2 credits a document.

That is two cents. There is no plan to choose, no minimum to hit and nothing to cancel — you spend Ounie credits from the same wallet every other Ounie app draws.

Per document

2credits($0.02)

Web pages, PDF, Word, PowerPoint, Excel, HTML, CSV, Markdown, plain text
Images read by OCR at the same price
Markdown, plain text, or JSON shaped to your schema
REST, MCP and keyless x402 — same engine, same price
Up to 50 pages per document; longer PDFs bill per block

Start with your Ounie account Buy credits

Unused reserves come back

Credits are held before the work and settled on what the document turned out to be. Quote four blocks, find text on one, pay for one — the refund is pool-exact and automatic, not a support ticket.

Empty means free

A scan with no text layer, a page that answers with a shell — the reserve refunds in full and no ledger row is written. We'd rather return nothing than charge for it.

Reading is always free

Fetching, exporting or downloading a document you already extracted costs nothing, forever. You paid for it once.

Long documents

The only thing that changes the price is size.

Up to 50 pages is one document. Past that it is 2 credits per 50-page block — and blocks are counted on pages that actually carried text, so a scanned archive doesn't cost you for the pages that turned out to be images of nothing.

Pages with text

121 × 50-page block

You pay

2credits

$0.02

Every 50 pages adds 2credits. Pages with no text layer don't count toward a block.

For agents with no account

$0.024 in USDC, per document, no login.

The x402 endpoint takes payment directly on Base. There is no key to mint, no wallet of ours to top up, and no account to create — POST a URL, get a 402 with terms, sign it, retry. Payment is verified before the work and settled only once the text is out, so an empty or oversized document costs nothing.

x402 docs

Audio and video are billed per minute rather than per document, so they live at transcribe.ounie.com.

Questions

Before you send the first document

What can it actually read?

Web pages, PDFs, Word documents, PowerPoint decks, Excel workbooks, HTML files, CSV, plain text, Markdown, and images (which go through OCR). A URL that points straight at a file is fetched and parsed like an upload; a URL that points at a page is rendered first, because half the modern web only exists after JavaScript runs.

Why not audio and video?

Because the honest billable unit for speech is a minute, not a document, and pretending otherwise would either overcharge a voice memo or undercharge a two-hour recording. Send those to transcribe.ounie.com. Extractor returns a 400 pointing there rather than failing quietly.

What happens to my documents?

The extracted text is stored so you can read it again without paying twice. Long documents spill to private storage and are deleted after 30 days; the row keeps only its metadata after that. Uploaded source files are parsed in memory and never persisted at all.

How accurate is the JSON mode?

It only fills a field from text that is actually in the document. If the document doesn't state a value the field comes back null and the name appears in missing_fields— we would rather hand you a gap you can see than a number that looks right and isn't.

Do I need a subscription?

No. Extractor has no plans and no tiers. You spend Ounie credits per document from the same wallet the rest of the Ounie apps use, and you can stop any time without cancelling anything.

Can an agent run this without an account?

Yes — that is what the x402 endpoint is for. An agent with a USDC wallet on Base pays per call with no login, no key and no wallet of ours to top up. Everything else needs an Ounie account, because credits belong to someone.

Point it at something messy.

A URL, a PDF, a deck someone emailed you. Two credits, a couple of seconds, and text you can actually use.

Start with your Ounie account Read the API docs

No subscription — pay in Ounie credits