API 调用

除了 CLI 工具，你也可以直接通过 HTTP 请求调用 RouterBus API。

API 基础信息

• OpenAI 兼容端点: https://www.routerbus.com/v1
• Claude 原生端点: https://www.routerbus.com
• Gemini 原生端点: https://www.routerbus.com/v1beta
• 认证方式: Bearer Token（Claude 原生格式用 x-api-key，Gemini 原生格式用 x-goog-api-key）

下面示例里的模型 ID 只是示例，实际可用的 ID 以 模型广场 为准。

Chat Completions

请求示例

curl https://www.routerbus.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

流式输出

curl https://www.routerbus.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "stream": true
  }'

Python SDK

使用 OpenAI Python SDK：

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://www.routerbus.com/v1"
)

response = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

Node.js SDK

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx',
  baseURL: 'https://www.routerbus.com/v1',
});

const response = await client.chat.completions.create({
  model: 'claude-sonnet-4-6',
  messages: [{ role: 'user', content: 'Hello!' }],
});

console.log(response.choices[0].message.content);

Claude API 原生格式

如果你需要使用 Claude 的原生 Messages API 格式：

curl https://www.routerbus.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Gemini 原生格式

curl "https://www.routerbus.com/v1beta/models/MODEL_ID:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
  -d '{
    "contents": [
      {"parts": [{"text": "Hello!"}]}
    ]
  }'

把 MODEL_ID 换成模型广场上的 Gemini 模型 ID。

TIP

推荐使用 OpenAI 兼容格式：绝大多数模型都在这个端点开放，换模型只改一个字符串，代码不用动。每个模型支持哪些端点，模型广场的模型详情里有标注。