              • server_tool_caller: object { tool_id, type }

                Tool invocation generated by a server-side tool.

                • tool_id: string

                • type: "code_execution_20250825"

              • server_tool_caller_20260120: object { tool_id, type }

                • tool_id: string

                • type: "code_execution_20260120"

            • content: WebFetchToolResultErrorBlock or WebFetchBlock

              • web_fetch_tool_result_error_block: object { error_code, type }

                • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

                  • "invalid_tool_input"

                  • "url_too_long"

                  • "url_not_allowed"

                  • "url_not_accessible"

                  • "unsupported_content_type"

                  • "too_many_requests"

                  • "max_uses_exceeded"

                  • "unavailable"

                • type: "web_fetch_tool_result_error"

              • web_fetch_block: object { content, retrieved_at, type, url }

                • content: object { citations, source, title, type }

                  • citations: object { enabled }

                    Citation configuration for the document

                    • enabled: boolean

                  • source: Base64PDFSource or PlainTextSource

                    • base64_pdf_source: object { data, media_type, type }

                      • data: string

                      • media_type: "application/pdf"

                      • type: "base64"

                    • plain_text_source: object { data, media_type, type }

                      • data: string

                      • media_type: "text/plain"

                      • type: "text"

                  • title: string

                    The title of the document

                  • type: "document"

                • retrieved_at: string

                  ISO 8601 timestamp when the content was retrieved

                • type: "web_fetch_result"

                • url: string

                  Fetched content URL

            • tool_use_id: string

            • type: "web_fetch_tool_result"

          • code_execution_tool_result_block: object { content, tool_use_id, type }

            • content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

              • code_execution_tool_result_error: object { error_code, type }

                • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

                  • "invalid_tool_input"

                  • "unavailable"

                  • "too_many_requests"

                  • "execution_time_exceeded"

                • type: "code_execution_tool_result_error"

              • code_execution_result_block: object { content, return_code, stderr, 2 more }

                • content: array of CodeExecutionOutputBlock

                  • file_id: string

                  • type: "code_execution_output"

                • return_code: number

                • stderr: string

                • stdout: string

                • type: "code_execution_result"

              • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

                • content: array of CodeExecutionOutputBlock

                  • file_id: string

                  • type: "code_execution_output"

                • encrypted_stdout: string

                • return_code: number

                • stderr: string

                • type: "encrypted_code_execution_result"

            • tool_use_id: string

            • type: "code_execution_tool_result"

          • bash_code_execution_tool_result_block: object { content, tool_use_id, type }

            • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

              • bash_code_execution_tool_result_error: object { error_code, type }

                • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

                  • "invalid_tool_input"

                  • "unavailable"

                  • "too_many_requests"

                  • "execution_time_exceeded"

                  • "output_file_too_large"

                • type: "bash_code_execution_tool_result_error"

              • bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

                • content: array of BashCodeExecutionOutputBlock

                  • file_id: string

                  • type: "bash_code_execution_output"

                • return_code: number

                • stderr: string

                • stdout: string

                • type: "bash_code_execution_result"

            • tool_use_id: string

            • type: "bash_code_execution_tool_result"

          • text_editor_code_execution_tool_result_block: object { content, tool_use_id, type }

            • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

              • text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

                • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

                  • "invalid_tool_input"

                  • "unavailable"

                  • "too_many_requests"

                  • "execution_time_exceeded"

                  • "file_not_found"

                • error_message: string

                • type: "text_editor_code_execution_tool_result_error"

              • text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

                • content: string

                • file_type: "text" or "image" or "pdf"

                  • "text"

                  • "image"

                  • "pdf"

                • num_lines: number

                • start_line: number

                • total_lines: number

                • type: "text_editor_code_execution_view_result"

              • text_editor_code_execution_create_result_block: object { is_file_update, type }

                • is_file_update: boolean

                • type: "text_editor_code_execution_create_result"

              • text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

                • lines: array of string

                • new_lines: number

                • new_start: number

                • old_lines: number

                • old_start: number

                • type: "text_editor_code_execution_str_replace_result"

            • tool_use_id: string

            • type: "text_editor_code_execution_tool_result"

          • tool_search_tool_result_block: object { content, tool_use_id, type }

            • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

              • tool_search_tool_result_error: object { error_code, error_message, type }

                • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

                  • "invalid_tool_input"

                  • "unavailable"

                  • "too_many_requests"

                  • "execution_time_exceeded"

                • error_message: string

                • type: "tool_search_tool_result_error"

              • tool_search_tool_search_result_block: object { tool_references, type }

                • tool_references: array of ToolReferenceBlock

                  • tool_name: string

                  • type: "tool_reference"

                • type: "tool_search_tool_search_result"

            • tool_use_id: string

            • type: "tool_search_tool_result"

          • container_upload_block: object { file_id, type }

            Response model for a file uploaded to the container.

