PDF to Excel
Commercial use OK
380+ models
No watermark
No sign-up needed
Model:
+ GPT-5, Claude, Gemini
Extract tables from a PDF into an editable XLSX. One Excel sheet per detected table, rows and columns preserved. We probe the first 10 pages on upload so you see the detected-table count before you commit. 100 tokens per page + 100 per table, 1,000-token floor.
Spreadsheet ready
What people extract PDF tables for
Invoices & bills
Extract line items from a vendor invoice into Excel for reconciliation with your ledger.
Financial statements
Pull balance-sheet + income-statement tables from an annual report into Excel for analysis.
Research results
Grab the results tables from a scientific paper so you can re-plot the data yourself.
Price lists & catalogs
Turn a wholesale price PDF into a spreadsheet you can VLOOKUP against your SKU list.
How to convert PDF to Excel in 4 steps
- Upload your PDF. We probe the first 10 pages via pdfplumber and show the estimated number of detected tables immediately.
- Pick scope: All pages (default) or First page only (fastest for one-table invoices).
- Confirm the cost. 100 tokens/page + 100 per detected table, 1K floor.
- Click Extract. We build a multi-sheet XLSX: one Overview sheet + one sheet per detected table (named P
_T ). Download the .xlsx.
Free.ai vs. Tabula vs. Nitro PDF
| Free.ai | Tabula | Nitro PDF Pro | |
|---|---|---|---|
| Starting price | Free | Free (desktop) | $179.99 |
| Browser-native (no install) | — | — | |
| Pre-flight table count probe | — | — | |
| One sheet per table | |||
| Public API | — | — | |
| No sign-up required | — |
Advanced options
Result
Tokens running low.
Get More Tokens
❤️ 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...
Convert PDF tables to Excel with free AI. Accurate spreadsheet extraction.
How to Use PDF to Excel
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"}'Related Free AI Tools
PDF to Excel — FAQ
Extract tables from a PDF into an editable XLSX spreadsheet — one sheet per detected table, rows and columns preserved. Great for financial reports, invoices, scientific results, and any printed table you need to recompute. Non-table content is skipped; for full document conversion use /pdf/to-word/.
We use pdfplumber, which identifies table structures from text positioning and ruled lines (not computer vision, so it works cleanly on digital PDFs without relying on fuzzy OCR heuristics). After upload we run a quick probe on the first 10 pages and surface the detected table count before you commit the conversion.
100 tokens per page + 100 tokens per detected table, 1,000-token floor. A 5-page report with 3 tables costs 800 + 300 = floor-enforced 1,000 tokens. Free users get 2,500 daily tokens. The exact quote appears after probe.
Up to 50 MB per PDF. Probe runs on the first 10 pages for speed — conversion scans all pages. 100+ page docs may take 15-30s; PDF to Excel shows a progress banner.
No — scanned PDFs have no text layer for pdfplumber to parse. Run /pdf/ocr/ first to produce a text-layer PDF, then feed that here. We detect image-only PDFs on upload and suggest the OCR route.
pdfplumber can detect tables without visible borders if column spacing is consistent (most CSV-exported-to-PDF invoices work). Highly irregular layouts may return partial data — in those cases, /pdf/to-word/ preserves the visual layout, or open the PDF directly in Excel via its import wizard.
Three scopes: all pages (default), first page only, or auto (let the detector pick pages where tables were found). First-page-only is fastest and cheapest for one-table invoices.
We still produce an XLSX (with just an Overview sheet) but skip the table sheets. If you expected tables but got none, the PDF is likely scanned or uses non-standard layout — try /pdf/ocr/ first or /pdf/to-word/ for text extraction.
One sheet per detected table named P<page>_T<table_index> (e.g. P3_T1 = page 3, first table). An Overview sheet at the front lists source filename + page count + tables extracted. Formulas are not inferred — cells contain the raw string values as the PDF wrote them.
No — extraction runs on our own API server using pdfplumber + openpyxl locally. The source PDF is deleted after conversion. XLSX output stays on our CDN for 24 hours (7 days with active credits).
Free.ai is free and ships a public API. Tabula is free and open-source too (same detection engine family) but requires Java + desktop install. Nitro PDF Pro ($179.99 one-time) does richer layout-aware extraction but costs more per-seat than most teams justify. We are the zero-install, browser-native choice.
Yes — POST multipart to /v1/pdf/to-excel/ with file + scope (all-pages / first-page / auto). Quote endpoint /v1/pdf/to-excel-quote/?pages=N&tables=T returns the cost. Probe endpoint /v1/pdf/to-excel/probe/ (POST, no deduction) returns the detected table count for preflight. Full curl recipe at /api/.
How would you rate this tool?