Groq

Direct

Fast inference on LPU hardware. Best-in-class throughput for open-weight models including Llama and Mistral.

Provider Info

"API Env Var" GROQ_API_KEY

"Rate Limits" 30 RPM, 14.4K req/day

Llama 3.3 70B

Llama 4 Scout

Llama 4 Maverick

Kimi K2

Mixtral 8x7B

Qwen 2.5 72B

Gemma 2 9B

Free

$0/mo

30 RPM, 14.4K req/day

All available models · Standard rate limits

Developer

$0/mo

60 RPM, 14.4K req/day

All models · Higher rate limits

Pro

$75.00/mo

600 RPM, Unlimited requests

Priority inference · Higher rate limits · Longer context

"Free Tier Available"

30 RPM, 1K–14.4K req/day, no credit card — No credit card required

DRACON20

20% off your first Pro plan

"Get deal →"

affiliate

Groq Affiliate Program

"Commission: Varies (one-time)"

"Join Program"