> ## Documentation Index
> Fetch the complete documentation index at: https://doc.tokendog.io/llms.txt
> Use this file to discover all available pages before exploring further.

# 快速上手

> 三步发出第一个请求

<Steps>
  <Step title="获取密钥">
    登录 [tokendog.io](https://tokendog.io) → 控制台 → 生成 API 密钥（形如 `sk-...`）。
  </Step>

  <Step title="设置基址">
    把客户端 Base URL 设为 `https://tokendog.io`，鉴权用 `Authorization: Bearer <你的密钥>`。
  </Step>

  <Step title="发出请求">
    运行下面任一示例。
  </Step>
</Steps>

<CodeGroup>
  ```bash curl theme={null}
  curl https://tokendog.io/v1/chat/completions \
    -H "Authorization: Bearer $TOKENDOG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gpt-5",
      "messages": [{"role": "user", "content": "你好，TokenDog！"}]
    }'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      base_url="https://tokendog.io/v1",
      api_key="YOUR_TOKENDOG_API_KEY",
  )

  resp = client.chat.completions.create(
      model="gpt-5",
      messages=[{"role": "user", "content": "你好，TokenDog！"}],
  )
  print(resp.choices[0].message.content)
  ```

  ```javascript Node theme={null}
  import OpenAI from "openai";

  const client = new OpenAI({
    baseURL: "https://tokendog.io/v1",
    apiKey: "YOUR_TOKENDOG_API_KEY",
  });

  const resp = await client.chat.completions.create({
    model: "gpt-5",
    messages: [{ role: "user", content: "你好，TokenDog！" }],
  });
  console.log(resp.choices[0].message.content);
  ```
</CodeGroup>

<Tip>把 `model` 换成其它厂商即可切换，例如智谱 `glm-5.1`、MiniMax `MiniMax-M2.7`，无需改基址或密钥。</Tip>

<Note>把密钥放进环境变量（如 `TOKENDOG_API_KEY`），不要硬编码进代码或提交到仓库。</Note>