OpenAI has introduced a new mode called Ultrafast, designed to significantly increase the speed of its latest and most powerful model, GPT-5.6 Sol.
The company says Ultrafast can operate at up to 14 times the speed of standard processing, reaching as much as 750 output tokens per second. Tokens are the individual pieces of text that large language models process and generate when responding to users.
“Until now, getting real-time speed typically meant choosing a smaller or more specialized model,” OpenAI said in its announcement. The company says Ultrafast represents a different approach by focusing on delivering more useful work per second.
Other AI companies have also introduced faster versions or modes for their models. Anthropic, for example, offers a Fast Mode for Claude, although OpenAI says Ultrafast is designed to deliver a substantially higher level of speed.
OpenAI expects the faster version of GPT-5.6 Sol to be useful across a range of business workflows. Potential applications include incident response, customer service and support, financial market analysis and e-commerce.
Ultrafast is currently available as a preview and is powered by OpenAI’s partnership with chipmaker Cerebras. The preview is initially limited to a small group of customers, with OpenAI saying it plans to expand availability as more capacity becomes available.
If this article helped you, please consider supporting our work. Every small contribution keeps Abijita.com independent and running.
