Pricing

Inference API access

Free Trial

Get started with $5 in free credits after making an account

Access to all Cerebras powered models
Up to 30x faster inference than GPU systems
Community support via Discord

get api key

Developer

Generous rate limits for power users

Everything in Free

Self-serve payment starting at just $10
10x higher rate limits than free tier
Higher priority processing

get api key

Enterprise

Highest throughput, custom weights, and guaranteed uptime

Everything in Developer, plus:

Highest rate limits for production workloads
Lowest latency with dedicated queue priority
Support for custom model weights
Model fine-tuning and training services
Dedicated support team with response time guarantees

contact sales

Developer Tier Pricing

*Preview models are intended for evaluation purposes only, and are not intended for use in production environments.

Partners

Get access to Cerebras Inference through our partner APIs

AWS Marketplace

Get started in minutes, test workloads with low latency, scale to real time applications, and move to production easily with simple controls and flexible pricing.

Buy with AWS

OpenRouter

Connect to Cerebras inference through OpenRouter and run models seamlessly via an intuitive, unified API.

learn more

HuggingFace

Access Cerebras-powered models directly from the Hugging Face Hub for high-performance inference and easy integration.

learn more

Vercel

Deploy and scale Cerebras inference endpoints effortlessly on Vercel with low latency and simple developer workflows.

learn more