# Document OCR - Text, Tables, Fields

OCR for scans, photos and PDF pages: image to text, a table as HTML, or exactly the fields you name as JSON.

Send a PNG, JPEG or WebP image, or a PDF with the page you want, by link or as base64. Choose text for everything on the page, table for a table as HTML, or fields with a list of names (invoice number, total, IBAN, anything) to get exactly those back as JSON. One page per call, usually a few seconds. The model runs on our own hardware in the EU: documents are read in memory, never stored and never sent to anyone else. A model can misread; check amounts before you rely on them.

- Name the fields you want (invoice number, total, IBAN, anything) and get exactly those back as JSON, not a wall of text.
- Table extraction: a table comes back as HTML with its rows and columns kept.
- Documents are read in memory on our own hardware in the EU, never stored and never sent to anyone else.

## Calls

### `POST https://readymadeapi.com/v1/documents/read`

Read one page from an image or PDF. mode=text returns the text, mode=table returns the table as HTML, mode=fields fills in the JSON fields you list.

- Price: $0.0028 per page
- MCP tool: `document_reader_read`
- Answers in the same call.

Request:

```json
{
  "fields": {
    "currency": "",
    "invoice_number": "",
    "issue_date": "",
    "seller_vat_id": "",
    "total_text": ""
  },
  "file_url": "https://readymadeapi.com/samples/invoice.png",
  "mode": "fields"
}
```

Answer:

```json
{
  "mode": "fields",
  "fields": {
    "currency": "EUR",
    "invoice_number": "2026-104",
    "issue_date": "2026-11-19",
    "seller_vat_id": "RO12345678",
    "total_text": "15.172,50"
  }
}
```

## Limits

- One page per call: PNG, JPEG, WebP or one page of a PDF.
- By link, up to 15 MB.
- Up to 40 field names in fields mode.

## Questions

**Which files?**

PNG, JPEG, WebP, or one page of a PDF, by link (up to 15 MB) or as base64. One page per call, usually a few seconds.

**How do I get amounts right?**

End a field name in _text, such as total_text, to get the number exactly as printed. A model asked for a plain number can turn 15.172,50 into 15.1725. For invoices and receipts, our Invoice OCR & Parser and Receipt OCR & Parser listings do this for you.

**Does it read handwriting?**

It is built and tested for printed documents. We do not promise handwriting.

**How long does a page take?**

Usually a few seconds. A call that runs past 25 seconds fails and is not charged.

## Using it

- Send `Authorization: Bearer <key>` and a JSON body. Keys and credit: https://readymadeapi.com/account
- Every answer carries `X-Request-Id`, `X-Units` and `X-Charged-Usd`.
- An error is a JSON problem with a `title` to act on and a `detail` in plain words; nothing is charged for it.
- Full schema: https://readymadeapi.com/openapi.json
