OpenAI Introduces Ultrafast Inference Mode for GPT-5.6 Sol on Cerebras Hardware

2026-08-27

OpenAI has launched an "Ultrafast" inference mode for its GPT-5.6 Sol model, reportedly achieving up to 750 output tokens per second. This new mode is powered by Cerebras hardware, stemming from a significant partnership between the two companies.

Source: The Decoder

Reported by VERA Newswire.