            • file_id: string

            • type: "container_upload"

        • model: "claude-opus-4-7" or "claude-mythos-preview" or "claude-opus-4-6" or 14 more or string

          The model that will complete your prompt.

          See models for additional details and options.

          • "claude-opus-4-7"

            Frontier intelligence for long-running agents and coding

          • "claude-mythos-preview"

            New class of intelligence, strongest in coding and cybersecurity

          • "claude-opus-4-6"

            Frontier 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"

            Premium model combining maximum intelligence with practical performance

          • "claude-opus-4-5-20251101"

            Premium model combining maximum intelligence with practical performance

          • "claude-sonnet-4-5"

            High-performance model for agents and coding

          • "claude-sonnet-4-5-20250929"

            High-performance model for agents and coding

          • "claude-opus-4-1"

            Exceptional model for specialized complex tasks

          • "claude-opus-4-1-20250805"

            Exceptional model for specialized complex tasks

          • "claude-opus-4-0"

            Powerful model for complex tasks

          • "claude-opus-4-20250514"

            Powerful model for complex tasks

          • "claude-sonnet-4-0"

            High-performance model with extended thinking

          • "claude-sonnet-4-20250514"

            High-performance model with extended thinking

          • "claude-3-haiku-20240307"

            Fast and cost-effective model

        • role: "assistant"

          Conversational role of the generated message.

          This will always be "assistant".

        • stop_details: object { category, explanation, type }

          Structured information about a refusal.

          • category: "cyber" or "bio"

            The policy category that triggered the refusal.

            null when the refusal doesn't map to a named category.

            • "cyber"

            • "bio"

          • explanation: string

            Human-readable explanation of the refusal.

            This text is not guaranteed to be stable. null when no explanation is available for the category.

          • type: "refusal"

        • stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 3 more

          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

          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"

        • stop_sequence: string

          Which custom stop sequence was generated, if any.

          This value will be a non-null string if one of your custom stop sequences was generated.

        • type: "message"

          Object type.

          For Messages, this is always "message".

        • usage: object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 5 more }

          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: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

            Breakdown of cached tokens by TTL

            • ephemeral_1h_input_tokens: number

              The number of input tokens used to create the 1 hour cache entry.

            • ephemeral_5m_input_tokens: number

              The number of input tokens used to create the 5 minute cache entry.

          • cache_creation_input_tokens: number

            The number of input tokens used to create the cache entry.

          • cache_read_input_tokens: number

            The number of input tokens read from the cache.

          • inference_geo: string

            The geographic region where inference was performed for this request.

          • input_tokens: number

            The number of input tokens which were used.

          • output_tokens: number

            The number of output tokens which were used.

          • server_tool_use: object { web_fetch_requests, web_search_requests }

            The number of server tool requests.

            • web_fetch_requests: number

              The number of web fetch tool requests.

            • web_search_requests: number

              The number of web search tool requests.

          • service_tier: "standard" or "priority" or "batch"

            If the request used the priority, standard, or batch tier.

            • "standard"

            • "priority"

            • "batch"

      • type: "succeeded"

    • message_batch_errored_result: object { error, type }

      • error: object { error, request_id, type }

        • error: InvalidRequestError or AuthenticationError or BillingError or 6 more

          • invalid_request_error: object { message, type }

            • message: string

            • type: "invalid_request_error"

          • authentication_error: object { message, type }

            • message: string

            • type: "authentication_error"

          • billing_error: object { message, type }

            • message: string

            • type: "billing_error"

          • permission_error: object { message, type }

            • message: string

            • type: "permission_error"

          • not_found_error: object { message, type }

            • message: string

            • type: "not_found_error"

          • rate_limit_error: object { message, type }

            • message: string

            • type: "rate_limit_error"

          • gateway_timeout_error: object { message, type }

            • message: string

            • type: "timeout_error"

          • api_error_object: object { message, type }

            • message: string

            • type: "api_error"

          • overloaded_error: object { message, type }

            • message: string

            • type: "overloaded_error"

        • request_id: string

        • type: "error"

      • type: "errored"

    • message_batch_canceled_result: object { type }

      • type: "canceled"

    • message_batch_expired_result: object { type }

      • type: "expired"

Message Batch Request Counts

• message_batch_request_counts: object { canceled, errored, expired, 2 more }

  • 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.

