发送消息

请求体

• modelstring必填◐ 部分支持

  Body param: The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.

  deepseek-v4-pro、glm-5.3-flash、qwen3.8-flash、claude-opus-5 可调用；deepseek-v4-flash 在此协议面返回 400。

• messagesarray必填◐ 部分支持

  Body param: 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://platform.claude.com/docs/en/build-with-claude/working-with-messages). Note that if you want to include a [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role), 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.

  文本和工具往返生效；document 的托管 file_id 返回 400，qwen3.8-flash 可读取内联 PDF；图片有模型尺寸限制。

  ▸ 展开子字段（2）

  • contentstring | array必填

    Message content: a plain string (shorthand for one text block) or an array of content blocks such as text, image, document, tool_use and tool_result.

  • rolestring必填

    Who produced the message. Use user for your turns and assistant to replay earlier model turns; system-role messages are accepted by the shape but system instructions normally go in the top-level system field.

• max_tokensnumber必填

  Body param: 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://platform.claude.com/docs/en/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://platform.claude.com/docs/en/about-claude/models/overview) for details.

  限制输出 token，思考也占用预算。

• streamboolean可选◐ 部分支持

  Body param: Whether to incrementally stream the response using server-sent events. See [streaming](https://platform.claude.com/docs/en/build-with-claude/streaming) for details.

  流式正文和工具事件可用；可能在正文前出现额外 message_delta，message_start 的用量为 0。

• systemstring | array可选

  Body param: 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://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role).

  已验证生效。

• temperaturenumber可选

  Sampling temperature between 0 and 1; defaults are model specific.

• top_pnumber可选

  Nucleus sampling: only tokens within this cumulative probability are considered.

• toolsarray可选

  Body param: 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://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools), see their individual documentation as each has its own behavior (e.g., the [web search tool](https://platform.claude.com/docs/en/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://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) for more details.

  已验证生效。

• tool_choiceobject可选◐ 部分支持

  Body param: 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.

  qwen3.8-flash 四种模式生效；deepseek-v4-pro 忽略 any/tool/none；glm-5.3-flash 忽略 none。

  ▸ 展开子字段（3）

  • typestring必填

    Disable tool calls for this request.

    取值 none
  • disable_parallel_tool_useboolean可选○ 当前不生效

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

    接受但当前不生效。true 仍可能返回多个工具调用。

  • namestring必填

    The name of the tool to use.

• cache_controlobject可选◐ 部分支持

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

  deepseek-v4-pro、qwen3.8-flash、glm-5.3-flash 有隐式缓存命中，但不能据此确认标记生效；claude-opus-5 未命中缓存，ttl=1h 未见效果。

  ▸ 展开子字段（2）

  • typestring必填

    Always `ephemeral`. Discriminator that marks this object as a CacheControlEphemeral in a `type`-tagged union.

    取值 ephemeral
  • ttlstring可选

    The time-to-live for the cache control breakpoint. This may be one the following values: - `5m`: 5 minutes - `1h`: 1 hour Defaults to `5m`. See [prompt caching pricing](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) for details.

• ▸ 更多参数（16）

  • containerstring | object可选○ 当前不生效

    接受并忽略 container；平台尚未实现此能力。

    ▸ 展开子字段（2）

    • idstring可选

      Container id

    • skillsarray可选

      List of skills to load in the container

  • inference_geostring可选○ 当前不生效

    接受并忽略 inference_geo；平台尚未实现此能力。

  • metadataobject可选◐ 部分支持

    Body param: An object describing metadata about the request.

    接受 metadata；metadata.user_id 由同协议线路传递，不承诺上游回显。

    ▸ 展开子字段（1）

    • user_idstring可选

      An external identifier for the user who is associated with the request. This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number.

  • output_configobject可选

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

    ▸ 展开子字段（2）

    • effortstring可选◐ 部分支持

      All possible effort levels.

      deepseek-v4-pro 仅 high/xhigh 可用，其余返回 400；qwen3.8-flash 全档返回 400；glm-5.3-flash 接受各档但消耗不随档位单调变化。

    • formatobject可选◐ 部分支持

      A schema to specify Claude's output format in responses. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs)

      json_schema 在 deepseek-v4-pro、qwen3.8-flash 生效；glm-5.3-flash 与 thinking 同传返回 400。

  • service_tierstring可选○ 当前不生效

    接受并忽略 service_tier；平台尚未实现此能力。

  • stop_sequencesarray可选◐ 部分支持

    Body param: 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.

    deepseek-v4-pro、qwen3.8-flash 生效；glm-5.3-flash 文本截断但 stop_reason 和 stop_sequence 未准确反映。

  • thinkingobject可选◐ 部分支持

    Body param: 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://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details.

    disabled 在 deepseek-v4-pro、qwen3.8-flash 生效；glm-5.3-flash 携带任何 thinking 都返回 400。adaptive 在已测的 deepseek-v4-pro、qwen3.8-flash 也返回 400。

    ▸ 展开子字段（3）

    • budget_tokensnumber必填◐ 部分支持

      Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Must be ≥1024 and less than `max_tokens`. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details.

      deepseek-v4-pro、qwen3.8-flash 接受，但预算不构成可靠上限；glm-5.3-flash 返回 400。

    • typestring必填

      Let the model choose its reasoning budget, subject to output_config.effort when supplied.

      取值 adaptive
    • displaystring可选○ 当前不生效

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

      接受但当前不生效。omitted 仍返回完整思考内容。

  • top_knumber可选

    Sample only from the top K options for each token.

  • context_managementobject可选○ 当前不生效

    接受并忽略 context_management；平台尚未实现此能力。

  • diagnosticsobject可选○ 当前不生效

    接受并忽略 diagnostics；平台尚未实现此能力。

  • mcp_serversarray可选○ 当前不生效

    接受并忽略 mcp_servers；平台尚未实现此能力。

  • speedstring可选○ 当前不生效

    接受并忽略 speed；平台尚未实现此能力。

  • output_formatobject可选○ 当前不生效

    接受并忽略此旧字段；结构化输出使用 output_config.format。

  • compactionobject可选○ 未支持

    已识别 compaction；尚未实现，传入返回 400 并明确说明不支持。

  • fallback_credit_tokenstring可选○ 未支持

    已识别 fallback_credit_token；尚未实现，传入返回 400 并明确说明不支持。

  • fallbacksstring可选○ 未支持

    已识别 fallbacks；尚未实现，传入返回 400 并明确说明不支持。

返回

200

stream=true 时以 SSE 增量返回（text/event-stream）。

未知顶层字段原样转发给同协议上游，由上游决定是否接受；已声明字段的类型与取值范围仍会校验，不合法时返回 400 并点名字段。

鉴权、限流、参数校验等平台错误按 problem+json 返回；OCR 的错误也为 problem+json，其它模型调用的错误按该端点所属格式（OpenAI 或 Anthropic）返回，参见 错误码