# Citation & Hallucination Checker — x402 ZadenWorks

> Citation & Hallucination Checker — x402 ZadenWorks is a paid API for AI agents from x402-zadenworks.zaden-gaming.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Verifies whether a claimed quote or fact actually appears at a given URL, returning exact_match, close_match with confidence score and closest passage, or not_found.

## Facts

- Endpoint: POST https://x402-zadenworks.zaden-gaming.workers.dev/verify
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/citation-hallucination-checker-x402-zadenworks-2fe8e15e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_odFWVqjL0b8eBZglL04t6

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 citation-hallucination-checker-x402-zadenworks-2fe8e15e -d '<json body>'
```

Example prompt: Can you check whether the quote 'AI systems will surpass human intelligence by 2030' actually appears on https://example.com/ai-report — tell me if it's an exact match, a close match, or not found at all?

## When to prefer this

Choose this endpoint when you need a lightweight, cheap ($0.01) programmatic check to verify whether AI-generated citations are real or hallucinated, or to confirm a specific quote or fact appears at a claimed URL. It is ideal for post-generation hallucination audits in RAG pipelines, research assistants, or content review workflows. Prefer it over full content extraction endpoints when the goal is specifically pass/fail citation verification rather than broad content analysis.

## Known failure modes

- URL is behind a paywall or login wall — page content inaccessible, returns not_found or error
- URL is dynamically rendered and content not accessible to scraper — may miss content
- Claimed quote is paraphrased so loosely that semantic matching fails to detect it
- Network timeout or unreachable URL returns an error response
- Very long pages may truncate, causing a legitimate passage to be missed
- Payment failure via x402 protocol results in 402 response before any verification occurs

## How this service works

Fourteen pay-per-call web tools for AI agents, billed in USDC on Base with no account or API key. START WITH /audit -- one call returns a complete page health check (SEO + structured data + accessibility, optionally plus links and sitemap) with a single score and one worst-first findings list. The parts are also sold individually. SITE AUDIT: /seo (on-page SEO and meta tags), /links (broken links), /sitemap (robots.txt and XML sitemap crawlability), /structured (JSON-LD and social preview tags), /a11y (WCAG accessibility) -- each scored 0-100 with a prioritised issue list. READING: /read (clean markdown), /snap (screenshot, PDF or rendered HTML), /tables (every HTML table as structured JSON), /verify (does a claim actually appear on this page). MONITORING: /watch (has this page changed), /compare (what differs between two pages). Plus /rank (best x402 service for a task) and /batch (several operations behind one payment).

## Output

Returns one of three match types: 'exact_match' if the claimed text is found verbatim; 'close_match' with a numeric confidence score (0–1) and the closest matching passage from the page; or 'not_found' if no semantically similar content exists. This allows the caller to assess whether a citation is valid, approximate, or fabricated.

## 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": {
     "type": "object",
     "required": [
      "url",
      "claim"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Public http/https URL to check the claim against"
      },
      "claim": {
       "type": "string",
       "description": "The quote or fact to verify appears on the page (max 2000 chars)"
      },
      "waitMs": {
       "type": "integer",
       "maximum": 5000,
       "minimum": 0
      },
      "selector": {
       "type": "string"
      }
     }
    },
    "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",
     "properties": {
      "verdict": {
       "enum": [
        "exact_match",
        "close_match",
        "not_found"
       ],
       "type": "string"
      },
      "confidence": {
       "type": "number"
      },
      "matchedText": {
       "type": [
        "string",
        "null"
       ]
      },
      "closestParagraph": {
       "type": [
        "string",
        "null"
       ]
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com",
  "verdict": "exact_match",
  "confidence": 1,
  "matchedText": "domain is for illustrative examples"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/citation-hallucination-checker-x402-zadenworks-2fe8e15e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-zadenworks.zaden-gaming.workers.dev](https://www.zero.xyz/host/x402-zadenworks.zaden-gaming.workers.dev/llms.txt)