Explainer · updated 2026-09-21
What is Jev? The System One model, explained
Jev is an AI model from TypeSafe AI that decides instead of writing. Give it any text or JSON and a few typed questions: it answers all of them at once, with a probability for every possible answer. It is the first System One model.
- Maker
- TypeSafe AI
- Launched
- 2026-09-15
- Answers
- choice, score, noul
- Price
- $0.042 / M input tokens, output free
- Median latency
- 0.44–0.48 s
- Model
- jev-1.13.0
What is a System One model?
An AI model that answers typed questions with probabilities, all in one pass, and never writes text.
System 1: fast
Jev
Every question answered at once, as probabilities.
System 2: slow
LLMs
Text one token at a time, reasoning by writing.
The name borrows the fast, intuitive System 1 of Daniel Kahneman's Thinking, Fast and Slow. Most decisions software makes are that kind: spam or not, which team, safe to run.
How does Jev work?
One API request carries the input and every question, and each question is answered on its own.
- State
- What the decision is about: any text or JSON. The context window is about 32,000 tokens, text only.
- Question
- A typed ask,
choice,scoreornoul, with an instruction. - Criteria
- The possible answers, described in plain words.
- Independence
- Questions never see each other's answers. Combine them in code.
What are choice, score and noul?
Jev's three question types: pick one option, place on an ordered scale, or answer yes or no.
choice → match
Pick one of up to 255 options.
request state + question
- message
- Can I move my table from Friday to Saturday night?
What does the customer want?
choicebookchangecancelaskwith descriptions
score → sort
Place it on 2 to 10 ordered levels.
request state + question
- review
- Food was fine and the service slow, but the view made up for it.
How positive is the review?
scoreNegativeMixedPositiveGlowing
noul → if
Yes or no, as the probability of yes.
request state + question
- Your parcel is held at customs. Pay the $2.99 release fee within 24 hours: parcel-release.help/pay
Is this a phishing attempt?
noulyesno
How is Jev different from ChatGPT and other LLMs?
An LLM writes its answer token by token, and your code parses it. Jev is not an LLM: it writes nothing and scores your answers, all at once.
LLM: one token at a time
Jev: every answer at once
| LLMs | Jev | |
|---|---|---|
| Output | Text to parse | Probabilities over your answers |
| Writes text or code | Yes | No |
| Reasons step by step | Yes | No: one look per question |
| Latency (median) | 0.53–2.21 s | 0.44–0.48 s |
| Cost per 1,000 decisions | $0.023–$1.5 | $0.029–$0.043 |
| Possible answers | Anything, including made-up ones | Only the options you defined |
| Probabilities | Only if asked to write them | Built in, trained to be calibrated |
| Best at | Open-ended work | Many fast decisions over known answers |
Measured on the Jevals boards: Jev and 6 LLMs, release 2026-09-18.
Is Jev just a classifier?
Close: it does zero-shot classification, and critics say so. The difference from a trained classifier: you describe the options in words and change them on any request.
| Trained classifier | LLM with structured outputs | Jev | |
|---|---|---|---|
| Training data | Needed | None | None |
| New answers | Retrain | Edit the prompt | Edit the request |
| Output | Scores per label | Text that should parse | Probabilities per answer |
| Speed and cost | Fastest | Slowest | Fast |
What do Jev's probabilities mean?
They are meant to be calibrated: answers given at 80% should be right 80% of the time. That lets code act alone when Jev is sure, and ask for help when it isn't.
Sure: act
Unsure: ask
yes/no
gap 5.0 pts
pick-one
gap 9.8 pts
rubric scores
gap 19.7 pts
What is Jev used for?
Decisions with known answers that software makes often: route, check, rank, choose.
- Propose
Code or an LLM lists the options.
- Decide
Jev scores them against the state.
- Gate
Code checks the confidence.
- Act
Sure: do it. Unsure: escalate.
choice
Routing
Send each ticket, email or prompt to the right place.
noul
Guardrails
Approve an agent's command, or ask a human.
choice, noul
Moderation
Publish, redact or reject.
score
Judges and linters
Grade outputs against a rubric, in place of an LLM-as-a-judge.
score
Ranking and reranking
Score every search result, then sort.
choice
Classification
Label a million rows by topic, intent or sentiment.
choice
Agents
Pick the next action or the element to click.
choice
Real-time loops
Game bots deciding several times a second.
choice
Extraction
Code finds candidates, Jev picks one or none.
Limitations: when not to use it
- Writing anything: replies, summaries, code.
- Answers you can't list in advance.
- Arithmetic or multi-step reasoning.
- Security boundaries: text in the state can sway it.
- Its documented weak spots: counting, dates, negation.
How does Jev score on benchmarks?
Tied for first on yes/no and tied for second on pick-one, for a fraction of most LLMs' cost. On rubric scores, no model clearly beats guessing.
| Board | Test | Jev Decision Score | Jev accuracy | Best other model |
|---|---|---|---|---|
noul | PubMedQA | 69.0 | 91.3% | Gemini 3.8 Flash 73.0 |
choice | Banking77 | 67.8 | 79.7% | Gemini 3.8 Flash 74.1 |
score | HelpSteer2 helpfulness | 9.2 | 41.3% | GLM-5.3 7.8 |
Scored against human labels, five runs per question; orange marks each board's top 2. Head to head: Jev vs Gemini 3.8 Flash.
Who makes Jev?
TypeSafe AI, a San Francisco startup led by CEO Diogo Almeida, a former OpenAI researcher on InstructGPT.
- TypeSafe AI founded, in stealth
- Talks on what comes after RLHF
- Jev launches
- On Vercel AI Gateway
- First independent benchmark
- Training
- RLCD, Reinforcement Learning for Calibrated Decisions. Unpublished, like the architecture.
- Name
- After the Jevons paradox: make something cheaper and use grows.
- Access
- TypeSafe's API (waitlist), or Vercel AI Gateway as
typesafe-ai/jev. - Funding
- $40M seed round led by DCVC.
What is a Jev-type model?
Any model that answers choice, score and noul with probabilities. Jev itself is closed; adapters and open-source alternatives now copy its interface.
| Model | What it is | Open | On Jevals |
|---|---|---|---|
| Jev | The native System One model | No | Listed |
| LLMs via an adapter | An LLM prompted for the same probabilities (system-one-adapter, AI SDK evaluate) | Varies | 6 listed |
| openjev | Option probabilities read from an open Qwen model | MIT | Coming |
| decider-2b | A 2B Qwen model fine-tuned for the three types | Apache-2.0 | Coming |
| DiffusionGemma | Google's diffusion model filling an answer template (open-jev) | Open weights | Not yet |
| GLiClass, GLiNER | Small zero-shot encoder classifiers, the prior art | Apache-2.0 | GLiClass coming |
What are the criticisms of Jev?
Mostly fair: it is close to a zero-shot classifier, and most claims about it are the vendor's own.
- "Just a zero-shot classifier." Partly true: encoders like GLiClass came first. New is one hosted model, three types, calibration as a goal.
- "Can't hallucinate." It can't invent an answer, but it can pick the wrong one, confidently.
- Vendor benchmarks. TypeSafe's Workflow Evals grade agreement with two LLMs, not human labels.
- A black box. No paper, no parameter count, no published calibration.
- The price. Critics suspect a subsidy; TypeSafe says it is profitable.
- The boards
Jev and 6 LLMs on three benchmarks.
- The explorer
Each model's answer to each question.
- The methodology
How each score is computed.
Facts checked 2026-09-21 against TypeSafe's and Vercel's public pages. Jevals is independent of TypeSafe AI.