Unnamed resource.

GET https://visual.hugen.tokyo/visual/ocr ↗

OCR extraction from scanned PDF documents (English). Uses Tesseract to read text from image-based pages that have no embedded text layer. Returns structured text and metadata. Ideal for invoices, receipts, contracts, and legacy documents. $0.05 per extraction.

Eligibility: probeable
Failures: 0
Last quote: —
Last probe: —

Payment requirements / accepts[] 2 options

State	Network	Scheme	Atomic amount	Asset	payTo / untrusted
active	eip155:8453	exact	50000	0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913	0x29322Ea7EcB34aA6164cb2ddeB9CE650902E4f60
active	solana:5eykt4usfv8p8njdtrepy1vzqkqzkvdp	exact	50000	EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v	4du4AfkjJEwch2zk3shkPJVZfyJHNDnNjEWC6AboaS5Z

All advertised payment options are stored. Base (`eip155:8453`) is the operational network for ranking and canaries; non-Base options remain visible for transparency.

Probe evidence 0 recent

No probe attempts recorded yet. Coverage runs prioritize never-probed endpoints.

Machine contract

Schemas.

InputJSON

{
  "method": "GET",
  "queryParams": {
    "max_pages": "50",
    "url": "https://example.com/scanned-invoice.pdf"
  },
  "type": "http"
}

OutputJSON

{
  "example": {
    "metadata": {
      "file_size_bytes": 1548290,
      "page_count": 3
    },
    "summary_stats": {
      "has_text": true,
      "ocr_pages": 3,
      "total_characters": 2840
    }
  },
  "type": "json"
}