OpenAI has introduced Ultrafast, a new mode for GPT-5.6 Sol that the company says can process tasks at up to 14 times the speed of standard processing.
According to OpenAI, Ultrafast can generate as many as 750 output tokens per second. The company said the mode is intended to deliver faster real-time performance without requiring users to switch to a smaller or more specialized model.
OpenAI is positioning the feature for business workflows including incident response, customer service and support, financial market analysis, and e-commerce.
Ultrafast is currently available in preview to a limited group of customers. The company said access will expand as capacity grows. The feature is powered by OpenAI’s partnership with chipmaker Cerebras.
The launch comes as other AI providers also work on faster model experiences, including Anthropic’s fast mode for Claude.
Source: TechCrunch
