Docs·API

Groq

InferenceFREE TIER

LPU inference — fastest tokens per second on the market

groq.com ↗Pricing →/api/v1/latency

Operational

All systems responding normally

Last checked 21/05/2026, 9:48:28 am

308ms response

Uptime History100.00% uptime

2026-05-16Today

Uptime

100.00%

Avg Latency

330ms

P95 Latency

415ms

Fastest

199ms

Checks

150

Response Time

Last 60 checks

199ms min330ms avg528ms max

💰 Pricing

llama-3.3-70bFREE

Input: $0.59/1MOutput: $0.79/1M

Fastest inference. mixtral-8x7b: $0.24/$0.24

14,400 req/day free

⚡ Rate Limits

free

RPM: 30TPM: 6,000RPD: 14,400TPD: 500,000

Per-model limits. llama-3.3-70b: 6k TPM free.

dev

RPM: 100TPM: 15,000

$0 plan with credit card.

🤖 Models (2)

Model	Task	Context	Vision	Tools	JSON
Llama 3.3 70B LPU inference — extremely fast	llm	128k	—	✅	✅
Mixtral 8x7B Cheapest on Groq: $0.24/$0.24	llm	33k	—	✅	✅

Recent Checks

Showing last 15

Operational

308ms21 May, 09:48 am

Operational

280ms21 May, 09:16 am

Operational

379ms21 May, 08:42 am

Operational

307ms21 May, 08:00 am

Operational

389ms21 May, 07:13 am

Operational

345ms21 May, 06:28 am

Operational

368ms21 May, 05:31 am

Operational

374ms21 May, 04:36 am

Operational

452ms21 May, 03:44 am

Operational

337ms21 May, 02:42 am

Operational

367ms21 May, 01:34 am

Operational

361ms21 May, 12:16 am

Operational

381ms20 May, 11:19 pm

Operational

442ms20 May, 10:12 pm

Operational

339ms20 May, 09:18 pm

API Quick Access

Health Latency Freshness Pricing Models

Other Inference Providers

Cerebras

Wafer-scale chip inference — 1,000+ tokens/sec

Together AI

Open-source model inference — Llama, Mixtral, FLUX

Fireworks AI

Fast open-model inference — FireFunction, Llama, Mixtral

OpenRouter

Unified API across 200+ models — route by price or speed

Hugging Face

Serverless inference API — 100k+ open models on demand

fal.ai

Ultra-fast image & video model inference for agents

Visit Groq →View Pricing ← All Providers