Structured evaluation with TypeSafe's Jev (System One) model
Structured evaluation with TypeSafe's Jev (System One) model. Send any state plus typed questions — noul (true/false), choice (pick one), or score (ordinal scale) — and get back calibrated probabilities and confidence for each. Built for routing, classification, triage and policy checks where a fast, predictable, machine-readable answer beats prose.
Not tested: has real-world effectsour last check, 2026-09-24
0 of 0checks answered this week
n/amedian answer time
$0.001listed price per call
n/aprice it asked us
Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.
Endpoint
POST https://jev-x402.vercel.app/jev
| Category | Everything else |
|---|---|
| Provider host | jev-x402.vercel.app |
| Networks | eip155:8453 |
| Payment schemes | exact |
| Self-reported calls, 30 days | 10 from 2 payers (the provider's figure, not ours) |
Our checks, last 30 days
We never call tools that send, buy, move money or file anything, not even without paying.
Example input (from the provider)
{
"body": {
"model": "jev-latest",
"questions": {
"needs_review": {
"criteria": {
"false": "a routine question a bot can close",
"true": "money, legal, or an unanswered complaint"
},
"instructions": "Does this ticket need a human agent?",
"type": "noul"
},
"route": {
"criteria": {
"billing": "payment or charge problems",
"shipping": "delivery problems",
"technical": "application bugs"
},
"instructions": "Route this ticket to a team.",
"type": "choice"
},
"urgency": {
"criteria": [
"low",
"medium",
"high"
],
"instructions": "How urgent is this ticket?",
"type": "score"
}
},
"state": "My card was charged twice for one order and nobody has replied in three days."
},
"bodyType": "json",
"method": "POST",
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"body": {
"properties": {
"model": {
"description": "Jev model id. Defaults to 'jev-latest'.",
"type": "string"
},
"questions": {
"additionalProperties": {
"properties": {
"criteria": {
"description": "Object of label -> meaning for 'noul'/'choice'; ordered array of labels for 'score'.",
"oneOf": [
{
"type": "object"
},
{
"items": {
"type": "string"
},
"type": "array"
}
]
},
"instructions": {
"type": "string"
},
"type": {
"enum": [
"noul",
"choice",
"score"
],
"type": "string"
}
},
"required": [
"type",
"instructions",
"criteria"
],
"type": "object"
},
"description": "Map of question name -> typed question. Each has a 'type' of 'noul' (true/false), 'choice' (pick one) or 'score' (ordinal scale), an 'instructions' string, and 'criteria'.",
"type": "object"
},
"state": {
"description": "The content to evaluate. String, or a JSON object of fields.",
"oneOf": [
{
"type": "string"
},
{
"type": "object"
}
]
}
},
"required": [
"state",
"questions"
],
"type": "object"
},
"bodyType": {
"enum": [
"json",
"form-data",
"text"
],
"type": "string"
},
"method": {
"enum": [
"POST"
],
"type": "string"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method",
"bodyType",
"body"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"properties": {
"answers": {
"description": "One entry per question asked. 'noul' answers carry a probability; 'choice' answers carry the chosen label, a confidence and per-option probabilities; 'score' answers carry a calibrated score, confidence, legend and per-level probabilities.",
"type": "object"
},
"model": {
"description": "Resolved Jev model version.",
"type": "string"
},
"usage": {
"properties": {
"input_tokens": {
"type": "number"
},
"output_tokens": {
"type": "number"
}
},
"type": "object"
}
},
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}