# PDF Table Extractor (x402)

> PDF Table Extractor (x402) is a paid API for AI agents from well-001-extract-table.mmelnyk2000.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-20).

Extracts structured tables from a PDF document (via URL or base64) and returns them as JSON with page numbers, headers, and rows

## Facts

- Endpoint: POST https://well-001-extract-table.mmelnyk2000.workers.dev/mcp?utm_source=zero.xyz#extract-table-from-pdf#extract-table-from-pdf
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pdf-table-extractor-x402-d3d173a0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nCtE5zYbZzDDcxzvNpE-j

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 pdf-table-extractor-x402-d3d173a0 -d '<json body>'
```

Example prompt: Can you extract all the tables from this PDF report and give me the data as structured JSON? Here's the URL: https://example.com/annual-report.pdf — check up to 5 pages.

## When to prefer this

Choose this endpoint when you need to programmatically extract structured tabular data from text-based PDFs and want a cheap per-call ($0.01 USDC) serverless solution. It supports both base64-encoded PDFs and HTTPS URLs, and allows optional schema mapping for known column headers. Best for text PDFs; scanned PDFs require an external hosted parser. Prefer this over general-purpose PDF tools when you need clean JSON output with per-table, per-page structure.

## Known failure modes

- PDF URL is not publicly accessible or requires authentication — returns error
- PDF is a scanned image and no HOSTED_PARSER_URL is configured — tables cannot be extracted, warning returned
- max_pages exceeds allowed range (1-10) — validation error
- base64 encoding is malformed — parse error
- PDF has no tabular content — returns empty tables array
- Payment of $0.01 USDC not completed via x402 — request rejected

## How this service works

Extract tables from a PDF ($0.01 USDC via x402). Pass pdf_base64 or a https pdf_url. Optional schema maps headers. Optional max_pages (1-10). Returns JSON { pages, tables: [{ page, headers, rows }], warnings }. Text PDFs are parsed in-worker; scans require HOSTED_PARSER_URL.

## Output

Returns a JSON object containing: total page count processed, an array of tables (each with the page number it appeared on, an array of header strings, and a 2D array of row data), and any warnings (e.g. about scan-based pages that couldn't be parsed in-worker).

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pdf-table-extractor-x402-d3d173a0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from well-001-extract-table.mmelnyk2000.workers.dev](https://www.zero.xyz/host/well-001-extract-table.mmelnyk2000.workers.dev/llms.txt)