Chat with PDF

Commercial use OK 380+ models No watermark No sign-up needed
Model:
+ GPT-5, Claude, Gemini
Upload a PDF, then chat with it. Ask questions, get quotes, pull tables or clauses, cross-reference sections. The AI has read every page. Private — your document never leaves our GPUs and is discarded after the session.

Drag a PDF here or click to upload

PDF up to 50 MB. Text-based PDFs work best. Scanned? Run OCR first.

1 /

PDF loaded. Ask me anything — summaries, quotes, specific clauses, numbers, tables. I have the full document.

~300 tokens per question · 0 chars loaded
Extracting text from PDF…

What Chat-with-PDF is great for

Legal contracts

Ask: who are the parties? What is the termination clause? List every deadline.

Financial filings

Pull specific metrics from a 10-K, earnings call transcript, or investor deck.

Research papers

Explain the methodology, list the datasets, compare results with another paper.

Textbooks

Explain concepts, generate practice problems, quiz yourself on a chapter.

Free.ai PDF Chat vs the paid tools

Free.aiChatPDFHumataAskYourPDF
Starting priceFree$5/mo$14.99/mo$9.99/mo
Pick your LLM
Long-context models (1M tokens)
Works without signup
Multi-turn follow-ups
Advanced options
Result
Tokens running low. Get More Tokens
Want better results? Premium models (GPT-5, Claude, Gemini) deliver higher quality. View Plans

❤️ Love Free.ai? Tell your friends!

Sign up to get a referral link and earn 25,000 tokens per friend.

Want more? Sign up free for 5K tokens/day + 10K bonus
Sign Up Free

Processing your request...

Upload a PDF and ask questions about it with AI.

How to Use Chat with PDF

1
Enter your input

Type text, upload a file, or describe what you want. No account needed.

2
Click generate

Our AI processes your request in seconds using the best open-source models.

3
Download & share

Download, copy, or share your result. Free for personal and commercial use.

Use this tool via API

Automate this tool from your own code. OpenAI-compatible REST endpoint, Bearer-token auth, no extra SDK required. Token costs match the web interface.

curl -X POST https://api.free.ai/v1/pdf/extract/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"file": "@document.pdf"}'

Chat with PDF — FAQ

Upload any PDF and have a back-and-forth conversation with the document. Ask for summaries, specific quotes, clauses, tables, numbers — the AI has read every page and cites them by [p.N] so you can click straight to the source page.

About 300 tokens per question on the Standard model (Qwen 3 30B, free). Premium long-context models (Gemini 2.5 Flash/Pro, Claude Sonnet, GPT-5) run roughly 540 to 1,800 tokens per question but understand dense legal or medical writing better. The live cost appears under the input box and updates when you switch models.

On upload we extract per-page text server-side and read PDF.js metadata client-side (page count, thumbnail, encryption). Each question wraps the relevant pages into the LLM prompt; for very long docs we chunk by page and send the most relevant sections. Your document never leaves our GPUs and is discarded after the session.

Text-based PDFs: research papers, contracts, annual reports, earnings transcripts, textbooks, manuals, government filings, whitepapers. Scanned image-only PDFs need OCR first — Chat with PDF detects them on upload and sends you to /pdf/ocr/.

Yes — the AI is prompted to return [p.5]-style inline citations. The citations in the chat window are clickable and jump the thumbnail panel to the cited page so you can verify at a glance.

Yes. The last 10 turns of the conversation are kept so you can naturally dig deeper: summarize section 3, then what did they conclude about X, then quote the exact sentence that says that.

No. The file is written to a temp directory on our server, extracted, then deleted. The chat history lives only in your browser tab. Close the tab, it is gone.

Up to 50 MB in file size. We read the full text but truncate to ~18K chars when sending to the standard-context model. Switch to a long-context premium model (Gemini 2.5 Flash handles 1M tokens) for full-book chat.

Any language the LLM reads. Qwen 3 30B speaks 100+ languages; Gemini / Claude / GPT cover 100+ with near-native quality. Chat in English about a Spanish PDF or vice-versa — the model handles both directions.

Yes — /pdf/summarizer/ is one-shot, non-conversational, with 5 length presets (short to executive summary). Chat is for exploration; summarize is for a clean deliverable.

Free.ai is free, lets you pick the LLM, supports 1M-token long-context models, and ships a public API. ChatPDF ($5/mo), Humata ($14.99/mo), AskYourPDF ($9.99/mo) pick one model for you and lock their API behind enterprise sales.

Yes — POST file to /v1/pdf/extract/ for server-side extraction, then POST to /v1/chat/ with a system prompt containing the extracted text. Full curl recipe at /api/. Quote endpoint /v1/pdf/chat-quote/?model=M returns the per-question cost before you hit submit.

Sign up free for 10,000 tokens

Create Free Account

No credit card required

How would you rate this tool?

Love Free.ai? Tell your friends!