Hallucination check for RAG
Hallucination check for RAG: is a claim supported by the source text? Returns supported, unsupported, contradicted or uncertain with probabilities, so an agent can verify an answer before showing it.
Answeringour last check, 2026-10-20
1 of 1checks answered this week
655 msmedian answer time
$0.0173listed price per call
$0.0176price 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://verdict.kechlab.com/v1/grounding
| Category | Everything else |
|---|---|
| Provider host | verdict.kechlab.com |
| Networks | eip155:8453 |
| Payment schemes | exact |
| Self-reported calls, 30 days | 0 from 0 payers (the provider's figure, not ours) |
Our checks, last 30 days
| Day | Result | HTTP | Asked | Time |
|---|---|---|---|---|
| 2026-10-20 | valid payment request | 402 | $0.0176 | 655 ms |
Example input (from the provider)
{
"body": {
"claim": "Customers have 30 days to ask for a refund.",
"source": "Our refund period is 14 days after delivery."
},
"bodyType": "json",
"method": "POST",
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"body": {
"properties": {
"claim": {
"description": "the claim to verify",
"type": "string"
},
"source": {
"description": "the reference text",
"type": "string"
}
},
"required": [
"source",
"claim"
],
"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": {
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}