Chat（结构化输出）

POST

/v1/chat/completions

所有对话模型，都可使用此接口，修改 model 属性为模型名
给定一个提示，该模型将返回一个或多个预测的完成，并且还可以返回每个位置的替代标记的概率。
为提供的提示和参数创建完成

请求参数

Header 参数

Body 参数application/json

示例

{
  "model": "gpt-4o-2024-08-06",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful math tutor. Guide the user through the solution step by step."
    },
    {
      "role": "user",
      "content": "9.11和9.8谁大"
    }
  ],
  "response_format": {
    "type": "json_schema",
    "json_schema": {
      "name": "math_reasoning",
      "schema": {
        "type": "object",
        "properties": {
          "steps": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "explanation": {
                  "type": "string"
                },
                "output": {
                  "type": "string"
                }
              },
              "required": [
                "explanation",
                "output"
              ],
              "additionalProperties": false
            }
          },
          "final_answer": {
            "type": "string"
          }
        },
        "required": [
          "steps",
          "final_answer"
        ],
        "additionalProperties": false
      },
      "strict": true
    }
  }
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.pro365.top/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "gpt-4o-2024-08-06",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful math tutor. Guide the user through the solution step by step."
    },
    {
      "role": "user",
      "content": "9.11和9.8谁大"
    }
  ],
  "response_format": {
    "type": "json_schema",
    "json_schema": {
      "name": "math_reasoning",
      "schema": {
        "type": "object",
        "properties": {
          "steps": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "explanation": {
                  "type": "string"
                },
                "output": {
                  "type": "string"
                }
              },
              "required": [
                "explanation",
                "output"
              ],
              "additionalProperties": false
            }
          },
          "final_answer": {
            "type": "string"
          }
        },
        "required": [
          "steps",
          "final_answer"
        ],
        "additionalProperties": false
      },
      "strict": true
    }
  }
}'

返回响应

🟢200OK

application/json

Body

示例

{
    "id": "chatcmpl-CRvyy29POfyOEE4ptJNWr9XnmNlvH",
    "object": "chat.completion",
    "created": 1760773776,
    "model": "gpt-4o-2024-08-06",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "{\"final_answer\":\"9.8\",\"steps\":[{\"explanation\":\"首先，我们比较两个数的整数部分。两个数的整数部分是相同的，都是9。\",\"output\":\"整数部分比较：9.11的整数部分是9，9.8的整数部分是9，二者相同，比较小数部分。\"},{\"explanation\":\"当整数部分相同时，我们比较小数部分的大小。小数部分其实就是去掉整数部分后的小数。\",\"output\":\"9.11的小数部分是0.11，9.8的小数部分是0.8。\"},{\"explanation\":\"为了更容易比较，我们把9.8的假设为分数形式，0.8实际上是0.80。\",\"output\":\"比较小数部分：0.11与0.80 (因为0.8可以写成0.80，不改变数值)。\"},{\"explanation\":\"比较0.11和0.80。我们发现0.80大于0.11。\",\"output\":\"0.80 > 0.11\"},{\"explanation\":\"所以比较得出9.8大于9.11。\",\"output\":\"结论：9.8大于9.11。\"}]}",
                "refusal": null,
                "annotations": []
            },
            "logprobs": null,
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 97,
        "completion_tokens": 257,
        "total_tokens": 354,
        "prompt_tokens_details": {
            "cached_tokens": 0,
            "audio_tokens": 0
        },
        "completion_tokens_details": {
            "reasoning_tokens": 0,
            "audio_tokens": 0,
            "accepted_prediction_tokens": 0,
            "rejected_prediction_tokens": 0
        }
    },
    "system_fingerprint": "fp_4a331a0222"
}

修改于 2025-10-18 07:51:23

Chat（视频识别分析）

OpenAI 格式（Responses）