Groq

Groq provides ultra-fast inference on open-source models (Llama, Gemma, Mistral, and more) using custom LPU hardware. OpenClaw connects to Groq through its OpenAI-compatible API.

Provider: groq
Auth: GROQ_API_KEY
API: OpenAI-compatible

Quick start

Get an API key from console.groq.com/keys.
Set the API key:

export GROQ_API_KEY="gsk_..."

Set a default model:

{
  agents: {
    defaults: {
      model: { primary: "groq/llama-3.3-70b-versatile" },
    },
  },
}

Config file example

{
  env: { GROQ_API_KEY: "gsk_..." },
  agents: {
    defaults: {
      model: { primary: "groq/llama-3.3-70b-versatile" },
    },
  },
}

Audio transcription

Groq also provides fast Whisper-based audio transcription. When configured as a media-understanding provider, OpenClaw uses Groq's whisper-large-v3-turbo model to transcribe voice messages.

{
  media: {
    understanding: {
      audio: {
        models: [{ provider: "groq" }],
      },
    },
  },
}

Environment note

If the Gateway runs as a daemon (launchd/systemd), make sure GROQ_API_KEY is available to that process (for example, in ~/.openclaw/.env or via env.shellEnv).

Available models

Groq's model catalog changes frequently. Run openclaw models list | grep groq to see currently available models, or check console.groq.com/docs/models.

Popular choices include:

Llama 3.3 70B Versatile - general-purpose, large context
Llama 3.1 8B Instant - fast, lightweight
Gemma 2 9B - compact, efficient
Mixtral 8x7B - MoE architecture, strong reasoning

2.0 KiB Raw Blame History