Accelerating GPT-5.6 Sol Ultrafast

Cerebras and OpenAI have launched Ultrafast Mode, a new service tier for GPT-5.6 Sol that delivers up to 750 output tokens per second—11x faster than competing models like Claude Fable 5 without sacrificing quality. In benchmarks, GPT-5.6 Sol Ultrafast completed a challenging 2,500-question exam in 11 hours compared to Claude's 78+ hours, making it suitable for time-sensitive applications like legal briefs, financial modeling, and engineering reports. The service is initially available to select customers through the OpenAI API, with broader access planned over time.