GPT-5.6 Sol Ultrafast Mode (Limited Preview)

A new OpenAI API service tier that runs GPT-5.6 Sol far faster than standard processing, open to a small set of customers.

Runs GPT-5.6 Sol up to 14 times faster than Standard processing, generating up to 750 output tokens per second
Runs on Cerebras hardware, with the same intelligence as GPT-5.6 Sol on Standard
OpenAI frames it as removing the usual tradeoff where real-time speed meant picking a smaller or more specialized model
Available in the OpenAI API only, as a limited preview to a select group of customers, expanding as capacity grows
Early scenarios OpenAI names include incident response, voice, customer support, commerce, developer agents, and financial research