330+ models, one async proxy,
orchestrated at the edge.🚀 RouterFuel is in open beta. All features are free during preview.
v0.6.0 — Tokio async runtime, now with sub-20ms p99
OpenRouter Compatible
330+ models, one async proxy,
orchestrated at the edge.RouterFuel is a single async proxy layer in front of every model provider you use — 330+ models via direct integration plus OpenRouter. Built on a Tokio and Axum network core, it multiplexes concurrent inference requests, negotiates provider failover in microseconds, and streams tokens back without adding measurable overhead.
Deploy Sandbox Instance View Documentation
cargo install routerfuel · zero telemetry sent off-cluster · AGPL-3.0 core
// quickstart
Running in under a minute.
terminal Copy
1. Install
cargo install routerfuel2. Run
ROUTEFUEL_API_KEYS="sha256:test:testclient" \ DATABASE_URL="postgres://..." \ ./routerfuel3. Make your first request
curl -X POST http://localhost:3000/v1/chat/completions \ -H "X-API-Key: test" \ -H "Content-Type: application/json" \ -d '{"model":"auto","messages":[{"role":"user","content":"Hello!"}]}'routerfuel — edge-proxy@us-east-1
LIVE
p99 latency
18ms
req / sec
2,155
tokens / sec
18.6k
cache hit rate
37%
active providers
openai ● healthy
anthropic ● healthy
openrouter ● healthy
330+ MODELS
Access 330+ LLMs through a single API — OpenAI, Anthropic, Google, Meta, Mistral, and every model on OpenRouter.
- ✅Works with OpenRouter — bring your own key
- ✅Automatic catalog sync for new models
- ✅One request format across every provider
- ✓35,000 requests / month included
- ✓Overages billed at $20 / 100k requests
- ✓Semantic caching & circuit breaking
- ✓Community support Join Waitlist
- ✓150,000 requests / month included
- ✓Overages billed at $15 / 100k requests
- ✓Priority provider failover routing
- ✓Email & Slack support Join Waitlist
- ✓Dedicated multi-region deployment
- ✓On-premise binary distribution
- ✓Custom rate limits
- ✓Air-gapped security profiles
// architecture
Four primitives, one binary.
Every RouterFuel deployment ships with the same resiliency core — no add-on modules, no separate billing for the parts that keep your inference layer alive.
Semantic Caching Engine
Vector-matches incoming prompts against prior completions and serves near-duplicates from cache, cutting repetitive API spend by up to 40%.
Circuit-Breaking Resiliency
Trips automatically on provider error spikes or latency drift, rerouting in-flight and new requests to a healthy fallback provider with no dropped calls.
Custom Proxy Middleware
Inject headers, rewrite request bodies, and track upstream server health parameters with a middleware chain that runs inline with zero added round-trips.
OpenRouter Integration — 300+ Models
Seamlessly route to any model OpenRouter supports. Automatic catalog sync means new models appear without code changes.
// pricing
Pay for throughput, not seats.
Every tier ships the full resiliency core. All features are free during the open beta.
Hobby
For side projects and prototypes.
Free (Launching Soon)
Most popular
Developer
For production workloads at scale.
$15/mo (Launching Soon)
Enterprise
For regulated and air-gapped environments.
Custom (Launching Soon)
// contact
Get in touch.
Questions, feedback, or want to talk deployment? Reach us directly.
// licensing
Need a commercial license?
RouterFuel's core is licensed under AGPL-3.0. That works great for self-hosting and open-source use, but if you're embedding RouterFuel in a closed-source product or run into AGPL's network-use clause at your company, we offer a separate commercial/enterprise license with no copyleft obligations.
Sign in
Accounts launch after the open beta — join the waitlist to get notified the moment they're live.
Password
Sign In
Not signed up yet? Join the waitlist
Join the waitlist
Free during the open beta. We'll email you when your access is ready.
Join Waitlist
You're on the list
We'll email you as soon as your access is ready.