Cerebras<br>Skip to main content

Products

Customers

Developers

Resources

Pricing<br>Company

Contact usGet Started

*:first-child]:mt-0 [&>*:last-child]:mb-0">Flex and Cerebras are scaling American manufacturing of AI supercomputers in Silicon Valley. Learn more >>

*:first-child]:mt-0 [&>*:last-child]:mb-0">Pricing

Inference API access

*:first-child]:mt-0 [&>*:last-child]:mb-0">Free Trial<br>Get started with $5 in free credits after making an account<br>Access to all Cerebras powered models<br>The world’s fastest inference – 20x faster than OpenAI and Anthropic<br>Community support via Discord

get api key<br>*:first-child]:mt-0 [&>*:last-child]:mb-0">Developer<br>Generous rate limits for power users<br>Everything in Free<br>Self-serve payment starting at just $10<br>10x higher rate limits than free tier<br>Higher priority processing

get api key<br>*:first-child]:mt-0 [&>*:last-child]:mb-0">Enterprise<br>Highest throughput, custom weights, and guaranteed uptime<br>Everything in Developer, plus:<br>Highest rate limits for production workloads<br>Lowest latency with dedicated queue priority<br>Support for custom model weights<br>Model fine-tuning and training services<br>Dedicated support team with response time guarantees

contact sales

Cerebras Code

*:first-child]:mt-0 [&>*:last-child]:mb-0">Pro<br>$50/month<br>Top open source model access with fast, high-context completions.<br>Send up to 24 million tokens/day ($48/day worth of value)<br>Ideal for indie devs, simple agentic workflows, and weekend projects.

sold out<br>*:first-child]:mt-0 [&>*:last-child]:mb-0">Max<br>$200/month<br>Top open source model for heavy coding workflows.<br>Send up to 120m tokens/day ($240/day worth of value)<br>Ideal for full-time development, IDE integrations, code refactoring, and multi-agent systems.

sold out

*:first-child]:mt-0 [&>*:last-child]:mb-0">Developer Tier Pricing<br>*Preview models are intended for evaluation purposes only, and are not intended for use in production environments.<br>** Deprecation date Aug 17, 2026.

*:first-child]:mt-0 [&>*:last-child]:mb-0">Partners<br>Get access to Cerebras Inference through our partner APIs

*:first-child]:mt-0 [&>*:last-child]:mb-0">AWS Marketplace

*:first-child]:mt-0 [&>*:last-child]:mb-0">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

*:first-child]:mt-0 [&>*:last-child]:mb-0">OpenRouter<br>Connect to Cerebras inference through OpenRouter and run models seamlessly via an intuitive, unified API.

*:first-child]:mt-0 [&>*:last-child]:mb-0">

learn more

*:first-child]:mt-0 [&>*:last-child]:mb-0">HuggingFace<br>Access Cerebras-powered models directly from the Hugging Face Hub for high-performance inference and easy integration.

*:first-child]:mt-0 [&>*:last-child]:mb-0">

learn more

*:first-child]:mt-0 [&>*:last-child]:mb-0">Vercel<br>Deploy and scale Cerebras inference endpoints effortlessly on Vercel with low latency and simple developer workflows.

*:first-child]:mt-0 [&>*:last-child]:mb-0">

learn more

Follow

Get Updates<br>Newsletter Signup

Company<br>About Us<br>Careers<br>Contact Us<br>Investor Relations<br>Website Terms of Use<br>Privacy Policy<br>Cookie Policy<br>Other Terms & Policies<br>Service Status<br>Trust Center

News<br>Newsroom<br>In the News<br>Press kit

Insights<br>Customer Spotlight<br>Blog<br>Publications<br>Whitepapers

Performance comparisons are based on third-party benchmarking or internal testing. Observed inference speed improvements versus GPU-based systems may vary depending on workload, configuration, date and models being tested.<br>info@cerebras.ai<br>1237 E. Arques Ave<br>Sunnyvale, CA 94085

© 2026 Cerebras.<br>All rights reserved.