# falcon.sol PDF to Text/Markdown

> falcon.sol PDF to Text/Markdown is a paid API for AI agents from falcon-docs.falcon-sol.workers.dev, paid per call via x402, $0.0025/call, status unknown (last checked 2026-10-31).

Converts a PDF (via URL or base64) to plain text or markdown with page-by-page extraction, including automatic OCR for scanned pages

## Facts

- Endpoint: POST https://falcon-docs.falcon-sol.workers.dev/v1/pdf-text?utm_source=zero.xyz
- Price: $0.0025/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-31
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/falcon-sol-pdf-to-text-markdown-51e103eb
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_F5ILrqyeVsgIHzLTF5Exq

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 falcon-sol-pdf-to-text-markdown-51e103eb -d '<json body>'
```

Example prompt: Can you extract the text from this PDF — https://example.com/report.pdf — and give it back to me in markdown format so I can use it in my RAG pipeline?

## When to prefer this

Choose this endpoint when you need fast, low-cost PDF text extraction for AI pipelines — especially when you need per-page text in reading order, automatic OCR fallback for scanned pages, or markdown output with structure preserved. Ideal for RAG document ingestion workflows where cost per document matters ($0.0025 USDC). Prefer over generic document parsers when you need both text-layer and OCR in a single call without managing infrastructure.

## Known failure modes

- PDF exceeds 60 pages or 4 MB size limit — request rejected
- Invalid or inaccessible URL — returns error if PDF cannot be fetched
- Corrupt or password-protected PDF — extraction fails or returns empty
- Completely blank PDF returns empty result (not charged)
- base64 encoding errors cause parse failure
- Network timeout if remote PDF URL is slow to respond

## How this service works

Bank statement extraction for agents: transactions and underwriting metrics from bank-statement PDFs, plus invoice/receipt/W-9 extraction. Paid per call with x402.

## Output

Returns a JSON object with the full extracted text, total page count, word count, output format used, extraction method (text_layer or OCR), and an array of per-page objects each containing character count and method used. For markdown format, headings, bullet points, and table rows are preserved.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public https URL of a PDF"
  },
  "type": {
   "enum": [
    "auto",
    "invoice",
    "receipt",
    "purchase_order",
    "w9",
    "bank_statement",
    "generic"
   ],
   "type": "string"
  },
  "format": {
   "enum": [
    "json",
    "csv",
    "xlsx"
   ],
   "type": "string"
  },
  "file_base64": {
   "type": "string",
   "description": "Base64 PDF (alternative to url, or send multipart 'file' / raw application/pdf)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "text": "INVOICE\nInvoice # INV-1042 ...",
  "pages": 2,
  "words": 140,
  "format": "text",
  "method": "text_layer",
  "page_texts": [
   {
    "page": 1,
    "chars": 812,
    "method": "text_layer"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/falcon-sol-pdf-to-text-markdown-51e103eb/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from falcon-docs.falcon-sol.workers.dev](https://www.zero.xyz/host/falcon-docs.falcon-sol.workers.dev/llms.txt)