# ScrapFly Keywords Extraction

> ScrapFly Keywords Extraction is a paid API for AI agents from scrapfly.vercel.app, paid per call via x402, $0.05/call, status unknown (last checked 2026-10-24).

Extracts a list of keywords from a given text passage, with optional control over the number of keywords returned.

## Facts

- Endpoint: POST https://scrapfly.vercel.app/api/content/keywords?utm_source=zero.xyz
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-24
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/scrapfly-keywords-extraction-a8d43d97
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_kNDngbOk5Pzkf2YdK13QV

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 scrapfly-keywords-extraction-a8d43d97 -d '<json body>'
```

Example prompt: Can you extract the top 10 keywords from this article text: 'Artificial intelligence is rapidly transforming industries including healthcare, finance, and education. Machine learning models now power everything from drug discovery to fraud detection...'?

## When to prefer this

Use this endpoint when you need fast, pay-per-use keyword extraction from arbitrary text without managing NLP infrastructure. Ideal for agents processing one-off documents, articles, or passages where spinning up a full NLP pipeline is overkill. Prefer this over general LLM summarization when you specifically need a structured keyword list rather than a prose summary.

## Known failure modes

- Empty or missing text field returns an error
- Very short text may yield fewer keywords than requested count
- Non-English or mixed-language text may produce lower quality results
- Count parameter exceeding available meaningful terms may return fewer keywords than requested
- Network or payment failures may result in no response

## How this service works

69 endpoints for data, content generation, and web scraping. Pay per request via x402 on Base chain.

## Output

Returns a JSON object with a success boolean and a data object containing the extracted keywords list derived from the input text. The number of keywords returned can be controlled via the optional count parameter.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string",
   "description": "text"
  },
  "count": {
   "type": "number",
   "description": "count"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "success"
 ],
 "properties": {
  "data": {
   "type": "object"
  },
  "success": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/scrapfly-keywords-extraction-a8d43d97/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from scrapfly.vercel.app](https://www.zero.xyz/host/scrapfly.vercel.app/llms.txt)