Groq

Groq

active

High-speed LLM inference powered by LPU hardware — free tier includes Llama, Kimi, Qwen and more with generous rate limits.

https://api.groq.com/openai/v1

Avg Latency

90-day Uptime

%

Rate Limits

30 RPM / 1,000 RPD

Sign-up Required

Yes

Info

Base URL https://api.groq.com/openai/v1
Sign-up Required Yes
Credit Card Not required
Context Window 128K
Last Verified 2026-03-30
fast-inferenceopenai-compatiblellamafunction-call

Models (14)

allam-2-7b

CTX: 4K · 30 RPM

active

groq/compound

CTX: 128K · 30 RPM

active

groq/compound-mini

CTX: 128K · 30 RPM

active

llama-3.1-8b-instant

CTX: 128K · 30 RPM

active

llama-3.3-70b-versatile

CTX: 128K · 30 RPM

active

meta-llama/llama-4-scout-17b-16e-instruct

CTX: 10M · 30 RPM

active

meta-llama/llama-prompt-guard-2-22m

CTX: 512 · 30 RPM

active

meta-llama/llama-prompt-guard-2-86m

CTX: 512 · 30 RPM

active

moonshotai/kimi-k2-instruct

CTX: 128K · 60 RPM

active

moonshotai/kimi-k2-instruct-0905

CTX: 128K · 60 RPM

active

openai/gpt-oss-120b

CTX: 128K · 30 RPM

active

openai/gpt-oss-20b

CTX: 128K · 30 RPM

active

openai/gpt-oss-safeguard-20b

CTX: 128K · 30 RPM

active

qwen/qwen3-32b

CTX: 128K · 60 RPM

active

Quick Start

bash
export API_KEY="your_api_key_here"
curl https://api.groq.com/openai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "llama-3.3-70b-versatile",
    "messages": [
      {"role": "user", "content": "Hello! How are you?"}
    ]
  }'