Chat Completions

创建聊天完成请求，支持流式输出。

请求

POST /v1/chat/completions

请求体

字段	类型	必填	说明
model	string	是	模型名称，如 gpt-4o
messages	array	是	消息列表
stream	boolean	否	是否流式输出，默认 false
temperature	number	否	采样温度，0-2，默认 1
max_tokens	integer	否	最大生成 Token 数
top_p	number	否	核采样概率阈值

Messages 格式

[
  {"role": "system", "content": "你是一个 helpful 助手"},
  {"role": "user", "content": "你好"}
]

响应

非流式

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1234567890,
  "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": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

流式

设置 stream: true，响应为 SSE 流：

data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"你好"}}]}

data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"！"}}]}

data: [DONE]

示例

curl http://124.221.16.139/v1/chat/completions \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": false
  }'