OpenAI Launches Ultrafast Mode for GPT-5.6 Sol, Boosting Processing Speed

OpenAI has introduced a new mode called Ultrafast for its latest model, GPT-5.6 Sol, aiming to significantly enhance processing speed. According to the company, Ultrafast operates at 14 times the speed of standard processing, capable of generating up to 750 output tokens per second. These tokens represent the individual pieces of text produced during interactions with users.

In a blog post released on Thursday, OpenAI noted, “Until now, getting real-time speed typically meant choosing a smaller or more specialized model. Ultrafast points to progress in a new direction: more useful work per second.”

OpenAI’s competitors, including Anthropic, have also rolled out accelerated versions of their AI models. However, their offerings, like Claude’s fast mode, do not match the speed of OpenAI’s new feature.

The Ultrafast mode is designed for various corporate applications, including incident response, customer service, financial market analysis, and e-commerce. Currently in preview, this feature is supported by a partnership with chipmaker Cerebras and is being made available to a limited group of customers. OpenAI has indicated that broader access will follow as capacity expands.