# ForgeMesh PDF to Text

> ForgeMesh PDF to Text is a paid API for AI agents from x402.forgemesh.io, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Fetches a public PDF URL and returns its full plain text content with layout preserved, up to 25MB or ~100 pages.

## Facts

- Endpoint: POST https://x402.forgemesh.io/pdf-to-text
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/forgemesh-pdf-to-text-af96a993
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_agV_l_ucG0gA2SRxDef8e

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 forgemesh-pdf-to-text-af96a993 -d '<json body>'
```

Example prompt: Can you pull all the text out of this PDF for me? Here's the URL: https://example.com/report.pdf — I need the plain text with the layout kept intact.

## When to prefer this

Use this endpoint when you have a public URL to a native (non-scanned) PDF and need its plain text quickly. Prefer this over /pdf-to-markdown when OCR is not needed and speed matters. Choose this over general-purpose scraping tools when the target is specifically a PDF document and layout-aware text extraction is important.

## Known failure modes

- PDF URL is not publicly accessible or returns a 403/404 — request fails
- PDF exceeds 25MB or ~100 pages — request rejected with size/page limit error
- PDF is scanned/image-based and requires OCR — text extraction will be poor or empty (use /pdf-to-markdown for OCR)
- URL does not point to a valid PDF file — parsing error returned
- Network timeout fetching the remote PDF — request fails

## How this service works

PDF to text API: fetches any public PDF URL and returns its full plain text, fast, with layout preserved. For scanned PDFs needing OCR see /pdf-to-markdown. 25MB / ~100 page cap. Nothing stored.

## Output

Full plain text of the PDF document with layout preserved, extracted from the provided public URL. No data is stored server-side. Covers PDFs up to 25MB or approximately 100 pages.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "pdf_url": {
   "type": "string",
   "description": "Public URL of a PDF file, max 25MB"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "text": "Hello World"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/forgemesh-pdf-to-text-af96a993/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.forgemesh.io](https://www.zero.xyz/host/x402.forgemesh.io/llms.txt)