Matt Wolfe introduces Jev, a new AI model from Typesafe AI that skips text generation and returns structured decisions instead. It costs four cents per million input tokens, runs fast, and can flag malicious URLs before you click them.
But there was something else causing a lot of buzz this week, and that's a model out of a company called Typesafe AI called Jev. When you think of like the GPT models, those create new text. Even when you ask it to make decisions for you, it's still creating text and writing code that then goes and makes those decisions. Jev, on the other hand, just skips straight to the decision-making. The output from existing LLMs are, you know, strings and generated text. The outputs from Jev are structured values, and there's really 3 types of structured output. You can give it a choice, a score, or a null, which is basically you know true or false. And because it's not outputting just a ton of text, it's just making these decisions. It is insanely cheap to use input tokens at four cents per million tokens or forty-two dollars per billion tokens. Output tokens are free because they're just too cheap to meter. It's also insanely fast. Stephen Tay here made an app where you can plug in a destination URL and it detects whether or not it believes it's a malicious URL before you go to. The link. You can literally go to Codex or Claude Code, tell it what you want Jev to do, and let it write the code to run Jev for you.
AI News: Dots, GPT-6.1 Sol, Sonnet 5.5, Gemini 4, and everything you need to know
