# falcon.sol Full Document Extraction

> falcon.sol Full Document Extraction is a paid API for AI agents from falcondocs.vercel.app, paid per call via x402, $0.03/call, status unknown (last checked 2026-10-31).

Extracts all fields, line items, and metadata from invoices, receipts, POs, W-9s, and generic PDFs with confidence scores.

## Facts

- Endpoint: POST https://falcondocs.vercel.app/v1/extract?utm_source=zero.xyz
- Price: $0.03/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-full-document-extraction-1082d996
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_9c-nzhyOwVaWGCw3IMlES

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-full-document-extraction-1082d996 -d '<json body>'
```

Example prompt: Can you extract all the fields and line items from this invoice PDF I'm uploading — I need the invoice number, total, and every line item with quantities and unit prices pulled out as structured data.

## When to prefer this

Choose this endpoint when you need full document extraction across all pages of structured financial documents like invoices, receipts, POs, or W-9s and require confidence scores alongside each extracted field. It is specifically optimized for these document types rather than arbitrary OCR. Prefer this over the sibling OCR endpoint when you need parsed, structured fields rather than raw text, and over the bank statement endpoint when the document is not a bank statement.

## Known failure modes

- Unsupported file format (non-PDF, non-image input) returns an error
- Low-quality or heavily corrupted PDFs may produce low confidence scores or missing fields
- Password-protected PDFs may fail to extract
- Very large documents beyond page limits may be truncated or rejected
- Network timeout for large multi-page documents
- Payment failure via x402 if USDC balance is insufficient

## How this service works

falcon.sol: Full document extraction (all pages) for invoices, receipts, POs, W-9s and generic PDFs. $0.03 USDC.

## Output

A JSON object containing the document type (e.g. 'invoice', 'receipt', 'W-9'), a fields map where each key has a value and a confidence score (0-1), and an array of line items each with amount, quantity, unit price, and description.

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "fields": {
   "total": {
    "value": 1180.5,
    "confidence": 0.99
   },
   "invoice_number": {
    "value": "INV-1042",
    "confidence": 0.93
   }
  },
  "line_items": [
   {
    "amount": 1000,
    "quantity": 4,
    "unit_price": 250,
    "description": "Consulting"
   }
  ],
  "document_type": "invoice"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/falcon-sol-full-document-extraction-1082d996/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from falcondocs.vercel.app](https://www.zero.xyz/host/falcondocs.vercel.app/llms.txt)