On October 8, 2026, OpenAI Developers announced that Ultrafast mode for GPT-6.1 Sol is rolling out in the API, Codex and ChatGPT Work. OpenAI describes it as near GPT-6 Astra intelligence at up to 8 times the speed of GPT-6.1 Sol in Standard mode. The 8x figure comes from OpenAI and measures token generation speed.
OpenAI says Ultrafast is built for work where both speed and intelligence matter, such as debugging an outage, agents navigating apps, and live experiences where every second counts. In the API, developers call the Responses API with the model set to gpt-6.1-sol and the service_tier set to ultrafast, and the documentation also shows how to use it over WebSockets.
OpenAI lists API pricing for GPT-6.1 Sol in Ultrafast mode at 12 dollars per million input tokens and 60 dollars per million output tokens, which it says is 1.2 times the cost of GPT-6 Astra. According to the model documentation, Ultrafast prices are six times Standard, while Fast mode costs twice Standard.
In Codex and ChatGPT Work, Ultrafast is available on the Pro 500 plan, eligible usage-based Enterprise plans and credit-based Edu plans, and Enterprise admins must enable it. Ultrafast for GPT-6.1 Sol is offered in all supported regions with data residency in the US and EU, and OpenAI also added EU data residency for GPT-6.1 Sol Fast and GPT-6 Luna Fast.