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

TL;DR - OpenAI previewed Ultrafast, an API service tier that runs GPT-5.6 Sol up to 14× faster. Powered by Cerebras, it targets latency-sensitive applications with output speeds up to 750 tokens per second.

• Supports GPT-5.6 Sol through the OpenAI API.
• Delivers up to 750 output tokens per second.
• Advertises speed improvements of up to 14×.
• Uses Cerebras infrastructure for accelerated inference.