# Arch Tools PDF Extractor

> Arch Tools PDF Extractor is a paid API for AI agents from archtools.dev, paid per call via x402, $0.015/call, status unknown (last checked 2026-09-13).

Extracts text and content from a PDF document provided via URL or base64-encoded data

## Facts

- Endpoint: POST https://archtools.dev/v1/tools/extract-pdf
- Price: $0.015/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/arch-tools-pdf-extractor-d01de818
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ubrI4-G_D_he1uZonE6vA

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 arch-tools-pdf-extractor-d01de818 -d '<json body>'
```

Example prompt: Can you extract all the text from this PDF? Here's the URL: https://example.com/annual-report-2024.pdf

## When to prefer this

Choose this endpoint when you need to programmatically extract text from a PDF document, either by pointing to a public URL or by sending the document as base64. It is ideal for agentic workflows that need to read PDF content before analysis, search, or data extraction. Costs $0.015 USDC per call via x402 micropayment on Base, making it practical for high-volume document processing pipelines.

## Known failure modes

- Invalid or inaccessible PDF URL returns an error
- Malformed base64 string causes parsing failure
- Password-protected or encrypted PDFs may not be extractable
- Very large PDFs may time out or return partial results
- Scanned image-only PDFs without OCR layer may return empty or minimal text
- Neither pdf_url nor pdf_base64 provided results in a validation error

## How this service works

Arch Tools — extract-pdf

## Output

A JSON object containing the extracted text and content from the PDF document, suitable for downstream processing, analysis, or search.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "pdf_url": {
   "type": "string",
   "description": "Public URL of the PDF (max 5MB / 50 pages per call — split larger documents into parts)"
  },
  "pdf_base64": {
   "type": "string",
   "description": "Base64-encoded PDF (alternative to pdf_url; same 5MB / 50-page limit applies)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/arch-tools-pdf-extractor-d01de818/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from archtools.dev](https://www.zero.xyz/host/archtools.dev/llms.txt)