OpenAI previews 'Ultrafast' GPT-5.6 Sol running up to 14 times faster
The limited preview serves GPT-5.6 Sol at up to 14 times standard speed, with early customers including Jane Street and Podium.
- On Thursday, OpenAI previewed 'Ultrafast,' a new API tier for GPT-5.6 Sol that runs up to 14 times faster than standard processing, reaching around 750 output tokens a second on Cerebras hardware.
- Cerebras builds dinner-plate-sized processors from single silicon wafers, allowing the model to sit on one chip rather than being split across Nvidia GPUs, which strips out internal traffic and collapses latency between prompts and replies.
- Early testers including Jane Street, Podium, Basis, and Rogo describe the change as qualitative rather than incremental, with one noting that speed "completely changes the call experience for complex work."
- The company is targeting time-sensitive tasks including incident response, financial research, and real-time customer support, though Ultrafast remains a limited preview for a small group of customers while OpenAI hunts for capacity.
- Rivals like Anthropic also offer accelerated models such as Claude, signaling that speed is becoming critical for agentic software that must respond conversationally rather than operate as static demonstrations.
43 Articles
43 Articles
OpenAI gives its most select customers a sample of GPT-5.6 in Ultrafast mode, this is what it can do
The new function seeks to make advanced intelligence “more accessible” for more people
OpenAI tests a new GPT-5.6 Sol mode that reaches up to 750 tokens per second without switching to a smaller version of the model
OpenAI’s new Ultrafast mode runs GPT-5.6 Sol 14 times faster, on Cerebras chips
OpenAI wants its cleverest model to also be its quickest. The company has previewed Ultrafast, a new tier of its API that runs the flagship GPT-5.6 Sol at up to 14 times the usual speed, reaching around 750 output tokens a second, on hardware built by the wafer-scale chipmaker Cerebras. Ultrafast is not a new model […] This story continues at The Next Web
OpenAI releases Ultrafast mode for GPT-5.6 Sol, makes the AI 14 times faster
OpenAI has introduced Ultrafast, a new service tier that runs GPT-5.6 Sol up to 14 times faster through its API. The preview, powered by Cerebras, targets time-sensitive business workflows where speed and frontier-level intelligence matter together.
Coverage Details
Bias Distribution
- 56% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
