DEVELOPER · EXAMPLES

代码示例

替换 sk-你的令牌 为你的真实 API Key 即可直接运行。所有示例兼容 OpenAI SDK。

cURL

curl https://api.queqiao.cloud/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-你的令牌" \
  -d '{
    "model": "deepseek-chat",
    "messages": [
      {"role": "system", "content": "你是一个简洁的助手"},
      {"role": "user", "content": "用三句话介绍北京"}
    ]
  }'

Python（OpenAI SDK）

安装：pip install openai

from openai import OpenAI

client = OpenAI(
    api_key="sk-你的令牌",
    base_url="https://api.queqiao.cloud/v1"
)

resp = client.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "system", "content": "你是一个简洁的助手"},
        {"role": "user", "content": "用三句话介绍北京"}
    ]
)
print(resp.choices[0].message.content)

Node.js（OpenAI SDK）

安装：npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-你的令牌",
  baseURL: "https://api.queqiao.cloud/v1",
});

const resp = await client.chat.completions.create({
  model: "deepseek-chat",
  messages: [
    { role: "system", content: "你是一个简洁的助手" },
    { role: "user", content: "用三句话介绍北京" },
  ],
});
console.log(resp.choices[0].message.content);

流式输出（Python）

stream = client.chat.completions.create(
    model="deepseek-chat",
    stream=True,
    messages=[{"role": "user", "content": "讲一个关于鹊桥的小故事"}]
)
for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

流式输出的首字延迟显著低于整段返回，推荐用于面向用户的聊天场景。

下一步：错误码参考 →