AI developers are licensing internal records from established companies to train their models. Process manuals, help desk history, CRM notes, project archives, QA logs and team chat all qualify. It is a license, so you keep your data and keep using it. Interested in selling? See if your business fits the program in under a minute.
Is your business eligible?
You're a match. Your business meets the program's requirements. Start your application to get your data valued.
Start My Application →Unfortunately you do not qualify.
Token and word counts for a whole stack of documents in one go, without uploading anything.
Pasting documents into a token counter one at a time is slow and does not work for Word or PowerPoint files at all. This counter takes the whole set. Drag in a group of files or select an entire folder, and each one is opened and measured in your browser. Office files are unpacked so only the real text is counted, not the formatting. For every file you see words, characters and an AI token estimate, and the top of the results shows the grand totals. Copy the table as CSV to keep it in a spreadsheet. Developers use it to plan AI costs and context limits, and business owners use it to see how much written knowledge their company actually holds.
| File | Words | Characters | Est. tokens |
|---|
Multiply the total tokens by the price per million input tokens of the model you plan to use. Then add a margin for prompts, outputs and repeated runs. Knowing the total up front avoids surprise bills.
If the total is below your model context window, you can send the documents in one request. If it is far above, you need retrieval: store the documents in a search index and send only the relevant parts with each question.
Run the counter on your SOP folder, proposals or project archive to see how much documented knowledge your company owns. Large, organized, English language collections are the kind AI companies license from established businesses.
Drop the .docx file into the box above. The tool reads the document text, ignores the formatting and shows the word count, character count and estimated tokens. You can drop many Word files at once.
Yes. Click the folder button and choose a folder. Every supported file inside it, including sub folders, is counted and listed with a combined total at the top.
Not yet. The tool reads .docx, .xlsx, .pptx and plain text formats. Save older Office files in the current format, and copy text out of PDFs, to include them.
The tool divides the character count by four, the standard rule of thumb for English text. Real counts vary a little between models, usually within 10 percent, which is fine for budgeting and planning.
No. Files are read by your browser on your own machine. Nothing is sent to a server, so confidential company documents stay private.