TypeSafe AI's Jev introduces 'decision models': text in, probabilistic scores out, at $0.042/M tokens

teropa · x · 2026-09-22

TypeSafe AI unveiled Jev, billed as the first of a new model category it calls "System One models"; Simon Willison prefers Maggie Appleton's name "decision models".
Jev takes text input but returns floating-point numbers instead of text: confidence scores for yes/no questions (called "Noul", from Bernoulli), choices among options, and ratings.
It's fast and cheap: only input is billed, output is free, at $0.042 per million input tokens—cheaper than OpenAI's GPT-5 Nano ($0.05/M).
You send a "state" object (string, string array, or name-value pairs describing an article, customer, or record) along with one or more questions, and get typed probabilistic answers back—useful for batch decisions over text or semi-structured data.

More from Models