## Create a Message `Message messages().create(MessageCreateParamsparams, RequestOptionsrequestOptions = RequestOptions.none())` **post** `/v1/messages` Send a structured list of input messages with text and/or image content, and the model will generate the next message in the conversation. The Messages API can be used for either single queries or stateless multi-turn conversations. Learn more about the Messages API in our [user guide](https://docs.claude.com/en/docs/initial-setup) ### Parameters - `MessageCreateParams params` - `long maxTokens` The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. Set to `0` to populate the [prompt cache](https://docs.claude.com/en/docs/build-with-claude/prompt-caching#pre-warming-the-cache) without generating a response. Different models have different maximum values for this parameter. See [models](https://docs.claude.com/en/docs/models-overview) for details. - `List messages` Input messages. Our models are trained to operate on alternating `user` and `assistant` conversational turns. When creating a new `Message`, you specify the prior conversational turns with the `messages` parameter, and the model then generates the next `Message` in the conversation. Consecutive `user` or `assistant` turns in your request will be combined into a single turn. Each input message must be an object with a `role` and `content`. You can specify a single `user`-role message, or you can include multiple `user` and `assistant` messages. If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response. Example with a single `user` message: ```json [{"role": "user", "content": "Hello, Claude"}] ``` Example with multiple conversational turns: ```json [ {"role": "user", "content": "Hello there."}, {"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"}, {"role": "user", "content": "Can you explain LLMs in plain English?"}, ] ``` Example with a partially-filled response from Claude: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("}, ] ``` Each input message `content` may be either a single `string` or an array of content blocks, where each block has a specific `type`. Using a `string` for `content` is shorthand for an array of one content block of type `"text"`. The following input messages are equivalent: ```json {"role": "user", "content": "Hello, Claude"} ``` ```json {"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]} ``` See [input examples](https://docs.claude.com/en/api/messages-examples). Note that if you want to include a [system prompt](https://docs.claude.com/en/docs/system-prompts), you can use the top-level `system` parameter — there is no `"system"` role for input messages in the Messages API. There is a limit of 100,000 messages in a single request. - `Content content` - `String` - `List` - `class TextBlockParam:` - `String text` - `JsonValue; type "text"constant` - `TEXT("text")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `JsonValue; type "ephemeral"constant` - `EPHEMERAL("ephemeral")` - `Optional ttl` 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`. - `TTL_5M("5m")` - `TTL_1H("1h")` - `Optional> citations` - `class CitationCharLocationParam:` - `String citedText` - `long documentIndex` - `Optional documentTitle` - `long endCharIndex` - `long startCharIndex` - `JsonValue; type "char_location"constant` - `CHAR_LOCATION("char_location")` - `class CitationPageLocationParam:` - `String citedText` - `long documentIndex` - `Optional documentTitle` - `long endPageNumber` - `long startPageNumber` - `JsonValue; type "page_location"constant` - `PAGE_LOCATION("page_location")` - `class CitationContentBlockLocationParam:` - `String citedText` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `long documentIndex` - `Optional documentTitle` - `long endBlockIndex` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `long startBlockIndex` 0-based index of the first cited block in the source's `content` array. - `JsonValue; type "content_block_location"constant` - `CONTENT_BLOCK_LOCATION("content_block_location")` - `class CitationWebSearchResultLocationParam:` - `String citedText` - `String encryptedIndex` - `Optional title` - `JsonValue; type "web_search_result_location"constant` - `WEB_SEARCH_RESULT_LOCATION("web_search_result_location")` - `String url` - `class CitationSearchResultLocationParam:` - `String citedText` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `long endBlockIndex` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `long searchResultIndex` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. - `String source` - `long startBlockIndex` 0-based index of the first cited block in the source's `content` array. - `Optional title` - `JsonValue; type "search_result_location"constant` - `SEARCH_RESULT_LOCATION("search_result_location")` - `class ImageBlockParam:` - `Source source` - `class Base64ImageSource:` - `String data` - `MediaType mediaType` - `IMAGE_JPEG("image/jpeg")` - `IMAGE_PNG("image/png")` - `IMAGE_GIF("image/gif")` - `IMAGE_WEBP("image/webp")` - `JsonValue; type "base64"constant` - `BASE64("base64")` - `class UrlImageSource:` - `JsonValue; type "url"constant` - `URL("url")` - `String url` - `JsonValue; type "image"constant` - `IMAGE("image")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `class DocumentBlockParam:` - `Source source` - `class Base64PdfSource:` - `String data` - `JsonValue; mediaType "application/pdf"constant` - `APPLICATION_PDF("application/pdf")` - `JsonValue; type "base64"constant` - `BASE64("base64")` - `class PlainTextSource:` - `String data` - `JsonValue; mediaType "text/plain"constant` - `TEXT_PLAIN("text/plain")` - `JsonValue; type "text"constant` - `TEXT("text")` - `class ContentBlockSource:` - `Content content` - `String` - `List` - `class TextBlockParam:` - `class ImageBlockParam:` - `JsonValue; type "content"constant` - `CONTENT("content")` - `class UrlPdfSource:` - `JsonValue; type "url"constant` - `URL("url")` - `String url` - `JsonValue; type "document"constant` - `DOCUMENT("document")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional citations` - `Optional enabled` - `Optional context` - `Optional title` - `class SearchResultBlockParam:` - `List content` - `String text` - `JsonValue; type "text"constant` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional> citations` - `String source` - `String title` - `JsonValue; type "search_result"constant` - `SEARCH_RESULT("search_result")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional