JevCodeJevCode · clavue-jev
The best Jev in the world, served here
JevCode is the home of Jev. This site serves one model, clavue-jev, and we hold it as the best Jev in the world today. Give it a state and a typed question, and it returns a judgment you can branch on. Tests on this page keep a narration and sit beside jev-1.13.0.
- 210ecosystem projects
- 275community posts
- 136head-to-head cases
clavue-jev
The model is clavue-jev
There is no multi-model catalog. clavue-jev is the best Jev in the world today, and live judgments go to it. jev-1.13.0 appears only as the other side of the same-question comparison.
Forty-five questions, five from each of nine banks. Run one, or send a whole category to clavue-jev and jev-1.13.0. Every result is written into the narration. 40 requests per IP per hour.
—
—
Limited-time offer: get $5 in credit on signup, free for one month. See how to connect
Watch a judgment land
Tetris, six rapid judgments, and a sort. The call sits beside the stage. Copy it and run it here again.
What's new
Recently updated docs, community benchmarks, and projects just added.
Recently updated docs
View allCommunity pulse
View all- Diogo Almeida: After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not le…
- tamara: found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is co…
- Matija Sosic: Here's a 45-second TL;DR on Jev. I find the core idea beautifully simple, but the video…
Three question primitives
Every decision reduces to one of three typed questions. Choosing the right primitive is the first step toward a reliable decision system.
Pick one from a set
Given a set of mutually exclusive options, the model returns the selected option with a confidence. Used for intent classification, ticket routing, action selection.
ScoreRate along a scale
Rate along a defined scale or rubric, returning a numeric value with confidence. Used for relevance ranking, quality assessment, risk grading.
NoulProbability of yes/no
Ask a yes/no question and get the probability the answer is yes. Used for verification, claim checking, agent guardrails.
Architecture patterns
From single calls to multi-stage pipelines, these patterns cover the decision architectures that show up most in production.
Intent routing
Dispatch requests to downstream handlers with a single Choice call, replacing brittle regex and keyword matching.
Confidence routing
Route by confidence: auto-execute when high, escalate to a human or a stronger model when low.
Composite scoring
Combine several Score dimensions into a single ranking metric, making ranking logic explainable and tunable.
Fan-out
Issue many independent judgements in parallel and aggregate, cutting total latency and raising throughput.
Ecosystem and real cases
Teams are already using Jev in production for classification and routing, verification, scoring and ranking, and agent guardrails.
Docs
Concepts, primitives, patterns, and SDKs, organized by task.
Quick start
A minimal call you can run in minutes.
Ecosystem
Community projects by category, with stars and the Jev decision point.
Community
Public benchmarks and discussion, each with its source.
44 documents available in this language.
The pages connect
Watch a call land on live scenes, see clavue-jev and jev-1.13.0 on the same item in compare, then read the quick start and the use-case map. Rates are on pricing, the call shape is on the API page, and every entrance is on the site directory.
Questions
What is JevCode?
The home of Jev. The model is clavue-jev, the best Jev in the world today. The concept pages are written here.
Which model does this site serve?
clavue-jev only. The compare page also asks jev-1.13.0 the same question, as a side-by-side check.
How is it billed?
Same as jev-1.13.0: input tokens only, $0.042 per million, output free. Signup credit is $5, drawn at that rate, and only after a successful call.
Can I try it without an account?
Yes. Anonymous calls are 20 per IP per hour and are not billed. "Run it here" on the live scenes page uses that path.
Where are the docs and cases?
The site directory lists try, docs, cases, and pricing on one page. Each page also links onward at the bottom.
Keep going on this site
Try, docs, cases, and pricing link to each other. The next page is on this site.
- Site directoryThe full list of the pages above.
- EcosystemCommunity projects by category.
- Jev coverageEach entry names the decision and its evidence.
- Daily casesThe next batch of coverage cases, each day.
- CommunityPublic posts, each with its source.
- BuildsNotes on model and site updates.
- PrimitivesChoice, Noul, and Score together.
- PatternsRouting, fan-out, and composite scoring.
- SDKsHTTP, Python, and JavaScript.
Use clavue-jev
- Try a judgmentSend a state and read the answer.
- Live scenesTetris, six rapid judgments, and a sort. Copy the call and run it again.
- Judgment LabSupport triage, release review, compliance routing — edit and run on the spot.
- Compareclavue-jev and jev-1.13.0 answer the same question.
- DemosJudgment examples you can edit.
- PricingInput is $0.042 per million tokens. Output is free.
- APICall POST /v1/judge with a key.
Docs
- IntroductionWhat this model is for.
- Quick startThe smallest call that runs.
- System OneWritten here: a state plus one typed question. The model is clavue-jev.
- StateThe text you send in.
- ConfidenceHow sure the answer is, and when to act on it.
- ChoicePick one mutually exclusive option.
- NoulA yes/no question, returned as the probability of yes.
- ScoreRate along a scale.
- Intent routingOne Choice call dispatches the request.
- Confidence routingAct when confidence is high. Hand off when it is low.
- Fan-outAsk several questions of one state.
- Composite scoringFold several scores into one ranking.
- HTTP APIThe request shape without an SDK.
- Python SDKCall a judgment from Python.
- JavaScript SDKCall a judgment from JavaScript.
Cases
- Use-case mapWhich primitive people use for which job.
- GuardrailsA yes/no check before an action runs.
- Function callingPick which function to call.
- Classify with confidenceDo not act when the class is unsure.
- Semantic findFind the passages that match.
- Parallel questionsAsk the whole set in one call.
- Hierarchical classificationCoarse class first, then the fine one.
- Citation checkWhether a sentence is supported by the source.
- Entity alignmentWhether two names are the same thing.
- Skill suggestionChoose which skill fits the moment.