AI PDF chat
Upload a PDF and ask questions about it. The PDF is parsed in your browser; only the extracted text and your question go to your chosen AI provider.
About this tool
Instead of skimming a long PDF yourself, this tool lets you ask it questions. The file — up to 20 MB and 500 pages — is parsed locally in your browser with PDF.js, and when you ask something, the extracted text (capped at 100,000 characters) plus your question is sent to the AI provider behind your own key. Contracts, manuals, research papers and reports are the typical candidates.
Two boundaries follow from how it works. The answers come from the document’s embedded text, so a scanned PDF with no text layer cannot be read — this tool performs no OCR. And very long documents are represented by the text that fits the cap, so answers are strongest for documents of moderate length.
How to use AI PDF chat
- Add your provider API key in the key panel (stored only in your browser).
- Choose a PDF (up to 20 MB). It is parsed locally — the file never leaves your device.
- Ask questions about the document. Only the extracted text goes to the provider you chose.
Keep the original files and inspect the exported result before publishing or sharing it.
Frequently asked questions
How does PDF chat work?
Your PDF is parsed in the browser with PDF.js. When you ask a question, the extracted text (up to 100,000 characters) plus your question is sent to the AI provider you selected.
Does the PDF leave my browser?
No. The file is parsed locally; only the extracted text is sent to the AI provider as part of your question.
What about scanned PDFs?
Scanned PDFs contain no embedded text — this tool does not do OCR. Use a text-based PDF.
How large can the PDF be?
Up to 20 MB and 500 pages. Extracted text sent to the AI is capped at 100,000 characters.
Related tools
- AI chat — Chat with OpenAI, Claude or Gemini using your own API key. Your key stays in your browser; requests go straight to the provider.
- AI summarizer — Summarize long text with your own OpenAI, Claude or Gemini API key. Brief, detailed or bullet-point summaries, all in your browser.
- AI translator — Translate text between 30 languages with your own OpenAI, Claude or Gemini API key. Private by design: key and text stay with you and the provider.
- AI writing assistant — Improve, expand, shorten or re-tone your writing with your own API key. Six editing modes, direct browser-to-provider calls.
- AI code explainer — Paste code and get a plain-English explanation using your own OpenAI, Claude or Gemini API key. Language auto-detect included.
- AI image analyzer — Upload an image and let AI describe it, extract text (OCR), or identify objects. Uses vision models from OpenAI, Claude or Gemini with your own key.
- AI voice generator — Turn text into natural-sounding speech with OpenAI TTS. Six voices, speed control, play in the browser and download MP3.
- AI data analyst — Upload a CSV and ask questions in plain English. The file is parsed locally; the AI sees only a schema summary and sample rows.
- Background remover — Remove image backgrounds entirely in your browser with a local AI model. No API key needed — the model downloads once and runs on your device.
- AI spend analyzer — Turn your AI provider usage export into an independent cost receipt: per-model and per-day breakdowns, spike alerts and a monthly projection. Runs 100% in your browser — your billing data is never uploaded.