OpenAI adds Ultrafast mode for GPT-6.1 Sol
The Responses API can run gpt-6.1-sol with service_tier ultrafast so tokens arrive with less delay.
Official source (opens in a new tab)
The OpenAI API changelog for 8 October 2026 adds Ultrafast mode for GPT-6.1 Sol. Call gpt-6.1-sol in the Responses API with service_tier set to "ultrafast" to shorten the time between output tokens. OpenAI says it is available to all API users, subject to rate limits, with global processing and US and EU data residency.
Who it's for: developers already calling GPT-6.1 Sol who care about how fast the tokens stream. It is not a new chat app.
Fits: Best for Vibe Coding, on the API side of that list, next to Codex rather than instead of an editor.