Tool · Search inside PDF Beta
Find anything in your PDF.
Instantly. Privately.
Drop a PDF, type a question, get the exact passages with page numbers in under 50 ms. No upload, no account, no AI download. Your file never leaves this tab.
No upload · No API key
Common questions
Frequently asked questions
How is this different from Ctrl+F?
It searches the extracted text of the whole document and ranks passages, then jumps you to the page a result came from — useful when you know roughly what was said but not the exact wording. Ctrl+F needs the literal string; this does not.
Does it work on scanned documents?
Only if the pages carry a text layer. A scan is an image until it has been through OCR, so run Make Searchable first and the search will then find text on those pages.
Does search upload my PDF to a server?
No. The file is opened, processed and saved back by code running in this browser tab — there is no upload endpoint on our servers to send it to. You can watch the Network panel in your browser's developer tools while you work and confirm nothing carrying the document leaves the page.
Is Search inside PDF free?
Search inside PDF is free, with no account required and no page or file-size caps imposed by the plan. No model download and no account are involved.
Does it work offline?
Yes. Once the page has loaded, every tool keeps working with the network disconnected, because the processing never depended on a server round-trip. AI features that use an on-device model need one download the first time; after that they run offline too.
Search Inside PDF runs in your browser. Try it now.
No account, no upload, no watermark on the way out. Open a file and see for yourself — the network panel is right there if you want to check.