Research paper to Markdown and LaTeX
A two-column page from the LLaMA paper with a table, a figure, inline math and a footnote. OXR keeps the table, the section headings and the reading order.
Check: one table cell reads "52°" instead of "52".
Powered by the OXR-1.0 document model
OXR: turn images & PDFs into editable text
Drop a scan, photo or PDF here and get clean Markdown, plain text or JSON back. Tables, formulas, headings and reading order are kept, so the output is ready to edit.
- Tables & formulas
- Markdown · Text · JSON
- PDFs up to 50 pages
Plans from $10.42/mo · 1 credit = 1 page
OXR workbench
§01 — Examples
OXR examples
Real pages and the unedited OXR output for each. Open one to compare them side by side.
Financial statement to Markdown tables
Page 5 of the U.S. Monthly Treasury Statement: two dense tables with multi-line headers, subtotals and negative values, rebuilt as Markdown tables.
Check: totals and negative values came through as printed; compare any figures you rely on.
Receipt photo to item lines
A phone photo of a long supermarket receipt. OXR lists every item with quantity, unit price and amount, plus the totals.
Check: "1 @" quantities read as "10", and the store address has two typos.
§02 — Definition
What is OXR?
OXR is an AI OCR tool that turns scanned documents, photos and PDFs into clean, editable text.
It runs on the OXR-1.0 document model, which reads a page the way a person does: headings, paragraphs, tables, formulas and multi-column layouts come back in reading order. Paste the output into Word, Notion or Google Docs, or feed the JSON into your own code.
Tables stay tables
Rows and columns come back as real Markdown tables instead of a jumble of words, so invoices, statements and spec sheets keep their structure.
Formulas as LaTeX
Equations in papers, exams and textbooks come out as LaTeX you can paste into Overleaf or any Markdown editor.
Reads the layout
Two-column papers, newspapers and forms are read in the right order. Running headers, footers and page numbers can be dropped for you.
Markdown, text or JSON
Copy or download results as Markdown, plain text, or JSON with block types and coordinates for every paragraph, table and formula.
§03 — Workflow
How to use OXR
Three steps, no software to install.
- 1
Upload your file
Drop a PDF of up to 50 pages or a photo or scan of a page into the workbench above.
- 2
Choose your options
Choose whether to detect heading levels and whether to keep headers and footers. The page count and credit cost show before you start.
- 3
Extract and download
Click Extract text. You get Markdown, plain text and JSON that you can copy or download right away.
§04 — Pricing
OXR pricing
Every plan includes the full tool. Pick the number of pages you need each month, or buy a credit pack.
Basic
For occasional scans and receipts
$10.42/mo$14.90
billed yearly · $0.017 / page
- 600 credits / month ≈ 600 pages
- Email support
- Markdown, plain text and JSON export
- Tables rebuilt as Markdown tables
- Formulas exported as LaTeX
- Heading and layout detection
- PDFs up to 50 pages, files up to 20 MB
- Failed pages refunded automatically
- Commercial use, no watermark
- Uploads deleted after processing; results kept 15 days
Pro
For weekly reports, papers and invoices
$20.75/mo$29.90
billed yearly · $0.017 / page
- 1,220 credits / month ≈ 1,220 pages
- Priority email support
- Lower price per page than Basic
- Markdown, plain text and JSON export
- Tables rebuilt as Markdown tables
- Formulas exported as LaTeX
- Heading and layout detection
- PDFs up to 50 pages, files up to 20 MB
- Failed pages refunded automatically
- Commercial use, no watermark
- Uploads deleted after processing; results kept 15 days
Max
For teams and heavy document workflows
$41.58/mo$59.90
billed yearly · $0.017 / page
- 2,460 credits / month ≈ 2,460 pages
- Priority email support
- Lowest price per page
- Markdown, plain text and JSON export
- Tables rebuilt as Markdown tables
- Formulas exported as LaTeX
- Heading and layout detection
- PDFs up to 50 pages, files up to 20 MB
- Failed pages refunded automatically
- Commercial use, no watermark
- Uploads deleted after processing; results kept 15 days
§05 — FAQ
OXR FAQ
Answers to common questions about pricing, files and privacy.
What is OXR?
OXR is an online AI OCR tool. You upload an image or a PDF and OXR returns the text as Markdown, plain text and JSON. OXR is powered by OXR-1.0, a document parsing model that keeps tables, formulas, headings and reading order.
What can OXR extract from a document?
OXR extracts printed text, headings, lists, tables (as Markdown tables) and math formulas (as LaTeX). Pictures inside the document are skipped, so results are text only.
How do I use OXR, and how long does it take?
Sign in, drop your file into the workbench at the top of this page and click Extract text. A single image usually takes a few seconds; a long PDF can take a minute or two.
Is OXR free? How do credits work?
There is no free plan. Every page costs 1 credit, and an image counts as one page. Subscriptions add credits every month, and unused subscription credits expire at the end of each monthly cycle. Credit packs are a one-time purchase and never expire.
Which files does OXR support?
OXR reads PDF files with up to 50 pages and PNG, JPG, WEBP, BMP, TIFF, GIF and HEIC images. Each file can be up to 20 MB.
Can I use OXR results commercially?
Yes. You own your documents and the extracted text, and you can use it in commercial work on any plan. No watermark is added.
Are my files private, and how long are results kept?
Files travel over HTTPS and are used only to process your request; uploaded files are kept only while they are processed and deleted as soon as processing ends. Extracted text is kept in your History for 15 days so you can download it again, then deleted automatically. Download anything you want to keep before then.
What happens if OXR fails to read my file?
If OXR cannot process a file, the credits for it are refunded automatically and nothing is deducted. Try a sharper scan, or split very large PDFs into smaller parts.
§06 — Start
Put OXR on your next document
Scans, photos and PDFs become editable text in seconds.
Try OXR now