liteLLM

I find myself recommending this library to serious LLM-powered app developers that are trying to standardize their codebase by unifying all the APIs they use. Love it!

Used as an LLM proxy, it allows the caching and load balancing between multiple AI services (Groq, OpenRouter, etc.) and even local with Ollama. It uses an OpenAI-compatible API that allows (when we can set the base URL) to use it in many apps or services. I use it configured with Langfuse which provides the performance analysis (monitoring) of each prompt/session.