If you've ever found yourself staring at your screen, tapping your foot, and muttering, "Come on, ChatGPT, I haven't got all day," then OpenAI has just the thing for you - because apparently, the speed at which a chatbot replies was the real bottleneck in our lives.
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. Yes, that's right: the model is called Sol, as if it needed to sound more like a sci-fi character.
The company claims that Ultrafast can work at 14x the speed of standard processing, delivering up to 750 output tokens per second. Those tokens, for the uninitiated, are the distinct pieces of text generated by an LLM when it interacts with a human - so essentially, it's the difference between a conversation with a fast-talking auctioneer and a contemplative philosopher.
"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." Because who doesn't want to quantify usefulness in terms of raw throughput?
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. So if you were worried that Claude was outpacing GPT, rest assured: OpenAI has thrown down the gauntlet, and it's made of silicon and hubris.
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. Because nothing says "calm under pressure" like a chatbot that responds to a server outage at the speed of light.
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." So for now, most of us will have to continue waiting the agonizing milliseconds it takes for GPT-5.6 Sol to respond. We'll try to cope.