  • 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.

  • expired: number

    Number of requests in the Message Batch that have expired.

    This is zero until processing of the entire Message Batch has ended.

  • processing: number

    Number of requests in the Message Batch that are processing.

  • 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.

Message Batch Result

• message_batch_result: MessageBatchSucceededResult or MessageBatchErroredResult or MessageBatchCanceledResult or MessageBatchExpiredResult

  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.

  • message_batch_succeeded_result: object { message, type }

    • message: object { id, container, content, 7 more }

      • id: string

        Unique object identifier.

        The format and length of IDs may change over time.

      • container: object { id, expires_at }

        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.

      • 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:

        [{"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:

        [
          {"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:

        [{"type": "text", "text": "B)"}]
        

        • text_block: object { citations, text, type }

          • citations: array of TextCitation

            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.

            • citation_char_location: object { cited_text, document_index, document_title, 4 more }

              • cited_text: string

              • document_index: number

              • document_title: string

              • end_char_index: number

              • file_id: string

              • start_char_index: number

              • type: "char_location"

            • citation_page_location: object { cited_text, document_index, document_title, 4 more }

              • cited_text: string

              • document_index: number

              • document_title: string

              • end_page_number: number

              • file_id: string

              • start_page_number: number

              • type: "page_location"

            • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

              • cited_text: string

              • document_index: number

              • document_title: string

              • end_block_index: number

              • file_id: string

              • start_block_index: number

              • type: "content_block_location"

            • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

              • cited_text: string

              • encrypted_index: string

              • title: string

              • type: "web_search_result_location"

              • url: string

            • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

              • cited_text: string

              • end_block_index: number

              • search_result_index: number

              • source: string

              • start_block_index: number

              • title: string

              • type: "search_result_location"

          • text: string

          • type: "text"

        • thinking_block: object { signature, thinking, type }

          • signature: string

          • thinking: string

          • type: "thinking"

        • redacted_thinking_block: object { data, type }

          • data: string

          • type: "redacted_thinking"

        • tool_use_block: object { id, caller, input, 2 more }

          • id: string

          • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

            Tool invocation directly from the model.

            • direct_caller: object { type }

              Tool invocation directly from the model.

              • type: "direct"

            • server_tool_caller: object { tool_id, type }

              Tool invocation generated by a server-side tool.

              • tool_id: string

              • type: "code_execution_20250825"

            • server_tool_caller_20260120: object { tool_id, type }

              • tool_id: string

              • type: "code_execution_20260120"

          • input: map[unknown]

          • name: string

          • type: "tool_use"

        • server_tool_use_block: object { id, caller, input, 2 more }

          • id: string

          • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

            Tool invocation directly from the model.

            • direct_caller: object { type }

              Tool invocation directly from the model.

              • type: "direct"

            • server_tool_caller: object { tool_id, type }

              Tool invocation generated by a server-side tool.

              • tool_id: string

              • type: "code_execution_20250825"

            • server_tool_caller_20260120: object { tool_id, type }

              • tool_id: string

              • type: "code_execution_20260120"

          • 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"

          • type: "server_tool_use"

        • web_search_tool_result_block: object { caller, content, tool_use_id, type }

          • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

            Tool invocation directly from the model.

            • direct_caller: object { type }

              Tool invocation directly from the model.

              • type: "direct"

            • server_tool_caller: object { tool_id, type }

              Tool invocation generated by a server-side tool.

