Cerebras Inference
Under review· 2Ultra-fast AI inference API powered by Cerebras hardware delivering 20x faster speeds than GPU-based providers for open-source and production models.
Cerebras Inference has 5 plans: a free plan, paid plans from $50/month and custom pricing for larger teams. We last read its pricing page on 3 October 2026. We have not recorded a price change.
Cerebras Inference plans and prices
Free
$0
- Access to all Cerebras models
- World's fastest inference
- Community support via Discord
Developer
usage basedCustom
Starting at $10
- All Free features
- Self-serve payment from $10
- 10x higher rate limits than Free
- Higher priority processing
Enterprise
Custom
- Highest throughput
- Custom weights
- Guaranteed uptime
- Lowest latency with dedicated queue priority
- Support for custom model weights
- Model fine-tuning and training services
- Dedicated support team with response time guarantees
Cerebras CodePro
monthly$50/mo
- Access to top open source model — Yes
- Tokens per day — 24 million
- Value per day — $48
- Ideal for — indie devs, simple agentic workflows, and weekend projects
Max
monthly$200/mo
- Access to top open source model — Yes
- Tokens per day — 120 million
- Value per day — $240
- Ideal for — full-time development, IDE integrations, code refactoring, and multi-agent systems
Price history
Last 2 recorded changes
| Date | Plan | Change | Old | New | Δ% |
|---|---|---|---|---|---|
| Jul 28, 2026 | Max | New plan | — | $200 | — |
| Jul 28, 2026 | Cerebras CodePro | New plan | — | $50 | — |
Other AI & ML products
No confirmed alternatives yet.