LLM Reference

Groq

Groq

AI

Platform

Groq LPU (Language Processing Unit) inference platform for ultra-low latency

About Groq

Groq LPU (Language Processing Unit) inference platform for ultra-low latency

Available Models(4)

ModelInput (per 1M)Output (per 1M)Type
Groq Llama3-8B-8192$0.05$0.1Serverless
Groq Llama3-70B-8192$0.7$0.8Serverless
Groq Mixtral-8x7B-32768$0.27$0.27Serverless
Groq Gemma-7B-it$0.1$0.1Serverless

Company Info

Links

Website