Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed

OpenAI is previewing Ultrafast, a new API service tier for GPT-5.6 Sol that runs up to 14 times faster than standard processing. Powered by Cerebras hardware, this deployment delivers up to 750 output tokens per second to support real-time AI workloads. Through a multi-year partnership, OpenAI and Cerebras are expanding inference infrastructure, planning 750 megawatts of ultra-low-latency capacity. This development enables frontier-model intelligence for enterprise workflows where latency significantly impacts business processes and user experiences.