x4PayAPI Market

Document, PDF and OCR APIs for AI agents

Document and PDF extraction APIs turn a file an agent has found into text or structured fields it can use: a PDF into Markdown, an image into text by OCR, or an invoice into vendor, amount and line items. This page keeps Tools, Data and Intelligence listings that mention PDF, OCR, document extraction or parsing, extracting text, or invoice and receipt parsing, or whose name says PDF, OCR, document or invoice. Some go the other way and render a PDF, and they are included because an agent working with documents needs both. Discovery is free in the PayAPI Market catalogue. The agent pays the provider per call over x402 in USDC on Base, Solana or Algorand, with no API key and no upload account. Settlement-verified means a paid route with an on-chain receipt, and the examples are claimed listings that have one. Unclaimed (bazaar) imports are labelled and appear afterwards. Listing is free and the provider keeps 100% of every settled call.

29 APIs and 370 endpoints match this page. 13 are settlement-verified: a paid route with an on-chain receipt.

Settlement-verified examples

Unclaimed (bazaar) imports

These rows were imported and the provider has not claimed them. They are not the examples above.

Related pages

Questions

How does an agent send a document to these APIs?

Usually as a public URL or as base64 in the request body. Size and page limits differ by listing, and the description states them.

Are uploaded documents stored?

That depends on the provider, so read its terms before sending anything private. PayAPI Market never sees the document, because the agent calls and pays the provider directly.

Can it read scanned documents?

Listings that offer OCR can read images and scanned pages. Plain PDF to text listings read the text layer only. The listing description says which method it uses.