Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed
OpenAI has announced Ultrafast, a new API service tier that runs GPT-5.6 Sol up to 14 times faster than standard versions, powered by Cerebras hardware and delivering up to 750 output tokens per second. The service is being offered as a preview tier for developers seeking higher-speed inference performance.
Source: OpenAI