OpenAI Partners with Cerebras to Bring High-Speed Inference to the Mainstream

OpenAI and Cerebras have signed a multi-year agreement to deploy 750 megawatts of Cerebras wafer-scale systems to serve OpenAI customers. This deployment will roll out in multiple stages beginning in 2026, making it the largest high-speed AI inference deployment in the world.

This partnership was a decade in the making. OpenAI and Cerebras were both founded around the same time with radically ambitious visions for the future of AI: OpenAI set out to create the software that powers AGI while Cerebras upended conventional wisdom about chip making to build a wafer scale AI processor that defied Moore’s Law. Our teams have met frequently since 2017, sharing research, early work, and a common belief that there would come a moment when model scale and hardware architecture would have to converge. That moment has arrived.

The release of ChatGPT set the direction for the entire AI industry. It showed the world what was possible. We are now in the next phase of AI adoption, the challenge is no longer proving what AI can do, but ensuring its benefits can reach everyone. The history of the technology industry has taught us a simple lesson: speed is the fundamental driver of technology adoption. The PC industry would not exist without the leap from kilohertz to megahertz to gigahertz, and the modern internet would not exist without the transition from dial-up to broadband.

Cerebras is the high-speed solution for AI. Whether running coding agents or voice chat, large language models on Cerebras deliver responses up to 15× faster than GPU-based systems. For consumers, this translates into greater engagement and novel applications. For the broader economy, where AI agents are expected to be a key growth driver over the coming decade, speed directly fuels productivity growth.

“OpenAI’s compute strategy is to build a resilient portfolio that matches the right systems to the right workloads. Cerebras adds a dedicated low-latency inference solution to our platform. That means faster responses, more natural interactions, and a stronger foundation to scale real-time AI to many more people,” said Sachin Katti of OpenAI.

For Cerebras, 2026 is shaping up to be an extraordinary year. In collaborating with OpenAI, the wafer-scale technology we pioneered will reach hundreds of millions—and eventually billions—of users. We’re thrilled to work alongside OpenAI to bring fast, frontier AI to people around the world.

Read more at: https://openai.com/index/cerebras-partnership/

Forward-Looking Statements

This blog contains forward-looking statements. You can identify forward-looking statements by the fact that they do not relate strictly to historical or current facts. These statements include words such as "will" and terms of similar meaning in connection with any discussion of this agreement between Cerebras and OpenAI. Forward-looking statements give our current expectations and projections relating to the information in this blog. Neither we nor any other person assumes responsibility for the accuracy and completeness of any of these forward-looking statements. The forward-looking statements included in this blog relate only to events and information as of the date hereof. Cerebras undertakes no obligation to update or revise any forward-looking statement as a result of new information, future events or otherwise, except as otherwise required by law. All forward-looking statements are subject to risks and uncertainties that may cause actual results to differ materially from those that we expected.