Hey Product Hunt! 👋 The idea for Free LLM Router came from a problem my co-founder and I faced while building another product, AutoApplyAI. Before we could even start serious development, our LLM API quotas were already exhausted. We tried running local models with Ollama, but they were too slow and not accurate enough for our use case. We then moved to OpenRouter, but after only a few tests, we ran into rate limits again. That frustration led us to build Free LLM Router. It brings together multiple free-tier LLM providers behind one API and intelligently routes each request to the best available provider and model. The routing behavior is fully configurable, so developers can optimize it for speed, reliability, provider priority, quota usage, or their own specific use case. The main goal is simple: your application should not stop working just because one provider is rate-limited, unavailable, or out of quota. The router can automatically skip unhealthy providers and fall back to another eligible model. We originally built this to solve our own problem, but we realized many developers experimenting with AI face the same issue. We would love to hear your feedback, especially around routing strategies, provider support, reliability features, and what would make this more useful in your own projects.

LLM Router · One API for every provider

Dev tool that worries about your LLM API failures.

Dev tool that worries about your LLM API failures.