OpenAI Previews Cerebras-Powered Ultrafast API Tier
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- OpenAI previewed a new API tier called Ultrafast, powered by Cerebras, designed to run its GPT-5.6 Sol model at dramatically higher speeds
- The Ultrafast tier delivers up to 14× faster performance versus standard runs and generates up to 750 output tokens per second on GPT-5.6 Sol
Why it matters: By tapping Cerebras rather than building or buying more conventional inference infrastructure, OpenAI is positioning its fastest GPT-5.6 Sol tier as a speed play for developers — the stated 14× speedup and 750 tokens-per-second ceiling lower the latency barrier for real-time applications built on the model.
Ask SkimNews
