What is Jev?
Jev is the first System One decision model, released by TypeSafe AI on September 15, 2026. You send it text plus typed questions; it returns typed answers with probabilities and a confidence score. It does not generate prose, code, or explanations — it only decides.
Updated Sep 2026 · 5 min read
In short
- → A frontier model optimized for decisions, not text generation
- → 20–200x faster and 40–400x cheaper than LLMs for the same judgment calls (output tokens are free)
- → Answers are typed: an option, a score, or a true/false probability — never a paragraph to parse
- → Per-question cost is so low that agents can ask 60 questions for the price of one LLM call
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
The launch announcement from Diogo Almeida, Jev's creator.
How a call works
One endpoint, one request: a state (the thing being judged) plus a map of questions. Three question types, mixable in a single call and evaluated in parallel:
| Type | Returns | Use for |
|---|---|---|
| choice | Picked option + probability per option (up to 255) | Routing, classification, picking |
| score | Probability-weighted value on an ordered scale | Severity, quality, sentiment |
| noul | A 0–1 probability | Yes/no gates, filters, verification |
This site itself uses Jev for submission review: paste a link, Jev decides whether it belongs (noul) and picks the use case (choice) — one call, fractions of a cent.
Speed, cost and accuracy
| Model | Accuracy | Cost / case | Time / case |
|---|---|---|---|
| Claude Opus 5 | 73.1% | $0.1761 | 37.8 s |
| Jev | 67.8% | $0.0004 | 0.07–0.5 s |
| Terra | 67.9% | $0.0304 | 10.1 s |
| Claude Haiku 4.5 | 53.6% | — | — |
Jev matches Claude Sonnet 5-class judgment accuracy at ~1/290th the cost. Caveat, honestly stated: reference answers in these evals come from two large models, not humans. Input pricing is $0.042 per million tokens; output tokens are free.
Models and limits
- → Models:
jev-latest,jev-preview - → Context: 64k tokens
- → Rate limits: 250k tokens/s, 1,200 requests/min
- → Response: typically 70–500 ms
Where it does not fit
- → It writes no text — summaries, code, and replies are out of scope
- → Options must be predefined; it cannot invent choices
- → Text-only input (no images or audio yet)
- → Questions are independent — no multi-step dependent reasoning inside one call
Why it is called Jev
From the Jevons paradox: when a resource gets radically cheaper, consumption explodes instead of shrinking. Make decisions 400x cheaper and agents stop rationing judgment — they ask everything. “System One” nods to Kahneman's fast, automatic mode of thinking: not deliberation, instant judgment.
What people build with it
Browser agents that search and book flights for $0.004 a run. Game agents holding 60fps decision loops. Inbox triage that reads 400 emails a day. Trading backtests where Jev plays the discretionary trader. Catalogs of 1,000+ papers classified for $0.08. The community ships new builds daily — the best of them live in our directory, ranked by upvotes.
Common questions
Is Jev an LLM?
No. It shares the transformer lineage but is trained and optimized for typed decisions. It never generates free-form text.
Can Jev hallucinate?
The answer format is type-safe — it always returns a valid option, score, or probability. It can still pick the wrong option (67.8% eval accuracy), so confidence scores are exposed for routing low-certainty cases to a bigger model.
How is it so cheap?
Output tokens are free and the model is non-autoregressive — it scores options instead of generating sequences, so a decision costs microseconds of compute, not seconds.
How do I try it?
Get an API key at TypeSafe AI, then make one POST to /v1/systemone. Or submit a link on this site — our reviewer is Jev itself.
BuiltOnJev is an independent community project, not affiliated with TypeSafe AI. Specs and eval numbers are from TypeSafe's published materials and the launch announcement above.