OpenAI: Rolls Out Ultrafast Mode for GPT-5.6 Sol

OpenAI previewed Ultrafast, a new API service tier that runs GPT-5.6 Sol up to 14 times faster with peak output of 750 tokens per second on Cerebras hardware. The move directly lifts OpenAI API performance for latency-sensitive workloads and sharpens GPT-5.6 Sol inference speed benchmarks while highlighting Cerebras AI deployment advantages in production inference clusters.