Body parameters
messages: array of MessageParamInput messages.
Our models are trained to operate on alternating
userandassistantconversational turns. When creating a newMessage, you specify the prior conversational turns with themessagesparameter, and the model then generates the nextMessagein the conversation. Consecutiveuserorassistantturns in your request will be combined into a single turn.Each input message must be an object with a
roleandcontent. You can specify a singleuser-role message, or you can include multipleuserandassistantmessages.If the final message uses the
assistantrole, 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
usermessage:json[{"role": "user", "content": "Hello, Claude"}]Example with multiple conversational turns:
json[ {"role": "user", "content": "Hello there."}, {"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"}, {"role": "user", "content": "Can you explain LLMs in plain English?"}, ]Example with a partially-filled response from Claude:
json[ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("}, ]Each input message
contentmay be either a singlestringor an array of content blocks, where each block has a specifictype. Using astringforcontentis shorthand for an array of one content block of type"text". The following input messages are equivalent:json{"role": "user", "content": "Hello, Claude"}json{"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]}See input examples.
Note that if you want to include a system prompt, you can use the top-level
systemparameter — there is no"system"role for input messages in the Messages API.There is a limit of 100,000 messages in a single request.
content: string or array of ContentBlockParamstringarray of ContentBlockParamTextBlockParam objecttype: "text"text: stringminLength: 1
cache_control: optional CacheControlEphemeral or nullCreate 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 minutes1h: 1 hour
Defaults to
5m. See prompt caching pricing for details."5m""1h"
citations: optional array of TextCitationParam or nullCitationCharLocationParam objecttype: "char_location"cited_text: stringdocument_index: numberminimum: 0
document_title: string or nullmaxLength: 500, minLength: 1
end_char_index: numberstart_char_index: numberminimum: 0
CitationPageLocationParam objecttype: "page_location"cited_text: stringdocument_index: numberminimum: 0
document_title: string or nullmaxLength: 500, minLength: 1
end_page_number: numberstart_page_number: numberminimum: 1
CitationContentBlockLocationParam objecttype: "content_block_location"cited_text: stringThe full text of the cited block range, concatenated.
Always equals the contents of
content[start_block_index:end_block_index]joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns.document_index: numberminimum: 0
document_title: string or nullmaxLength: 500, minLength: 1
end_block_index: numberExclusive 0-based end index of the cited block range in the source's
contentarray.Always greater than
start_block_index; a single-block citation hasend_block_index = start_block_index + 1.start_block_index: number0-based index of the first cited block in the source's
contentarray.minimum: 0
CitationWebSearchResultLocationParam objecttype: "web_search_result_location"cited_text: stringencrypted_index: stringtitle: string or nullmaxLength: 512, minLength: 1
url: stringminLength: 1
CitationSearchResultLocationParam objecttype: "search_result_location"cited_text: stringThe full text of the cited block range, concatenated.
Always equals the contents of
content[start_block_index:end_block_index]joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns.end_block_index: numberExclusive 0-based end index of the cited block range in the source's
contentarray.Always greater than
start_block_index; a single-block citation hasend_block_index = start_block_index + 1.search_result_index: number0-based index of the cited search result among all
search_resultcontent blocks in the request, in the order they appear across messages and tool results.Counted separately from
document_index; server-side web search results are not included in this count.minimum: 0
source: stringstart_block_index: number0-based index of the first cited block in the source's
contentarray.minimum: 0
title: string or null
ImageBlockParam objecttype: "image"source: Base64ImageSource or URLImageSource or FileImageSourceBase64ImageSource objecttype: "base64"data: stringformat: byte
media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp""image/jpeg""image/png""image/gif""image/webp"
URLImageSource objecttype: "url"url: string
FileImageSource objecttype: "file"file_id: string
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
transformations: optional ImageTransformationsParam or nullConfigures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field.
oversized_image: optional "downsize" or "error"What the server does when this image exceeds the model's maximum image size.
