Skip to main content

Groq

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

Getting started

1

Get an API key

Create an API key at console.groq.com/keys.
2

Set the API key

3

Set a default model

Config file example

Available models

Groq’s model catalog changes frequently. Run velaclaw models list | grep groq to see currently available models, or check console.groq.com/docs/models.
Use velaclaw models list --provider groq for the most up-to-date list of models available on your account.

Audio transcription

Groq also provides fast Whisper-based audio transcription. When configured as a media-understanding provider, Velaclaw uses Groq’s whisper-large-v3-turbo model to transcribe voice messages through the shared tools.media.audio surface.
If the Gateway runs as a daemon (launchd/systemd), make sure GROQ_API_KEY is available to that process (for example, in ~/.velaclaw/.env or via env.shellEnv).
Keys set only in your interactive shell are not visible to daemon-managed gateway processes. Use ~/.velaclaw/.env or env.shellEnv config for persistent availability.

Model selection

Choosing providers, model refs, and failover behavior.

Configuration reference

Full config schema including provider and audio settings.

Groq Console

Groq dashboard, API docs, and pricing.

Groq model list

Official Groq model catalog.