citations` - `class ThinkingBlockParam:` - `String signature` - `String thinking` - `JsonValue; type "thinking"constant` - `THINKING("thinking")` - `class RedactedThinkingBlockParam:` - `String data` - `JsonValue; type "redacted_thinking"constant` - `REDACTED_THINKING("redacted_thinking")` - `class ToolUseBlockParam:` - `String id` - `Input input` - `String name` - `JsonValue; type "tool_use"constant` - `TOOL_USE("tool_use")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional caller` Tool invocation directly from the model. - `class DirectCaller:` Tool invocation directly from the model. - `JsonValue; type "direct"constant` - `DIRECT("direct")` - `class ServerToolCaller:` Tool invocation generated by a server-side tool. - `String toolId` - `JsonValue; type "code_execution_20250825"constant` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `class ServerToolCaller20260120:` - `String toolId` - `JsonValue; type "code_execution_20260120"constant` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `class ToolResultBlockParam:` - `String toolUseId` - `JsonValue; type "tool_result"constant` - `TOOL_RESULT("tool_result")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional content` - `String` - `List` - `class TextBlockParam:` - `class ImageBlockParam:` - `class SearchResultBlockParam:` - `class DocumentBlockParam:` - `class ToolReferenceBlockParam:` Tool reference block that can be included in tool_result content. - `String toolName` - `JsonValue; type "tool_reference"constant` - `TOOL_REFERENCE("tool_reference")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional isError` - `class ServerToolUseBlockParam:` - `String id` - `Input input` - `Name name` - `WEB_SEARCH("web_search")` - `WEB_FETCH("web_fetch")` - `CODE_EXECUTION("code_execution")` - `BASH_CODE_EXECUTION("bash_code_execution")` - `TEXT_EDITOR_CODE_EXECUTION("text_editor_code_execution")` - `TOOL_SEARCH_TOOL_REGEX("tool_search_tool_regex")` - `TOOL_SEARCH_TOOL_BM25("tool_search_tool_bm25")` - `JsonValue; type "server_tool_use"constant` - `SERVER_TOOL_USE("server_tool_use")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional caller` Tool invocation directly from the model. - `class DirectCaller:` Tool invocation directly from the model. - `class ServerToolCaller:` Tool invocation generated by a server-side tool. - `class ServerToolCaller20260120:` - `class WebSearchToolResultBlockParam:` - `WebSearchToolResultBlockParamContent content` - `List` - `String encryptedContent` - `String title` - `JsonValue; type "web_search_result"constant` - `WEB_SEARCH_RESULT("web_search_result")` - `String url` - `Optional pageAge` - `class WebSearchToolRequestError:` - `WebSearchToolResultErrorCode errorCode` - `INVALID_TOOL_INPUT("invalid_tool_input")` - `UNAVAILABLE("unavailable")` - `MAX_USES_EXCEEDED("max_uses_exceeded")` - `TOO_MANY_REQUESTS("too_many_requests")` - `QUERY_TOO_LONG("query_too_long")` - `REQUEST_TOO_LARGE("request_too_large")` - `JsonValue; type "web_search_tool_result_error"constant` - `WEB_SEARCH_TOOL_RESULT_ERROR("web_search_tool_result_error")` - `String toolUseId` - `JsonValue; type "web_search_tool_result"constant` - `WEB_SEARCH_TOOL_RESULT("web_search_tool_result")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional caller` Tool invocation directly from the model. - `class DirectCaller:` Tool invocation directly from the model. - `class ServerToolCaller:` Tool invocation generated by a server-side tool. - `class ServerToolCaller20260120:` - `class WebFetchToolResultBlockParam:` - `Content content` - `class WebFetchToolResultErrorBlockParam:` - `WebFetchToolResultErrorCode errorCode` - `INVALID_TOOL_INPUT("invalid_tool_input")` - `URL_TOO_LONG("url_too_long")` - `URL_NOT_ALLOWED("url_not_allowed")` - `URL_NOT_IN_PRIOR_CONTEXT("url_not_in_prior_context")` - `URL_NOT_ACCESSIBLE("url_not_accessible")` - `UNSUPPORTED_CONTENT_TYPE("unsupported_content_type")` - `TOO_MANY_REQUESTS("too_many_requests")` - `MAX_USES_EXCEEDED("max_uses_exceeded")` - `UNAVAILABLE("unavailable")` - `JsonValue; type "web_fetch_tool_result_error"constant` - `WEB_FETCH_TOOL_RESULT_ERROR("web_fetch_tool_result_error")` - `class WebFetchBlockParam:` - `DocumentBlockParam content` - `JsonValue; type "web_fetch_result"constant` - `WEB_FETCH_RESULT("web_fetch_result")` - `String url` Fetched content URL - `Optional retrievedAt` ISO 8601 timestamp when the content was retrieved - `String toolUseId` - `JsonValue; type "web_fetch_tool_result"constant` - `WEB_FETCH_TOOL_RESULT("web_fetch_tool_result")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional caller` Tool invocation directly from the model. - `class DirectCaller:` Tool invocation directly from the model. - `class ServerToolCaller:` Tool invocation generated by a server-side tool. - `class ServerToolCaller20260120:` - `class CodeExecutionToolResultBlockParam:` - `CodeExecutionToolResultBlockParamContent content` Code execution result with encrypted stdout for PFC + web_search results. - `class CodeExecutionToolResultErrorParam:` - `CodeExecutionToolResultErrorCode errorCode` - `INVALID_TOOL_INPUT("invalid_tool_input")` - `UNAVAILABLE("unavailable")` - `TOO_MANY_REQUESTS("too_many_requests")` - `EXECUTION_TIME_EXCEEDED("execution_time_exceeded")` - `JsonValue; type "code_execution_tool_result_error"constant` - `CODE_EXECUTION_TOOL_RESULT_ERROR("code_execution_tool_result_error")` - `class CodeExecutionResultBlockParam:` - `List content` - `String fileId` - `JsonValue; type "code_execution_output"constant` - `CODE_EXECUTION_OUTPUT("code_execution_output")` - `long returnCode` - `String stderr` - `String stdout` - `JsonValue; type "code_execution_result"constant` - `CODE_EXECUTION_RESULT("code_execution_result")` - `class EncryptedCodeExecutionResultBlockParam:` Code execution result with encrypted stdout for PFC + web_search results. - `List content` - `String fileId` - `JsonValue; type "code_execution_output"constant` - `String encryptedStdout` - `long returnCode` - `String stderr` - `JsonValue; type "encrypted_code_execution_result"constant` - `ENCRYPTED_CODE_EXECUTION_RESULT("encrypted_code_execution_result")` - `String toolUseId` - `JsonValue; type "code_execution_tool_result"constant` - `CODE_EXECUTION_TOOL_RESULT("code_execution_tool_result")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `class BashCodeExecutionToolResultBlockParam:` - `Content content` - `class