# Cited Brief Page Text Extractor

> Cited Brief Page Text Extractor is a paid API for AI agents from cited-brief.cited-brief.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-17).

Fetches and returns the plain text content of a public web page, up to a configurable character limit, paid per call in USDC via x402.

## Facts

- Endpoint: POST https://cited-brief.cited-brief.workers.dev/page-text?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-17
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/cited-brief-page-text-extractor-97fb31a8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_lSIG1O-33ZNcFsSdL1sCE

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 cited-brief-page-text-extractor-97fb31a8 -d '<json body>'
```

Example prompt: Can you read the text on https://openai.com/pricing and return up to 50000 characters so I can see what their plans cost?

## When to prefer this

Use this endpoint when you need to retrieve the plain text content of a specific, known public webpage for reading, summarization, or research purposes and want a simple per-call pay-as-you-go model in USDC with no subscription. Prefer it over general-purpose scrapers when you want a clean text output without HTML parsing overhead.

## Known failure modes

- URL is not publicly accessible or returns a non-200 HTTP status — endpoint may return an error or empty text
- Page is behind authentication or a paywall — text returned may be empty or just the login prompt
- Page is JavaScript-rendered with no server-side HTML — text extraction may be incomplete or empty
- max_chars below minimum (100) or above maximum (100000) — request rejected with validation error
- Payment not included or insufficient USDC — 402 Payment Required response before content is returned
- URL is malformed or points to a non-HTTP resource — request rejected

## How this service works

Pay-per-call web research tools for AI agents, paid in USDC over x402.

## Output

Returns a JSON object containing the extracted plain text of the page (up to the requested character limit), the page title, the final URL after any redirects, the number of characters returned, and a boolean indicating whether the text was truncated due to the limit.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public http(s) page to read"
  },
  "max_chars": {
   "type": "integer",
   "maximum": 100000,
   "minimum": 100,
   "description": "Maximum characters of text to return (default 20000)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com/pricing",
  "text": "Pricing\nPro & Teams: Pro costs $10 per user/month when billed annually, or $12 monthly.",
  "chars": 74,
  "title": "Pricing",
  "final_url": "https://example.com/pricing",
  "truncated": false
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/cited-brief-page-text-extractor-97fb31a8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from cited-brief.cited-brief.workers.dev](https://www.zero.xyz/host/cited-brief.cited-brief.workers.dev/llms.txt)