Cerebras
Ultra-fast AI inference platform with custom wafer-scale chips, 20x faster than conventional GPU inference
Cerebras 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 3.1 8B Input: $0.1/1,000,000 per tokens
Llama 3.1 8B Output: $0.1/1,000,000 per tokens
GPT OSS 120B Input: $0.35/1,000,000 per tokens
GPT OSS 120B Output: $0.75/1,000,000 per tokens
|
|
Enterprise
custom
|
Contact Sales
|
— | — |
Portability
Switching Cost
drop-in
Open Standard
OpenAI-compatible API
What You Lose
Ultra-fast inference speed, Cerebras-specific model optimizations
Transparency Score
C
55/100
Pricing Transparency Score
Score breakdown
✕
Publishes pricing.md
0/30
✓
Free tier available
10/10
✕
All prices public
0/15
✓
Usage pricing documented
15/15
✓
Portability documented
10/10
✓
Open standard
10/10
✓
Recently verified
10/10