创建函数调用

使用 Responses API 创建一次模型响应，并在请求中声明可调用的函数工具。当模型判断需要调用函数时，响应的 output 中会返回 function_call 项，其中包含函数名、调用 ID 以及序列化后的参数。

部分模型仅支持 Responses 格式，例如 o3-pro、codex-mini-latest。

请求

POST https://www.vortapapi.com/v1/responses

请求头

名称	必填	说明
Content-Type	是	请求体格式，通常为 application/json
Accept	是	期望的响应格式，通常为 application/json
Authorization	否	API 密钥，例如 Bearer sk-***

请求示例

curl https://www.vortapapi.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer sk-***" \
  -d '{
    "model": "gpt-4.1-data",
    "input": "What is my horoscope today? I am an Aquarius.",
    "tools": [
      {
        "type": "function",
        "name": "get_horoscope",
        "description": "Get today'\''s horoscope for an astrological sign.",
        "parameters": {
          "type": "object",
          "properties": {
            "sign": {
              "type": "string",
              "description": "An astrological sign like Taurus or Aquarius"
            }
          },
          "required": ["sign"]
        },
        "strict": true
      }
    ],
    "tool_choice": "auto"
  }'

响应示例

{
  "id": "resp_68ac1558e9488190bcc2cbb94c7d7a140b8064b15a091a77",
  "object": "response",
  "created_at": 1756108120,
  "status": "completed",
  "background": false,
  "content_filters": null,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "model": "gpt-4.1-data",
  "output": [
    {
      "id": "fc_68ac15594be88190a58217f75a6a54cc0b8064b15a091a77",
      "type": "function_call",
      "status": "completed",
      "arguments": "{\"sign\":\"Aquarius\"}",
      "call_id": "call_6kbB2GTk62PPUNdGuBJPx9KQ",
      "name": "get_horoscope"
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "reasoning": {
    "effort": null,
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "store": true,
  "temperature": 1.0,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [
    {
      "type": "function",
      "description": "Get today's horoscope for an astrological sign.",
      "name": "get_horoscope",
      "parameters": {
        "properties": {
          "sign": {
            "description": "An astrological sign like Taurus or Aquarius",
            "type": "string"
          }
        },
        "required": [
          "sign"
        ],
        "type": "object"
      },
      "strict": true
    }
  ],
  "top_p": 1.0,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 62,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 18,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 80
  },
  "user": null,
  "metadata": {}
}

关键字段说明

字段	说明
output	模型生成的输出列表。函数调用会以 type: "function_call" 的形式出现。
output[].name	模型选择调用的函数名称。
output[].arguments	函数入参，通常是 JSON 字符串，需要在业务代码中解析后再执行函数。
output[].call_id	本次函数调用的唯一标识，用于后续提交工具结果时关联调用。
tools	请求中提供给模型的工具定义。
tool_choice	控制模型是否以及如何选择工具。auto 表示由模型自行判断。
parallel_tool_calls	表示是否允许模型并行发起多个工具调用。
usage	Token 用量统计，包含输入、输出以及总 Token 数。