Test record & evaluation basis

SnapEdit (Remove Background) · Background removal

Guest trial credits and login-free downloads ease access; free output is 1280px, full size needs Pro, and size limits are disclosed late.

Test date 2026-10-17Free tier + subscriptionNative output attachedMethod 2.3.1
1 · Date, environment & tier2026-10-17 · Guest flow

US-West (California, AS2914)

2 · Fixture & native exportCurly-haired portrait (anchor_bgremove_v1)

1280 × 1280 · PNG · 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

Web personal free, monthly/annual and per-seat Business; excludes API · 2026-10-21

Plan · source date
Monthly / one-time
Annual bill / period
Quota & limits
Free
Free
Free 10 credits/month; standard quality up to 1600px, watermarked
USD 10/month
USD 72/year
Annual 4,800 credits/year; 1 credit per background removal

No watermark; up to 5600px; batch processing;Requires sign-in before checkout; includes a 3-day free trial, then bills USD 72/year ($6/month equivalent) via Paddle

Rules [1]
Monthly 400 credits/month; 1 credit per removal

No watermark, up to 5600px, batch processing

USD 20/month
USD 144/year
Annual 18,000 credits/year; 1 credit per background removal

No watermark; up to 5600px; batch processing;Requires sign-in before checkout; includes a 3-day free trial, then bills USD 144/year ($12/month equivalent) via Paddle

Rules [1]
Monthly 1,500 credits/month; 1 credit per removal

No watermark, up to 5600px, batch processing

USD 15/month
USD 120/year
Monthly 1,000 credits/month/seat; shared credits, assets and automated workflows
Annual 12,000 credits/year/seat; shared credits, assets and automated workflows

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

[1] Unused credits roll over while subscribed

Personal annual checkout opens a Paddle modal after login: Standard annual includes a 3-day free trial followed by USD 72/year ($6/month equivalent), and PRO annual includes a 3-day free trial followed by USD 144/year ($12/month equivalent). Business explicitly lists $120/seat/year. The free card claims no ads but conflicts with its comparison table; ad-free use is not promised.

Cancellation, sources & verification record

Cancel anytime; refund eligibility unverified.

Official plans and usage terms ↗ · 2026-10-20 Capture 1 ↗ · Capture 2 ↗ · Capture 3 ↗

Login gate on personal annual purchase entry ↗ · 2026-10-20 Capture 1 ↗

Personal annual Paddle checkout summary (verified after sign-in) ↗ · 2026-10-21 Capture 1 ↗

Pricing recorded on the test date · 2026-10-17

$5.00/mo (billed annually) or $9.99/mo

5 free daily coins + monthly/annual PRO subscription + developer API

Historical context only; not current purchase guidance.

Delivery & access

Free delivery record
1280×1280 (PNG, RGBA, 2.51 MB, retains 39.1% pixel area)
Attached file dimensions
1280 × 1280 · PNG

Read directly from the attached file; this does not establish free download availability at that size.

Watermark
No watermark (unlike its object remover, the free 1280p cutout PNG has no corner watermark)
Free allowance
5 free coins daily; free tier exports 1280×1280 unwatermarked transparent PNG
Account requirements
No login required (5 free daily coins, 1 coin per cutout)
Maximum specification record
1280×1280 (PNG, RGBA, 2.51 MB, retains 39.1% pixel area)

May include advertised capabilities; this does not establish a tested paid tier.

Batch & API
Supports batch processing (PRO) and mobile app sync
Manual refinement
Not recorded or not verified

Tested result & sample

Across green and pure-black backdrops, the main curly hair volume remains solid, with a thin warm background halo around outer flyaway strands.

Edge error MAD
0.1287 · Lower is better
Global error SAD(k)
58.511 · Lower is better
Foreground retention
99.530% · Higher is better
Background residue
0.078% · Lower is better

These historical measurements describe alpha error at edges (MAD), total alpha error / 1000 (SAD), foreground retention and background residue. Low-resolution outputs are aligned to the reference under the original protocol; this does not imply a full-resolution export.

Fixture
anchor_bgremove_v1
Recorded environment
US-West (California, AS2914)
Network-observed server wait
5.42 s
End-to-end reference
6.52 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
Disclosed in the Download menu (shows 1280p Free vs 1920p/Original PRO after clicking Download)
Interaction
Automatically runs AI cutout upon upload without login pop-ups and exports a 1280×1280 unwatermarked transparent PNG in one click.
Entity record
SilverAI (SnapEdit Team)
Origin
Vietnam / Singapore (SilverAI)
Domain history record
snapedit.app (2022–Present, tens of millions of web & mobile users)
Third-party tracking record
Not recorded or not verified
External information
Not recorded or not verified
Processing
Cloud GPU inference (be-prod-web.snapedit.app/api/rmbg/v1)
Retention statement
Automatically purges unsaved session images after temporary cloud processing

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 Curly-haired portrait

anchor_bgremove_v1 · Inspect fixture & file inspector →

Stage B · Same-run screenshots 3 flow screenshots archived

Captures entry rules, result view and export disclosure.

Stage C · Native exported file 1280 × 1280 · PNG

Open native exported file ↗

Stage D · Archived pricing sources 3 official source snapshots

Official plans and usage terms (snapshot ↗) · Login gate on personal annual purchase entry (snapshot ↗) · Personal annual Paddle checkout summary (verified after sign-in) (snapshot ↗)

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

Evaluation basis & full scores · Overall 70.3/100

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_bgremove_v1

Honesty & reputation · 80/100 · 30%

CriterionScoreRationaleBasis
Pricing transparency26 / 40 Does not disclose the free export resolution cap on the landing hero; anonymous visitors receive 5 free daily coins (1 Credit per cutout) and clicking Download reveals the tier menu (03_download.png): Small 1280×1280 unwatermarked transparent PNG (2.51 MB) is free, while Medium 1920×1920 and Large Original 2048×2048 require PRO. Evidence A →
Interaction restraint19 / 20 Automatically runs AI cutout upon upload without login pop-ups and exports a 1280×1280 unwatermarked transparent PNG in one click. Evidence A →
Background & reputation21 / 25 Developed by SilverAI (SnapEdit), a major cross-platform AI photo editing suite across Web, iOS, Android, and developer APIs. Evidence C →
Engineering & privacy14 / 15 Completes server-side inference via be-prod-web.snapedit.app/api/rmbg/v1 in 5.42s and exports a clean RGBA transparent PNG. Evidence A →

Capability · 66.1/100 · 70%

CriterionScoreRationaleBasis
Task quality39.6 / 65 Transition band error mad_band=0.1287 · Global SAD(k)=58.511 · Foreground recall 99.53% / Background leak 0.078% Evidence A →
Deliverable specifications15 / 20 True Alpha channel (8/8); Max deliverable spec: 1280×1280 (PNG, RGBA, 2.51 MB, retains 39.1% pixel area) Evidence A →
Processing speed11.5 / 15 Network-observed server wait: 5.42s (API mode: sync_post; network upload 1.1s / end-to-end 6.52s shown for reference only, never penalized) 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

Prepare a correction or update →
Benchmark evidence preview

Open original ↗