              • tool_id: string

              • type: "code_execution_20250825"

            • server_tool_caller_20260120: object { tool_id, type }

              • tool_id: string

              • type: "code_execution_20260120"

          • content: WebSearchToolResultError or array of WebSearchResultBlock

            • web_search_tool_result_error: object { error_code, type }

              • error_code: "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"

              • type: "web_search_tool_result_error"

            • union_member_1: array of WebSearchResultBlock

              • encrypted_content: string

              • page_age: string

              • title: string

              • type: "web_search_result"

              • url: string

          • tool_use_id: string

          • type: "web_search_tool_result"

        • web_fetch_tool_result_block: object { caller, content, tool_use_id, type }

          • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

            Tool invocation directly from the model.

            • direct_caller: object { type }

              Tool invocation directly from the model.

              • type: "direct"

            • server_tool_caller: object { tool_id, type }

              Tool invocation generated by a server-side tool.

              • tool_id: string

              • type: "code_execution_20250825"

            • server_tool_caller_20260120: object { tool_id, type }

              • tool_id: string

              • type: "code_execution_20260120"

          • content: WebFetchToolResultErrorBlock or WebFetchBlock

            • web_fetch_tool_result_error_block: object { error_code, type }

              • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

                • "invalid_tool_input"

                • "url_too_long"

                • "url_not_allowed"

                • "url_not_accessible"

                • "unsupported_content_type"

                • "too_many_requests"

                • "max_uses_exceeded"

                • "unavailable"

              • type: "web_fetch_tool_result_error"

            • web_fetch_block: object { content, retrieved_at, type, url }

              • content: object { citations, source, title, type }

                • citations: object { enabled }

                  Citation configuration for the document

                  • enabled: boolean

                • source: Base64PDFSource or PlainTextSource

                  • base64_pdf_source: object { data, media_type, type }

                    • data: string

                    • media_type: "application/pdf"

                    • type: "base64"

                  • plain_text_source: object { data, media_type, type }

                    • data: string

                    • media_type: "text/plain"

                    • type: "text"

                • title: string

                  The title of the document

                • type: "document"

              • retrieved_at: string

                ISO 8601 timestamp when the content was retrieved

              • type: "web_fetch_result"

              • url: string

                Fetched content URL

          • tool_use_id: string

          • type: "web_fetch_tool_result"

        • code_execution_tool_result_block: object { content, tool_use_id, type }

          • content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

            • code_execution_tool_result_error: object { error_code, type }

              • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

              • type: "code_execution_tool_result_error"

            • code_execution_result_block: object { content, return_code, stderr, 2 more }

              • content: array of CodeExecutionOutputBlock

                • file_id: string

                • type: "code_execution_output"

              • return_code: number

              • stderr: string

              • stdout: string

              • type: "code_execution_result"

            • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

              • content: array of CodeExecutionOutputBlock

                • file_id: string

                • type: "code_execution_output"

              • encrypted_stdout: string

              • return_code: number

              • stderr: string

              • type: "encrypted_code_execution_result"

          • tool_use_id: string

          • type: "code_execution_tool_result"

        • bash_code_execution_tool_result_block: object { content, tool_use_id, type }

          • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

            • bash_code_execution_tool_result_error: object { error_code, type }

              • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

                • "output_file_too_large"

              • type: "bash_code_execution_tool_result_error"

            • bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

              • content: array of BashCodeExecutionOutputBlock

                • file_id: string

                • type: "bash_code_execution_output"

              • return_code: number

              • stderr: string

              • stdout: string

              • type: "bash_code_execution_result"

          • tool_use_id: string

          • type: "bash_code_execution_tool_result"

        • text_editor_code_execution_tool_result_block: object { content, tool_use_id, type }

          • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

            • text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

              • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

                • "file_not_found"

              • error_message: string

              • type: "text_editor_code_execution_tool_result_error"

            • text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

              • content: string

              • file_type: "text" or "image" or "pdf"

                • "text"

                • "image"

                • "pdf"

              • num_lines: number

              • start_line: number

              • total_lines: number

              • type: "text_editor_code_execution_view_result"

            • text_editor_code_execution_create_result_block: object { is_file_update, type }

              • is_file_update: boolean

              • type: "text_editor_code_execution_create_result"

            • text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

              • lines: array of string

              • new_lines: number

              • new_start: number

              • old_lines: number

              • old_start: number

              • type: "text_editor_code_execution_str_replace_result"

          • tool_use_id: string

          • type: "text_editor_code_execution_tool_result"

