# call402 Text Extract API

> call402 Text Extract API is a paid API for AI agents from call402.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-30).

Extracts the main readable text content from any public webpage URL using Mozilla Readability, returning clean body text, title, excerpt, and metadata

## Facts

- Endpoint: POST https://call402.com/api/text-extract?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/call402-text-extract-api-887a27ee
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nFK8V5pSEBKP-siBYXn3w

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 call402-text-extract-api-887a27ee -d '<json body>'
```

Example prompt: Pull the full readable text from https://www.bbc.com/news/technology-12345678 so I can summarize it.

## When to prefer this

Choose this endpoint when you need clean, readable main-body text from a public webpage without dealing with HTML parsing yourself. It's ideal for feeding article content into summarization, Q&A, or analysis pipelines. Prefer it over raw HTML scrapers when you want Readability-processed prose rather than full DOM content. Best for news articles, blog posts, documentation pages, and other text-heavy public URLs. Avoid it for paywalled, login-required, or JavaScript-heavy single-page applications.

## Known failure modes

- URL is not publicly accessible or requires authentication — extraction will fail or return empty content
- Page is JavaScript-rendered (SPA) with no server-side HTML — Readability may return little or no text
- URL points to a PDF, image, or non-HTML resource — not supported
- Malformed or invalid URL in request body — likely 4xx error
- Page blocks server-side crawlers via robots.txt or IP blocking — may return empty or partial content
- Payment not attached or invalid PAYMENT-SIGNATURE header — returns HTTP 402 with payment requirements

## How this service works

USDC pay-per-call APIs for AI agents via the x402 protocol (v2, exact, Base mainnet). Send a request, receive HTTP 402 with payment requirements, pay with @x402/fetch or any x402 client, retry with the PAYMENT-SIGNATURE header.

## Output

Returns a JSON object containing: the original URL, the full readable body text extracted by Mozilla Readability, the page title, a short excerpt/summary, total character count, a boolean indicating whether the text was truncated, and metadata about the extractor used.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public http(s) page URL to extract"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/article",
  "meta": {
   "extractor": "mozilla readability (apache-2.0), first-party servers"
  },
  "text": "Full readable body text...",
  "chars": 4200,
  "title": "Example article",
  "excerpt": "Short summary",
  "truncated": false
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/call402-text-extract-api-887a27ee/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from call402.com](https://www.zero.xyz/host/call402.com/llms.txt)