Removal.AI · Background removal
Direct preview downloads and accessible HD pricing accompany good hair handling; free output is 600px, full size costs credits, and a promotion widget is present.
US-West (California, AS2914)
600 × 600 · PNG · 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
Public web packs, monthly and high-volume options (dollar pricing) · 2026-10-20
12 plan / billing-period records, all listed; — means that period is not recorded.
Packs are labelled Lifetime but explicitly expire after 3 years. The stated validity limits apply.
Cancellation, sources & verification record
Page advertises a 14-day money-back guarantee and flexible changes/cancellation; eligibility is subject to terms.
Official plans and usage terms ↗ · 2026-10-20 Capture 1 ↗
Pricing recorded on the test date · 2026-10-15
Pay-as-you-go from $1.89 (3 credits, valid 3 years); Monthly subscription from $5.99/mo (40 credits)
Small pay-as-you-go packs (valid 3 years) + monthly/annual subscriptions
Historical context only; not current purchase guidance.
Delivery & access
- Free delivery record
- 600×600 (8.6% pixel area retained, no watermark)
- Attached file dimensions
- 600 × 600 · PNG
Read directly from the attached file; this does not establish free download availability at that size.
- Watermark
- None (free tier is gated by 600×600 preview resolution)
- Free allowance
- Unlimited guest 600×600 previews; new registered accounts receive 1 free High-Quality credit
- Account requirements
- No login required for 600×600 preview; High Quality (2048×2048) requires login and 1 Credit
- Maximum specification record
- 2048×2048 (Paid/Credit unlocks full 2048×2048; free guest preview exports 600×600)
May include advertised capabilities; this does not establish a tested paid tier.
- Batch & API
- Desktop bulk remover app & API available
- Manual refinement
- Built-in online photo editor with erase/restore brush and background templates
Tested result & sample
Balanced hair edge transition (mad_band=0.0970, SAD(k)=36.6, bg_leak=0.013%), slightly higher preview resolution (600×600) than remove.bg/Slazzer (500×500), though server processing is slower (8.55s).
- Edge error MAD
- 0.0846 · Lower is better
- Global error SAD(k)
- 41.816 · Lower is better
- Foreground retention
- 99.760% · Higher is better
- Background residue
- 0.013% · 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
- 8.55 s
- End-to-end reference
- 11.91 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 directly on the result page download buttons before clicking
- Interaction
- No login required for 600×600 preview download; minor promotional banner on result page.
- Entity record
- Removal.AI ( Grafika / Removal AI Team )
- Origin
- Ho Chi Minh City, Vietnam / Singapore
- Domain history record
- Launched 2020
- Third-party tracking record
- Google Analytics · Facebook Pixel
- External information
- Praised for consumer-friendly small credit packs ($1.89 for 3 credits valid for 3 years) without forcing monthly subscriptions.
- Processing
- Cloud synchronous API (api.removal.ai, 8.55s server time)
- Retention statement
- Uploaded guest files are automatically deleted after temporary processing window
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_bgremove_v1 · Inspect fixture & file inspector →
Captures entry rules, result view and export disclosure.
Screenshots, native output and official claims support different conclusions. Evidence grades are not product safety certifications.
Evaluation basis & full scores · Overall 82.4/100
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 · 79/100 · 30%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Pricing transparency | 28 / 40 | Result view clearly labels 'Preview Image (600×600) Free' vs 'High Quality (2048×2048) 1 Credit' before download; pricing page offers transparent micro-packs starting at $1.89 for 3 credits. | Evidence A → |
| Interaction restraint | 16 / 20 | No login required for 600×600 preview download; minor promotional banner on result page. | Evidence A → |
| Background & reputation | 21 / 25 | Removal.AI (Vietnam / Singapore visual AI team, launched 2020), well-known remove.bg alternative. | Evidence C → |
| Engineering & privacy | 14 / 15 | Standard multipart upload over HTTPS; server processing took 8.55s. | Evidence A → |
Capability · 83.8/100 · 70%
| Criterion | Score | Rationale | Basis |
|---|---|---|---|
| Task quality | 53.8 / 65 | Transition band error mad_band=0.0846 · Global SAD(k)=41.816 · Foreground recall 99.76% / Background leak 0.013% | Evidence A → |
| Deliverable specifications | 20 / 20 | True Alpha channel (8/8); Max deliverable spec: 2048×2048 (Paid/Credit unlocks full 2048×2048; free guest preview exports 600×600) | Evidence A → |
| Processing speed | 10 / 15 | Network-observed server wait: 8.55s (API mode: async; network upload 0.52s / end-to-end 11.91s 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
- 2026-10-15
Initial real-machine evaluation using synthetic ground-truth anchor_bgremove_v1 and CDP network timing isolation.