agentskit.js
Providers

groq

Groq — ultra-low-latency inference on custom LPU hardware. Llama + Mixtral + Gemma.

import { groq } from '@agentskit/adapters'

const adapter = groq({
  apiKey: process.env.GROQ_API_KEY!,
  model: 'llama-3.3-70b-versatile',
})

Options

OptionTypeDefault
apiKeystringrequired
modelstringrequired
baseUrlstringhttps://api.groq.com/openai/v1
fetchtypeof fetchglobal

Why groq

  • Sub-100 ms first-token latency — best for realtime voice + chat.
  • OpenAI-compatible.

Env

VarPurpose
GROQ_API_KEYAPI key
✎ Edit this page on GitHub·Found a problem? Open an issue →·How to contribute →

On this page