Do I get an Excel file?

Yes, an .xlsx file with each table on its own sheet. It opens in Excel, Numbers and Google Sheets.

Can it read a handwritten table?

Yes, if the writing is clear and columns are lined up. Check the numbers before you rely on them.

Can I do many images at once?

Through the API, yes. Each image returns its table; combine them in your own script.

Will it read a chart and give me the data?

Only if the values are printed on the chart. It does not estimate values from bar heights or line positions.

Yes, 3 pages a day without an account. Sign up for 200 free credits if you need more.

What happens to my file?

Files are deleted after 24 hours. We do not train on them.

Convert image to Excel

Photograph or screenshot a table and get it back as an Excel file with real rows and columns.

Result

Your Markdown or JSON shows up here.

3 free pages a day, no sign-up.

How it works

1Upload a photo or screenshot of the table
2We read the rows and columns
3Download the .xlsx file

Why use this Image to Excel converter

From a phone photo
Works on photos of printed sheets, whiteboards and screens, not only clean scans.
Columns stay aligned
Each value stays in its column, which is what breaks when you copy text from an image by hand.
Checkable
The table is plain text, so you can scan it for misreads before it goes into a spreadsheet.

What people use it for

Putting a printed price list or timetable into a spreadsheet
Digitising handwritten tally sheets and logs
Copying a table from a screenshot of a website or app
Getting data from a photographed report page

Models that do this well

The free tool picks one for you. With the API you choose, and can set fallbacks so a failed page is retried on the next model.

1Gemini FlashGeneral vision model with strong handwriting and layout understanding at a low price.google/gemini-flash3 credits / page 2Mistral OCRFast document OCR that returns clean Markdown with tables and embedded images.mistral/mistral-ocr6 credits / page 3Azure Document IntelligenceAzure layout model with tables, selection marks and prebuilt invoice and ID readers.azure/document-intelligence15 credits / page 4GPTGeneral vision model. Good at messy scans and following extraction instructions.openai/gpt11 credits / page

Do it with the API

Converting more than a few files? The same conversion is one request. Pick any model, or let auto choose.

Get API key

curl https://api.ocrrouter.ai/v1/ocr \
  -H "Authorization: Bearer $OCRROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "file_url": "https://example.com/invoice.pdf",
    "format": "markdown"
  }'

Questions

OCR API by document and language

Receipt OCR API Business card OCR API Bengali OCR API Portuguese OCR API Ukrainian OCR API Urdu OCR API