Providers

Groq

Groq provides ultra-fast inference on open-weight models (Llama, Gemma, Kimi, Qwen, GPT OSS, and more) using custom LPU hardware. The Groq plugin registers both an OpenAI-compatible chat provider and an audio media-understanding provider.

Property	Value
Provider id	`groq`
Plugin	official external package
Auth env var	`GROQ_API_KEY`
API	OpenAI-compatible (`openai-completions`)
Base URL	`https://api.groq.com/openai/v1`
Audio transcription	`whisper-large-v3-turbo` (default)
Suggested chat default	`groq/openai/gpt-oss-120b`

Install plugin

Install the official plugin:

bash

openclaw plugins install @openclaw/groq-provider

Installation applies to a running Gateway automatically; otherwise it takes effect on the next startup. See Apply changes and inspect.

Getting started

Get an API key

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

Set the API key

bash

export GROQ_API_KEY=gsk_...

Set a default model

json5

{  agents: {    defaults: {      model: { primary: "groq/openai/gpt-oss-120b" },    },  },}

Verify the catalog is reachable

bash

openclaw models list --provider groq

Config file example

json5

{  env: { vars: { GROQ_API_KEY: "gsk_..." } },  agents: {    defaults: {      model: { primary: "groq/openai/gpt-oss-120b" },    },  },}

Built-in catalog

OpenClaw ships a manifest-backed Groq catalog of reasoning models. Run openclaw models list --provider groq to see the static rows for your installed version, or check console.groq.com/docs/models for Groq's authoritative list.

Model ref	Name	Reasoning	Input	Context
`groq/openai/gpt-oss-120b`	GPT OSS 120B	yes	text	131,072
`groq/openai/gpt-oss-20b`	GPT OSS 20B	yes	text	131,072
`groq/openai/gpt-oss-safeguard-20b`	Safety GPT OSS 20B	yes	text	131,072
`groq/qwen/qwen3.6-27b`	Qwen 3.6 27B	yes	text	131,072

Reasoning models

Groq's GPT OSS reasoning models map OpenClaw's shared /think levels onto reasoning_effort values of low, medium, or high. /think off or /think none omits reasoning_effort from those requests rather than sending a disabled value.

Qwen 3.6 27B is text-only on Groq and supports two wire reasoning modes. /think off or /think none sends reasoning_effort: "none"; every enabled level sends "default". When reasoning is enabled on Groq Qwen models, OpenClaw requests reasoning_format: "parsed" so reasoning stays in thinking blocks instead of visible answer text. Disabled reasoning and GPT OSS requests are left unchanged by this format hook.

See Thinking modes for the shared /think levels and how OpenClaw translates them per provider.

Audio transcription

Groq's plugin also registers an audio media-understanding provider so voice messages can be transcribed through the shared tools.media.audio surface.

Property	Value
Shared model path	`tools.media.models`
Default base URL	`https://api.groq.com/openai/v1`
Default model	`whisper-large-v3-turbo`
Auto priority	20
API endpoint	OpenAI-compatible `/audio/transcriptions`

To make Groq the default audio backend:

json5

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

Environment availability for the daemon

If the Gateway runs as a managed service (launchd, systemd, Docker), GROQ_API_KEY must be visible to that process — not just to your interactive shell.

Custom Groq model ids

OpenClaw accepts any Groq model id at runtime. Use the exact id shown by Groq and prefix it with groq/. The static catalog covers the common cases; uncatalogued ids fall through to the default OpenAI-compatible template.

json5

{  agents: {    defaults: {      model: { primary: "groq/<your-model-id>" },    },  },}

Model providers

Choosing providers, model refs, and failover behavior.

Thinking modes

Reasoning effort levels and provider-policy interaction.

Configuration reference

Full config schema including provider and audio settings.

Groq Console

Groq dashboard, API docs, and pricing.

Was this useful?