Hey everyone!
I'm currently building a backend project using FastAPI and looking to integrate an LLM. I've been testing the free tiers of Gemini and Groq, but the rate limits run out extremely fast during active development and testing.
Do you know of any platforms, providers, or alternatives that offer a free tier (or a very generous free API limit) for LLMs without getting throttled so quickly?
Any recommendations or strategies you usually use to handle this during development would be greatly appreciated. Thanks in advance!