Cerebras

Cerebras Pricing

Visit cerebras.ai →

Compare Cerebras inference pricing for 2 models. The world's fastest inference — up to 20x faster than alternatives.

Last updated: Nov 21, 2026

Get our weekly newsletter on pricing changes, new releases, and tools.

Cerebras has a free tier

$5 (30-day trial) — see the full Cerebras free tier guide

Cerebras offers 2 models with published API pricing. The cheapest is GPT-OSS-120b at $0.350 per million input tokens. Input prices range from $0.350 to $0.990 per million tokens.

2
Models
~3,000
Fastest (tok/s)
$0.35
Cheapest Input/1M
0
Preview Models
Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Speed (tok/s)
Context
Status
Input/1M
Output/1M
~3,000
—
GA
$0.350
$0.750
~1,850
—
GA
$0.990
$1.490

Pricing from Cerebras. Prices per 1M tokens. Preview models (*) are not recommended for production use.

Frequently Asked Questions

Cerebras offers 2 models with published per-token API pricing on Price Per Token.
GPT-OSS-120b is the cheapest Cerebras model at $0.350 per million input tokens.

Compare Cerebras with Other Providers