​
单轮对话：

文本推理（“stream”=false）：

{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "model": "DeepSeek-R1",
    "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
    },
    "prefill_time": 200,
    "decode_time_arr": [56, 28, 28]
}

​
多轮对话：

​
响应样例1：

{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "model": "DeepSeek-R1",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "",
                "tool_calls": [
                    {
                        "function": {
                            "arguments": "{\"order_id\": \"12345\"}",
                            "name": "get_delivery_date"
                        },
                        "id": "call_JwmTNF3O",
                        "type": "function"
                    }
                ]
            },
            "finish_reason": "tool_calls"
        }
    ],
    "usage": {
        "prompt_tokens": 226,
        "completion_tokens": 122,
        "total_tokens": 348
    },
    "prefill_time": 200,
    "decode_time_arr": [56, 28, 28]
}

​
响应样例2：

{
    "id": "endpoint_common_25",
    "object": "chat.completion",
    "created": 1728959154,
    "model": "DeepSeek-R1",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "\n Your order with ID 12345 is scheduled for delivery on September 10th, 2024.",
                "tool_calls": null
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 265,
        "completion_tokens": 30,
        "total_tokens": 295
    },
    "prefill_time": 200,
    "decode_time_arr": [56, 28, 28]
}