Jev introduces a new shape of LLM
TypeSafe AI has launched Jev, a new type of 'decision model' designed to output structured, probabilistic data rather than natural language. The model is optimized for classification tasks and is significantly cheaper than traditional LLMs because it does not charge for output tokens.
Why it matters
This represents a shift toward specialized, cost-effective AI models that prioritize functional decision-making over generative text, potentially disrupting enterprise automation workflows.
Last week TypeSafe AI unveiled Jev , their first example of a new category of model that they are calling “System One models” (I’m with Maggie Appleton, I think “decision models” is a better name for these). Jev is an interesting variant on the usual LLM format: it still accepts text inputs, but instead of text output it returns floating point numbers corresponding to categories, yes/no questions, ratings, and associated confidence scores.
Think of Jev as a frontier-intelligence function call: unstructured state in, typed probabilistic decisions out.
It’s also very fast, and really cheap . Regular LLMs are priced in terms of input and output tokens, with output generally charged at significantly higher rates. Jev charges only for input—output is free—and the input price of their first model is $0.042 per million tokens—cheaper even than OpenAI’s GPT-5 Nano ($0.05/million).
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in