Test record & evaluation basis

Sejda PDF · Scanned PDF OCR

Offers 3 free OCR tasks per hour (up to 10 pages) without login, converting our 2-page raster scan into a 651.9 KB searchable PDF in 7.50s with 100% recall across all 4 headings and 12 confusable table cells.

Test date 2026-10-25Subscription + creditsNative output attachedMethod 2.3.1

Use this capability ↗View product profile →Compare alternatives Audit trail ↓

1 · Date, environment & tier2026-10-25 · Guest flow

US-West (California, AS2914)

2 · Fixture & native export2-page raster scanned PDF (0 embedded text, 644.4 KB) (anchor_pdfocr_v1)

PDF · Output attached · Open native file ↗

3 · Price checks vs. test scoreOfficial pricing checked 2026-10-21

Subsequent pricing and service checks are shown separately without altering historical scores.

4 · What one test cannot proveScoped to this fixture & path

One run does not establish all complex scenes, untested paid maxima or long-term uptime.

Plans & historical pricing

Sejda personal web and desktop plans (Free / Web Week Pass / Web Monthly / Desktop+Web Annual); USD · 2026-10-21

Plan · source date

Monthly / one-time

Annual bill / period

Quota & limits

Free2026-10-21 ↗

Free

Free No account required; documents up to 50 pages or 50 MB and up to 3 tasks per hour; files automatically deleted after 2 hours.

Web Week Pass2026-10-21 ↗

USD 5 · one-time payment

Usage / one-time

Usage / one-time One-time payment of USD 5 for 7 days of Sejda Web access (unlimited documents, no page or hourly limits, up to 500 MB per file; excludes Sejda Desktop).

One-time payment; does not auto-renew

Web Monthly2026-10-21 ↗

USD 7.5/month

—

Monthly Sejda Web monthly subscription (unlimited documents, no page or hourly limits, batch multi-file processing; excludes Sejda Desktop).

Recurring monthly billing; cancel anytime

Desktop+Web Annual2026-10-21 ↗

—

USD 63/year

Annual Billed annually at USD 63/year (save 30% over monthly), including 1 year of unlimited access to both Sejda Web and Sejda Desktop.

Recurring annual billing; cancel anytime

4 plan / billing-period records, all listed; — means that period is not recorded.

The converter page states the free allowance (documents up to 50 pages or 50 MB, 3 tasks per hour, files deleted after 2 hours); the official pricing page (/upgrade) lists the 7-day Web Week Pass (USD 5 one-time payment), Web Monthly (USD 7.50/month), and Desktop+Web Annual (USD 63/year).

Cancellation, sources & verification record

Web Week Pass is a one-time 7-day payment with no auto-renewal; monthly and annual plans use recurring billing and can be cancelled anytime.

Sejda official pricing and upgrade page ↗ · 2026-10-21 Capture 1 ↗

Pricing recorded on the test date · 2026-10-25

3 Free Tasks/Hour (≤10 Pages) + Web Pro Subscription

Historical context only; not current purchase guidance.

Delivery & access

Free delivery record: Full 2-page searchable PDF (651.9 KB · 40 BT / 265 TJ · watermark-free)
Watermark: Watermark-free
Free allowance: 3 Free Tasks/Hour (≤10 Pages) + Web Pro Subscription
Account requirements: No Login Required
Maximum specification record: Full 2-page searchable PDF (651.9 KB · 40 BT / 265 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 (40 BT / 265 TJ text operators) with 100% recall across 4/4 headings, 12/12 invoice table cells, and the Page 2 verification token.

Fixture: anchor_pdfocr_v1
Recorded environment: US-West (California, AS2914)
Network-observed server wait: 7.5 s
End-to-end reference: 10.6 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.

Open native file ↗

Experience, rules & trust

Disclosure: Options disclosed upfront with no post-OCR paywall trap
Interaction: Zero ad popups or registration dark patterns; clearly presents output format (Searchable PDF / Text) and language selectors before processing, followed by a direct Download button.
Entity record: Sejda BV (Amsterdam PDF Utility Vendor)
Origin: Amsterdam, Netherlands
Domain history record: 2016–Present
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_sejda_ocr_worker)
Retention statement: Uploaded and converted files are automatically deleted from servers after 2 hours, with an immediate manual delete option on the result page
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.

Stage A · Benchmark fixture 2-page raster scanned PDF (0 embedded text, 644.4 KB)

anchor_pdfocr_v1 · Inspect fixture & file inspector →

Stage B · Same-run screenshots 4 flow screenshots archived

Captures entry rules, result view and export disclosure.

Stage C · Native exported file PDF · Output attached

Open native exported file ↗

Stage D · Archived pricing sources 1 official source snapshots

Sejda official pricing and upgrade page (snapshot ↗)

Entry & rules ↗

Result screen ↗

Download & limits ↗

Additional screenshot 1 ↗

Screenshots, native output and official claims support different conclusions. Evidence grades are not product safety certifications.

Evaluation basis & full scores · Overall 94.6/100

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 · 90/100 · 30%

Criterion	Score	Rationale	Basis
Pricing transparency	30 / 35	Highly transparent free-tier limits (3 free tasks per hour, up to 10 pages / 50 MB per file). Uploading our 644.4 KB 2-page raster scan without login completes server OCR in 7.50s and exports an unwatermarked 2-page searchable PDF alongside a live text preview (01_landing.png, 02_workspace.png, 03_download.png).	Evidence A →
Interaction restraint	28 / 30	Zero ad popups or registration dark patterns; clearly presents output format (Searchable PDF / Text) and language selectors before processing, followed by a direct Download button.	Evidence A →
Background & reputation	18 / 20	Developed and operated in Amsterdam, Netherlands by Sejda BV since 2010 (founded by the open-source PDFsam team), maintaining a strong reputation among technical and office users.	Evidence A →
Engineering & privacy	14 / 15	EU GDPR-compliant architecture that automatically purges uploaded files after 2 hours and provides an immediate delete action on the result screen.	Evidence A →

Capability · 96.5/100 · 70%

Criterion	Score	Rationale	Basis
Task quality	65 / 65	Deterministic searchable PDF stream & table inspection: reconstructs a 2-page selectable text layer (40 BT / 265 TJ operators) over the 644.4 KB zero-font raster scan, recovering 4/4 headings and 12/12 confusable invoice table cells (100% table accuracy, 100% overall text recall) with the Page 2 verification token intact (65/65)	Evidence A →
Deliverable specifications	19 / 20	Exports a complete 2-page watermark-free searchable PDF (651.9 KB) without login (19/20)	Evidence A →
Processing speed	12.5 / 15	Upload took 2.73s and cloud OCR server processing completed in 7.5s (10.6s end-to-end) (12.5/15)	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.

Prepare a correction or update →