OpenAI adds Ultrafast mode for GPT-6.1 Sol in the Responses API
Original titleAdded Ultrafast mode for GPT-6.1 Sol in the Responses API.
AISummary
OpenAI added an Ultrafast mode for gpt-6.1-sol in the Responses API, enabled with service_tier set to "ultrafast". The mode reduces the time between generated output tokens and is available to all API users, subject to rate limits, with global processing and US and EU data residency. Pricing is listed separately under Ultrafast pricing.
AIWhy it matters
The changelog gives the exact request parameter and access terms, so developers can check whether the mode fits their latency and residency needs.
Source: OpenAI API Changelog · developers.openai.comPublished · added here