Model & officialOfficial
Jev
The model this site is about. Jev takes your program state plus a set of typed questions and answers all of them in one pass, returning a choice, a score or a probability rather than a sentence. Because the answer is picked from a schema you wrote, it cannot come back off-schema. TypeSafe describes it as the first of a class they call System One models, and publishes speed and price comparisons against chat models; those figures are the vendor's own.
- system-one
- typed-decisions
- calibration
- rlcd
- From
- TypeSafe AI (US)
- Published
- 2026-09
- Listed here
- 2026-09-26
Sources checked
Also in this category
Model & official- Model & officialOfficial
Introducing System One Models & Jev
The launch post, and the clearest statement of the design bet: give up string generation entirely, and train instead for probabilities that mean what they say. It names the training approach Reinforcement Learning for Calibrated Decisions, and frames the model as a function call rather than a conversation. Read it for the reasoning; read the evaluations elsewhere on this site for how it holds up.
TypeSafe AI2026-09 - Model & officialOfficial
Jev model card (ids, context, limits)
The page to check before you pin anything: the current model id and the moving alias, how the context budget is split between the state and the longest question, the published rate limits, and the note that English is where accuracy is currently best. It also links out to the known-failure-mode page for the specific version you are calling.
TypeSafe AI2026-09
