文本生成/流式输出

流式输出

通过服务器发送事件 (SSE) 实现聊天补全的增量输出。

接口说明

项目值
方法POST
路径/v1/chat/completions
设置"stream": true
Gemini SSE/v1beta/models/{model}:streamGenerateContent?alt=sse

cURL

curl https://api.unigateway.ai/v1/chat/completions \
  -H "Authorization: Bearer $UNIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -N \
  -d '{
    "model": "gpt-5.4",
    "stream": true,
    "messages": [{"role": "user", "content": "说你好"}]
  }'

-N 关闭输出缓冲。

SSE 格式

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

Python

from openai import OpenAI
client = OpenAI(api_key="<YOUR_UNIGATEWAY_API_KEY>", base_url="https://api.unigateway.ai/v1")
stream = client.chat.completions.create(model="gpt-5.4", stream=True, messages=[{"role": "user", "content": "说你好"}])
for chunk in stream:
    delta = chunk.choices[0].delta.content or ""
    if delta: print(delta, end="", flush=True)

TypeScript

import OpenAI from "openai";
const client = new OpenAI({ apiKey: process.env.UNIGATEWAY_API_KEY, baseURL: "https://api.unigateway.ai/v1" });
const stream = await client.chat.completions.create({ model: "gpt-5.4", stream: true, messages: [{ role: "user", content: "说你好" }] });
for await (const chunk of stream) {
  const delta = chunk.choices[0]?.delta?.content ?? "";
  if (delta) process.stdout.write(delta);
}

Gemini SSE 流式

curl "https://api.unigateway.ai/v1beta/models/gemini-3-pro-preview:streamGenerateContent?alt=sse" \
  -H "Authorization: Bearer $UNIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents": [{"parts": [{"text": "说你好"}]}]}'

图片生成流式

图片生成也支持 SSE 流式推送，用于渐进渲染中间图和最终图。

请求

curl -sS -X POST "https://api.unigateway.ai/v1/images/generations" \
  -H "Authorization: Bearer $UNIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -N \
  -d '{"model":"gpt-image-2","prompt":"A winter landscape.","stream":true,"partial_images":2}'

SSE 事件格式

事件类型字段说明
image_generation.partial_imageb64_json, partial_image_index中间低分辨率图像
image_generation.completedb64_json最终完整图像
event: image_generation.partial_image
data: {"created_at":1718000000,"type":"image_generation.partial_image","b64_json":"iVBOR...","partial_image_index":0}

event: image_generation.completed
data: {"created_at":1718000000,"type":"image_generation.completed","b64_json":"iVBOR..."}

端点兼容性：并非所有上游端点都支持真正的 SSE 流式。详见 OpenAI Images API → 端点兼容性。

错误处理

场景处理
中途断开发起新请求
无 token 返回重试一次后换模型
SSE 保活 : UNIGATEWAY PROCESSING正常 — 忽略以 : 开头的注释行