        • tool_search_tool_result_block: object { content, tool_use_id, type }

          • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

            • tool_search_tool_result_error: object { error_code, error_message, type }

              • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

                • "invalid_tool_input"

                • "unavailable"

                • "too_many_requests"

                • "execution_time_exceeded"

              • error_message: string

              • type: "tool_search_tool_result_error"

            • tool_search_tool_search_result_block: object { tool_references, type }

              • tool_references: array of ToolReferenceBlock

                • tool_name: string

                • type: "tool_reference"

              • type: "tool_search_tool_search_result"

          • tool_use_id: string

          • type: "tool_search_tool_result"

        • container_upload_block: object { file_id, type }

          Response model for a file uploaded to the container.

          • file_id: string

          • type: "container_upload"

      • model: "claude-opus-4-7" or "claude-mythos-preview" or "claude-opus-4-6" or 14 more or string

        The model that will complete your prompt.

        See models for additional details and options.

        • "claude-opus-4-7"

          Frontier intelligence for long-running agents and coding

        • "claude-mythos-preview"

          New class of intelligence, strongest in coding and cybersecurity

        • "claude-opus-4-6"

          Frontier 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"

          Premium model combining maximum intelligence with practical performance

        • "claude-opus-4-5-20251101"

          Premium model combining maximum intelligence with practical performance

        • "claude-sonnet-4-5"

          High-performance model for agents and coding

        • "claude-sonnet-4-5-20250929"

          High-performance model for agents and coding

        • "claude-opus-4-1"

          Exceptional model for specialized complex tasks

        • "claude-opus-4-1-20250805"

          Exceptional model for specialized complex tasks

        • "claude-opus-4-0"

          Powerful model for complex tasks

        • "claude-opus-4-20250514"

          Powerful model for complex tasks

        • "claude-sonnet-4-0"

          High-performance model with extended thinking

        • "claude-sonnet-4-20250514"

          High-performance model with extended thinking

        • "claude-3-haiku-20240307"

          Fast and cost-effective model

      • role: "assistant"

        Conversational role of the generated message.

        This will always be "assistant".

      • stop_details: object { category, explanation, type }

        Structured information about a refusal.

        • category: "cyber" or "bio"

          The policy category that triggered the refusal.

          null when the refusal doesn't map to a named category.

          • "cyber"

          • "bio"

        • explanation: string

          Human-readable explanation of the refusal.

          This text is not guaranteed to be stable. null when no explanation is available for the category.

        • type: "refusal"

      • stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 3 more

        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

        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"

      • stop_sequence: string

        Which custom stop sequence was generated, if any.

        This value will be a non-null string if one of your custom stop sequences was generated.

      • type: "message"

        Object type.

        For Messages, this is always "message".

      • usage: object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 5 more }

        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: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

          Breakdown of cached tokens by TTL

          • ephemeral_1h_input_tokens: number

            The number of input tokens used to create the 1 hour cache entry.

          • ephemeral_5m_input_tokens: number

            The number of input tokens used to create the 5 minute cache entry.

        • cache_creation_input_tokens: number

          The number of input tokens used to create the cache entry.

        • cache_read_input_tokens: number

          The number of input tokens read from the cache.

        • inference_geo: string

          The geographic region where inference was performed for this request.

        • input_tokens: number

          The number of input tokens which were used.

        • output_tokens: number

          The number of output tokens which were used.

        • server_tool_use: object { web_fetch_requests, web_search_requests }

          The number of server tool requests.

          • web_fetch_requests: number

            The number of web fetch tool requests.

          • web_search_requests: number

            The number of web search tool requests.

        • service_tier: "standard" or "priority" or "batch"

          If the request used the priority, standard, or batch tier.

