What is ARouter?
ARouter is a unified LLM API gateway that sits between your application and upstream model providers. Use one API key to access OpenAI, Anthropic, Google Gemini, DeepSeek, Mistral, Groq, and many more — without changing your existing code.Quick Start
Get up and running in under 2 minutes
API Reference
Explore every endpoint
SDKs
Python, Node.js, Go & cURL examples
Key Management
Fine-grained access control for your team
Why ARouter?
Drop-in compatible
Drop-in compatible
Use the official OpenAI, Anthropic, or Gemini SDK you already know.
Just change
base_url and api_key — zero code changes.Multi-provider routing
Multi-provider routing
Route requests to 14+ providers through a single endpoint using the
provider/model format.
No need to manage separate API keys and base URLs for each provider.Key pooling & failover
Key pooling & failover
Pool multiple API keys per provider with weighted round-robin selection.
Automatic health checking, circuit breaking, and failover across keys and providers.
Key management
Key management
Create scoped API keys with provider whitelists, model restrictions,
spending limits, and expiry — all via the management API.
Global multi-region
Global multi-region
Deploy across multiple regions with intelligent request routing.
Requests from latency-sensitive or network-restricted regions are automatically proxied through the nearest edge node to reach upstream providers.
Usage tracking
Usage tracking
Every request is metered with input/output tokens, latency, and status.
Monitor usage per key, per model, per provider in real time.
Supported Providers
| Provider | Models | Native SDK Support |
|---|---|---|
| OpenAI | GPT-4o, GPT-4-Turbo, o1, o3-mini, … | OpenAI SDK |
| Anthropic | Claude Sonnet 4, Claude 3.5 Haiku, Claude 3 Opus, … | Anthropic SDK |
| Gemini 2.0 Flash, Gemini 1.5 Pro, … | Gemini SDK | |
| DeepSeek | DeepSeek Chat, DeepSeek Reasoner | OpenAI SDK |
| xAI | Grok-2, Grok-2 Mini | OpenAI SDK |
| Mistral | Mistral Large, Codestral, … | OpenAI SDK |
| Groq | Llama 3.3 70B, Mixtral 8x7B, … | OpenAI SDK |
| Kimi | Moonshot v1 8K/32K/128K | OpenAI SDK |
| MiniMax | abab6.5s, abab6.5, abab5.5 | MiniMax SDK |
How It Works
model field from your request, determines the target provider,
selects a healthy API key from the pool, and proxies the request — including streaming responses.
All of this happens transparently. Your application code stays exactly the same.