聊天(responses) - UnifiedAPI

请求参数

Header 参数

Body 参数application/json

示例

{
    "model": "gpt-5",
    "input": [
        {
            "role": "user",
            "content": "Hello!"
        }
    ]
}

请求示例代码

Shell

JavaScript

Java

Swift

Go

PHP

Python

HTTP

C

C#

Objective-C

Ruby

OCaml

Dart

R

curl --location '/v1/responses' \
--header 'Authorization: Bearer {YOUR_API_KEY}' \
--header 'Content-Type: application/json' \
--data '{
    "model": "gpt-5",
    "input": [
        {
            "role": "user",
            "content": "Hello!"
        }
    ]
}'

返回响应

🟢200成功

application/json

Bodyapplication/json

示例

{
    "id": "resp_6895b537f6e08198b985851c6c78daaa0cdc1fb5affdb381",
    "object": "response",
    "created_at": 1754641720,
    "status": "completed",
    "background": false,
    "error": null,
    "incomplete_details": null,
    "instructions": null,
    "max_output_tokens": null,
    "max_tool_calls": null,
    "model": "gpt-5-2025-08-07",
    "output": [
        {
            "id": "rs_6895b5387e408198987a544cee1da0730cdc1fb5affdb381",
            "type": "reasoning",
            "summary": []
        },
        {
            "id": "msg_6895b53ff5748198aac63a412a34c9e10cdc1fb5affdb381",
            "type": "message",
            "status": "completed",
            "content": [
                {
                    "type": "output_text",
                    "annotations": [],
                    "logprobs": [],
                    "text": "Hi! How can I help you today?"
                }
            ],
            "role": "assistant"
        }
    ],
    "parallel_tool_calls": true,
    "previous_response_id": null,
    "prompt_cache_key": null,
    "reasoning": {
        "effort": "medium",
        "summary": null
    },
    "safety_identifier": null,
    "service_tier": "default",
    "store": true,
    "temperature": 1.0,
    "text": {
        "format": {
            "type": "text"
        },
        "verbosity": "medium"
    },
    "tool_choice": "auto",
    "tools": [],
    "top_logprobs": 0,
    "top_p": 1.0,
    "truncation": "disabled",
    "usage": {
        "input_tokens": 7,
        "input_tokens_details": {
            "cached_tokens": 0
        },
        "output_tokens": 79,
        "output_tokens_details": {
            "reasoning_tokens": 64
        },
        "total_tokens": 86
    },
    "user": null,
    "metadata": {}
}