BashCodeExecutionToolResultErrorParam:` - `BashCodeExecutionToolResultErrorCode errorCode` - `INVALID_TOOL_INPUT("invalid_tool_input")` - `UNAVAILABLE("unavailable")` - `TOO_MANY_REQUESTS("too_many_requests")` - `EXECUTION_TIME_EXCEEDED("execution_time_exceeded")` - `OUTPUT_FILE_TOO_LARGE("output_file_too_large")` - `JsonValue; type "bash_code_execution_tool_result_error"constant` - `BASH_CODE_EXECUTION_TOOL_RESULT_ERROR("bash_code_execution_tool_result_error")` - `class BashCodeExecutionResultBlockParam:` - `List content` - `String fileId` - `JsonValue; type "bash_code_execution_output"constant` - `BASH_CODE_EXECUTION_OUTPUT("bash_code_execution_output")` - `long returnCode` - `String stderr` - `String stdout` - `JsonValue; type "bash_code_execution_result"constant` - `BASH_CODE_EXECUTION_RESULT("bash_code_execution_result")` - `String toolUseId` - `JsonValue; type "bash_code_execution_tool_result"constant` - `BASH_CODE_EXECUTION_TOOL_RESULT("bash_code_execution_tool_result")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `class TextEditorCodeExecutionToolResultBlockParam:` - `Content content` - `class TextEditorCodeExecutionToolResultErrorParam:` - `TextEditorCodeExecutionToolResultErrorCode errorCode` - `INVALID_TOOL_INPUT("invalid_tool_input")` - `UNAVAILABLE("unavailable")` - `TOO_MANY_REQUESTS("too_many_requests")` - `EXECUTION_TIME_EXCEEDED("execution_time_exceeded")` - `FILE_NOT_FOUND("file_not_found")` - `JsonValue; type "text_editor_code_execution_tool_result_error"constant` - `TEXT_EDITOR_CODE_EXECUTION_TOOL_RESULT_ERROR("text_editor_code_execution_tool_result_error")` - `Optional errorMessage` - `class TextEditorCodeExecutionViewResultBlockParam:` - `String content` - `FileType fileType` - `TEXT("text")` - `IMAGE("image")` - `PDF("pdf")` - `JsonValue; type "text_editor_code_execution_view_result"constant` - `TEXT_EDITOR_CODE_EXECUTION_VIEW_RESULT("text_editor_code_execution_view_result")` - `Optional numLines` - `Optional startLine` - `Optional totalLines` - `class TextEditorCodeExecutionCreateResultBlockParam:` - `boolean isFileUpdate` - `JsonValue; type "text_editor_code_execution_create_result"constant` - `TEXT_EDITOR_CODE_EXECUTION_CREATE_RESULT("text_editor_code_execution_create_result")` - `class TextEditorCodeExecutionStrReplaceResultBlockParam:` - `JsonValue; type "text_editor_code_execution_str_replace_result"constant` - `TEXT_EDITOR_CODE_EXECUTION_STR_REPLACE_RESULT("text_editor_code_execution_str_replace_result")` - `Optional> lines` - `Optional newLines` - `Optional newStart` - `Optional oldLines` - `Optional oldStart` - `String toolUseId` - `JsonValue; type "text_editor_code_execution_tool_result"constant` - `TEXT_EDITOR_CODE_EXECUTION_TOOL_RESULT("text_editor_code_execution_tool_result")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `class ToolSearchToolResultBlockParam:` - `Content content` - `class ToolSearchToolResultErrorParam:` - `ToolSearchToolResultErrorCode errorCode` - `INVALID_TOOL_INPUT("invalid_tool_input")` - `UNAVAILABLE("unavailable")` - `TOO_MANY_REQUESTS("too_many_requests")` - `EXECUTION_TIME_EXCEEDED("execution_time_exceeded")` - `JsonValue; type "tool_search_tool_result_error"constant` - `TOOL_SEARCH_TOOL_RESULT_ERROR("tool_search_tool_result_error")` - `class ToolSearchToolSearchResultBlockParam:` - `List toolReferences` - `String toolName` - `JsonValue; type "tool_reference"constant` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `JsonValue; type "tool_search_tool_search_result"constant` - `TOOL_SEARCH_TOOL_SEARCH_RESULT("tool_search_tool_search_result")` - `String toolUseId` - `JsonValue; type "tool_search_tool_result"constant` - `TOOL_SEARCH_TOOL_RESULT("tool_search_tool_result")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `class ContainerUploadBlockParam:` 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. - `String fileId` - `JsonValue; type "container_upload"constant` - `CONTAINER_UPLOAD("container_upload")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `class MidConversationSystemBlockParam:` System instructions that appear mid-conversation. Use this block to provide or update system-level instructions at a specific point in the conversation, rather than only via the top-level `system` parameter. - `List content` System instruction text blocks. - `String text` - `JsonValue; type "text"constant` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional> citations` - `JsonValue; type "mid_conv_system"constant` - `MID_CONV_SYSTEM("mid_conv_system")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Role role` - `USER("user")` - `ASSISTANT("assistant")` - `SYSTEM("system")` - `Model model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `Optional cacheControl` Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request. - `Optional container` Container identifier for reuse across requests. - `Optional inferenceGeo` Specifies the geographic region for inference processing. If not specified, the workspace's `default_inference_geo` is used. - `Optional metadata` An object describing metadata about the request. - `Optional outputConfig` Configuration options for the model's output, such as the output format. - `Optional serviceTier` Determines whether to use priority capacity (if available) or standard capacity for this request. Anthropic offers different levels of service for your API requests. See [service-tiers](https://docs.claude.com/en/api/service-tiers) for details. - `AUTO("auto")` - `STANDARD_ONLY("standard_only")` - `Optional> stopSequences` 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. - `Optional system` System prompt. A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role. See our [guide to system prompts](https://docs.claude.com/en/docs/system-prompts). - `String` - `List` - `String text` - `JsonValue; type "text"constant` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional> citations` - `Optional temperature` 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. - `Optional thinking` Configuration for enabling Claude's extended thinking. When enabled, responses include `thinking` content blocks showing Claude's thinking process before the final answer. Requires a minimum budget of 1,024 tokens and counts towards your `max_tokens` limit. See [extended thinking](https://docs.claude.com/en/docs/build-with-claude/extended-thinking) for details. - `Optional toolChoice` How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all. - `Optional> tools` Definitions