工具调用

POST

/v1/responses

请求参数

Header 参数

Body 参数application/json必填

示例

{
  "model": "deepseek-v4-flash-0731",
  "input": [
    {
      "role": "user",
      "content": "今天广州天气怎么样"
    }
  ],
  "tools": [
    {
      "type": "function",
      "name": "get_weather",
      "description": "Get weather of a location, the user should supply a location first.",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. San Francisco, CA",
          }
        },
        "required": [
          "location"
        ]
      }
    }
  ]
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/v1/responses' \
--header 'Accept: application/json' \
--header 'Authorization: sk-xxx' \
--header 'Content-Type: application/json' \
--data '{
  "model": "deepseek-v4-flash-0731",
  "input": [
    {
      "role": "user",
      "content": "今天广州天气怎么样"
    }
  ],
  "tools": [
    {
      "type": "function",
      "name": "get_weather",
      "description": "Get weather of a location, the user should supply a location first.",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. San Francisco, CA",
          }
        },
        "required": [
          "location"
        ]
      }
    }
  ]
}'

返回响应

🟢200成功

application/json

Bodyapplication/json

示例

{
  "id": "24778070-1c36-4ae0-a4bd-870afc7fc13e",
  "object": "response",
  "created_at": 1753000000,
  "status": "completed",
  "model": "deepseek-v4-flash",
  "output": [
    {
      "type": "reasoning",
      "id": "rs_1",
      "status": "completed",
      "content": [
        {
          "type": "reasoning_text",
          "text": "The user greets me. I should reply politely."
        }
      ],
      "summary": []
    },
    {
      "type": "message",
      "id": "msg_1",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Hello! How can I help you today?",
          "annotations": []
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 22,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 29,
    "output_tokens_details": {
      "reasoning_tokens": 27
    },
    "total_tokens": 51
  },
  "store": false,
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "error": null,
  "incomplete_details": null
}

修改于 2026-08-20 09:06:46

思考模式

流式输出