Responses格式

开发中

POST

/v1/responses

请求参数

Header 参数

Body 参数application/json必填

示例

{
  "model": "qwen3.6-plus",
  "input": [
    {
      "role": "user",
      "content": "你好"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1024
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://ai.interwestinfo.com/v1/responses' \
--header 'Authorization: sk-************************************************' \
--header 'Content-Type: application/json' \
--data '{
  "model": "qwen3.6-plus",
  "input": [
    {
      "role": "user",
      "content": "你好"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1024
}'

返回响应

🟢200成功

application/json

Bodyapplication/json

示例

{
    "background": false,
    "completed_at": 1779173565,
    "created_at": 1779173557,
    "frequency_penalty": 0.0,
    "id": "resp_4ab5fe23-6b2f-9d70-aec7-f6e24bd8143e",
    "metadata": {},
    "model": "qwen3.6-plus",
    "object": "response",
    "output": [
        {
            "id": "msg_4f47784c-eb3c-444f-b260-4673c83d2383",
            "summary": [
                {
                    "text": "Here's a thinking process:\n\n1.  **Analyze User Input:**\n   - User said: \"你好\" (Hello in Chinese)\n   - Language: Chinese\n   - Intent: Greeting/Initiating conversation\n\n2.  **Identify Key Constraints/Context:**\n   - Current actual time: Tuesday, May 19, 2026\n   - Knowledge cutoff: 2026\n   - Language: Chinese (should respond in Chinese)\n\n3.  **Determine Response Strategy:**\n   - Acknowledge the greeting politely\n   - Respond in the same language (Chinese)\n   - Offer assistance\n   - Keep it concise and friendly\n\n4.  **Draft Response (Internal Refinement):**\n   你好！有什么我可以帮你的吗？无论是回答问题、提供建议，还是聊天，我都很乐意为你效劳。\n\n5.  **Check against Constraints:**\n   - Language: Chinese ✓\n   - Tone: Friendly, helpful ✓\n   - No specific time/date needed unless relevant, but current context is noted ✓\n   - Matches cutoff (no future references beyond 2026) ✓\n\n6.  **Final Output Generation:** (matches the draft)✅\n   \"你好！有什么我可以帮你的吗？无论是回答问题、提供建议，还是闲聊，我都很乐意为你效劳。\" (Slightly polished for natural flow)✅\n   Ready. \n   Output matches the final response. \n   Proceeds. \n   [Done.] \n   *Self-Correction/Verification during thought:* \n   - Is there any need to mention the date? No, not unless asked.\n   - Is the tone appropriate? Yes.\n   - Language correct? Yes.\n   All good.✅",
                    "type": "summary_text"
                }
            ],
            "type": "reasoning"
        },
        {
            "content": [
                {
                    "annotations": [],
                    "text": "你好！有什么我可以帮你的吗？无论是解答问题、提供建议，还是随便聊聊，我都很乐意为你效劳。",
                    "type": "output_text"
                }
            ],
            "id": "msg_d23bf29a-7b58-4c3f-8ab8-9ab1185b0556",
            "role": "assistant",
            "status": "completed",
            "type": "message"
        }
    ],
    "parallel_tool_calls": true,
    "presence_penalty": 0.0,
    "service_tier": "default",
    "status": "completed",
    "store": true,
    "temperature": 0.7,
    "tool_choice": "auto",
    "tools": [],
    "top_logprobs": 0,
    "top_p": 1.0,
    "usage": {
        "input_tokens": 47,
        "input_tokens_details": {
            "cached_tokens": 0
        },
        "output_tokens": 397,
        "output_tokens_details": {
            "reasoning_tokens": 367
        },
        "total_tokens": 444,
        "x_details": [
            {
                "input_tokens": 47,
                "output_tokens": 397,
                "output_tokens_details": {
                    "reasoning_tokens": 367
                },
                "total_tokens": 444,
                "x_billing_type": "response_api"
            }
        ]
    }
}

ChatCompletions格式

原生Claude格式