          • "standard"

          • "priority"

          • "batch"

    • type: "succeeded"

  • message_batch_errored_result: object { error, type }

    • error: object { error, request_id, type }

      • error: InvalidRequestError or AuthenticationError or BillingError or 6 more

        • invalid_request_error: object { message, type }

          • message: string

          • type: "invalid_request_error"

        • authentication_error: object { message, type }

          • message: string

          • type: "authentication_error"

        • billing_error: object { message, type }

          • message: string

          • type: "billing_error"

        • permission_error: object { message, type }

          • message: string

          • type: "permission_error"

        • not_found_error: object { message, type }

          • message: string

          • type: "not_found_error"

        • rate_limit_error: object { message, type }

          • message: string

          • type: "rate_limit_error"

        • gateway_timeout_error: object { message, type }

          • message: string

          • type: "timeout_error"

        • api_error_object: object { message, type }

          • message: string

          • type: "api_error"

        • overloaded_error: object { message, type }

          • message: string

          • type: "overloaded_error"

      • request_id: string

      • type: "error"

    • type: "errored"

  • message_batch_canceled_result: object { type }

    • type: "canceled"

  • message_batch_expired_result: object { type }

    • type: "expired"

Message Batch Succeeded Result

• message_batch_succeeded_result: object { message, type }

  • message: object { id, container, content, 7 more }

    • id: string

      Unique object identifier.

      The format and length of IDs may change over time.

    • container: object { id, expires_at }

      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.

    • 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:

      [{"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:

      [
        {"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:

      [{"type": "text", "text": "B)"}]
      

      • text_block: object { citations, text, type }

        • citations: array of TextCitation

          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.

          • citation_char_location: object { cited_text, document_index, document_title, 4 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_char_index: number

            • file_id: string

            • start_char_index: number

            • type: "char_location"

          • citation_page_location: object { cited_text, document_index, document_title, 4 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_page_number: number

            • file_id: string

            • start_page_number: number

            • type: "page_location"

          • citation_content_block_location: object { cited_text, document_index, document_title, 4 more }

            • cited_text: string

            • document_index: number

            • document_title: string

            • end_block_index: number

            • file_id: string

            • start_block_index: number

            • type: "content_block_location"

          • citations_web_search_result_location: object { cited_text, encrypted_index, title, 2 more }

            • cited_text: string

            • encrypted_index: string

            • title: string

            • type: "web_search_result_location"

            • url: string

          • citations_search_result_location: object { cited_text, end_block_index, search_result_index, 4 more }

            • cited_text: string

            • end_block_index: number

            • search_result_index: number

            • source: string

            • start_block_index: number

            • title: string

            • type: "search_result_location"

        • text: string

        • type: "text"

      • thinking_block: object { signature, thinking, type }

        • signature: string

        • thinking: string

        • type: "thinking"

      • redacted_thinking_block: object { data, type }

        • data: string

        • type: "redacted_thinking"

      • tool_use_block: object { id, caller, input, 2 more }

        • id: string

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          Tool invocation directly from the model.

          • direct_caller: object { type }

            Tool invocation directly from the model.

            • type: "direct"

          • server_tool_caller: object { tool_id, type }

            Tool invocation generated by a server-side tool.

            • tool_id: string

            • type: "code_execution_20250825"

          • server_tool_caller_20260120: object { tool_id, type }

            • tool_id: string

            • type: "code_execution_20260120"

        • input: map[unknown]

        • name: string

        • type: "tool_use"

      • server_tool_use_block: object { id, caller, input, 2 more }

        • id: string

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          Tool invocation directly from the model.

          • direct_caller: object { type }

            Tool invocation directly from the model.

            • type: "direct"

          • server_tool_caller: object { tool_id, type }

            Tool invocation generated by a server-side tool.

            • tool_id: string

            • type: "code_execution_20250825"

          • server_tool_caller_20260120: object { tool_id, type }

            • tool_id: string

            • type: "code_execution_20260120"

        • 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"

        • type: "server_tool_use"

      • web_search_tool_result_block: object { caller, content, tool_use_id, type }

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          Tool invocation directly from the model.

          • direct_caller: object { type }

            Tool invocation directly from the model.

            • type: "direct"

          • server_tool_caller: object { tool_id, type }

            Tool invocation generated by a server-side tool.

            • tool_id: string

            • type: "code_execution_20250825"

          • server_tool_caller_20260120: object { tool_id, type }

            • tool_id: string

            • type: "code_execution_20260120"

        • content: WebSearchToolResultError or array of WebSearchResultBlock

          • web_search_tool_result_error: object { error_code, type }

            • error_code: "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"

            • type: "web_search_tool_result_error"

          • union_member_1: array of WebSearchResultBlock

            • encrypted_content: string

            • page_age: string

            • title: string

            • type: "web_search_result"

            • url: string

        • tool_use_id: string

        • type: "web_search_tool_result"

      • web_fetch_tool_result_block: object { caller, content, tool_use_id, type }

        • caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120

          Tool invocation directly from the model.

