API Usage

In addition to CLI tools, you can call RouterBus APIs directly via HTTP requests.

API Information

• OpenAI-compatible endpoint: https://www.routerbus.com/v1
• Claude native endpoint: https://www.routerbus.com
• Gemini native endpoint: https://www.routerbus.com/v1beta
• Authentication: Bearer token (x-api-key for the Claude native format, x-goog-api-key for the Gemini native one)

The model IDs in the examples below are just examples — the IDs that actually work are the ones in Model Square.

Chat Completions

Request Example

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!"}
    ]
  }'

Streaming

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

Using the 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 Native API Format

To use Claude's native Messages API format:

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 native format

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!"}]}
    ]
  }'

Replace MODEL_ID with a Gemini model ID from Model Square.

TIP

Prefer the OpenAI-compatible format: nearly every model is open on it, so switching models means changing one string rather than your code. Each model's detail page in Model Square says which endpoints it accepts.