OpenAI previews Ultrafast, an API tier powered by Cerebras that runs GPT-5.6 Sol up to 14× faster and generates up to 750 output tokens per second (Zac Hall/9to5Mac)
OpenAI says Ultrafast runs the full GPT-5.6 Sol model, not a smaller variant.
The new API tier is powered by Cerebras and is launching first to a select group of customers. OpenAI says it can generate up to 750 output tokens per second, up to 14 times faster than Standard processing. Expanded access is planned as capacity grows. Techmeme's note
The new API tier is powered by Cerebras and is launching first to a select group of customers. OpenAI says it can generate up to 750 output tokens per second, up to 14 times faster than Standard processing. Expanded access is planned as capacity grows. Techmeme's note
score 7