创建结构化输出

POST

/v1/chat/completions

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

官方文档：https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses

请求参数

Authorization

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Header 参数

Body 参数application/json

示例

{
    "model": "gpt-4.1-2025-04-14",
    "messages": [
      {
        "role": "system",
        "content": "Determine if the user input violates specific guidelines and explain if they do."
      },
      {
        "role": "user",
        "content": "How do I prepare for a job interview?"
      }
    ],
    "response_format": {
      "type": "json_schema",
      "json_schema": {
        "name": "content_compliance",
        "description": "Determines if content is violating specific moderation rules",
        "schema": {
          "type": "object",
          "properties": {
            "is_violating": {
              "type": "boolean",
              "description": "Indicates if the content is violating guidelines"
            },
            "category": {
              "type": ["string", "null"],
              "description": "Type of violation, if the content is violating guidelines. Null otherwise.",
              "enum": ["violence", "sexual", "self_harm"]
            },
            "explanation_if_violating": {
              "type": ["string", "null"],
              "description": "Explanation of why the content is violating"
            }
          },
          "required": ["is_violating", "category", "explanation_if_violating"],
          "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.cursorai.art/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "gpt-4.1-2025-04-14",
    "messages": [
      {
        "role": "system",
        "content": "Determine if the user input violates specific guidelines and explain if they do."
      },
      {
        "role": "user",
        "content": "How do I prepare for a job interview?"
      }
    ],
    "response_format": {
      "type": "json_schema",
      "json_schema": {
        "name": "content_compliance",
        "description": "Determines if content is violating specific moderation rules",
        "schema": {
          "type": "object",
          "properties": {
            "is_violating": {
              "type": "boolean",
              "description": "Indicates if the content is violating guidelines"
            },
            "category": {
              "type": ["string", "null"],
              "description": "Type of violation, if the content is violating guidelines. Null otherwise.",
              "enum": ["violence", "sexual", "self_harm"]
            },
            "explanation_if_violating": {
              "type": ["string", "null"],
              "description": "Explanation of why the content is violating"
            }
          },
          "required": ["is_violating", "category", "explanation_if_violating"],
          "additionalProperties": false
        },
        "strict": true
      }
    }
  }'

返回响应

🟢200OK

application/json

Body

示例

{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "\n\nHello there, how may I assist you today?"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 9,
        "completion_tokens": 12,
        "total_tokens": 21
    }
}

修改于 2025-08-10 08:41:05

创建聊天函数调用 (只能非流)

控制推理模型努力程度