Jev is a decision model, not a chat model
Projects that put Jev ahead of generation are collected in the Jev project directory.
Jev is TypeSafe AI’s first public System One model, announced on 15 September 2026. You send the state your software already has — a ticket, a log line, a tool call, a retrieved passage — plus questions whose answers are bounded in advance. What comes back is a typed value, not a paragraph.
That is the product. TypeSafe trained Jev to make fast, structured judgments that code can consume directly. It is a poor fit for drafting, summarizing, or explaining, and TypeSafe says the current version is not trained to generate text.
What Jev returns: choice, score, and noul
Every question is one of three types. A choice picks one label from a set you define, up to 255 options, and returns the winner plus a probability for each option. A score places the state on an ordered 2–10 level rubric and can land between levels. A noul answers a yes/no question with a single probability from 0 to 1.
Several questions can share one request and are evaluated against the same state. Your application still owns the side effect: Jev can select “billing”, but it does not issue the refund.
- Stable model: jev-1.13.0 (alias jev-latest). Newest release: jev-1.14.0 (alias jev-preview), with experimental image input, Box and long context.
- Vendor latency claims for System One tasks are typically 70–500ms; measure your own path.
- Input is billed at $0.042 per million tokens. Output is free because the response is a typed value, not generated text.
Where the Jev model is a good fit
Start with narrow, repeated judgments: support triage, model routing, moderation gates, lead scoring, citation checks, and “should this tool call run?”. Keep open-ended writing, deep research, and long reasoning with a general-purpose language model.
The usual production pattern is hybrid. Jev decides the branch; GPT, Claude, or another LLM writes whatever a person will read. That is also why “Jev vs GPT” is the wrong framing if you expect one model to replace the other.
Who makes Jev, and what System One means
TypeSafe AI is a San Francisco lab that came out of stealth with a $40M seed round led by DCVC. The company names the category System One after fast, intuitive System 1 judgments — the cheap branches software makes all day — rather than slow System 2 reasoning.
TypeSafe also describes a training method it calls Reinforcement Learning for Calibrated Decisions (RLCD). Treat vendor speed, cost, and “zero hallucination” claims as claims about schema-bounded output, not as proof that the selected label is always the correct one.
FAQ
Is Jev a large language model?
Not in the usual sense. Jev is a System One decision model: it reads state and returns a typed choice, score, or yes/no probability. TypeSafe states the current version is not trained to generate text.
What does "System One" mean?
TypeSafe’s name for the fast, intuitive judgments software makes constantly — route this, score that, allow or block — named after System 1 thinking, as opposed to slow multi-step reasoning.
Which Jev model version is live?
The stable model is jev-1.13.0 (alias jev-latest). jev-1.14.0, released 14 October 2026, is the newest release (alias jev-preview) with experimental image input, Box questions and long context. Pin a version string in production so behavior does not shift under your prompts.
What question types does Jev answer?
Three: choice (pick one label from up to 255 options, with per-option probabilities), score (an ordered 2–10 level rubric that can land between levels), and noul (a yes/no probability from 0 to 1).
Can Jev browse the web or call tools?
No. Jev judges the state you send it. If a decision needs fresh evidence, fetch it first — your code or a retrieval step — then include it in the state.
Who makes Jev?
TypeSafe AI, a San Francisco lab that exited stealth with a $40M seed round led by DCVC. jevmodel.org is an independent guide and hosted API wrapper, not affiliated with TypeSafe.