# Messages ## OpenAPI Specification ```yaml openapi: 3.0.1 info: title: '' description: '' version: 1.0.0 paths: /v1/messages: post: summary: Messages deprecated: false description: >- 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. tags: - 'SSE API Documentations/Example: Anthropic' parameters: - name: anthropic-beta in: header description: >- Optional header to specify the beta version(s) you want to use. To use multiple betas, use a comma separated list like `beta1,beta2` or specify the header multiple times for each beta. required: false example: '' schema: type: string - name: anthropic-version in: header description: The version of the Anthropic API you want to use. required: true example: '2023-06-01' schema: type: string - name: x-api-key in: header description: >- Your unique API key for authentication. This key is required in the header of all API requests, to authenticate your account and access Anthropic's services. Get your API key through the Console. Each key is scoped to a Workspace. required: true example: $ANTHROPIC_API_KEY schema: type: string requestBody: content: application/json: schema: type: object properties: max_tokens: type: integer description: >- The maximum number of tokens to generate before stopping. Note that our models may stop *before* reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. Different models have different maximum values for this parameter. minimum: 1 exclusiveMinimum: true messages: type: object properties: content: type: string role: type: string enum: - user - assistant x-apidog-enum: - value: user name: '' description: '' - value: assistant name: '' description: '' x-apidog-orders: - content - role description: >- 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"} {"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]} ``` Starting with Claude 3 models, you can also send image content blocks: ```json {"role": "user", "content": [ { "type": "image", "source": { "type": "base64", "media_type": "image/jpeg", "data": "/9j/4AAQSkZJRg...", } }, {"type": "text", "text": "What is in this image?"} ]} ``` We currently support the `base64` source type for images, and the `image/jpeg`, `image/png`, `image/gif`, and `image/webp` media types. See [examples](https://docs.anthropic.com/en/api/messages-examples#vision) for more input examples. Note that if you want to include a [system prompt](https://docs.anthropic.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. required: - content - role model: type: string description: The model that will complete your prompt. minLength: 1 maxLength: 256 metadata: type: object properties: user_id: type: string description: >- An external identifier for the user who is associated with the request. This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number. maxLength: 256 nullable: true x-apidog-orders: - user_id description: An object describing metadata about the request. required: - user_id stop_sequences: type: string description: >- Custom text sequences that will cause the model to stop generating. Our models will normally stop when they have naturally completed their turn, which will result in a response `stop_reason` of `"end_turn"`. If you want the model to stop generating when it encounters custom strings of text, you can use the `stop_sequences` parameter. If the model encounters one of the custom sequences, the response `stop_reason` value will be `"stop_sequence"` and the response `stop_sequence` value will contain the matched stop sequence. stream: type: boolean description: >- Whether to incrementally stream the response using server-sent events. system: type: string description: >- System prompt. A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role. temperature: type: number description: >- 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. minimum: 0 maximum: 1 exclusiveMinimum: true exclusiveMaximum: true thinking: oneOf: - type: object properties: budget_tokens: type: integer description: >- Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. minimum: 1024 exclusiveMinimum: true type: type: string enum: - enabled x-apidog-enum: - value: enabled name: '' description: '' x-apidog-orders: - budget_tokens - type description: Enabled required: - budget_tokens - type - type: object properties: type: type: string enum: - disabled x-apidog-enum: - value: disabled name: '' description: '' x-apidog-orders: - type description: Disabled required: - type description: >- 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. tool_choice: oneOf: - type: object properties: type: type: string enum: - auto x-apidog-enum: - value: auto name: '' description: '' disable_parallel_tool_use: type: boolean description: >- Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. x-apidog-orders: - type - disable_parallel_tool_use description: Auto required: - type - disable_parallel_tool_use - type: object properties: type: type: string description: >- Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. enum: - any x-apidog-enum: - value: any name: '' description: '' disable_parallel_tool_use: type: string description: >- Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. x-apidog-orders: - type - disable_parallel_tool_use required: - type - disable_parallel_tool_use description: Any - type: object properties: name: type: string description: The name of the tool to use. type: type: string enum: - tool x-apidog-enum: - value: tool name: '' description: '' disable_parallel_tool_use: type: string description: >- Whether to disable parallel tool use. Defaults to `false`. If set to `true`, the model will output at most one tool use. x-apidog-orders: - name - type - disable_parallel_tool_use description: Tool required: - name - type - disable_parallel_tool_use - type: object properties: type: type: string enum: - none x-apidog-enum: - value: none name: '' description: '' x-apidog-orders: - type description: ToolChoiceNone required: - type tools: type: object properties: {} x-apidog-orders: [] description: >- 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. 