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 (Zac Hall/9to5Mac)

Techmeme ·

OpenAI previewed a Cerebras-powered API tier that serves GPT-5.6 Sol at much higher generation speeds for latency-sensitive applications.

Categories: Model Releases

Excerpt

<a href="https://9to5mac.com/2026/08/13/openai-previews-ultrafast-gpt-5-6-sol-running-up-to-14-times-faster/"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260813/i39.jpg" vspace="4" /></a> <p><a href="https://www.techmeme.com/260813/p39#a260813p39" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> Zac Hall / <a href="https://9to5mac.com/">9to5Mac</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://9to5mac.com/2026/08/13/openai-previews-ultrafast-gpt-5-6-sol-running-up-to-14-times-faster/">OpenAI previews Ultrafast, an API tier powered by Cerebras that runs GPT-5.6 Sol up to 14&times; faster and generates up to 750 output tokens per second</a></b></span>&nbsp; &mdash;&nbsp; OpenAI is previewing a new way to run its most capable GPT-5.6 model at dramatically higher speeds.&nbsp; The company says its new Ultrafast &hellip; </p>

Read at source: https://www.techmeme.com/260813/p39#a260813p39