Skip to main content
kRouter
All providers

Pay-per-token

groq/

Groq

Wafer-fast inference for Llama, Mixtral.

groq.com

Quick setup

  1. Open the kRouter dashboard at http://localhost:20128

  2. Go to Providers → click Groq

  3. Paste your API key, click Save

  4. Test the connection

Use in your IDE

Point any OpenAI-compatible client at kRouter using your local API key.

ide configbash
# Endpoint
http://localhost:20128/v1

# API key (from Dashboard → API Keys)
sk-krouter-XXXX

# Model
groq/llama-4-405b

How Groq billing works with kRouter

Groq is pay-per-token. You bring your own API key and kRouter routes to it, so you keep your own rate limits and billing relationship. kRouter authenticates it via apikey. 7 models are routable as groq/<model>.

Through kRouter, Groq serves chat and code completion, image understanding (OCR / vision-to-text), speech-to-text, exposed on /v1/audio/transcriptions. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from Groq is a one-line model change in your client rather than a rewrite.

Groq models & pricing

Prices are USD per 1M tokens, cheapest first. kRouter bills nothing on top; this is the provider's own rate.

ModelRoute asInput /1MOutput /1M
Qwen3 32Bgroq/qwen/qwen3-32b$0.50$2.00
Llama 3.3 70Bgroq/llama-3.3-70b-versatile——
Llama 4 Maverickgroq/meta-llama/llama-4-maverick-17b-128e-instruct——
GPT-OSS 120Bgroq/openai/gpt-oss-120b——
Whisper Large v3groq/whisper-large-v3——
Whisper Large v3 Turbogroq/whisper-large-v3-turbo——
Distil Whisper Large v3 ENgroq/distil-whisper-large-v3-en——

Groq FAQ

Is Groq free through kRouter?

Groq is pay-per-token: you bring your own API key and are billed by Groq at their rates. kRouter adds nothing on top and is free and MIT-licensed.

How do I use Groq with Claude Code or Cursor?

Connect Groq in the kRouter dashboard, then point your tool at kRouter's local endpoint (http://localhost:20128/v1) with a kRouter API key. Any OpenAI-compatible client works, and models are addressed as groq/<model>.

Which Groq models can kRouter route to?

7 models, including Llama 3.3 70B, Llama 4 Maverick, Qwen3 32B. Every one is addressed as groq/<model> from any client.

What happens when Groq is rate limited?

kRouter detects the limit, parks that account until its real reset time, and fails over to your next connected account or provider — so the request still completes instead of erroring.