Explainers· Last updated 2026-09-21

What is Jev?

Jev is TypeSafe AI’s first public System One model. You send a state (the material to judge) and a map of typed questions. Jev returns one typed answer per question, with probabilities your code can branch on.

It is not a chat model. Official docs are explicit: System One models do not write replies, produce code, or generate explanations of their reasoning. The useful contract is closer to a function call than a conversation.

TypeSafe’s launch post (15 September 2026) frames Jev as “a frontier-intelligence function call: unstructured state in, typed probabilistic decisions out.” The same post says Jev “gives up string generation,” is optimized for structured outputs, and “can’t hallucinate” in the sense that outputs are constrained to the schema you supplied.

What you send

Every evaluation request has three top-level fields:

1. model — usually jev-latest, or a pinned version such as jev-1.13.0.
2. state — a string, JSON object, or array of text. Images, audio, and video are not accepted.
3. questions — a map of IDs you choose to Choice, Score, or Noul questions.

Question IDs are for your code. TypeSafe’s primitives page says they are not sent to the underlying model. Write the complete question in instructions.

What you get back

All questions in one request see the same state and are evaluated independently and in parallel. Adding questions costs the extra question tokens; docs say it barely changes response time.

What Jev is not

• Not a drop-in ChatGPT replacement.
• Not a generator for emails, code, or JSON documents.
• Not a calculator. The jaggedness note for jev-1.13 tells you to keep arithmetic in code.
• Not an official product of this site. jev.pro is independent and unofficial.

Where to read first

Start at docs.typesafe.ai, then the quick start and models pages. This site restates those public pages for search and internal linking. If we disagree with the docs, the docs win.