of tools that the model may use. If you include `tools` in your API request, the model may return `tool_use` content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using `tool_result` content blocks. There are two types of tools: **client tools** and **server tools**. The behavior described below applies to client tools. For [server tools](https://docs.claude.com/en/docs/agents-and-tools/tool-use/overview#server-tools), see their individual documentation as each has its own behavior (e.g., the [web search tool](https://docs.claude.com/en/docs/agents-and-tools/tool-use/web-search-tool)). Each tool definition includes: * `name`: Name of the tool. * `description`: Optional, but strongly-recommended description of the tool. * `input_schema`: [JSON schema](https://json-schema.org/draft/2020-12) for the tool `input` shape that the model will produce in `tool_use` output content blocks. For example, if you defined `tools` as: ```json [ { "name": "get_stock_price", "description": "Get the current stock price for a given ticker symbol.", "input_schema": { "type": "object", "properties": { "ticker": { "type": "string", "description": "The stock ticker symbol, e.g. AAPL for Apple Inc." } }, "required": ["ticker"] } } ] ``` And then asked the model "What's the S&P 500 at today?", the model might produce `tool_use` content blocks in the response like this: ```json [ { "type": "tool_use", "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "name": "get_stock_price", "input": { "ticker": "^GSPC" } } ] ``` You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an input, and return the following back to the model in a subsequent `user` message: ```json [ { "type": "tool_result", "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "content": "259.75 USD" } ] ``` Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output. See our [guide](https://docs.claude.com/en/docs/tool-use) for more details. - `class Tool:` - `InputSchema inputSchema` [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input. This defines the shape of the `input` that your tool accepts and that the model will produce. - `JsonValue; type "object"constant` - `OBJECT("object")` - `Optional properties` - `Optional> required` - `String name` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional description` 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. - `Optional eagerInputStreaming` 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. - `Optional> inputExamples` - `Optional strict` When true, guarantees schema validation on tool names and inputs - `Optional type` - `CUSTOM("custom")` - `class ToolBash20250124:` - `JsonValue; name "bash"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `BASH("bash")` - `JsonValue; type "bash_20250124"constant` - `BASH_20250124("bash_20250124")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional> inputExamples` - `Optional strict` When true, guarantees schema validation on tool names and inputs - `class CodeExecutionTool20250522:` - `JsonValue; name "code_execution"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `CODE_EXECUTION("code_execution")` - `JsonValue; type "code_execution_20250522"constant` - `CODE_EXECUTION_20250522("code_execution_20250522")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional strict` When true, guarantees schema validation on tool names and inputs - `class CodeExecutionTool20250825:` - `JsonValue; name "code_execution"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `CODE_EXECUTION("code_execution")` - `JsonValue; type "code_execution_20250825"constant` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional strict` When true, guarantees schema validation on tool names and inputs - `class CodeExecutionTool20260120:` Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint). - `JsonValue; name "code_execution"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `CODE_EXECUTION("code_execution")` - `JsonValue; type "code_execution_20260120"constant` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional strict` When true, guarantees schema validation on tool names and inputs - `class MemoryTool20250818:` - `JsonValue; name "memory"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `MEMORY("memory")` - `JsonValue; type "memory_20250818"constant` - `MEMORY_20250818("memory_20250818")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional> inputExamples` - `Optional strict` When true, guarantees schema validation on tool names and inputs - `class ToolTextEditor20250124:` - `JsonValue; name "str_replace_editor"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `STR_REPLACE_EDITOR("str_replace_editor")` - `JsonValue; type "text_editor_20250124"constant` - `TEXT_EDITOR_20250124("text_editor_20250124")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional> inputExamples` - `Optional strict` When true, guarantees schema validation on tool names and inputs - `class ToolTextEditor20250429:` - `JsonValue; name "str_replace_based_edit_tool"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `STR_REPLACE_BASED_EDIT_TOOL("str_replace_based_edit_tool")` - `JsonValue; type "text_editor_20250429"constant` - `TEXT_EDITOR_20250429("text_editor_20250429")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional> inputExamples` - `Optional strict` When true, guarantees schema validation on tool names and inputs - `class ToolTextEditor20250728:` - `JsonValue; name "str_replace_based_edit_tool"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `STR_REPLACE_BASED_EDIT_TOOL("str_replace_based_edit_tool")` - `JsonValue; type "text_editor_20250728"constant` - `TEXT_EDITOR_20250728("text_editor_20250728")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional> inputExamples` - `Optional maxCharacters` Maximum number of characters to display when viewing a file. If not specified, defaults to displaying the full file. - `Optional strict` When true, guarantees schema validation on tool names and inputs - `class WebSearchTool20250305:` - `JsonValue; name "web_search"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `WEB_SEARCH("web_search")` - `JsonValue; type "web_search_20250305"constant` - `WEB_SEARCH_20250305("web_search_20250305")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional> allowedDomains` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `Optional> blockedDomains` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional