# Evidence Extractor from URL

> Evidence Extractor from URL is a paid API for AI agents from red-breeze-8b8c.keenanbooker83.workers.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Extracts factual evidence, quotations, dates, names, organizations, and numbers from a public source URL

## Facts

- Endpoint: POST https://red-breeze-8b8c.keenanbooker83.workers.dev/extract-evidence
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/evidence-extractor-from-url-1da1d195
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_4-jOF3YIvLeIaRfqN33PT

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 evidence-extractor-from-url-1da1d195 -d '<json body>'
```

Example prompt: Can you pull all the key facts, quotes, names, dates, and numbers from this article — https://example.com/article — and focus specifically on claims about climate policy?

## When to prefer this

Choose this endpoint when you need to pull structured factual entities — quotes, dates, names, organizations, numbers — from a single public URL, especially as a first step before fact-checking, claim verification, or research synthesis. Prefer it over general web scraping tools when you specifically want named entity and evidence extraction rather than raw HTML or full-text retrieval. It pairs naturally with sibling endpoints for fact-checking, conflict detection, and source credibility evaluation.

## Known failure modes

- Source URL is inaccessible, paywalled, or returns a non-200 response — extraction fails with an error
- URL points to a binary file (PDF, image) that cannot be parsed as text
- Focus instructions are too vague or contradictory, resulting in low-relevance extractions
- Source content is too short or contains no structured factual information
- Rate limiting or bot-blocking on the target URL prevents fetching

## How this service works

CitationVerifier evidence extraction: extract factual evidence, quotations, dates, names, organizations, and numbers from a source

## Output

A structured set of extracted entities and factual evidence from the source URL, including verbatim quotations, specific dates, named people and organizations, and numerical figures, optionally filtered or prioritized by the focus instructions provided.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "focus": {
   "type": "string",
   "maxLength": 2000,
   "minLength": 1,
   "description": "Optional instructions identifying the evidence or subject to prioritize."
  },
  "sourceUrl": {
   "type": "string",
   "maxLength": 2048,
   "minLength": 1,
   "description": "Public URL of the source from which evidence should be extracted."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "agent": "Evidence Extraction Agent",
  "focus": "Extract direct quotations, dates, people, organizations, and numerical evidence.",
  "evidence": [
   {
    "text": "Yesterday, December 7, 1941—a date which will live in infamy...",
    "type": "quotation"
   }
  ],
  "sourceUrl": "https://www.archives.gov/milestone-documents/joint-address-to-congress-declaration-of-war-against-japan",
  "requestAccepted": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/evidence-extractor-from-url-1da1d195/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from red-breeze-8b8c.keenanbooker83.workers.dev](https://www.zero.xyz/host/red-breeze-8b8c.keenanbooker83.workers.dev/llms.txt)