AI DocPrep / save tokens
Stop paying to send invisible XML to the model.
Raw office files are stuffed with formatting metadata that burns tokens and muddies answers. Convert to Markdown first and the same document costs a fraction of the context — with structure the model can actually follow. It's the trick you've seen on the terminal, as an app.
A 40-page PDF is billed as text plus an image of every page.
Upload it raw and you pay for all of it. Convert to Markdown first and you send only the words — which is why the same report drops from tens of thousands of tokens to a few thousand, and fits in the context window with room to spare.
The same document, a fraction of the tokens.
Every file shows its estimated token count and how much it saved versus a raw upload — so you know what you're about to paste before you paste it.
No terminal. Just drop the folder.
Ten mixed documents converted in 38 seconds, fully offline, with the token count and savings shown for every file.
Beyond the token count.
Cheaper every prompt
You pay by the token. Strip the formatting bloat and the same document costs a fraction to send, every single time.
Sharper answers
Clean Markdown headers, lists, and tables give the model a structure it follows — instead of guessing through extraction noise.
Whole folders at once
Drop a directory, get one combined Markdown file with a table of contents. Paste it, or feed it straight to your RAG pipeline.
Convert your next upload first.
Free while it's in beta — no account, nothing to pay. Signed and ready to run on macOS and Windows.