📄 OCR & Documents

Read text from images and PDFs. Multilingual — no language setting needed.

from $3.00 / 1,000 POST /v1/query USDC on Base · x402

What you get

Images: $3/1k — receipts, invoices, scans, photos
PDF: $20/doc-1k — up to 10 pages per request
Multilingual: Cyrillic, Latin, CJK, Arabic — all at once
Long documents handled with page markers
No language configuration required

Tools in this group

Tool	What it does	Docs
`ocr_document`	Text from images	Full docs →
`ocr_pdf`	Text from PDFs	Full docs →

Request

curl -X POST https://api.serp-base.com/v1/query \
  -H "Content-Type: application/json" \
  -d '{"tool": "ocr_document", "image": "<base64-encoded-image>"}'

Key parameters

Field	Description
`image / pdf`	Base64-encoded file
`pages`	Page range for PDF

Response

{
  "text": "INVOICE #1047 ...",
  "pages": 1,
  "language": "auto"
}

Payment: pay per request with USDC on Base via the x402 protocol. Gas is covered by the facilitator. Charged only when data is returned. Test the whole flow free on Base Sepolia.

Read full API docs → Get API key