# SiteCheck Keyword Extraction

> SiteCheck Keyword Extraction is a paid API for AI agents from api.sitecheck-api.workers.dev, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-20).

Extracts ranked keywords from text using the RAKE algorithm, returning scored keyword phrases with frequency counts

## Facts

- Endpoint: POST https://api.sitecheck-api.workers.dev/api/text/keywords?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sitecheck-keyword-extraction-c378476f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_HvYQw9K68uRVvpgz14LTO

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-keyword-extraction-c378476f -d '<json body>'
```

Example prompt: Extract the top 15 keywords from this article text using English stopwords and rank them by relevance score: 'Machine learning and deep learning are transforming how we process data and build intelligent systems that adapt over time.'

## When to prefer this

Choose this endpoint when you need lightweight, fast, pay-per-call keyword extraction without setting up an NLP pipeline. It is ideal for agents processing documents in supported European languages (en, de, fr, es, it, pt, nl, tr) that need scored keyword phrases rather than simple word frequencies. Prefer it over embeddings-based approaches when you need human-readable ranked terms rather than vector representations.

## Known failure modes

- Text exceeding 100 KB limit may be rejected or truncated
- Unsupported language codes return an error or fall back to English
- Empty or whitespace-only text returns zero keywords
- Limit values outside 1–50 range may be clamped or cause validation errors
- Very short texts may yield no meaningful keyword phrases

## How this service works

Keywords and keyphrases from a text by RAKE (Rose et al., 2010) in pure code: phrases between stopwords and punctuation, scored by word degree and frequency, with counts. Stopword lists for en, de, fr, es, it, pt, nl and tr. Body { text, language, limit }: up to 100 KB, limit 1 to 50.

## Output

Returns a JSON object containing a list of keyword phrases, each with a relevance score (computed via RAKE algorithm) and occurrence count, along with the total keyword count, the detected or specified language, and the timestamp of the analysis.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "The text, up to 100 KB (JSON body field)"
  },
  "limit": {
   "type": "string",
   "description": "Keywords to return, 1 to 50, default 10"
  },
  "language": {
   "type": "string",
   "description": "en (default), de, fr, es, it, pt, nl or tr"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "count": 4,
  "source": "Computed here (RAKE, Rose et al. 2010), stopword list: short original lists per language",
  "keywords": [
   {
    "count": 1,
    "score": 6.5,
    "keyword": "machine learning"
   },
   {
    "count": 1,
    "score": 5,
    "keyword": "deep learning"
   },
   {
    "count": 1,
    "score": 1,
    "keyword": "data"
   }
  ],
  "language": "en",
  "checkedAt": "2026-10-15T13:48:02.045Z"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sitecheck-keyword-extraction-c378476f/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)