Fastllm-proxy

The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLLM/SGLang — 0.76 µs p

What is Fastllm-proxy?

The lowest-overhead LLM router. Production-ready, highly available, one OpenAI-compatible endpoint in front of 80 providers and your own vLLM/SGLang — 0.76 µs per request, no I/O on the request path, cache-affinity routing, RBAC, budgets and a 13-screen UI in the binary.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/azrtydxbfastllm-proxy.svg)](https://yunodb.com/tools/azrtydxbfastllm-proxy?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/azrtydxbfastllm-proxy?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/azrtydxbfastllm-proxy.svg" alt="Featured on YunoDB" height="20"></a>