Cerebras Powers Perplexity Sonar with Industry’s Fastest AI Inference

SUNNYVALE, Calif., Feb. 13, 2025 — Cerebras Systems has announced its pivotal role in powering Sonar, an advanced model optimized for Perplexity search. Built on the robust foundation of Llama 3.3 70B, Sonar represents a significant advancement in answer quality, factuality, and readability, setting new standards for user satisfaction in search technology. The new Sonar search experience, powered by Cerebras, is available now for Perplexity Pro users.

“Our partnership with Cerebras has been instrumental in bringing Sonar to life,” said Denis Yarats, CTO, Perplexity. “Cerebras’ cutting-edge AI inference infrastructure has enabled us to achieve unprecedented speeds and efficiency, setting a new standard for search. We look forward to continuing to work with a company that shares our commitment to innovation and user satisfaction.”

Unparalleled Inference Infrastructure

At the heart of Sonar’s blazing fast performance is Cerebras’ state-of-the-art AI inference infrastructure. As the world’s fastest AI inference provider, Cerebras enables Sonar to process 1,200 tokens per second, delivering near-instant answer generation. This unprecedented speed ensures that users receive accurate and relevant information in real-time, transforming the way they search and discover information.

A New Era in Search Technology

The launch of Perplexity Sonar powered by Cerebras marks a monumental shift in the search technology landscape. By combining advanced model training with unparalleled inference speed, we are redefining what is possible in terms of answer quality and user experience. Whether you are seeking quick answers to complex questions or need reliable information on the go, Sonar delivers with unmatched precision and speed.

Commitment to Innovation

“At Cerebras, we are dedicated to pushing the boundaries of what is possible in AI and machine learning,” said Andrew Feldman, CEO and co-founder, Cerebras. “Our collaboration with Perplexity on Sonar accelerates our vision in bringing fast, accurate, and reliable information to everyone with real-time accessible search.”

About Cerebras Systems

Cerebras Systems is a team of pioneering computer architects, computer scientists, deep learning researchers, and engineers of all types. We have come together to accelerate generative AI by building from the ground up a new class of AI supercomputer. Our flagship product, the CS-3 system, is powered by the world’s largest and fastest commercially available AI processor, our Wafer-Scale Engine-3. CS-3s are quickly and easily clustered together to make the largest AI supercomputers in the world, and make placing models on the supercomputers dead simple by avoiding the complexity of distributed computing. Cerebras Inference delivers breakthrough inference speeds, empowering customers to create cutting-edge AI applications. Leading corporations, research institutions, and governments use Cerebras solutions for the development of pathbreaking proprietary models, and to train open-source models with millions of downloads. Cerebras solutions are available through the Cerebras Cloud and on premise.

Source: Cerebras Systems