# Agent Toolbox – Structured Data Extraction from Web/PDF/Text

> Agent Toolbox – Structured Data Extraction from Web/PDF/Text is a paid API for AI agents from agent-toolbox.zafermemon87.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-30).

Extracts named fields as structured JSON from a URL, PDF, or raw text, returning each value with the exact source quote and a verification status

## Facts

- Endpoint: POST https://agent-toolbox.zafermemon87.workers.dev/v1/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/agent-toolbox-structured-data-extraction-from-web-pdf-text-400c3093
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_l0yAQ1yJwt6HbF7N_vfWR

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 agent-toolbox-structured-data-extraction-from-web-pdf-text-400c3093 -d '<json body>'
```

Example prompt: Go to https://www.example.com/product/widget-pro and extract these fields for me: product_name (string: the product title), price (number: the listed price in USD), and availability (string: in stock or out of stock) — and show me the exact quote from the page for each one.

## When to prefer this

Choose this endpoint when you need to extract specific named fields from an arbitrary web page, PDF, or block of text and require cited evidence (source quotes) for each value rather than a plain scrape. It is especially valuable when auditability matters — each extracted value is tied to a verbatim quote that is verified against the source, so values are never hallucinated. Prefer it over generic LLM extraction when you need structured JSON with provenance, or over raw scraping when you need selective field targeting rather than full-page content.

## Known failure modes

- URL is not publicly accessible or requires authentication — field returns not_found
- PDF is encrypted or scanned image — text extraction fails
- Requested field genuinely absent from document — returns not_found with null value
- Text input exceeds 60,000 character limit — request rejected
- More than 25 fields requested — request rejected
- Malformed field definition (wrong type string) — validation error
- Network timeout fetching URL — extraction error returned

## How this service works

Extract structured JSON from a web page, PDF or text: name the fields you want (up to 25, with types) and get each value with the exact quote from the page that states it. Every quote is checked against the page itself (verified, quoted, unverified or not_found), so values are never invented. Charged only when at least one field is found.

## Output

A JSON object mapping each requested field name to its extracted value, the exact verbatim quote from the source that supports that value, and a verification status (one of: verified, quoted, unverified, or not_found) indicating how confidently the quote was matched back to the source document.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "A public http(s) URL"
  },
  "text": {
   "type": "string",
   "description": "Text to read instead of a URL (up to 60,000 characters)"
  },
  "fields": {
   "type": "object",
   "description": "Field name -> \"type: what it is\" (types: string, number, integer, boolean), e.g. {\"price\": \"number: the current price\"}; a JSON Schema with properties also works",
   "additionalProperties": {
    "type": "string"
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-toolbox-structured-data-extraction-from-web-pdf-text-400c3093/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-toolbox.zafermemon87.workers.dev](https://www.zero.xyz/host/agent-toolbox.zafermemon87.workers.dev/llms.txt)