maxUses` Maximum number of times the tool can be used in the API request. - `Optional strict` When true, guarantees schema validation on tool names and inputs - `Optional userLocation` Parameters for the user's location. Used to provide more relevant search results. - `JsonValue; type "approximate"constant` - `APPROXIMATE("approximate")` - `Optional city` The city of the user. - `Optional country` The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user. - `Optional region` The region of the user. - `Optional timezone` The [IANA timezone](https://nodatime.org/TimeZones) of the user. - `class WebFetchTool20250910:` - `JsonValue; name "web_fetch"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `WEB_FETCH("web_fetch")` - `JsonValue; type "web_fetch_20250910"constant` - `WEB_FETCH_20250910("web_fetch_20250910")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional> allowedDomains` List of domains to allow fetching from - `Optional> blockedDomains` List of domains to block fetching from - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional citations` Citations configuration for fetched documents. Citations are disabled by default. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional maxContentTokens` 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. - `Optional maxUses` Maximum number of times the tool can be used in the API request. - `Optional strict` When true, guarantees schema validation on tool names and inputs - `class WebSearchTool20260209:` - `JsonValue; name "web_search"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `WEB_SEARCH("web_search")` - `JsonValue; type "web_search_20260209"constant` - `WEB_SEARCH_20260209("web_search_20260209")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional> allowedDomains` If provided, only these domains will be included in results. Cannot be used alongside `blocked_domains`. - `Optional> blockedDomains` If provided, these domains will never appear in results. Cannot be used alongside `allowed_domains`. - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional maxUses` Maximum number of times the tool can be used in the API request. - `Optional strict` When true, guarantees schema validation on tool names and inputs - `Optional userLocation` Parameters for the user's location. Used to provide more relevant search results. - `class WebFetchTool20260209:` - `JsonValue; name "web_fetch"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `WEB_FETCH("web_fetch")` - `JsonValue; type "web_fetch_20260209"constant` - `WEB_FETCH_20260209("web_fetch_20260209")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional> allowedDomains` List of domains to allow fetching from - `Optional> blockedDomains` List of domains to block fetching from - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional citations` Citations configuration for fetched documents. Citations are disabled by default. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional maxContentTokens` 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. - `Optional maxUses` Maximum number of times the tool can be used in the API request. - `Optional strict` When true, guarantees schema validation on tool names and inputs - `class WebFetchTool20260309:` Web fetch tool with use_cache parameter for bypassing cached content. - `JsonValue; name "web_fetch"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `WEB_FETCH("web_fetch")` - `JsonValue; type "web_fetch_20260309"constant` - `WEB_FETCH_20260309("web_fetch_20260309")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional> allowedDomains` List of domains to allow fetching from - `Optional> blockedDomains` List of domains to block fetching from - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional citations` Citations configuration for fetched documents. Citations are disabled by default. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional maxContentTokens` 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. - `Optional maxUses` Maximum number of times the tool can be used in the API request. - `Optional strict` When true, guarantees schema validation on tool names and inputs - `Optional useCache` 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. - `class ToolSearchToolBm25_20251119:` - `JsonValue; name "tool_search_tool_bm25"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `TOOL_SEARCH_TOOL_BM25("tool_search_tool_bm25")` - `Type type` - `TOOL_SEARCH_TOOL_BM25_20251119("tool_search_tool_bm25_20251119")` - `TOOL_SEARCH_TOOL_BM25("tool_search_tool_bm25")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional strict` When true, guarantees schema validation on tool names and inputs - `class ToolSearchToolRegex20251119:` - `JsonValue; name "tool_search_tool_regex"constant` Name of the tool. This is how the tool will be called by the model and in `tool_use` blocks. - `TOOL_SEARCH_TOOL_REGEX("tool_search_tool_regex")` - `Type type` - `TOOL_SEARCH_TOOL_REGEX_20251119("tool_search_tool_regex_20251119")` - `TOOL_SEARCH_TOOL_REGEX("tool_search_tool_regex")` - `Optional> allowedCallers` - `DIRECT("direct")` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Optional cacheControl` Create a cache control breakpoint at this content block. - `Optional deferLoading` If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search. - `Optional strict` When true, guarantees schema validation on tool names and inputs - `Optional topK` Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277). Recommended for advanced use cases only. - `Optional topP` Use nucleus sampling. In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`. Recommended for advanced use cases only. ### Returns - `class Message:` - `String id` Unique object identifier. The format and length of IDs may change over time. - `Optional container` Information about the container used in the request (for the code execution tool) - `String id` Identifier for the container used in this request - `LocalDateTime expiresAt` The time at which the container will expire. - `List content` Content generated by the model. This is an array of content blocks, each of which has a `type` that determines its shape. Example: ```json [{"type": "text", "text": "Hi, I'm Claude."