# Claim Evaluator

> Claim Evaluator is a paid API for AI agents from claim-evaluator.com, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-14).

Scores the likelihood (0–100) that a factual claim is true, returning reasoning and cited web sources

## Facts

- Endpoint: POST https://claim-evaluator.com/v1/evaluate
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/claim-evaluator-518ea8fa
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_7OfaT52-7jlvGEjrWFOGn

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability claim-evaluator-518ea8fa -d '<json body>'
```

Example prompt: Can you fact-check this claim for me and give it a truth score from 0 to 100 with sources: 'The Eiffel Tower is taller than the Empire State Building'?

## When to prefer this

Choose this endpoint when you need a structured, sourced truth score for a specific factual claim — especially to validate LLM-generated statements, fact-check user assertions, or add citation-backed credibility scoring to a pipeline. It is purpose-built for single-claim evaluation with a numerical score and cited stances, making it ideal over general web search when you need structured verification output rather than raw search results.

## Known failure modes

- Claim is too vague or opinion-based — endpoint performs best on concrete, checkable statements
- No reliable sources found for very obscure or niche claims — may return sources with 'unclear' stance
- LLM hallucination in reasoning if claim touches highly specialized domains
- Rate limiting or payment failure if USDC balance is insufficient for the $0.05 per-call fee
- Empty or malformed `claim` field returns a validation error

## How this service works

Evaluate the likelihood of an LLM statement being true — with sources. Score 0–100, reasoning, and cited web sources. Pay per call via MPP.

## Output

A JSON object containing: a `likelihood` score (0–100 integer, where 0 = definitely false and 100 = definitely true), a `reasoning` string (2–3 sentence assessment of the evidence), and a `sources` array of 3–5 web sources each with a name, URL, stance (confirm/deny/unclear), and a brief summary of what that source says about the claim.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "claim"
 ],
 "properties": {
  "claim": {
   "type": "string",
   "description": "Single factual claim to score. Prefer concrete, checkable statements over opinions or forecasts."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "likelihood",
  "reasoning",
  "sources"
 ],
 "properties": {
  "sources": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "name",
     "url",
     "stance",
     "summary"
    ],
    "properties": {
     "url": {
      "type": "string"
     },
     "name": {
      "type": "string"
     },
     "stance": {
      "enum": [
       "confirm",
       "deny",
       "unclear"
      ],
      "type": "string"
     },
     "summary": {
      "type": "string"
     }
    }
   },
   "maxItems": 5,
   "minItems": 3
  },
  "reasoning": {
   "type": "string",
   "description": "2–3 sentence assessment"
  },
  "likelihood": {
   "type": "number",
   "maximum": 100,
   "minimum": 0,
   "description": "0 = definitely false, 100 = definitely true"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/claim-evaluator-518ea8fa/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from claim-evaluator.com](https://www.zero.xyz/host/claim-evaluator.com/llms.txt)