          • direct_caller: object { type }

            Tool invocation directly from the model.

            • type: "direct"

          • server_tool_caller: object { tool_id, type }

            Tool invocation generated by a server-side tool.

            • tool_id: string

            • type: "code_execution_20250825"

          • server_tool_caller_20260120: object { tool_id, type }

            • tool_id: string

            • type: "code_execution_20260120"

        • content: WebFetchToolResultErrorBlock or WebFetchBlock

          • web_fetch_tool_result_error_block: object { error_code, type }

            • error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 5 more

              • "invalid_tool_input"

              • "url_too_long"

              • "url_not_allowed"

              • "url_not_accessible"

              • "unsupported_content_type"

              • "too_many_requests"

              • "max_uses_exceeded"

              • "unavailable"

            • type: "web_fetch_tool_result_error"

          • web_fetch_block: object { content, retrieved_at, type, url }

            • content: object { citations, source, title, type }

              • citations: object { enabled }

                Citation configuration for the document

                • enabled: boolean

              • source: Base64PDFSource or PlainTextSource

                • base64_pdf_source: object { data, media_type, type }

                  • data: string

                  • media_type: "application/pdf"

                  • type: "base64"

                • plain_text_source: object { data, media_type, type }

                  • data: string

                  • media_type: "text/plain"

                  • type: "text"

              • title: string

                The title of the document

              • type: "document"

            • retrieved_at: string

              ISO 8601 timestamp when the content was retrieved

            • type: "web_fetch_result"

            • url: string

              Fetched content URL

        • tool_use_id: string

        • type: "web_fetch_tool_result"

      • code_execution_tool_result_block: object { content, tool_use_id, type }

        • content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock

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

          • code_execution_tool_result_error: object { error_code, type }

            • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

            • type: "code_execution_tool_result_error"

          • code_execution_result_block: object { content, return_code, stderr, 2 more }

            • content: array of CodeExecutionOutputBlock

              • file_id: string

              • type: "code_execution_output"

            • return_code: number

            • stderr: string

            • stdout: string

            • type: "code_execution_result"

          • encrypted_code_execution_result_block: object { content, encrypted_stdout, return_code, 2 more }

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

            • content: array of CodeExecutionOutputBlock

              • file_id: string

              • type: "code_execution_output"

            • encrypted_stdout: string

            • return_code: number

            • stderr: string

            • type: "encrypted_code_execution_result"

        • tool_use_id: string

        • type: "code_execution_tool_result"

      • bash_code_execution_tool_result_block: object { content, tool_use_id, type }

        • content: BashCodeExecutionToolResultError or BashCodeExecutionResultBlock

          • bash_code_execution_tool_result_error: object { error_code, type }

            • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

              • "output_file_too_large"

            • type: "bash_code_execution_tool_result_error"

          • bash_code_execution_result_block: object { content, return_code, stderr, 2 more }

            • content: array of BashCodeExecutionOutputBlock

              • file_id: string

              • type: "bash_code_execution_output"

            • return_code: number

            • stderr: string

            • stdout: string

            • type: "bash_code_execution_result"

        • tool_use_id: string

        • type: "bash_code_execution_tool_result"

      • text_editor_code_execution_tool_result_block: object { content, tool_use_id, type }

        • content: TextEditorCodeExecutionToolResultError or TextEditorCodeExecutionViewResultBlock or TextEditorCodeExecutionCreateResultBlock or TextEditorCodeExecutionStrReplaceResultBlock

          • text_editor_code_execution_tool_result_error: object { error_code, error_message, type }

            • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

              • "file_not_found"

            • error_message: string

            • type: "text_editor_code_execution_tool_result_error"

          • text_editor_code_execution_view_result_block: object { content, file_type, num_lines, 3 more }

            • content: string

            • file_type: "text" or "image" or "pdf"

              • "text"

              • "image"

              • "pdf"

            • num_lines: number

            • start_line: number

            • total_lines: number

            • type: "text_editor_code_execution_view_result"

          • text_editor_code_execution_create_result_block: object { is_file_update, type }

