Groq for latency

Hey guys! I’ve been thinking about developing a web app using Groq with the open-source LLaMA model for low latency. I might sell the app on Gumroad as a subscription and was wondering if any creators have suggestions or tips. Thanks!

Hi there!

There are a bunch of models available on Groq, you can get started with the free tier of the API for prototyping and testing the waters so to speak, and once you get a feel for what you want to build and have built a working prototype, you can get on the paid developer plan and go on from there.

Thank you, I will use it for prototyping first!