"downsize"(the default) scales the image down to fit, which changes the dimensions the model observes without telling you."error"instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down."downsize""error"
DocumentBlockParam objecttype: "document"source: Base64PDFSource or PlainTextSource or ContentBlockSource or 2 moreBase64PDFSource objecttype: "base64"data: stringformat: byte
media_type: "application/pdf"
PlainTextSource objecttype: "text"data: stringmedia_type: "text/plain"
ContentBlockSource objecttype: "content"content: string or array of ContentBlockSourceContentstringContentBlockSourceContent = array of ContentBlockSourceContentTextBlockParam objectImageBlockParam object
URLPDFSource objecttype: "url"url: string
FileDocumentSource objecttype: "file"file_id: string
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
citations: optional CitationsConfigParam or nullenabled: optional boolean
context: optional string or nullminLength: 1
title: optional string or nullmaxLength: 500, minLength: 1
SearchResultBlockParam objecttype: "search_result"content: array of TextBlockParamtype: "text"text: stringminLength: 1
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
citations: optional array of TextCitationParam or null
source: stringtitle: stringcache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
citations: optional CitationsConfigParam
ThinkingBlockParam objecttype: "thinking"signature: stringThe
signaturevalue of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude.Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400
invalid_request_error.thinking: stringThe
thinkingtext of this block as returned by the API.
RedactedThinkingBlockParam objecttype: "redacted_thinking"data: stringThe
datavalue of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged.
ToolUseBlockParam objecttype: "tool_use"id: stringpattern: ^[a-zA-Z0-9_-]+$
input: map[unknown]name: stringmaxLength: 200, minLength: 1
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120Tool invocation directly from the model.
DirectCaller objectTool invocation directly from the model.
type: "direct"
ServerToolCaller objectTool invocation generated by a server-side tool.
type: "code_execution_20250825"tool_id: stringpattern: ^srvtoolu_[a-zA-Z0-9_]+$
ServerToolCaller20260120 objecttype: "code_execution_20260120"tool_id: stringpattern: ^srvtoolu_[a-zA-Z0-9_]+$
toolset_name: optional string or nullFor a toolset member tool_use, the toolset family this member belongs to.
maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
ToolResultBlockParam objecttype: "tool_result"tool_use_id: stringpattern: ^[a-zA-Z0-9_-]+$
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
content: optional string or array of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 morestringarray of TextBlockParam or ImageBlockParam or SearchResultBlockParam or 3 moreTextBlockParam objectImageBlockParam objectSearchResultBlockParam objectDocumentBlockParam objectToolReferenceBlockParam objectTool reference block that can be included in tool_result content.
type: "tool_reference"tool_name: stringmaxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
BrowserStateBlockParam objectThe caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side effects (tabs opened, download state changes) the call produced.
At most one per
tool_result, only on a non-error result answering a browser toolset membertool_use. The server renders the model-visible text from it; the model never sees the raw fields.type: "browser_state"tabs: array of BrowserStateTabEntryAll tabs open in the browser after this call — the full inventory, not a delta. May be empty. Whenever non-empty, exactly one entry carries
active: true.maxItems: 100
tab_id: stringThe caller-assigned identifier for this tab, unique within the inventory.
maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
title: stringThe title of the page the tab is showing. May be empty.
maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
url: stringThe URL of the page the tab is showing. May be empty.
maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
active: optional booleanWhether this tab is the active tab after this call. Whenever
tabsis non-empty, exactly one entry is markedactive: true.
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
state_changes: optional array of BrowserStateChange or nullTabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list.
maxItems: 200, minItems: 1
BrowserStateChangeTabOpened objectA tab this call's execution opened that remains open at its end — the creation delta of the
tabsinventory, not an event log.Carries only the
tab_id; the tab'stitleandurllive on itstabsentry, which must include the sametab_id. A tab opened during a failed call gets no deferredtab_opened; it simply appears in the next result'stabsinventory.type: "tab_opened"tab_id: stringThe
tab_idof the opened tab, present intabs.maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
BrowserStateChangeDownloadStarted objectA file download that started during this call.
type: "download_started"download_id: stringThe caller-assigned identifier for this download, stable across the state changes reporting it.
maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
url: stringThe final post-redirect URL the download was served from.
maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
BrowserStateChangeDownloadCompleted objectA file download that finished during this call, reported with the same
download_idas itsdownload_started— or without a priordownload_started, when the download finished during the call that started it (at most one state change perdownload_idper result).type: "download_completed"download_id: stringThe caller-assigned identifier for this download, stable across the state changes reporting it.
maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
url: stringThe final post-redirect URL the download was served from.
maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
path: optional string or nullWhere the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path.
pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
size_bytes: optional number or nullThe completed download's size.
minimum: 0
BrowserStateChangeDownloadFailed objectA file download that failed — or was cancelled — during this call.
type: "download_failed"download_id: stringThe caller-assigned identifier for this download, stable across the state changes reporting it.
maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
url: stringThe final post-redirect URL the download was served from.
maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
error: optional string or nullThe failure or cancellation detail, when known.
pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
is_error: optional booleantoolset_name: optional string or nullFor a toolset member tool_result, the toolset family of the paired tool_use.
maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
ServerToolUseBlockParam objecttype: "server_tool_use"id: stringpattern: ^srvtoolu_[a-zA-Z0-9_]+$
input: map[unknown]name: "web_search" or "web_fetch" or "code_execution" or 4 more"web_search""web_fetch""code_execution""bash_code_execution""text_editor_code_execution""tool_search_tool_regex""tool_search_tool_bm25"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120Tool invocation directly from the model.
DirectCaller objectTool invocation directly from the model.
ServerToolCaller objectTool invocation generated by a server-side tool.
ServerToolCaller20260120 object
WebSearchToolResultBlockParam objecttype: "web_search_tool_result"content: WebSearchToolResultBlockParamContentWebSearchToolResultBlockItem = array of WebSearchResultBlockParamtype: "web_search_result"encrypted_content: stringtitle: stringurl: stringpage_age: optional string or null
WebSearchToolRequestError objecttype: "web_search_tool_result_error"error_code: WebSearchToolResultErrorCode"invalid_tool_input""unavailable""max_uses_exceeded""too_many_requests""query_too_long""request_too_large"
tool_use_id: stringpattern: ^srvtoolu_[a-zA-Z0-9_]+$
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120Tool invocation directly from the model.
DirectCaller objectTool invocation directly from the model.
ServerToolCaller objectTool invocation generated by a server-side tool.
ServerToolCaller20260120 object
WebFetchToolResultBlockParam objecttype: "web_fetch_tool_result"content: WebFetchToolResultErrorBlockParam or WebFetchBlockParamWebFetchToolResultErrorBlockParam objecttype: "web_fetch_tool_result_error"error_code: WebFetchToolResultErrorCode"invalid_tool_input""url_too_long""url_not_allowed""url_not_in_prior_context""url_not_accessible""unsupported_content_type""too_many_requests""max_uses_exceeded""unavailable""content_too_large"
WebFetchBlockParam objecttype: "web_fetch_result"content: DocumentBlockParamurl: stringFetched content URL
retrieved_at: optional string or nullISO 8601 timestamp when the content was retrieved
tool_use_id: stringpattern: ^srvtoolu_[a-zA-Z0-9_]+$
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
caller: optional DirectCaller or ServerToolCaller or ServerToolCaller20260120Tool invocation directly from the model.
DirectCaller objectTool invocation directly from the model.
ServerToolCaller objectTool invocation generated by a server-side tool.
ServerToolCaller20260120 object
CodeExecutionToolResultBlockParam objecttype: "code_execution_tool_result"content: CodeExecutionToolResultBlockParamContentCode execution result with encrypted stdout for PFC + web_search results.
