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

OpenAI has introduced Ultrafast, a new API service tier for GPT-5.6 Sol that utilizes Cerebras infrastructure to increase output speeds by up to 14 times. This service reaches rates of 750 tokens per second, significantly reducing latency for developers. The update is intended for real-time applications where rapid response times are critical, marking a shift toward high-throughput model performance in production environments.