Xodo PDF Studio · Scanned PDF OCR
Powered by Apryse (PDFTron) cloud OCR with 1 free daily task without login, exporting a 687.6 KB 2-page searchable PDF in 5.00s; achieves 100% accuracy on body text and all 12 confusable invoice table cells, though binarization skips the two white-on-navy top banners (88.9% overall text recall).
US-West (California, AS2914)
PDF · Output attached · Open native file ↗
Subsequent pricing and service checks are shown separately without altering historical scores.
One run does not establish all complex scenes, untested paid maxima or long-term uptime.
Plans & historical pricing
Xodo USD individual web and cross-platform suite; desktop alternative identified · 2026-10-20
9 plan / billing-period records, all listed; — means that period is not recorded.
Monthly and annual bills confirmed. Document Suite USD 107.93/year is a new-annual-subscription promotion through 2026-12-31, retained while the annual subscription stays active. Team seat combinations and desktop perpetual licences were not exhaustively checked.
Verification has gaps; unknown prices and quotas are not inferred.
Cancellation, sources & verification record
Monthly subscriptions can be cancelled anytime; trials require a valid payment method. Refund terms were not fully verified.
Official feature and pricing page ↗ · 2026-10-20 Capture 1 ↗
Official feature and pricing page ↗ · 2026-10-20 Capture 1 ↗
Official feature and pricing page ↗ · 2026-10-20 Capture 1 ↗
Pricing recorded on the test date · 2026-10-25
1 Free Task/Day + Xodo Pro Subscription ($12/mo)
1 Free Task/Day + Xodo Pro Subscription ($12/mo)
Historical context only; not current purchase guidance.
Delivery & access
- Free delivery record
- Full 2-page searchable PDF (687.6 KB · 456 BT / 456 TJ · watermark-free)
- Watermark
- Watermark-free
- Free allowance
- 1 Free Task/Day + Xodo Pro Subscription ($12/mo)
- Account requirements
- No Login Required (1 Free Daily Task)
- Maximum specification record
- Full 2-page searchable PDF (687.6 KB · 456 BT / 456 TJ · watermark-free)
May include advertised capabilities; this does not establish a tested paid tier.
- Batch & API
- Single-file OCR on free tier; batch processing per plan quota
- Manual refinement
- Not recorded or not verified
Tested result & sample
Generated a 2-page searchable PDF (456 BT / 456 TJ text operators) with 12/12 invoice table cells, 2/2 body phrases, and the Page 2 verification token intact, skipping only the 2 dark-background white-text header banners (88.9% text recall).
- Fixture
- anchor_pdfocr_v1
- Recorded environment
- US-West (California, AS2914)
- Network-observed server wait
- 5 s
- End-to-end reference
- 8.72 s
Network wait includes round trips, queuing and polling error, not pure inference time. Local timings depend on the device; repetition counts are not standardized in legacy records.
Experience, rules & trust
- Disclosure
- Options disclosed upfront with no post-OCR paywall trap
- Interaction
- Clean professional workspace supporting .pdf or .txt output format and language selection with zero third-party ad popups.
- Entity record
- Apryse Software Corp. (formerly PDFTron Systems Inc.)
- Origin
- Vancouver, Canada / Denver, USA
- Domain history record
- Xodo launched in 2014 (parent company PDFTron founded in 1998)
- Third-party tracking record
- No third-party services listed in this record; this is not proof that none exist.
- External information
- Not recorded or not verified
- Processing
- Cloud OCR engine (cloud_xodo_apryse_ocr)
- Retention statement
- Supports one-click manual trash deletion on the download screen or automatic permanent purge after 1 hour
A recorded statement does not verify deletion or all data-processing behavior.
Verifiable audit trail & evidence
Four SHA-256-verified stages link the benchmark fixture, same-run interface screenshots, native exported artifact and archived pricing sources.
anchor_pdfocr_v1 · Inspect fixture & file inspector →
Captures entry rules, result view and export disclosure.
Official feature and pricing page (snapshot ↗) · Official feature and pricing page (snapshot ↗) · Official feature and pricing page (snapshot ↗)
Screenshots, native output and official claims support different conclusions. Evidence grades are not product safety certifications.
Evaluation basis & full scores · Overall 89.5/100
Overall = honesty & reputation × 30% + capability × 70%. Component maxima follow this report’s rubric. List scores are rounded for display; original precision is retained here.
Scoring version 2.3.1 · Test fixture anchor_pdfocr_v1
Honesty & reputation · 82/100 · 30%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Pricing transparency | 24 / 35 | Allows 1 free daily PDF OCR task without login (01_landing.png, 02_workspace.png, 03_download.png), completing server OCR on our 644.4 KB 2-page raster scan in 5.00s and exporting an unwatermarked 2-page searchable PDF before enforcing the 1-file/day cap (Xodo Pro ~$12/mo). | Evidence A → |
| Interaction restraint | 25 / 30 | Clean professional workspace supporting .pdf or .txt output format and language selection with zero third-party ad popups. | Evidence A → |
| Background & reputation | 19 / 20 | Developed and operated in Vancouver, Canada by enterprise PDF SDK leader Apryse (formerly PDFTron Systems Inc.), powered by the commercial Apryse OCR module. | Evidence A → |
| Engineering & privacy | 14 / 15 | Uses encrypted AWS S3 direct upload and stateless `/production/ocr` processing endpoints with automatic temporary file purge. | Evidence A → |
Capability · 92.7/100 · 70%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Task quality | 61.7 / 65 | Deterministic searchable PDF stream & table inspection: reconstructs a 2-page selectable text layer (456 BT / 456 TJ operators) over the 644.4 KB zero-font raster scan, recovering 2/4 headings and 12/12 confusable invoice table cells (100% table accuracy, 88.9% overall text recall) with the Page 2 verification token intact (61.7/65) | Evidence A → |
| Deliverable specifications | 17.5 / 20 | Exports a complete 2-page watermark-free searchable PDF (687.6 KB) without login (17.5/20) | Evidence A → |
| Processing speed | 13.5 / 15 | Upload took 2.15s and cloud OCR server processing completed in 5s (8.72s end-to-end) (13.5/15) | Evidence A → |
Legacy scores may include advertised maximum capabilities. Read tested output separately from paid capabilities. Records without matching tiers and scope are not ranked together.
Revisions & corrections
- 2026-10-25
Initial scanned PDF OCR text layer, confusable invoice table cell accuracy, and server timing benchmark on anchor_pdfocr_v1.