# Machina Agent Services – PDF Large Document Extractor

> Machina Agent Services – PDF Large Document Extractor is a paid API for AI agents from mach402.dev, paid per call via x402, $0.18/call, status unknown (last checked 2026-10-22).

Extracts full text content from large PDF documents (up to 200 pages) and returns structured Markdown along with page and word counts

## Facts

- Endpoint: POST https://mach402.dev/pdf/extract/large?utm_source=zero.xyz
- Price: $0.18/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-22
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/machina-agent-services-pdf-large-document-extractor-9c86a706
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_rXKLMDMD1CLA_MHfmiruT

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 machina-agent-services-pdf-large-document-extractor-9c86a706 -d '<json body>'
```

Example prompt: Can you extract all the text from this large PDF document — it's about 120 pages — and give me the content in markdown format along with the page count and word count?

## When to prefer this

Choose this endpoint when dealing with large PDFs up to 200 pages that need full-document text extraction into Markdown. It is specifically optimized for large documents (as opposed to smaller/standard PDF extraction endpoints on the same service). Prefer this over general-purpose PDF tools when you need structured Markdown output with metadata like page and word counts, and when your workflow supports x402 micropayment authentication.

## Known failure modes

- PDF exceeds 200-page limit — request rejected or truncated
- Malformed or corrupted PDF bytes — parsing error returned
- Non-PDF binary content submitted — content-type mismatch error
- Payment not completed via x402 protocol — 402 Payment Required returned
- Scanned/image-only PDF with no embedded text — empty or minimal markdown output
- Request timeout for extremely large or complex documents

## How this service works

x402-powered API services for AI agents

## Output

Returns a JSON object containing: 'markdown' (the full extracted document text formatted as Markdown), 'page_count' (total number of pages processed), and 'word_count' (total word count of the extracted content).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "http://json-schema.org/draft-07/schema#",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType"
   ],
   "properties": {
    "body": {
     "type": "string",
     "description": "Raw PDF bytes (Content-Type: application/pdf), max 200 pages"
    },
    "type": {
     "const": "http"
    },
    "method": {
     "const": "POST"
    },
    "bodyType": {
     "const": "json"
    }
   }
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "const": "json"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "markdown": "# Title\n\nContent...",
  "page_count": 120,
  "word_count": 45000
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/machina-agent-services-pdf-large-document-extractor-9c86a706/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mach402.dev](https://www.zero.xyz/host/mach402.dev/llms.txt)