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

OpenAI is launching a new API service tier called Preview Ultrafast, which runs GPT-5.6 Sol up to 14 times faster than before. This service is powered by Cerebras and can produce up to 750 output tokens per second.

מקור: OpenAI News — לכתבה המלאה