# SiteCheck Entity Extraction

> SiteCheck Entity Extraction is a paid API for AI agents from api.sitecheck-api.workers.dev, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-28).

Extracts named entities (people, places, organisations, emails, phones, dates, money, URLs) from a URL or raw text using an LLM plus regex/libphonenumber

## Facts

- Endpoint: POST https://api.sitecheck-api.workers.dev/api/entities?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-28
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sitecheck-entity-extraction-5b4d6547
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ylavYqsdULGCJ9f5mdl3r

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 sitecheck-entity-extraction-5b4d6547 -d '<json body>'
```

Example prompt: Can you extract all the people, organisations, email addresses, phone numbers, and places mentioned on https://example.com/about-us and give me a structured list?

## When to prefer this

Choose this endpoint when you need structured named-entity extraction from either a live URL or raw text in a single pay-per-call step, without managing your own NLP pipeline. It combines LLM-based name extraction with regex/libphonenumber for contacts, making it stronger than pure-regex approaches for mixed content. Prefer it over general LLM chat when you want a guaranteed structured JSON response with deduplicated, counted entities rather than free-text output.

## Known failure modes

- Text exceeds 12,000 character limit — request rejected or truncated
- URL is inaccessible or returns non-HTML content — may return empty entity arrays
- LLM hallucination of entity names not present in source text
- Regex misses non-standard phone/email formats
- Payment not received — HTTP 402 returned before processing
- Groq fallback unavailable — increased latency or failure

## How this service works

Named entities in a text or a page: people, organisations, places, dates and money amounts (from the chat model), plus e-mail addresses, URLs and phone numbers (from patterns), each de-duplicated with a count. With url, the page's readable text is used (robots.txt is respected).

## Output

A JSON object with arrays for people, places, organisations, emails, phones, dates, money, and URLs — each entry includes the entity value and a count of occurrences. Also includes the model used, data source description, and a checkedAt timestamp.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Or a page address, https://…"
  },
  "text": {
   "type": "string",
   "description": "Text, up to 12,000 characters"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": null,
  "urls": [],
  "dates": [
   {
    "name": "1843",
    "count": 1
   }
  ],
  "model": "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
  "money": [],
  "emails": [
   {
    "count": 1,
    "value": "ada@example.org"
   }
  ],
  "people": [
   {
    "name": "Ada Lovelace",
    "count": 1
   },
   {
    "name": "Charles Babbage",
    "count": 1
   }
  ],
  "phones": [
   {
    "count": 1,
    "value": "+442079460958"
   }
  ],
  "places": [
   {
    "name": "London",
    "count": 1
   }
  ],
  "source": "chat model (Workers AI, Groq fallback) for names; regex and libphonenumber for e-mails, URLs and phones",
  "checkedAt": "2026-10-14T07:05:00.000Z",
  "organisations": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sitecheck-entity-extraction-5b4d6547/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.sitecheck-api.workers.dev](https://www.zero.xyz/host/api.sitecheck-api.workers.dev/llms.txt)