Free tools › Understand
Split PDF by topic
No page numbers to type: the model reads each page and finds where the topics change.
This one runs on your credits. No page numbers to type: the model reads each page and finds where the topics change.
Sign in and get 500 free credits every month — enough for many files — then drop the file in the workbench and run split pdf by topic there.
Pick a file below to see exactly what it would cost.
More free conversions, where you upload. The Fylane extension does the same work inside any upload form, on its own free share every day.Add to Chrome
How to split PDF by topic
- Sign in — 500 free credits a month.
- Drop the PDF (up to 60 pages).
- Run Split and download the ZIP of sections.
What happens to your file
The first words of every page go to the Qwen 2.5 model in Fylane’s own sandbox with one question: where do the topics change? Its answer — titles and start pages — is made lawful (sorted, starting at page 1) and the PDF is cut at those pages into one file per section, named “01 - Title.pdf”, with report.json listing every boundary. Nothing leaves the platform.
A document the model reads as one topic comes back unsplit and says so; a scan with no text layer is refused with the advice to OCR first.
Questions
How accurate are the boundaries?
Good where chapters open with a heading on a fresh page; rougher where topics change mid-page, since the cut is always at a page edge. Check report.json against the table of contents where there is one, and use Split PDF by page range to adjust.
Why sixty pages?
The model reads every page’s opening in one pass; sixty keeps that within its context and a job within its minutes.
Do it once, not on every form
Fixing a file here means downloading it and going back to the form. The Fylane extension does this work inside the form instead, on the file you already have.
And it keeps the result. The next application that asks for a résumé, a cover letter and a photo fills all three from one tap, each one refitted to what that site accepts.
Your files stay in the browser, encrypted, on your machine. Nothing is uploaded to keep them and nothing is sent anywhere to fill a form.
Related tools
Do this in code
curl -X POST https://api.fylane.dev/v1/jobs \
-H "Authorization: Bearer $FYLANE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"file_id": "<file id>",
"operation": "pdf.split-topics",
"options": {}
}'The same operation, pdf.split-topics — A PDF of up to 60 pages divided into its topics by the sandbox model reading each page’s opening words: a ZIP of one PDF per section, named by title, with report.json naming the boundaries. Upload first with the quickstart; every option is on the operations page. 500 free credits a month, then $5 per thousand.