流式调用
在请求体中设置 "stream": true,服务端以 SSE 形式返回增量内容。
cURL
curl https://api.haiyushuke.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-4o-mini","stream":true,"messages":[{"role":"user","content":"写一首四句诗"}]}'OpenAI SDK(Node)
const stream = await client.chat.completions.create({
model: "gpt-4o-mini",
stream: true,
messages: [{ role: "user", content: "你好" }],
});
for await (const chunk of stream) {
const text = chunk.choices[0]?.delta?.content;
if (text) process.stdout.write(text);
}注意
- 客户端需正确处理连接中断与超时重试
- 流式场景下计费通常按 输出 token 累计,以账单规则为准
