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

OpenAI has announced Ultrafast, a new service tier that runs GPT-5.6 Sol (their most advanced model) up to 14 times faster than standard processing by using hardware from Cerebras, generating up to 750 output tokens per second (units of AI-generated text). This faster version allows businesses to use advanced AI for time-sensitive tasks like incident response, financial analysis, and customer support without sacrificing the model's intelligence.