OpenAI Introduces Ultrafast Version to Accelerate GPT-5.6 Sol Processing

OpenAI has launched a new mode called Ultrafast for its latest model, GPT-5.6 Sol, designed to drastically increase processing speed. - The Ultrafast mode delivers performance at 14 times the speed of standard processing, achieving up to 750 output tokens per second. - Previously, real-time speed was achieved by using smaller or specialized models, but Ultrafast represents progress towards doing more work per second with comprehensive models. - This mode is aimed at enhancing corporate workflows such as incident response, customer service, financial market analysis, and e-commerce. - OpenAI’s competitors, like Anthropic, have also launched accelerated model versions, but none match the speed offered by Ultrafast. - The preview release of Ultrafast is part of a partnership with chipmaker Cerebras and is limited to a small group of customers initially, with plans for wider availability as capacity expands.