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. top_k: type: integer description: >- Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. Recommended for advanced use cases only. You usually only need to use `temperature`. minimum: 0 exclusiveMinimum: true top_p: type: number minimum: 0 maximum: 1 exclusiveMinimum: true exclusiveMaximum: true description: >- Use nucleus sampling. In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`. You should either alter `temperature` or `top_p`, but not both. Recommended for advanced use cases only. You usually only need to use `temperature`. x-apidog-orders: - max_tokens - messages - model - metadata - stop_sequences - stream - system - temperature - thinking - tool_choice - tools - top_k - top_p required: - max_tokens - messages - model - metadata - stop_sequences - stream - system - temperature - thinking - tool_choice - tools - top_k - top_p example: model: claude-3-7-sonnet-20250219 max_tokens: 1024 messages: - role: user content: Hello, world responses: '200': description: '' content: application/json: schema: type: object properties: content: oneOf: - type: object properties: citations: type: object properties: {} x-apidog-orders: [] description: >- 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`. nullable: true text: type: string maxLength: 5000000 type: type: string enum: - text x-apidog-enum: - value: text name: '' description: '' default: text x-apidog-orders: - citations - text - type description: Text required: - citations - text - type - type: object properties: id: type: string input: type: object properties: {} x-apidog-orders: [] name: type: string minLength: 1 type: type: string enum: - tool_use x-apidog-enum: - value: tool_use name: '' description: '' default: tool_use x-apidog-orders: - id - input - name - type description: Tool Use required: - id - input - name - type - type: object properties: signature: type: string thinking: type: string type: type: string enum: - thinking x-apidog-enum: - value: thinking name: '' description: '' default: thinking x-apidog-orders: - signature - thinking - type description: Thinking required: - signature - thinking - type - type: object properties: data: type: string type: type: string default: redacted_thinking enum: - redacted_thinking x-apidog-enum: - value: redacted_thinking name: '' description: '' x-apidog-orders: - data - type description: Redacted Thinking required: - data - type description: >- 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)"}] ``` id: type: string description: |- Unique object identifier. The format and length of IDs may change over time. model: type: string description: The model that handled the request. minLength: 1 maxLength: 256 role: type: string enum: - assistant x-apidog-enum: - value: assistant name: '' description: '' default: assistant description: |- Conversational role of the generated message. This will always be `"assistant"`. stop_reason: type: string enum: - end_turn - max_tokens - stop_sequence - tool_use x-apidog-enum: - value: end_turn name: '' description: the model reached a natural stopping point - value: max_tokens name: '' description: >- we exceeded the requested `max_tokens` or the model's maximum - value: stop_sequence name: '' description: >- one of your provided custom `stop_sequences` was generated - value: tool_use name: '' description: the model invoked one or more tools description: >- The reason that we stopped. 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. stop_sequence: type: string description: >- 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. nullable: true type: type: string enum: - message x-apidog-enum: - value: message name: '' description: '' default: message description: |- Object type. For Messages, this is always `"message"`. usage: type: object properties: cache_creation_input_tokens: type: integer description: >- The number of input tokens used to create the cache entry. minimum: 0 exclusiveMinimum: true nullable: true cache_read_input_tokens: type: integer minimum: 0 exclusiveMinimum: true description: The number of input tokens read from the cache. nullable: true input_tokens: type: integer description: The number of input tokens which were used. minimum: 0 exclusiveMinimum: true output_tokens: type: integer minimum: 0 exclusiveMinimum: true x-apidog-orders: - cache_creation_input_tokens - cache_read_input_tokens - input_tokens - output_tokens description: >- 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`. required: - cache_creation_input_tokens - cache_read_input_tokens - input_tokens - output_tokens x-apidog-orders: - content - id - model - role - stop_reason - stop_sequence - type - usage required: - content - id - model - role - stop_reason - stop_sequence - type - usage example: content: - text: Hi! My name is Claude. type: text id: msg_013Zva2CMHLNnXjNJJKqJ2EF model: claude-3-7-sonnet-20250219 role: assistant stop_reason: end_turn stop_sequence: null type: message usage: input_tokens: 2095 output_tokens: 503 headers: {} x-apidog-name: Success '400': description: '' content: application/json: schema: type: object properties: type: type: string error: type: object properties: type: type: string message: type: string required: - type - message x-apidog-orders: - type - message required: - type - error x-apidog-orders: - type - error example: type: error error: type: invalid_request_error message: Invalid request headers: {} x-apidog-name: Bad Request security: [] x-apidog-folder: 'SSE API Documentations/Example: Anthropic' x-apidog-status: released x-run-in-apidog: https://app.apidog.com/web/project/849209/apis/api-15106326-run components: schemas: {} securitySchemes: {} servers: [] security: [] ```