CodeExecutionToolResultErrorParam objecttype: "code_execution_tool_result_error"error_code: CodeExecutionToolResultErrorCode"invalid_tool_input""unavailable""too_many_requests""execution_time_exceeded"
CodeExecutionResultBlockParam objecttype: "code_execution_result"content: array of CodeExecutionOutputBlockParamtype: "code_execution_output"file_id: string
return_code: numberstderr: stringstdout: string
EncryptedCodeExecutionResultBlockParam objectCode execution result with encrypted stdout for PFC + web_search results.
type: "encrypted_code_execution_result"content: array of CodeExecutionOutputBlockParamtype: "code_execution_output"file_id: string
encrypted_stdout: stringreturn_code: numberstderr: string
tool_use_id: stringpattern: ^srvtoolu_[a-zA-Z0-9_]+$
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
BashCodeExecutionToolResultBlockParam objecttype: "bash_code_execution_tool_result"content: BashCodeExecutionToolResultErrorParam or BashCodeExecutionResultBlockParamBashCodeExecutionToolResultErrorParam objecttype: "bash_code_execution_tool_result_error"error_code: BashCodeExecutionToolResultErrorCode"invalid_tool_input""unavailable""too_many_requests""execution_time_exceeded""output_file_too_large"
BashCodeExecutionResultBlockParam objecttype: "bash_code_execution_result"content: array of BashCodeExecutionOutputBlockParamtype: "bash_code_execution_output"file_id: string
return_code: numberstderr: stringstdout: string
tool_use_id: stringpattern: ^srvtoolu_[a-zA-Z0-9_]+$
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
TextEditorCodeExecutionToolResultBlockParam objecttype: "text_editor_code_execution_tool_result"content: TextEditorCodeExecutionToolResultErrorParam or TextEditorCodeExecutionViewResultBlockParam or TextEditorCodeExecutionCreateResultBlockParam or TextEditorCodeExecutionStrReplaceResultBlockParamTextEditorCodeExecutionToolResultErrorParam objecttype: "text_editor_code_execution_tool_result_error"error_code: TextEditorCodeExecutionToolResultErrorCode"invalid_tool_input""unavailable""too_many_requests""execution_time_exceeded""file_not_found"
error_message: optional string or null
TextEditorCodeExecutionViewResultBlockParam objecttype: "text_editor_code_execution_view_result"content: stringfile_type: "text" or "image" or "pdf""text""image""pdf"
num_lines: optional number or nullstart_line: optional number or nulltotal_lines: optional number or null
TextEditorCodeExecutionCreateResultBlockParam objecttype: "text_editor_code_execution_create_result"is_file_update: boolean
TextEditorCodeExecutionStrReplaceResultBlockParam objecttype: "text_editor_code_execution_str_replace_result"lines: optional array of string or nullnew_lines: optional number or nullnew_start: optional number or nullold_lines: optional number or nullold_start: optional number or null
tool_use_id: stringpattern: ^srvtoolu_[a-zA-Z0-9_]+$
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
ToolSearchToolResultBlockParam objecttype: "tool_search_tool_result"content: ToolSearchToolResultErrorParam or ToolSearchToolSearchResultBlockParamToolSearchToolResultErrorParam objecttype: "tool_search_tool_result_error"error_code: ToolSearchToolResultErrorCode"invalid_tool_input""unavailable""too_many_requests""execution_time_exceeded"
error_message: optional string or null
ToolSearchToolSearchResultBlockParam objecttype: "tool_search_tool_search_result"tool_references: array of ToolReferenceBlockParamtype: "tool_reference"tool_name: stringmaxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
tool_use_id: stringpattern: ^srvtoolu_[a-zA-Z0-9_]+$
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
ContainerUploadBlockParam objectA content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory.
type: "container_upload"file_id: stringcache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
role: "user" or "assistant" or "system""user""assistant""system"
model: ModelThe model that will complete your prompt.
See models for additional details and options.
"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 moreThe model that will complete your prompt.
See models for additional details and options.
