Groq

Groq API Β· Ultra-fast LLM inference on custom LPU hardware.

Groq logo

Groq

LLM API
Groq API

Ultra-fast LLM inference on custom LPU hardware.

All Models & Pricing
Model Input / 1M tokCached / 1M tokOutput / 1M tok
Free Tier
Rate-limited free access for testing and prototyping
Rate-limited free access for testing and prototyping
Free tier β€” β€”
llama-3.3-70b
Llama 3.3 70B β€” fast inference, strong quality
$0.590 β€” $0.790
llama-3.1-8b
Very cheap, fastest option for simple tasks
$0.050 β€” $0.080
mixtral-8x7b
Mixtral MoE β€” balanced speed and quality
$0.240 β€” $0.240
gemma2-9b
Google Gemma 2 9B on Groq LPU
$0.200 β€” $0.200
Price History

Checked daily by our automated scraper.

Groq
Get started with Groq

Ultra-fast LLM inference on custom LPU hardware.

View official pricing β†’
Prices verified on official pricing page. Always confirm before purchase.
Details
Category
LLM API
Last checked
2026-03-29 21:44 EST
Last price change
2026-03-14
Compare with alternatives
See how Groq stacks up against other providers.
Browse API providers β†’
CloudMart AI
Compute
What are you building?
Ask about providers, compare options, or get a plan recommendation.
Compare:
Report a problem