}] ``` If the request input `messages` ended with an `assistant` turn, then the response `content` will continue directly from that last turn. You can use this to constrain the model's output. For example, if the input `messages` were: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("} ] ``` Then the response `content` might be: ```json [{"type": "text", "text": "B)"}] ``` - `class TextBlock:` - `Optional> citations` 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`. - `class CitationCharLocation:` - `String citedText` - `long documentIndex` - `Optional documentTitle` - `long endCharIndex` - `Optional fileId` - `long startCharIndex` - `JsonValue; type "char_location"constant` - `CHAR_LOCATION("char_location")` - `class CitationPageLocation:` - `String citedText` - `long documentIndex` - `Optional documentTitle` - `long endPageNumber` - `Optional fileId` - `long startPageNumber` - `JsonValue; type "page_location"constant` - `PAGE_LOCATION("page_location")` - `class CitationContentBlockLocation:` - `String citedText` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `long documentIndex` - `Optional documentTitle` - `long endBlockIndex` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `Optional fileId` - `long startBlockIndex` 0-based index of the first cited block in the source's `content` array. - `JsonValue; type "content_block_location"constant` - `CONTENT_BLOCK_LOCATION("content_block_location")` - `class CitationsWebSearchResultLocation:` - `String citedText` - `String encryptedIndex` - `Optional title` - `JsonValue; type "web_search_result_location"constant` - `WEB_SEARCH_RESULT_LOCATION("web_search_result_location")` - `String url` - `class CitationsSearchResultLocation:` - `String citedText` The full text of the cited block range, concatenated. Always equals the contents of `content[start_block_index:end_block_index]` joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns. - `long endBlockIndex` Exclusive 0-based end index of the cited block range in the source's `content` array. Always greater than `start_block_index`; a single-block citation has `end_block_index = start_block_index + 1`. - `long searchResultIndex` 0-based index of the cited search result among all `search_result` content blocks in the request, in the order they appear across messages and tool results. Counted separately from `document_index`; server-side web search results are not included in this count. - `String source` - `long startBlockIndex` 0-based index of the first cited block in the source's `content` array. - `Optional title` - `JsonValue; type "search_result_location"constant` - `SEARCH_RESULT_LOCATION("search_result_location")` - `String text` - `JsonValue; type "text"constant` - `TEXT("text")` - `class ThinkingBlock:` - `String signature` - `String thinking` - `JsonValue; type "thinking"constant` - `THINKING("thinking")` - `class RedactedThinkingBlock:` - `String data` - `JsonValue; type "redacted_thinking"constant` - `REDACTED_THINKING("redacted_thinking")` - `class ToolUseBlock:` - `String id` - `Caller caller` Tool invocation directly from the model. - `class DirectCaller:` Tool invocation directly from the model. - `JsonValue; type "direct"constant` - `DIRECT("direct")` - `class ServerToolCaller:` Tool invocation generated by a server-side tool. - `String toolId` - `JsonValue; type "code_execution_20250825"constant` - `CODE_EXECUTION_20250825("code_execution_20250825")` - `class ServerToolCaller20260120:` - `String toolId` - `JsonValue; type "code_execution_20260120"constant` - `CODE_EXECUTION_20260120("code_execution_20260120")` - `Input input` - `String name` - `JsonValue; type "tool_use"constant` - `TOOL_USE("tool_use")` - `class ServerToolUseBlock:` - `String id` - `Caller caller` Tool invocation directly from the model. - `class DirectCaller:` Tool invocation directly from the model. - `class ServerToolCaller:` Tool invocation generated by a server-side tool. - `class ServerToolCaller20260120:` - `Input input` - `Name name` - `WEB_SEARCH("web_search")` - `WEB_FETCH("web_fetch")` - `CODE_EXECUTION("code_execution")` - `BASH_CODE_EXECUTION("bash_code_execution")` - `TEXT_EDITOR_CODE_EXECUTION("text_editor_code_execution")` - `TOOL_SEARCH_TOOL_REGEX("tool_search_tool_regex")` - `TOOL_SEARCH_TOOL_BM25("tool_search_tool_bm25")` - `JsonValue; type "server_tool_use"constant` - `SERVER_TOOL_USE("server_tool_use")` - `class WebSearchToolResultBlock:` - `Caller caller` Tool invocation directly from the model. - `class DirectCaller:` Tool invocation directly from the model. - `class ServerToolCaller:` Tool invocation generated by a server-side tool. - `class ServerToolCaller20260120:` - `WebSearchToolResultBlockContent content` - `class WebSearchToolResultError:` - `WebSearchToolResultErrorCode errorCode` - `INVALID_TOOL_INPUT("invalid_tool_input")` - `UNAVAILABLE("unavailable")` - `MAX_USES_EXCEEDED("max_uses_exceeded")` - `TOO_MANY_REQUESTS("too_many_requests")` - `QUERY_TOO_LONG("query_too_long")` - `REQUEST_TOO_LARGE("request_too_large")` - `JsonValue; type "web_search_tool_result_error"constant` - `WEB_SEARCH_TOOL_RESULT_ERROR("web_search_tool_result_error")` - `List` - `String encryptedContent` - `Optional pageAge` - `String title` - `JsonValue; type "web_search_result"constant` - `WEB_SEARCH_RESULT("web_search_result")` - `String url` - `String toolUseId` - `JsonValue; type "web_search_tool_result"constant` - `WEB_SEARCH_TOOL_RESULT("web_search_tool_result")` - `class WebFetchToolResultBlock:` - `Caller caller` Tool invocation directly from the model. - `class DirectCaller:` Tool invocation directly from the model. - `class ServerToolCaller:` Tool invocation generated by a server-side tool. - `class ServerToolCaller20260120:` - `Content content` - `class WebFetchToolResultErrorBlock:` - `WebFetchToolResultErrorCode errorCode` - `INVALID_TOOL_INPUT("invalid_tool_input")` - `URL_TOO_LONG("url_too_long")` - `URL_NOT_ALLOWED("url_not_allowed")` - `URL_NOT_IN_PRIOR_CONTEXT("url_not_in_prior_context")` - `URL_NOT_ACCESSIBLE("url_not_accessible")` - `UNSUPPORTED_CONTENT_TYPE("unsupported_content_type")` - `TOO_MANY_REQUESTS("too_many_requests")` - `MAX_USES_EXCEEDED("max_uses_exceeded")` - `UNAVAILABLE("unavailable")` - `JsonValue; type "web_fetch_tool_result_error"constant` - `WEB_FETCH_TOOL_RESULT_ERROR("web_fetch_tool_result_error")` - `class WebFetchBlock:` - `DocumentBlock content` - `Optional citations` Citation configuration for the document - `boolean enabled` - `Source source` - `class Base64PdfSource:` - `String data` - `JsonValue; mediaType "application/pdf"constant` - `APPLICATION_PDF("application/pdf")` - `JsonValue; type "base64"constant` - `BASE64("base64")` - `class PlainTextSource:` - `String data` - `JsonValue; mediaType "text/plain"constant` - `TEXT_PLAIN("text/plain")` - `JsonValue; type "text"constant` - `TEXT("text")` - `Optional title` The title of the document - `JsonValue; type "document"constant` - `DOCUMENT("document")` - `Optional retrievedAt` ISO 8601 timestamp when the content was retrieved - `JsonValue; type "web_fetch_result"constant` - `WEB_FETCH_RESULT("web_fetch_result")` - `String url` Fetched content URL - `String toolUseId` - `JsonValue; type "web_fetch_tool_result"constant` - `WEB_FETCH_TOOL_RESULT("web_fetch_tool_result")` - `class CodeExecutionToolResultBlock:` - `CodeExecutionToolResultBlockContent content` Code execution result with encrypted stdout for PFC + web_search results. - `class CodeExecutionToolResultError:` - `CodeExecutionToolResultErrorCode errorCode` - `INVALID_TOOL_INPUT("invalid_tool_input")` - `UNAVAILABLE("unavailable")` - `TOO_MANY_REQUESTS("too_many_requests")` - `EXECUTION_TIME_EXCEEDED("execution_time_exceeded")` - `JsonValue; type "code_execution_tool_result_error"constant` - `CODE_EXECUTION_TOOL_RESULT_ERROR("code_execution_tool_result_error")` - `class CodeExecutionResultBlock:` - `List content` - `String fileId` - `JsonValue; type "code_execution_output"constant` - `CODE_EXECUTION_OUTPUT("code_execution_output")` - `long returnCode` - `String stderr` - `String stdout` - `JsonValue; type "code_execution_result"constant` - `CODE_EXECUTION_RESULT("code_execution_result")` - `class EncryptedCodeExecutionResultBlock:` Code execution result with encrypted stdout for PFC + web_search results. - `List content` - `String fileId` - `JsonValue; type "code_execution_output"constant` - `String encryptedStdout` - `long returnCode` - `String stderr` - `JsonValue; type "encrypted_code_execution_result"constant` - `ENCRYPTED_CODE_EXECUTION_RESULT("encrypted_code_execution_result")` - `String toolUseId` - `JsonValue; type "code_execution_tool_result"constant` - `CODE_EXECUTION_TOOL_RESULT("code_execution_tool_result")` - `class BashCodeExecutionToolResultBlock:` - `Content content` - `class BashCodeExecutionToolResultError:` - `BashCodeExecutionToolResultErrorCode errorCode` - `INVALID_TOOL_INPUT("invalid_tool_input")` - `UNAVAILABLE("unavailable")` - `TOO_MANY_REQUESTS("too_many_requests")` - `EXECUTION_TIME_EXCEEDED("execution_time_exceeded")` - `OUTPUT_FILE_TOO_LARGE("output_file_too_large")` - `JsonValue; type "bash_code_execution_tool_result_error"constant` - `BASH_CODE_EXECUTION_TOOL_RESULT_ERROR("bash_code_execution_tool_result_error")` - `class BashCodeExecutionResultBlock:` - `List content` - `String fileId` - `JsonValue; type "bash_code_execution_output"constant` - `BASH_CODE_EXECUTION_OUTPUT("bash_code_execution_output")` - `long returnCode` - `String stderr` - `String stdout` - `JsonValue; type "bash_code_execution_result"constant` - `BASH_CODE_EXECUTION_RESULT("bash_code_execution_result")` - `String toolUseId` - `JsonValue; type "bash_code_execution_tool_result"constant` - `BASH_CODE_EXECUTION_TOOL_RESULT("bash_code_execution_tool_result")` - `class TextEditorCodeExecutionToolResultBlock:` - `Content content` - `class TextEditorCodeExecutionToolResultError:` - `TextEditorCodeExecutionToolResultErrorCode errorCode` - `INVALID_TOOL_INPUT("invalid_tool_input")` - `UNAVAILABLE("unavailable")` - `TOO_MANY_REQUESTS("too_many_requests")` - `EXECUTION_TIME_EXCEEDED("execution_time_exceeded")` - `FILE_NOT_FOUND("file_not_found")` - `Optional errorMessage` - `JsonValue; type "text_editor_code_execution_tool_result_error"constant` - `TEXT_EDITOR_CODE_EXECUTION_TOOL_RESULT_ERROR("text_editor_code_execution_tool_result_error")` - `class TextEditorCodeExecutionViewResultBlock:` - `String content` - `FileType fileType` - `TEXT("text")` - `IMAGE("image")` - `PDF("pdf")` - `Optional numLines` - `Optional startLine` - `Optional totalLines` - `JsonValue; type "text_editor_code_execution_view_result"constant` - `TEXT_EDITOR_CODE_EXECUTION_VIEW_RESULT("text_editor_code_execution_view_result")` - `class TextEditorCodeExecutionCreateResultBlock:` - `boolean isFileUpdate` - `JsonValue; type "text_editor_code_execution_create_result"constant` - `TEXT_EDITOR_CODE_EXECUTION_CREATE_RESULT("text_editor_code_execution_create_result")` - `class TextEditorCodeExecutionStrReplaceResultBlock:` - `Optional> lines` - `Optional newLines` - `Optional newStart` - `Optional oldLines` - `Optional oldStart` - `JsonValue; type "text_editor_code_execution_str_replace_result"constant` - `TEXT_EDITOR_CODE_EXECUTION_STR_REPLACE_RESULT("text_editor_code_execution_str_replace_result")` - `String toolUseId` - `JsonValue; type "text_editor_code_execution_tool_result"constant` - `TEXT_EDITOR_CODE_EXECUTION_TOOL_RESULT("text_editor_code_execution_tool_result")` - `class ToolSearchToolResultBlock:` - `Content content` - `class ToolSearchToolResultError:` - `ToolSearchToolResultErrorCode errorCode` - `INVALID_TOOL_INPUT("invalid_tool_input")` - `UNAVAILABLE("unavailable")` - `TOO_MANY_REQUESTS("too_many_requests")` - `EXECUTION_TIME_EXCEEDED("execution_time_exceeded")` - `Optional errorMessage` - `JsonValue; type "tool_search_tool_result_error"constant` - `TOOL_SEARCH_TOOL_RESULT_ERROR("tool_search_tool_result_error")` - `class ToolSearchToolSearchResultBlock:` - `List toolReferences` - `String toolName` - `JsonValue; type "tool_reference"constant` - `TOOL_REFERENCE("tool_reference")` - `JsonValue; type "tool_search_tool_search_result"constant` - `TOOL_SEARCH_TOOL_SEARCH_RESULT("tool_search_tool_search_result")` - `String toolUseId` - `JsonValue; type "tool_search_tool_result"constant` - `TOOL_SEARCH_TOOL_RESULT("tool_search_tool_result")` - `class ContainerUploadBlock:` Response model for a file uploaded to the container. - `String fileId` - `JsonValue; type "container_upload"constant` - `CONTAINER_UPLOAD("container_upload")` - `Model model` The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options. - `CLAUDE_OPUS_4_8("claude-opus-4-8")` Frontier intelligence for long-running agents and coding - `CLAUDE_OPUS_4_7("claude-opus-4-7")` Frontier intelligence for long-running agents and coding - `CLAUDE_MYTHOS_PREVIEW("claude-mythos-preview")` New class of intelligence, strongest in coding and cybersecurity - `CLAUDE_OPUS_4_6("claude-opus-4-6")` Frontier intelligence for long-running agents and coding - `CLAUDE_SONNET_4_6("claude-sonnet-4-6")` Best