Ultrafast mode for GPT-6.1 Sol
OpenAI added Ultrafast mode for GPT-6.1 Sol in the Responses API, a service tier that reduces the time between generated output tokens.
Developers set gpt-6.1-sol with service_tier "ultrafast" in the Responses API to get faster output token generation. It is available to all API users, subject to rate limits, with global processing and US and EU data residency. The changelog points to a separate Ultrafast pricing page, which was not read, so the price is not recorded here.
- Date
- Thursday 8 October 2026
- Lab
- OpenAI
- Kind
- feature
- Access
- closed API
This is a serving tier for the existing GPT-6.1 Sol model released 2026-09-29, so it is recorded as a feature and not as a new model.
Sources
This record was checked against its sources on 8 October 2026. How we check