PDF to JSON
PDFs in. JSON out.
Upload a PDF, born-digital or scanned, forward it by e-mail or send it to the API. Parsevix reads every page and returns the data as JSON, in your own fields or named with the document's own labels. Try it with the real documents in the demo.
- Text PDFs and scanned PDFs alike
- Up to 30 pages per file
- Your own fields, or no schema at all
No credit card · 20 free pages every month
We blacked out the names of private persons. Nothing is uploaded: the demo replays the stored result.
Two ways to shape the JSON
Your schema, or none at all.
The same document can come back in the fields you defined, or in the fields it has. Pick per upload, per e-mail address or per API call.
With a category
Name the fields you need once, or start from a built-in category such as Invoice or Contract. Every document of that kind comes back in the same shape, with ISO dates and plain numbers.
- invoice_number
- invoice_date
- seller_info
- line_items
- total_due
- currency
Built-in categories for invoices, receipts, contracts, IDs and more; your own for everything else.
Without a schema
Send the document without a category and get every field Parsevix finds, named with the document's own labels and in its language, values as printed. The demo above works this way.
The start of the shoe-shop receipt's result, as it came back.
How a PDF is read
Every page, every line.
PDFs come from accounting systems, scanners and e-mail attachments, with and without a text layer. Parsevix treats them all the same way.
Every page read as an image
Parsevix renders each page and reads it with OCR, even when the PDF has a text layer, so text in stamps, scanned pages and embedded images is read too. The language is detected on every page, and the lines go to the extraction in reading order.
- 02
Tables become lists
Rows of a table come back as a list, one item per row, also when the table continues on the next page.
- 03
Long documents in one go
A PDF of up to 30 pages is read and extracted as one document, so totals and line items from different pages end up in one result.
- 04
Many languages and scripts
Latin, Cyrillic, Greek, Arabic, Chinese, Japanese and Korean script among others; the language is detected on every page.
- 05
Personal data masked
Names, addresses and numbers are masked automatically before any text goes to the AI model and put back in your result. Detection catches most personal data, not necessarily every item.
- 06
Every value linked to its page
Each value is linked to the spot on the page it came from. Click it in the dashboard to see where it was printed.
- 07
PDFs from your inbox
Forward e-mails with PDF attachments to your project's address, and each attachment becomes a document.
How PDFs get in
Upload them, forward them or send them from your system.
Dashboard
Drop PDFs into the dashboard, one at a time or many at once. Check each result next to its pages and approve it.
E-mail address
Paid plansEvery project gets its own address. Forward PDFs to it, and each attachment becomes a document.
API
Send PDFs from your own system and get the JSON in the same response, or receive results by signed webhook or through Zapier.
Request
curl https://parsevix.com/api/v1/extract-auto \ -H "X-API-Key: $PARSEVIX_API_KEY" \ -F file=@invoice.pdf
The request stays open until the document is read and answers with the JSON.
- POST /documentsUpload without waiting; the result arrives by webhook or callback.
- POST /extract-autoNo category: every field Parsevix finds, named as in the document.
- POST /classifyOnly the document's category, for 1 credit.
Response · trimmed
Security & compliance
- PII maskedautomatically, before the AI step
- Encryptedin transit and at rest
- No AI trainingon your documents
- API files deletedafter processing
Priced per page, not per feature.
Every plan reads, sorts and masks documents the same way. Picking the category is included, and a document that fails costs nothing.
See pricing- credit per page
- 1
- free pages every month
- 20
- a month for 500 pages
- $39
PDF to JSON FAQ
PDF to JSON,
answered.
What people ask before they convert their first PDFs.
Up to 10 MB and 30 pages per file. A longer PDF has to be split into files, and each part comes back as a result of its own.
Yes. Every page is read as an image, so a scan without a text layer is read the same way as a PDF straight from an accounting system.
A PDF that needs a password to open can't be read and fails with a clear error. Remove the password, then upload it again.
Yes. A Word file (DOCX) is turned into a PDF first and then read like any other PDF.
One credit per page: a ten-page PDF uses ten. Choosing the category is included, and if a document fails, its credits are given back.
PDFs uploaded in the dashboard or sent by e-mail stay in your project until you delete them. Files sent through the API are deleted after processing unless you turn on keeping them for the project. Your documents are never used to train AI.
Related use cases
Documents that travel with this one.
Invoice parser
Supplier, totals, VAT and every line item from invoices in any layout.
Contract data extraction
Parties, dates, value and the main clauses of a contract.
Bank statement converter
Account, balances and every transaction from statement PDFs.