Skip to main content
chatbot

Groq

Ultra-fast AI inference platform using custom LPU hardware. Provides the fastest token generation speeds for open-source LLMs like Llama and Mixtral.

Capabilities

What it does

chatbotmodel servingcode generationspeech recognition

Accepts

text:prompttext:codeaudio:speech

Produces

text:answercode:snippet
EN

Pricing

freemium

Samples