Ultrafast mode preview: GPT‑5.6 Sol at up to 14X the speed in the API

API
1

OpenAI is previewing Ultrafast, a new service tier that runs GPT‑5.6 Sol up to 14× faster than Standard processing.

Powered by Cerebras, Ultrafast can generate up to 750 output tokens per second, bringing frontier intelligence to products and workflows where every second matters.

GPT‑5.6 Sol on Ultrafast mode is launching first in the OpenAI API. It is currently available as a limited preview to a select group of customers, with access expanding as capacity grows.

Sign up for Ultrafast access updates

Learn more in the official announcement.

5

Never was the :rocket: emoji more missing from the reactions list!

6

So, now we can use our week usage on the $200 plan in 12 minutes rather than 3 hours? Sounds incredible!

7

Only on the API for now … but of course I’m sure some version of this may arrive on Codex via ChatGPT auth soon …