Streaming

零派智能API 支持 SSE（Server-Sent Events）流式响应，适用于 Chat Completions 和 Responses 接口。流式模式下，模型逐 token 返回内容，实现实时输出效果。

stream 参数

在请求体中将 stream 设置为 true 即可启用流式响应：

{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": "写一首关于秋天的诗"
    }
  ],
  "stream": true
}

SSE 格式

流式响应使用 SSE 格式，每条消息以 data: 前缀开头，以两个换行符分隔：

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1699999999,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1699999999,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"content":"秋"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1699999999,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"content":"风"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1699999999,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]