§ models · storyline

OpenAI previews Cerebras-powered Ultrafast API tier, 14× faster

OpenAI previews Ultrafast, an API tier powered by Cerebras that runs GPT-5.6 Sol at up to 750 tokens per second, roughly 14× faster than standard inference.

today · 19:35:01 · primary fetch3 sourcesupdated today · 20:10:02

Zac Hall / 9to5Mac: OpenAI previews Ultrafast, an API tier powered by Cerebras that runs GPT-5.6 Sol up to 14× faster and generates up to 750 output tokens per second — OpenAI is previewing a new way to run its most capable GPT-5.6 model at dramatically higher speeds.

The company says its new Ultrafast …

read full article on 9to5mac.com ↗

§ sources3 publications · timeline below

9to5mac.comOpenAI previews Ultrafast, an API tier powered by Cerebras that runs GPT-5.6 Sol up to 14× faster and generates up to 750 output tokens per second (Zac Hall/9to5Mac)primary19:35:01
cerebras.aiAccelerating GPT-5.6 Sol Ultrafast20:10:02
OpenAIPreviewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed19:02:46

§ how this story moved

19:02:46primary — OpenAI publishes the launch post.
19:35:019to5Mac picks up coverage.
20:10:02HN Algolia — OpenAI / GPT picks up coverage.