流式响应

Chat Completions 流式请求

设置 stream: true 后，接口以 SSE 格式返回增量事件。

curl -N "${BASE_URL}/v1/chat/completions" \
  -H "Authorization: Bearer ${API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "messages": [
      {
        "role": "user",
        "content": "连续输出三条排查建议"
      }
    ],
    "stream": true,
    "stream_options": {
      "include_usage": true
    }
  }'

SSE 事件形状

data: {"id":"chatcmpl_xxx","object":"chat.completion.chunk","choices":[{"delta":{"content":"第一"}}]}

data: {"id":"chatcmpl_xxx","object":"chat.completion.chunk","choices":[{"delta":{"content":"条建议"}}]}

data: {"id":"chatcmpl_xxx","object":"chat.completion.chunk","choices":[{"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":20,"completion_tokens":30,"total_tokens":50}}

data: [DONE]

客户端处理建议

• 按 SSE 的 data: 行逐条解析
• 收到 [DONE] 后关闭本次流
• 如果需要在客户端展示用量，传入 stream_options.include_usage=true
• 客户端断开后，本次请求可能仍会完成计费

Python SDK 示例

stream = client.chat.completions.create(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "连续输出三条排查建议"}],
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")