从账户到第一次调用。

curl -N https://api.yunluapi.com/v1/responses \
  -H "Authorization: Bearer $YUNLU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_AVAILABLE_MODEL",
    "instructions": "You are a helpful coding assistant.",
    "input": [{"role": "user", "content": "请用一句话解释 Python 列表推导式。"}],
    "store": false,
    "stream": true
  }'

适用于 macOS / Linux shell；Windows 可使用 Bash 或参考对应终端的语法。

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["YUNLU_API_KEY"],
    base_url="https://api.yunluapi.com/v1",
)

stream = client.responses.create(
    model="YOUR_AVAILABLE_MODEL",
    instructions="You are a helpful coding assistant.",
    input=[{"role": "user", "content": "请用一句话解释 Python 列表推导式。"}],
    store=False,
    stream=True,
)
for event in stream:
    if event.type == "response.output_text.delta":
        print(event.delta, end="", flush=True)
    elif event.type in ("response.failed", "error"):
        raise RuntimeError("请求未成功完成，请核对错误事件和调用日志。")
print()

先安装 OpenAI Python SDK：pip install openai。

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.YUNLU_API_KEY,
  baseURL: "https://api.yunluapi.com/v1",
});

const stream = await client.responses.create({
  model: "YOUR_AVAILABLE_MODEL",
  instructions: "You are a helpful coding assistant.",
  input: [{ role: "user", content: "请用一句话解释 Python 列表推导式。" }],
  store: false,
  stream: true,
});
for await (const event of stream) {
  if (event.type === "response.output_text.delta") {
    process.stdout.write(event.delta);
  } else if (event.type === "response.failed" || event.type === "error") {
    throw new Error("请求未成功完成，请核对错误事件和调用日志。");
  }
}
process.stdout.write("\n");

用于 Node.js 服务端；先运行 npm install openai，以 ESM 方式执行。