Powered by Unlimited OCR 2 · open 3B model
Drop in a scanned PDF or photo. Unlimited OCR 2 reads every page in order and returns clean Markdown, with headings, tables and formulas where they belong.
Unlimited OCR 2 plans from $6.58/mo. No free tier, no watermark.
Unlimited OCR 2 plans from $6.58/mo. No free tier, no watermark.
The model and the tool
Unlimited OCR 2 is an online OCR tool that turns long scanned documents into editable Markdown and plain text, using the open-source Unlimited OCR 2 model that reads a file as one ordered document instead of a pile of separate pages.
The Unlimited OCR 2 model is a 3B vision-language model released under the MIT license. Its sparse reference attention keeps memory nearly flat as pages are added, so a 300-page report goes through in a single request. We run the model for you: no GPU, no setup, just a browser tab.
Send a complete book chapter, contract or annual report, up to 800 pages per file. Unlimited OCR 2 keeps context across pages, so a table that breaks over a page stays one table.
Unlimited OCR 2 returns multi-column layouts in the order a person would read them. Tables become Markdown tables and formulas are kept as LaTeX, ready for your editor or notebook.
Preview the result, copy it, or download .md and .txt files. Every Unlimited OCR 2 job stays in your history until you delete it.
On Unlimited OCR 2, 1 credit reads one page and an image counts as one page. If a job fails, the credits go straight back to your balance.
How it works
Three steps from a scan to text you can edit. No install, works on phone and desktop.
Choose a PDF, PNG, JPG, WEBP file or drag it onto the Unlimited OCR 2 studio. The page count and the credit cost appear right away.
Tell Unlimited OCR 2 to read the whole file or only a page range, and pick Markdown or plain text as the main output.
Unlimited OCR 2 reads the pages in order while a progress bar counts them. Preview, copy, or download .md and .txt.
Pricing
On Unlimited OCR 2, one credit reads one page. A plan refills credits every month at the lowest rate; a pack adds credits that never expire.
For occasional scans and short reports
Billed yearly · 33% off
For regular work with long PDFs
Billed yearly · 33% off
For archives, books and team volumes
Billed yearly · 33% off
Pay once, no subscription. Pack credits never expire and are used after plan credits.
A handful of documents
A project's worth of scans
Books, archives and backlogs
All prices in US dollars. Any tax is added at checkout.
FAQ
Files, pricing, privacy and the model. Still stuck? Write to us from the contact page.
Unlimited OCR 2 is an online OCR tool for long documents. You upload a scanned PDF or an image, and the open-source Unlimited OCR 2 model reads the pages in order and returns Markdown or plain text with headings, tables and formulas kept. It runs in your browser with nothing to install.
Unlimited OCR 2 keeps headings, paragraphs, lists, tables (as Markdown tables), formulas (as LaTeX) and the reading order of multi-column pages. Pictures are not exported as image files; their captions and any text inside them are kept as text.
Unlimited OCR 2 accepts PDF, PNG, JPG, WEBP. PDFs up to 50 MB, images up to 20 MB, one file per job. A document can have up to 50 pages with credit packs and up to 800 pages on the largest plan; for longer files, read them in page ranges. Password-protected PDFs are not supported.
Unlimited OCR 2 usually returns a single image in a few seconds. Long PDFs are read page by page while a counter shows progress; a few hundred pages can take several minutes. You can leave the page open or come back later: the finished result waits in your dashboard.
There is no free tier. Every page you read costs 1 credit and an image counts as one page, so a 40-page PDF costs 40 credits. Credits come from a monthly or yearly plan, or from one-time packs that never expire. The cost is shown before you start.
Credits are taken when a job starts. If Unlimited OCR 2 cannot read the file or the job fails, the full amount returns to your balance automatically and the job is marked as failed in your history. Scans that are very blurry or rotated may give weaker text, so check the preview before you rely on it.
Uploaded files and results are stored privately in your account and are only used to run your Unlimited OCR 2 job. They are never shared, published or used to train models. You can delete a job, together with its source file and result, from your dashboard at any time.
Yes. The text you extract with Unlimited OCR 2 belongs to you and can be used in commercial work. There is no watermark and no attribution requirement. You are responsible for having the rights to the documents you upload.
Unlimited OCR 2, a 3-billion-parameter open-source OCR model released by Baidu under the MIT license and designed for documents of hundreds of pages. This website is an independent service that runs the open model; it is not affiliated with Baidu.
Upload a PDF to Unlimited OCR 2 and have editable Markdown in minutes.
Open the OCR studio