响应数据格式

AMAX Token Router 对上游模型厂商的响应进行透传，响应格式与 OpenAI / Anthropic 官方一致。

OpenAI 协议响应

普通对话（非流式）


{
  "id": "chatcmpl-xxxxxxxx",
  "object": "chat.completion",
  "created": 1710000000,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好！有什么可以帮助你的吗？"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 10,
    "total_tokens": 30
  }
}

字段	说明
`id`	本次请求的唯一标识
`object`	对象类型，固定为 `chat.completion`
`choices[].message`	模型回复的消息
`choices[].finish_reason`	结束原因：`stop`（正常结束）、`length`（达到最大长度）
`usage`	Token 用量统计

流式输出（SSE）


data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"你"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"好"},"finish_reason":null}]}

data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

流式输出采用 SSE（Server-Sent Events）协议，每条数据以 data: 开头，以 [DONE] 结束。

Anthropic 协议响应


{
  "id": "msg_xxx",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I help you?"
    }
  ],
  "model": "claude-sonnet-4-6",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 10,
    "output_tokens": 8
  }
}

无论你使用 OpenAI 还是 Anthropic SDK，响应格式都是对应协议的标准格式。协议互转由网关自动完成。