OpenAI added an Ultrafast mode for GPT-6.1 Sol in the Responses API on October 8, 2026, according to its developer changelog.
What to know
- You select it with
service_tier: "ultrafast"ongpt-6.1-sol. OpenAI says it reduces the time between generated output tokens. - It is available to all API users, subject to rate limits, with global processing and US and EU data residency.
- Ultrafast has its own pricing; OpenAI points to an Ultrafast pricing page rather than a single number in the changelog.
- On October 7 the same changelog also notes that the
chat-latestsnapshot, which points to the latest model in ChatGPT for Plus, Pro, Business and Enterprise users, was updated. OpenAI recommends the GPT-6 family for production API use.
Why it matters
Faster output matters most for live tools and agents. For everyday writing and prompt work in ChatGPT you will not need to change anything. See ChatGPT, our GPT-6.1 Sol summary and the model tracker.
Source: OpenAI API changelog. We summarise in our own words; check the source for the full details.