Groq
Ultra-fast AI inference platform powered by custom LPU hardware, offering open-source models at low latency
Groq doesn't publish a pricing.md file yet.
This pricing data is community-maintained and last verified 2026-10-11.
Pricing Tiers
| Tier | Price | Includes | Overage |
|---|---|---|---|
|
Free
free
|
Free
|
— | — |
|
Pay-as-you-go
usage based
|
Free
|
— |
Llama 3.3 70B input: $0.59/1,000,000 per tokens
Llama 3.3 70B output: $0.79/1,000,000 per tokens
Llama 4 Scout input: $0.11/1,000,000 per tokens
Llama 4 Scout output: $0.34/1,000,000 per tokens
Llama 3.1 8B input: $0.05/1,000,000 per tokens
Llama 3.1 8B output: $0.08/1,000,000 per tokens
Whisper Large v3 Turbo: $0.04 per hours
|
Portability
Switching Cost
drop-in
Open Standard
OpenAI-compatible Chat Completions API
What You Lose
LPU-accelerated inference speed; models themselves are open-source and portable
Transparency Score
B
70/100
Pricing Transparency Score
Score breakdown
✕
Publishes pricing.md
0/30
✓
Free tier available
10/10
✓
All prices public
15/15
✓
Usage pricing documented
15/15
✓
Portability documented
10/10
✓
Open standard
10/10
✓
Recently verified
10/10