"claude-fable-5-1"Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
"claude-mythos-5-1"Our most capable model for cybersecurity and biology research, available through trusted access programs
"claude-sonnet-5"High-performance model for coding and agents
"claude-fable-5"Next generation of intelligence for the hardest knowledge work and coding problems
"claude-mythos-5"Most capable model for cybersecurity and biology research
"claude-opus-5"Powerful intelligence for long-running agents and coding
"claude-opus-4-8"Powerful intelligence for long-running agents and coding
"claude-opus-4-7"Powerful intelligence for long-running agents and coding
"claude-mythos-preview"New class of intelligence, strongest in coding and cybersecurity
"claude-opus-4-6"Powerful intelligence for long-running agents and coding
"claude-sonnet-4-6"Best combination of speed and intelligence
"claude-haiku-4-5"Fastest model with near-frontier intelligence
"claude-haiku-4-5-20251001"Fastest model with near-frontier intelligence
"claude-opus-4-5"Powerful intelligence for long-running agents and coding
"claude-opus-4-5-20251101"Powerful intelligence for long-running agents and coding
"claude-sonnet-4-5"High-performance model for agents and coding
"claude-sonnet-4-5-20250929"High-performance model for agents and coding
string
cache_control: optional CacheControlEphemeral or nullTop-level cache control automatically applies a cache_control marker to the last cacheable block in the request.
output_config: optional OutputConfigConfiguration options for the model's output, such as the output format.
effort: optional "low" or "medium" or "high" or 2 more or nullAll possible effort levels.
"low""medium""high""xhigh""max"
format: optional JSONOutputFormat or nullA schema to specify Claude's output format in responses. See structured outputs
type: "json_schema"schema: map[unknown]The JSON schema of the format
system: optional string or array of TextBlockParamSystem 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.
stringarray of TextBlockParamtype: "text"text: stringminLength: 1
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
citations: optional array of TextCitationParam or null
thinking: optional ThinkingConfigParamConfiguration for enabling Claude's extended thinking.
When enabled, responses include
thinkingcontent blocks showing Claude's thinking process before the final answer. Requires a minimum budget of 1,024 tokens and counts towards yourmax_tokenslimit.See extended thinking for details.
ThinkingConfigEnabled objecttype: "enabled"budget_tokens: numberDetermines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality.
Must be ≥1024 and less than
max_tokens.See extended thinking for details.
minimum: 1024
display: optional "summarized" or "omitted" or nullControls how thinking content appears in the response. When set to
summarized, thinking is returned normally. When set toomitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults tosummarized."summarized""omitted"
ThinkingConfigDisabled objecttype: "disabled"
ThinkingConfigAdaptive objecttype: "adaptive"display: optional "summarized" or "omitted" or nullControls how thinking content appears in the response. When set to
summarized, thinking is returned normally. When set toomitted, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults tosummarized."summarized""omitted"
tool_choice: optional ToolChoiceHow the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.
ToolChoiceAuto objectThe model will automatically decide whether to use tools.
type: "auto"disable_parallel_tool_use: optional booleanWhether to disable parallel tool use.
Defaults to
false. If set totrue, the model will output at most one tool use.
ToolChoiceAny objectThe model will use any available tools.
type: "any"disable_parallel_tool_use: optional booleanWhether to disable parallel tool use.
Defaults to
false. If set totrue, the model will output exactly one tool use.
ToolChoiceTool objectThe model will use the specified tool with
tool_choice.name.type: "tool"name: stringThe name of the tool to use.
disable_parallel_tool_use: optional booleanWhether to disable parallel tool use.
Defaults to
false. If set totrue, the model will output exactly one tool use.
ToolChoiceNone objectThe model will not be allowed to use tools.
type: "none"
tools: optional array of MessageCountTokensToolDefinitions of tools that the model may use.
If you include
toolsin your API request, the model may returntool_usecontent 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 usingtool_resultcontent 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 toolinputshape that the model will produce intool_useoutput content blocks.
For example, if you defined
toolsas:json[ { "name": "get_stock_price", "description": "Get the current stock price for a given ticker symbol.", "input_schema": { "type": "object", "properties": { "ticker": { "type": "string", "description": "The stock ticker symbol, e.g. AAPL for Apple Inc." } }, "required": ["ticker"] } } ]And then asked the model "What's the S&P 500 at today?", the model might produce
tool_usecontent blocks in the response like this:json[ { "type": "tool_use", "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "name": "get_stock_price", "input": { "ticker": "^GSPC" } } ]You might then run your
get_stock_pricetool with\{"ticker": "^GSPC"\}as an input, and return the following back to the model in a subsequentusermessage:json[ { "type": "tool_result", "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "content": "259.75 USD" } ]Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output.
