# PDF Parser & Table Extractor

> PDF Parser & Table Extractor is a paid API for AI agents from visual.hugen.tokyo, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Extracts structured text, tables as JSON arrays, and metadata from any PDF URL on a pay-per-use basis

## Facts

- Endpoint: GET https://visual.hugen.tokyo/visual/parse
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/visual-hugen-tokyo-3a41e326
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_xh0O3yuALFoHrDJrDNe1F

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 visual-hugen-tokyo-3a41e326
```

Example prompt: Can you extract all the text and any tables from this PDF — https://example.com/annual-report-2024.pdf — and give me the document metadata like title, author, and page count?

## When to prefer this

Use this endpoint when you need to extract structured content from a PDF hosted at a public URL without setting up any local PDF libraries, OCR infrastructure, or browser automation. Ideal for document intelligence pipelines, data extraction from reports, invoices, research papers, or any PDF with tabular data.

## Known failure modes

- Invalid or inaccessible PDF URL returns an error
- Password-protected PDFs cannot be parsed
- Very large PDFs may time out
- Non-PDF URLs will fail or return unexpected results
- Scanned image-only PDFs may yield empty text if no OCR is performed

## How this service works

Extract structured text, tables, and metadata from any PDF URL. Returns page-by-page text content, detected tables as JSON arrays, and document metadata (title, author, page count). No PDF library or OCR setup needed — pay per extraction. AI agent API for document intelligence and data extraction

## Output

Returns page-by-page text content, all detected tables as JSON arrays (rows and columns), and document metadata including title, author, and total page count — all structured and ready to use programmatically.

## Example request

```json
{
 "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
 "max_pages": 1
}
```

## Request schema (JSON Schema)

```json
{
 "properties": {
  "input": {
   "required": [
    "method"
   ]
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "metadata": {
   "title": "Q1 2026 Financial Report",
   "page_count": 12,
   "file_size_bytes": 284672
  },
  "summary_stats": {
   "has_text": true,
   "total_tables": 3,
   "total_characters": 18420
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/visual-hugen-tokyo-3a41e326/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from visual.hugen.tokyo](https://www.zero.xyz/host/visual.hugen.tokyo/llms.txt)