Le recours aux puces spécialisées de Cerebras démontre la stratégie d'OpenAI pour contourner la saturation de bande passante mémoire des GPU classiques en inférence.
Cette annonce supprime le compromis historique imposant de choisir entre la puissance d'un modèle frontière et une vitesse d'exécution adaptée au temps réel.
Propulsé par les infrastructures matérielles de la société Cerebras, le mode Ultrafast permet à GPT-5.6 Sol de générer des réponses 14 fois plus vite qu'en traitement standard. OpenAI restreint pour l'instant cette prévisualisation à un panel réduit de clients professionnels avant d'élargir la capacité de ses serveurs.
Impact concret
Les architectes logiciels et équipes DevOps peuvent intégrer un modèle généraliste complet dans des architectures exigeant une réponse sous la seconde.
Applications concrètes
Gestion d'incidents informatiques en temps réel, analyse instantanée de données de marchés financiers et agents virtuels de service client sans latence.
In Brief Posted: 12:22 PM PDT · August 13, 2026 Image Credits: Olivier Morin/AFP / Getty Images Lucas Ropek OpenAI introduces ‘Ultrafast,’ a new mode that makes GPT-5.6 Sol work at 14x the speed If you’ve ever found yourself wishing that ChatGPT was a little bit quicker on the uptake, OpenAI seems to be answering your prayers. The AI lab has rolled out a new mode called Ultrafast , which it says is designed to seriously accelerate the pace at which its latest and most powerful model, GPT-5.6 Sol , accomplishes its work. The company says that Ultrafast can work at 14x the speed of standard processing, delivering up to 750 output tokens — such tokens represent the distinct pieces of text generated by an LLM when it interacts with a human — per second. “Until now, getting real-time speed typically meant choosing a smaller or more specialized model,” the company said in the blog post on Thursday. “Ultrafast points to progress in a new direction: more useful work per second.” OpenAI’s competitors, like Anthropic, have similarly launched accelerated versions of their models. Claude has fast mode , although it doesn’t deliver the kind of speed that OpenAI is offering here. OpenAI suggests that this high-octane version of GPT-5.6 Sol can be deployed across a number of different corporate workflows, most notably incident response, customer service and support, financial market analysis, and e-commerce, among other relevant areas. Ultrafast, which is currently being released in preview, is being powered by OpenAI’s partnership with chipmaker Cerebras. Currently, that preview is only being made available to a small group of customers, although OpenAI says that it will expand access to the feature as “capacity grows.” Topics AI , Anthropic , ChatGPT , Claude , In Brief , OpenAI October 13 – 15 San Francisco Scale faster. Grow your portfolio. Gain practical expertise. No matter your goal, Disrupt can empower you. Save up to $300 toda y! REGISTER NOW Newsletters See More Subscribe for the industry’s biggest tech news TechCrunch Daily News Every weekday and Sunday, you can get the best of TechCrunch’s coverage. TechCrunch Mobility TechCrunch Mobility is your destination for transportation news and insight. Startups Weekly Startups are the core of TechCrunch, so get our best coverage delivered weekly. StrictlyVC Provides movers and shakers with the info they need to start their day. No newsletters selected. Subscribe By submitting your email, you agree to our Terms and Privacy Notice . Related AI IBM partners with OpenAI to bolster enterprise AI push Jagmeet Singh 1 day ago AI Anthropic set AI agents loose on the same task. They started a turf war. Rebecca Bellan 1 day ago AI OpenAI hires new CRO as executive shake-up continues Tim Fernholz 1 day ago Latest in AI In Brief Google will now allow users to remove visible watermark from its AI generations Ivan Mehta 11 hours ago AI Does Mark Zuckerberg really believe AI is ‘for everyone’? Theresa Loconsolo 12 hours ago 33 min AI Kog is going deeper to squeeze more inference out of GPUs Anna Heim 13 hours ago