See our guide for more details.
Tool objecttype: optional "custom" or nullinput_schema: objectJSON schema for this tool's input.
This defines the shape of the
inputthat your tool accepts and that the model will produce.type: "object"properties: optional map[unknown] or nullrequired: optional array of string or null
name: stringName of the tool.
This is how the tool will be called by the model and in
tool_useblocks.maxLength: 128, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,128}$
allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
description: optional stringDescription of what this tool does.
Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema.
eager_input_streaming: optional boolean or nullEnable 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 booleanWhen true, guarantees schema validation on tool names and inputs
ToolBash20250124 objecttype: "bash_20250124"name: "bash"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf 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 booleanWhen true, guarantees schema validation on tool names and inputs
CodeExecutionTool20250522 objecttype: "code_execution_20250522"name: "code_execution"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
CodeExecutionTool20250825 objecttype: "code_execution_20250825"name: "code_execution"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
CodeExecutionTool20260120 objectCode execution tool with REPL state persistence (daemon mode + gVisor checkpoint).
type: "code_execution_20260120"name: "code_execution"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
CodeExecutionTool20260521 objectCode execution tool with REPL state persistence.
type: "code_execution_20260521"name: "code_execution"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
BrowserToolset20260801 objectThe browser toolset: a single
tools[]entry (carrying noname) that declares the browser tool family. The model is served the family's tool with any members disabled viaconfigsremoved from its schema.type: "browser_toolset_20260801"cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
configs: optional BrowserToolsetConfigs or nullPer-member configuration for
browser_toolset_20260801: one optional field per member tool, keyed by the member name — the same name the member'stool_useblocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set.type: optional BrowserTypeConfig or nulltype's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
close_tab: optional BrowserCloseTabConfig or nullclose_tab's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
double_click: optional BrowserDoubleClickConfig or nulldouble_click's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
file_upload: optional BrowserFileUploadConfig or nullfile_upload's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
find: optional BrowserFindConfig or nullfind's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
form_input: optional BrowserFormInputConfig or nullform_input's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
get_page_text: optional BrowserGetPageTextConfig or nullget_page_text's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
hold_key: optional BrowserHoldKeyConfig or nullhold_key's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
hover: optional BrowserHoverConfig or nullhover's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
javascript_exec: optional BrowserJavascriptExecConfig or nulljavascript_exec's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
key: optional BrowserKeyConfig or nullkey's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
left_click: optional BrowserLeftClickConfig or nullleft_click's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
left_click_drag: optional BrowserLeftClickDragConfig or nullleft_click_drag's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
left_mouse_down: optional BrowserLeftMouseDownConfig or nullleft_mouse_down's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
left_mouse_up: optional BrowserLeftMouseUpConfig or nullleft_mouse_up's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
list_tabs: optional BrowserListTabsConfig or nulllist_tabs's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
middle_click: optional BrowserMiddleClickConfig or nullmiddle_click's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
mouse_move: optional BrowserMouseMoveConfig or nullmouse_move's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
navigate: optional BrowserNavigateConfig or nullnavigate's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
new_tab: optional BrowserNewTabConfig or nullnew_tab's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
read_console: optional BrowserReadConsoleConfig or nullread_console's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
read_network: optional BrowserReadNetworkConfig or nullread_network's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
read_page: optional BrowserReadPageConfig or nullread_page's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
right_click: optional BrowserRightClickConfig or nullright_click's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
screenshot: optional BrowserScreenshotConfig or nullscreenshot's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
scroll: optional BrowserScrollConfig or nullscroll's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
scroll_to: optional BrowserScrollToConfig or nullscroll_to's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
switch_tab: optional BrowserSwitchTabConfig or nullswitch_tab's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
triple_click: optional BrowserTripleClickConfig or nulltriple_click's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
wait: optional BrowserWaitConfig or nullwait's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
zoom: optional BrowserZoomConfig or nullzoom's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
MemoryTool20250818 objecttype: "memory_20250818"name: "memory"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf 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 booleanWhen true, guarantees schema validation on tool names and inputs
ComputerToolset20260801 objectThe computer toolset: a single
tools[]entry (carrying noname) that declares the computer tool family. The model is served the family's tool with any members disabled viaconfigsremoved from its schema. Every member is enabled by default, zoom included. The single-tool optionsdisplay_numberandenable_zoomare not fields of a toolset entry — it carries onlytype,configs, andcache_control; zoom is controlled viaconfigs.zoom.enabled.type: "computer_toolset_20260801"cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