            • is_file_update: boolean

            • type: "text_editor_code_execution_create_result"

          • text_editor_code_execution_str_replace_result_block: object { lines, new_lines, new_start, 3 more }

            • lines: array of string

            • new_lines: number

            • new_start: number

            • old_lines: number

            • old_start: number

            • type: "text_editor_code_execution_str_replace_result"

        • tool_use_id: string

        • type: "text_editor_code_execution_tool_result"

      • tool_search_tool_result_block: object { content, tool_use_id, type }

        • content: ToolSearchToolResultError or ToolSearchToolSearchResultBlock

          • tool_search_tool_result_error: object { error_code, error_message, type }

            • error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"

              • "invalid_tool_input"

              • "unavailable"

              • "too_many_requests"

              • "execution_time_exceeded"

            • error_message: string

            • type: "tool_search_tool_result_error"

          • tool_search_tool_search_result_block: object { tool_references, type }

            • tool_references: array of ToolReferenceBlock

              • tool_name: string

              • type: "tool_reference"

            • type: "tool_search_tool_search_result"

        • tool_use_id: string

        • type: "tool_search_tool_result"

      • container_upload_block: object { file_id, type }

        Response model for a file uploaded to the container.

        • file_id: string

        • type: "container_upload"

    • model: "claude-opus-4-7" or "claude-mythos-preview" or "claude-opus-4-6" or 14 more or string

      The model that will complete your prompt.

      See models for additional details and options.

      • "claude-opus-4-7"

        Frontier intelligence for long-running agents and coding

      • "claude-mythos-preview"

        New class of intelligence, strongest in coding and cybersecurity

      • "claude-opus-4-6"

        Frontier 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"

        Premium model combining maximum intelligence with practical performance

      • "claude-opus-4-5-20251101"

        Premium model combining maximum intelligence with practical performance

      • "claude-sonnet-4-5"

        High-performance model for agents and coding

      • "claude-sonnet-4-5-20250929"

        High-performance model for agents and coding

      • "claude-opus-4-1"

        Exceptional model for specialized complex tasks

      • "claude-opus-4-1-20250805"

        Exceptional model for specialized complex tasks

      • "claude-opus-4-0"

        Powerful model for complex tasks

      • "claude-opus-4-20250514"

        Powerful model for complex tasks

      • "claude-sonnet-4-0"

        High-performance model with extended thinking

      • "claude-sonnet-4-20250514"

        High-performance model with extended thinking

      • "claude-3-haiku-20240307"

        Fast and cost-effective model

    • role: "assistant"

      Conversational role of the generated message.

      This will always be "assistant".

    • stop_details: object { category, explanation, type }

      Structured information about a refusal.

      • category: "cyber" or "bio"

        The policy category that triggered the refusal.

        null when the refusal doesn't map to a named category.

        • "cyber"

        • "bio"

      • explanation: string

        Human-readable explanation of the refusal.

        This text is not guaranteed to be stable. null when no explanation is available for the category.

      • type: "refusal"

    • stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 3 more

      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

      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"

    • stop_sequence: string

      Which custom stop sequence was generated, if any.

      This value will be a non-null string if one of your custom stop sequences was generated.

    • type: "message"

      Object type.

      For Messages, this is always "message".

    • usage: object { cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 5 more }

      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: object { ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }

        Breakdown of cached tokens by TTL

        • ephemeral_1h_input_tokens: number

          The number of input tokens used to create the 1 hour cache entry.

        • ephemeral_5m_input_tokens: number

          The number of input tokens used to create the 5 minute cache entry.

      • cache_creation_input_tokens: number

        The number of input tokens used to create the cache entry.

      • cache_read_input_tokens: number

        The number of input tokens read from the cache.

      • inference_geo: string

        The geographic region where inference was performed for this request.

      • input_tokens: number

        The number of input tokens which were used.

      • output_tokens: number

        The number of output tokens which were used.

      • server_tool_use: object { web_fetch_requests, web_search_requests }

        The number of server tool requests.

        • web_fetch_requests: number

          The number of web fetch tool requests.

        • web_search_requests: number

          The number of web search tool requests.

      • service_tier: "standard" or "priority" or "batch"

        If the request used the priority, standard, or batch tier.

        • "standard"

        • "priority"

        • "batch"

  • type: "succeeded"