OpenAI has introduced its new GPT-5.6 Sol Ultrafast mode in limited preview, running frontier model intelligence on Cerebras hardware at speeds reaching 750 output tokens per second.

OpenAI is previewing a new way to run its most capable GPT-5.6 model at dramatically higher speeds. The company says...

Google's Gemini 3.7 Flash model is live and built for cheap agents; OpenAI's GPT-5.6 Sol Ultrafast is quicker but locked behind a waitlist.