configs: optional ComputerToolsetConfigs or nullPer-member configuration for
computer_toolset_20260801: one optional field per member tool, keyed by the member name — the same name the member'stool_useblocks carry. Every member is an accepted key, and a member's defaults apply wherever its key is absent. Unknown keys are rejected: the field set is this toolset version's complete member set.type: optional ComputerTypeConfig or nulltype's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
cursor_position: optional ComputerCursorPositionConfig or nullcursor_position's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
double_click: optional ComputerDoubleClickConfig or nulldouble_click's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
hold_key: optional ComputerHoldKeyConfig or nullhold_key's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
key: optional ComputerKeyConfig or nullkey's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
left_click: optional ComputerLeftClickConfig or nullleft_click's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
left_click_drag: optional ComputerLeftClickDragConfig or nullleft_click_drag's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
left_mouse_down: optional ComputerLeftMouseDownConfig or nullleft_mouse_down's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
left_mouse_up: optional ComputerLeftMouseUpConfig or nullleft_mouse_up's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
middle_click: optional ComputerMiddleClickConfig or nullmiddle_click's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
mouse_move: optional ComputerMouseMoveConfig or nullmouse_move's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
right_click: optional ComputerRightClickConfig or nullright_click's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
screenshot: optional ComputerScreenshotConfig or nullscreenshot's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
scroll: optional ComputerScrollConfig or nullscroll's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
triple_click: optional ComputerTripleClickConfig or nulltriple_click's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
wait: optional ComputerWaitConfig or nullwait's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
zoom: optional ComputerZoomConfig or nullzoom's config overrides.defer_loading: optional boolean or nullDefer loading for this member. Must resolve to the same value on every enabled member of the toolset.
enabled: optional boolean or nullWhether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
ToolTextEditor20250124 objecttype: "text_editor_20250124"name: "str_replace_editor"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf 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 booleanWhen true, guarantees schema validation on tool names and inputs
ToolTextEditor20250429 objecttype: "text_editor_20250429"name: "str_replace_based_edit_tool"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf 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 booleanWhen true, guarantees schema validation on tool names and inputs
ToolTextEditor20250728 objecttype: "text_editor_20250728"name: "str_replace_based_edit_tool"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
input_examples: optional array of map[unknown]max_characters: optional number or nullMaximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file.
minimum: 1
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
WebSearchTool20250305 objecttype: "web_search_20250305"name: "web_search"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
allowed_domains: optional array of string or nullIf provided, only these domains will be included in results. Cannot be used alongside
blocked_domains.blocked_domains: optional array of string or nullIf provided, these domains will never appear in results. Cannot be used alongside
allowed_domains.cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
max_uses: optional number or nullMaximum number of times the tool can be used in the API request.
exclusiveMinimum: 0
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
user_location: optional UserLocation or nullParameters for the user's location. Used to provide more relevant search results.
type: "approximate"city: optional string or nullThe city of the user.
maxLength: 255, minLength: 1
country: optional string or nullThe two letter ISO country code of the user.
maxLength: 2, minLength: 2
region: optional string or nullThe region of the user.
maxLength: 255, minLength: 1
timezone: optional string or nullThe IANA timezone of the user.
maxLength: 255, minLength: 1
WebFetchTool20250910 objecttype: "web_fetch_20250910"name: "web_fetch"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
allowed_domains: optional array of string or nullList of domains to allow fetching from
blocked_domains: optional array of string or nullList of domains to block fetching from
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
citations: optional CitationsConfigParam or nullCitations configuration for fetched documents. Citations are disabled by default.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
max_content_tokens: optional number or nullMaximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
exclusiveMinimum: 0
max_uses: optional number or nullMaximum number of times the tool can be used in the API request.
exclusiveMinimum: 0
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
WebSearchTool20260209 objecttype: "web_search_20260209"name: "web_search"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
allowed_domains: optional array of string or nullIf provided, only these domains will be included in results. Cannot be used alongside
blocked_domains.blocked_domains: optional array of string or nullIf provided, these domains will never appear in results. Cannot be used alongside
allowed_domains.cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
max_uses: optional number or nullMaximum number of times the tool can be used in the API request.
exclusiveMinimum: 0
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
user_location: optional UserLocation or nullParameters for the user's location. Used to provide more relevant search results.
