RouterHub API

Unified access to Claude, Gemini, and GPT models through OpenAI-compatible and Anthropic-compatible endpoints.

Base URL https://api.routerhub.ai

Quick Start

Make your first API call in seconds. Replace YOUR_API_KEY with your RouterHub API key.

curl https://api.routerhub.ai/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4",
    "messages": [
      {"role": "user", "content": "Hello, what can you do?"}
    ]
  }'
import requests

response = requests.post(
    "https://api.routerhub.ai/v1/chat/completions",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "anthropic/claude-sonnet-4",
        "messages": [
            {"role": "user", "content": "Hello, what can you do?"}
        ],
    },
)
print(response.json()["choices"][0]["message"]["content"])
from openai import OpenAI

client = OpenAI(
    base_url="https://api.routerhub.ai/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4",
    messages=[
        {"role": "user", "content": "Hello, what can you do?"}
    ],
)
print(response.choices[0].message.content)

Two APIs

RouterHub exposes two fully compatible API surfaces. Use whichever fits your existing workflow.

OpenAI-Compatible

POST /v1/chat/completions

Works with any OpenAI SDK. Drop in your RouterHub base URL and API key to route requests to Claude, Gemini, or GPT models without changing your code.

View documentation →

Anthropic-Compatible

POST /v1/messages

Works with the Anthropic SDK. Use the native Anthropic Messages API format with full support for thinking, tool use, and streaming.

View documentation →

Features

Streaming

Real-time server-sent events for low-latency token-by-token output across all providers.

Learn more →

Tool Calling

Define functions and let models invoke them with structured arguments in a single request flow.

Learn more →

Structured Output

Constrain model responses to a JSON schema for reliable, parseable output every time.

Learn more →

Reasoning

Enable extended thinking to let models work through complex problems step by step before responding.

Learn more →

Available Models

RouterHub provides access to leading model families from Anthropic, Google, and OpenAI.

Claude

7 models

Claude Opus 4, Claude Sonnet 4.5, Claude Sonnet 4, Claude Opus 4.1, Claude Haiku 4.5, Claude 3.5 Sonnet v2, Claude 3.5 Haiku

Gemini

5 models

Gemini 3 Pro Preview, Gemini 3 Flash Preview, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash Lite

GPT

10 models

GPT-5, GPT-5.2 Chat, GPT-5.2, GPT-5.2 Codex, GPT-5.1, GPT-5.1 Codex, GPT-5.1 Codex Mini, GPT-4.1, GPT-4o, o1

View the full model list with IDs and capabilities →