# Agent Evidence API – Claim Verification

> Agent Evidence API – Claim Verification is a paid API for AI agents from agent-evidence.thx93.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-22).

Verifies a factual claim or question against up to 5 provided URLs, returning cited evidence passages that support, contradict, or fail to settle the claim.

## Facts

- Endpoint: POST https://agent-evidence.thx93.dev/v1/evidence?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-22
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-evidence-api-claim-verification-d5e18b5a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_9g6FFH7sSHGf7Tebod2nM

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 agent-evidence-api-claim-verification-d5e18b5a -d '<json body>'
```

Example prompt: Can you verify whether 'Acme Corp is the largest producer of industrial valves in North America' is supported by what's on these two pages: https://acmecorp.com/about and https://acmecorp.com/manufacturing?

## When to prefer this

Choose this endpoint when you need verifiable, cited evidence from specific URLs to support or refute a factual claim — particularly when auditability matters (content hashes, retrieval times). It is ideal for due diligence workflows, pre-publication fact-checking, or any scenario where you need traceable sourcing rather than a generative answer. Prefer it over general web search APIs when you already have candidate URLs and need passage-level citations. Note that matching is lexical, not semantic, so it works best for specific, concrete factual claims.

## Known failure modes

- URLs are inaccessible or return non-200 status — source flagged with warning, no excerpt returned
- Question is too vague for lexical matching — assessment may be 'unresolved' even with relevant pages
- Content behind paywalls or requiring authentication cannot be retrieved
- Non-HTML content types may not be parsed — warnings included in response
- Rate limiting or network timeouts on target URLs may result in partial results

## How this service works

Verify a claim or fact check a statement against public web sources: send a question and up to 5 URLs, get cited evidence - passages that support, contradict or fail to settle it. Claim verification with a citation for every excerpt: source URL, retrieval time, content hash. Never charges when nothing is retrieved. Free to evaluate: the `sample` tool returns one real response at no cost, so you can judge the output before paying for your own question.

## Output

A structured JSON response containing an assessment status (supported, contradicted, or unresolved), one or more evidence excerpts with source URL, content context, relevance classification, retrieval timestamp, and SHA-256 content hash per source, plus a plain-English basis statement, processing time in milliseconds, and a unique request ID. Nothing is charged if no content is retrieved.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "properties": {}
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "sources": [
   {
    "title": "Company X - About",
    "status": 200,
    "evidence": [
     {
      "context": "h2:Products > p[1]",
      "excerpt": "Company X manufactures centrifugal pumps at its facility.",
      "relevance": "direct"
     }
    ],
    "language": "en",
    "warnings": [],
    "final_url": "https://company.example/about",
    "publisher": "Company X",
    "word_count": 412,
    "content_type": "text/html; charset=utf-8",
    "retrieved_at": "2026-01-01T00:00:00.000Z",
    "canonical_url": "https://company.example/about",
    "requested_url": "https://company.example/about",
    "content_hash_sha256": "9f2c…"
   }
  ],
  "version": "1",
  "question": "Is Company X a manufacturer of centrifugal pumps?",
  "assessment": {
   "basis": "1 source(s) contained passages matching the question (company.example) with no contradicting passages found.",
   "status": "supported"
  },
  "request_id": "req_1f2e3d4c5b6a7988",
  "limitations": [
   "Assessment is derived from deterministic lexical matching, not semantic reasoning."
  ],
  "processing_ms": 812
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-evidence-api-claim-verification-d5e18b5a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-evidence.thx93.dev](https://www.zero.xyz/host/agent-evidence.thx93.dev/llms.txt)