Extract text via OCR
~3 credits / page (up to 3000)Runs OCR over a scanned PDF or a standalone document image and returns the recognized content as markdown per page, in reading order, with tables reconstructed as markdown tables. Use `pages` to limit which pages are processed on long documents (billing is per page processed).
Use when
You have a scanned PDF or a photo of a document with no selectable text layer and need its contents as text.
Not for
PDFs that already have a selectable text layer (pdf extract_text is cheaper), describing photos, or translating.
Cost
~3 credits / page (up to 3000)
Billed at 1.5 credits per page processed.
Estimated; the actual charge depends on your input and is shown in the response.
What it accepts
Set these inside the intent when you run it.
Pre-signed GET URL of the scanned PDF or document image to read.
Optional 0-indexed page numbers to process. Defaults to all pages.
What you get back
The recognized text as markdown per page, in reading order, with tables preserved.
Run it
Run this sub-skill directly: pin it with operation and pass its inputs in the intent. (Omit operation and the OCR skill will route from your intent instead.)
curl -X POST "https://skill.askfaro.com/skills/ocr/run" \
-H "Authorization: Bearer $FARO_TOKEN" \
-H "Content-Type: application/json" \
-d '{"intent":{"operation":"extract","document":"https://files.example.com/uploads/scan.pdf?sig=...","pages":"[0, 1]"}}'Example requests
- ›Extract the text from this scanned PDF
- ›OCR this photo of a receipt
- ›Read the tables out of this scanned report as markdown