combination of speed and intelligence - `CLAUDE_HAIKU_4_5("claude-haiku-4-5")` Fastest model with near-frontier intelligence - `CLAUDE_HAIKU_4_5_20251001("claude-haiku-4-5-20251001")` Fastest model with near-frontier intelligence - `CLAUDE_OPUS_4_5("claude-opus-4-5")` Premium model combining maximum intelligence with practical performance - `CLAUDE_OPUS_4_5_20251101("claude-opus-4-5-20251101")` Premium model combining maximum intelligence with practical performance - `CLAUDE_SONNET_4_5("claude-sonnet-4-5")` High-performance model for agents and coding - `CLAUDE_SONNET_4_5_20250929("claude-sonnet-4-5-20250929")` High-performance model for agents and coding - `CLAUDE_OPUS_4_1("claude-opus-4-1")` Exceptional model for specialized complex tasks - `CLAUDE_OPUS_4_1_20250805("claude-opus-4-1-20250805")` Exceptional model for specialized complex tasks - `CLAUDE_OPUS_4_0("claude-opus-4-0")` Powerful model for complex tasks - `CLAUDE_OPUS_4_20250514("claude-opus-4-20250514")` Powerful model for complex tasks - `CLAUDE_SONNET_4_0("claude-sonnet-4-0")` High-performance model with extended thinking - `CLAUDE_SONNET_4_20250514("claude-sonnet-4-20250514")` High-performance model with extended thinking - `CLAUDE_3_HAIKU_20240307("claude-3-haiku-20240307")` Fast and cost-effective model - `JsonValue; role "assistant"constant` Conversational role of the generated message. This will always be `"assistant"`. - `ASSISTANT("assistant")` - `Optional stopDetails` Structured information about a refusal. - `Optional category` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `CYBER("cyber")` - `BIO("bio")` - `Optional explanation` Human-readable explanation of the refusal. This text is not guaranteed to be stable. `null` when no explanation is available for the category. - `JsonValue; type "refusal"constant` - `REFUSAL("refusal")` - `Optional stopReason` 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("end_turn")` - `MAX_TOKENS("max_tokens")` - `STOP_SEQUENCE("stop_sequence")` - `TOOL_USE("tool_use")` - `PAUSE_TURN("pause_turn")` - `REFUSAL("refusal")` - `Optional stopSequence` 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. - `JsonValue; type "message"constant` Object type. For Messages, this is always `"message"`. - `MESSAGE("message")` - `Usage usage` Billing and rate-limit usage. Anthropic's API bills and rate-limits by token counts, as tokens represent the underlying cost to our systems. Under the hood, the API transforms requests into a format suitable for the model. The model's output then goes through a parsing stage before becoming an API response. As a result, the token counts in `usage` will not match one-to-one with the exact visible content of an API request or response. For example, `output_tokens` will be non-zero, even for an empty string response from Claude. Total input tokens in a request is the summation of `input_tokens`, `cache_creation_input_tokens`, and `cache_read_input_tokens`. - `Optional cacheCreation` Breakdown of cached tokens by TTL - `long ephemeral1hInputTokens` The number of input tokens used to create the 1 hour cache entry. - `long ephemeral5mInputTokens` The number of input tokens used to create the 5 minute cache entry. - `Optional cacheCreationInputTokens` The number of input tokens used to create the cache entry. - `Optional cacheReadInputTokens` The number of input tokens read from the cache. - `Optional inferenceGeo` The geographic region where inference was performed for this request. - `long inputTokens` The number of input tokens which were used. - `long outputTokens` The number of output tokens which were used. - `Optional outputTokensDetails` Breakdown of output tokens by category. `output_tokens` remains the inclusive, authoritative total used for billing. This object provides a read-only decomposition for observability — for example, how many of the billed output tokens were spent on internal reasoning that may have been summarized before being returned to you. - `long thinkingTokens` Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens. Reflects the raw reasoning the model produced, not the (possibly shorter) summarized thinking text returned in the response body. Computed by re-tokenizing the raw reasoning text, so it may differ from the model's exact generation count by a small number of tokens. Always ≤ `output_tokens`; `output_tokens - thinking_tokens` approximates the non-reasoning output. - `Optional serverToolUse` The number of server tool requests. - `long webFetchRequests` The number of web fetch tool requests. - `long webSearchRequests` The number of web search tool requests. - `Optional serviceTier` If the request used the priority, standard, or batch tier. - `STANDARD("standard")` - `PRIORITY("priority")` - `BATCH("batch")` ### Example ```java package com.anthropic.example; import com.anthropic.client.AnthropicClient; import com.anthropic.client.okhttp.AnthropicOkHttpClient; import com.anthropic.models.messages.Message; import com.anthropic.models.messages.MessageCreateParams; import com.anthropic.models.messages.Model; public final class Main { private Main() {} public static void main(String[] args) { AnthropicClient client = AnthropicOkHttpClient.fromEnv(); MessageCreateParams params = MessageCreateParams.builder() .maxTokens(1024L) .addUserMessage("Hello, world") .model(Model.CLAUDE_OPUS_4_6) .build(); Message message = client.messages().create(params); } } ``` #### Response ```json { "id": "msg_013Zva2CMHLNnXjNJJKqJ2EF", "container": { "id": "id", "expires_at": "2019-12-27T18:11:19.117Z" }, "content": [ { "citations": [ { "cited_text": "cited_text", "document_index": 0, "document_title": "document_title", "end_char_index": 0, "file_id": "file_id", "start_char_index": 0, "type": "char_location" } ], "text": "Hi! My name is Claude.", "type": "text" } ], "model": "claude-opus-4-6", "role": "assistant", "stop_details": { "category": "cyber", "explanation": "explanation", "type": "refusal" }, "stop_reason": "end_turn", "stop_sequence": null, "type": "message", "usage": { "cache_creation": { "ephemeral_1h_input_tokens": 0, "ephemeral_5m_input_tokens": 0 }, "cache_creation_input_tokens": 2051, "cache_read_input_tokens": 2051, "inference_geo": "inference_geo", "input_tokens": 2095, "output_tokens": 503, "output_tokens_details": { "thinking_tokens": 0 }, "server_tool_use": { "web_fetch_requests": 2, "web_search_requests": 0 }, "service_tier": "standard" } } ```