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 launches GPT-5.6 Sol Ultrafast mode (750 tokens/sec, 14x faster) on Cerebras without model downgrade. Frontier-model latency now viable for incident response and real-time support—no more small-model tradeoff for time-critical operations.
When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works.
Powered by Cerebras' Wafer-Scale Engine, this Ultrafast processing tier operates up to 14 times faster than standard mode.
Pradeep Viswanathan
Neowin
@pradeepviswav ·
OpenAI unveils Ultrafast mode for GPT-5.6 Sol, boosting speed by 14x
OpenAI previews 'Ultrafast' GPT-5.6 Sol running up to 14 times faster - 9to5Mac
OpenAI’s new Ultrafast mode runs GPT-5.6 Sol 14 times faster, on Cerebras chips
OpenAI releases 'Ultrafast' mode to make GPT-5.6 Sol 14x faster
GPT-5.6 Sol goes 14x faster as OpenAI launches Ultrafast mode powered by Cerebras
OpenAI and Cerebras Bring GPT-5.6 Sol Ultrafast to Enterprise Inference
GPT-5.6 Sol � 14 volte pi� veloce con Ultrafast: il modello a 750 token/secondo sembra utopia
OpenAI acelera GPT-5.6 Sol con ‘Ultrafast’: así funciona el nuevo modo que genera hasta 750 tokens por segundo
OpenAI presentó Ultrafast, el modo que acelera GPT-5.6 hasta 14 veces
Google and OpenAI Debut Super Fast AI Models - Decrypt
OpenAI launches Ultrafast mode for GPT-5.6 Sol, delivering 750 tokens per second via Cerebras hardware for enterprise real-time…
OpenAI is previewing a new way to run its most capable GPT-5.6 model at dramatically higher speeds. The company says...
OpenAI has previewed Ultrafast, an API tier that runs GPT-5.6 Sol at up to 14x speed on Cerebras hardware, betting that latency,…
OpenAI has launched Ultrafast mode, enabling its GPT-5.6 Sol model to operate at 14 times the speed, revolutionizing AI…
OpenAI is launching "Ultrafast," a new inference mode that delivers GPT-5.6 Sol at up to 750 output tokens per second, powered by…
OpenAI is expanding its inference infrastructure through a multi-year partnership with Cerebras,...
