# Foundry PDF Text Extractor

> Foundry PDF Text Extractor is a paid API for AI agents from minty-sprout.onrender.com, paid per call via x402, $0.001/call, status unknown (last checked 2026-11-01).

Extracts page count, title, author, and the text of the first 20 pages from a PDF at a given URL

## Facts

- Endpoint: POST https://minty-sprout.onrender.com/v1/pdf-text?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-01
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/foundry-pdf-text-extractor-5d21c971
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_vbr-C63bc_pHaYo9gzflT

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 foundry-pdf-text-extractor-5d21c971 -d '<json body>'
```

Example prompt: Can you pull the text out of this PDF for me? https://example.com/report.pdf — I want to know the title, author, how many pages it has, and what the text says.

## When to prefer this

Choose this endpoint when you need to programmatically read text from a publicly accessible PDF URL without downloading and parsing the file locally. It is ideal for agents that need to summarize, index, or analyze PDF content on the fly. Prefer it over general web scrapers when the target is specifically a PDF document. It is limited to the first 20 pages, so for full extraction of very long documents an alternative may be needed.

## Known failure modes

- Invalid or inaccessible URL returns an error — PDF must be publicly reachable
- Non-PDF URLs may fail to parse or return empty/incorrect output
- Very large PDFs are truncated after 20 pages (truncated: true in response)
- Password-protected or encrypted PDFs cannot be extracted
- Scanned image-only PDFs (no embedded text) will return empty text
- Slow or unreliable remote PDF hosts may cause timeout errors

## How this service works

PDF text extractor: page count, title, author and text of the first 20 pages of a PDF URL. Input: a PDF URL.

## Output

Returns a JSON object containing the PDF's URL, extracted text (up to the first 20 pages), total page count, pages read, title, author, character count, and a truncated flag indicating whether the document was cut off due to length.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string",
   "maxLength": 8000,
   "description": "A PDF URL"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
  "text": "Dummy PDF file",
  "pages": 1,
  "title": null,
  "author": "Evangelos Vlachogiannis",
  "truncated": false,
  "characters": 14,
  "pages_read": 1
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/foundry-pdf-text-extractor-5d21c971/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from minty-sprout.onrender.com](https://www.zero.xyz/host/minty-sprout.onrender.com/llms.txt)