OpenAI previews Ultrafast mode for GPT-5.6 Sol
OpenAI has introduced Ultrafast, a preview mode intended to accelerate its latest and most powerful model, GPT-5.6 Sol. The company says the mode can operate at up to 14 times the speed of standard processing and generate as many as 750 output tokens per second. Tokens are the individual pieces of text produced by a language model during an interaction.
OpenAI says Ultrafast is aimed at making real-time access to a more capable model possible, rather than requiring users to switch to a smaller or more specialized system. The company identifies incident response, customer service and support, financial market analysis, and e-commerce as potential corporate applications. Ultrafast is powered by OpenAI’s partnership with chipmaker Cerebras and is currently available only to a small group of customers. OpenAI plans to broaden access as capacity increases. Competitors have also introduced faster model options; Anthropic’s Claude has a fast mode, although OpenAI says its offering reaches a different level of speed.
Written by Sakhanda Wire AI from reporting by TechCrunch. Facts, quotes and full context are in the original article below.