WebFetchTool20260209 objecttype: "web_fetch_20260209"name: "web_fetch"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
allowed_domains: optional array of string or nullList of domains to allow fetching from
blocked_domains: optional array of string or nullList of domains to block fetching from
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
citations: optional CitationsConfigParam or nullCitations configuration for fetched documents. Citations are disabled by default.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
max_content_tokens: optional number or nullMaximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
exclusiveMinimum: 0
max_uses: optional number or nullMaximum number of times the tool can be used in the API request.
exclusiveMinimum: 0
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
WebFetchTool20260309 objectWeb fetch tool with use_cache parameter for bypassing cached content.
type: "web_fetch_20260309"name: "web_fetch"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
allowed_domains: optional array of string or nullList of domains to allow fetching from
blocked_domains: optional array of string or nullList of domains to block fetching from
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
citations: optional CitationsConfigParam or nullCitations configuration for fetched documents. Citations are disabled by default.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
max_content_tokens: optional number or nullMaximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
exclusiveMinimum: 0
max_uses: optional number or nullMaximum number of times the tool can be used in the API request.
exclusiveMinimum: 0
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
use_cache: optional booleanWhether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
WebSearchTool20260318 objecttype: "web_search_20260318"name: "web_search"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
allowed_domains: optional array of string or nullIf provided, only these domains will be included in results. Cannot be used alongside
blocked_domains.blocked_domains: optional array of string or nullIf provided, these domains will never appear in results. Cannot be used alongside
allowed_domains.cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
max_uses: optional number or nullMaximum number of times the tool can be used in the API request.
exclusiveMinimum: 0
response_inclusion: optional "full" or "excluded"How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn.
"full""excluded"
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
user_location: optional UserLocation or nullParameters for the user's location. Used to provide more relevant search results.
WebFetchTool20260318 objecttype: "web_fetch_20260318"name: "web_fetch"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
allowed_domains: optional array of string or nullList of domains to allow fetching from
blocked_domains: optional array of string or nullList of domains to block fetching from
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
citations: optional CitationsConfigParam or nullCitations configuration for fetched documents. Citations are disabled by default.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
max_content_tokens: optional number or nullMaximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
exclusiveMinimum: 0
max_uses: optional number or nullMaximum number of times the tool can be used in the API request.
exclusiveMinimum: 0
response_inclusion: optional "full" or "excluded"How this tool's result blocks appear in the API response when the result was consumed by a completed code_execution call in the same turn. 'full' returns the complete content (default). 'excluded' drops the nested server_tool_use and result block pair entirely. Results from direct calls, or from code_execution calls that paused before completing, are always returned in full so they can be sent back on the next turn.
"full""excluded"
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
use_cache: optional booleanWhether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
ToolSearchToolBm25_20251119 objecttype: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25""tool_search_tool_bm25_20251119""tool_search_tool_bm25"
name: "tool_search_tool_bm25"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs
ToolSearchToolRegex20251119 objecttype: "tool_search_tool_regex_20251119" or "tool_search_tool_regex""tool_search_tool_regex_20251119""tool_search_tool_regex"
name: "tool_search_tool_regex"Name of the tool.
This is how the tool will be called by the model and in
tool_useblocks.allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521""direct""code_execution_20250825""code_execution_20260120""code_execution_20260521"
cache_control: optional CacheControlEphemeral or nullCreate a cache control breakpoint at this content block.
defer_loading: optional booleanIf true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
strict: optional booleanWhen true, guarantees schema validation on tool names and inputs