OpenAI Rolls Out GPT-5.6 Sol Ultrafast Mode at 750 Tokens/s, 14x Faster Than Standard
According to Beating, OpenAI is currently previewing GPT-5.6 Sol's Ultrafast mode, powered by Cerebras, reaching a maximum output speed of 750 tokens per second—14 times faster than Standard mode. The feature is currently available to select API customers only. OpenAI has tested Ultrafast in
GateNews·08-14 01:09

