待翻譯：Show HN: AI gateway open source integrated with cursor and open router

AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。

RouterFuel — 330+ LLMs, Single API 🚀 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 # 1. Install cargo install routerfuel # 2. Run ROUTEFUEL_API_KEYS="sha256:test:testclient" \ DATABASE_URL="postgres://..." \ ./routerfuel # 3. 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 // 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) ✓35,000 requests / month included ✓Overages billed at $20 / 100k requests ✓Semantic caching & circuit breaking ✓Community support Most popular Developer For production workloads at scale. $15/mo (Launching Soon) ✓150,000 requests / month included ✓Overages billed at $15 / 100k requests ✓Priority provider failover routing ✓Email & Slack support Enterprise For regulated and air-gapped environments. Custom (Launching Soon) ✓Dedicated multi-region deployment ✓On-premise binary distribution ✓Custom rate limits ✓Air-gapped security profiles Talk to sales // contact Get in touch. Questions, feedback, or want to talk deployment? Reach us directly. [email protected] // 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. Talk to us about licensing You're on the list We'll email you as soon as your access is ready.