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

OpenAI Blog reports: Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed. Preview Ultrafast, a new OpenAI API service tier that runs GPT-5.6 Sol up to 14× faster. Powered by Cerebras, it delivers up to 750 output tokens per second.

What we know

Preview Ultrafast, a new OpenAI API service tier that runs GPT-5.6 Sol up to 14× faster. Powered by Cerebras, it delivers up to 750 output tokens per second.

OpenAI Blog also published these related stories:

• #Exploration: A study of count-based exploration for deep reinforcement learning
• OpenAI and Microsoft
• On the quantitative analysis of decoder-based generative models

Why it matters

AI is moving fast enough that announcements from major players tend to ripple across the whole industry within weeks. If OpenAI Blog is shifting direction here, developers, businesses, and anyone building on top of these tools will want to pay attention.

What to watch

This story is developing. Keep an eye on OpenAI Blog for updates and reactions from the wider industry.