API
API
Call judgments from your own program with an API key. Sign up and get $$5.00 in credit. Same as jev-1.13.0: input tokens only, $$0.042 per million, output free.
Issue a key on your account page. The plaintext is shown once; the server keeps only its sha256.
Get a key on your account pageAuthentication
Every /v1/* request needs a Bearer key. Keys only — session cookies are not accepted, so browser sign-in and billed API calls stay separate.
Authorization: Bearer jev_...Endpoints
POST /v1/judge | Run one judgment. Billed on the input tokens of this call, and only after it succeeds. Upstream failures are not charged. |
GET /v1/me | Current user, balance, and total spend. |
GET /v1/usage | Balance, total spend, and recent ledger entries. |
Request body (/v1/judge)
state | The text to judge, 8–4000 chars. |
questions | Up to 6 questions; keys must be lowercase-letter identifiers. |
Question types
noul | Relevance, returns a float 0–1. |
confidence | Confidence, returns a float 0–1. |
choice | Pick one option and return the chosen string. Send an options array or a criteria object; options are folded into criteria before the model sees them. |
Response
Balance after this call.
{
"id": "k3f9a1c2b4d5",
"model": "clavue-jev",
"answers": {
"relevance": { "noul": 0.92 },
"confidence": { "noul": 0.78 },
"severity": { "choice": "medium" }
},
"credit": { "cents": 500, "usd": "5.00", "microUsd": 5000000, "inputTokensLeft": 119047619 }
}The credit object
{
"cents": 500,
"usd": "5.00",
"microUsd": 5000000,
"inputTokensLeft": 119047619
}cents | Remaining balance rounded to the nearest cent. usd and microUsd are exact. |
usd | USD string. Small amounts keep microdollar digits. |
microUsd | Remaining microdollars. 1 USD = 1,000,000. |
inputTokensLeft | Input tokens this balance still covers at $0.042 per million. |
Errors
| Status | error | |
|---|---|---|
401 | unauthorized / invalid_api_key | Missing or invalid API key. |
400 | invalid_request | State too short, or no questions. |
429 | quota_exceeded | Not enough balance; includes retry-after. |
502 | upstream_unavailable | Judgment backend is down. Not charged. |
Example
curl https://api.jevcode.ai/v1/judge \
-H "Authorization: Bearer jev_..." \
-H "Content-Type: application/json" \
-d '{
"state": "The build failed on the second job, then passed after a retry.",
"questions": {
"relevance": { "type": "noul", "instructions": "Is this about CI?" },
"confidence": { "type": "confidence", "instructions": "How sure are you?" },
"severity": { "type": "choice", "instructions": "Pick one.",
"options": ["low", "medium", "high"] }
}
}'Keep going on this site
Try, docs, cases, and pricing link to each other. The next page is on this site.
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.
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.
- 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.