OpenAI ha svelato in anteprima Ultrafast, un nuovo profilo API basato sull'hardware Cerebras per spingere le prestazioni del modello GPT-5.6 Sol. L'infrastruttura genera fino a 750 token al secondo abbattendo la latenza

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

OpenAI is expanding its inference infrastructure through a multi-year partnership with Cerebras,...