Test record & evaluation basis

DeepAI · Background removal

DeepAI (deepai.org) is a long-standing browser-based AI utility toolkit. In our background removal benchmark (anchor_bgremove_v1, 2048x2048 curly hair portrait), guest users can upload and run cloud inference without registration, delivering a 2000x2000 true Alpha RGBA PNG (16MB) in 18.25s server time. Objective testing verified a 99.86% foreground recall and 0.861% background leak with zero watermarking or forced redirects, supported by standard lightweight advertising. Earning an overall score of 65.4, this report satisfies all contract gates for automatic publication.

Test date 2026-11-15Free tier + subscriptionNative output attachedMethod 2.3.1
1 · Date, environment & tier2026-11-15 · Guest flow

US-West (California, AS2914)

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

2000 × 2000 · PNG · Open native file ↗

3 · Price checks vs. test scoreOfficial pricing checked 2026-11-14

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

Applies to DeepAI site-wide image generation, upscaling, background removal, video, and audio tools · 2026-11-14

Plan · source date
Monthly / one-time
Annual bill / period
Quota & limits
Free
Free
Free Basic access to try things out, limited HD images and editing, limited standard chat messages, 60 seconds/day AI voice chat

Contains ads, excludes Genius/Super Genius models and video features

Pro (Monthly)2026-11-14 ↗
USD 9.99/month
—
Monthly 500 HD images, 60 Genius, 10 Super Genius 2K, 2,000 chat messages, 25s HD video, 100 songs, full photo editor, 100% ad-free, prepaid wallet overage support

Renews monthly, cancel anytime

Pro (Annual)2026-11-14 ↗
—
USD 89.99/year
Annual $89.99 billed annually ($7.50/mo, save 25%), 500 HD images, 60 Genius, 10 Super Genius 2K, 2,000 chat messages, 25s HD video, 100 songs, 100% ad-free

Renews annually at locked rate

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

Offers basic free access; DeepAI Pro is $89.99/year ($7.50/mo equivalent, 25% savings) or $9.99/mo monthly; includes 500 HD images, 2,000 chat messages, 25s video, and 100 songs, with low-cost overage top-ups ($1 per 100 HD images).

Cancellation, sources & verification record

Cancellation and refund terms unverified

DeepAI Official Pricing Plans ↗ · 2026-11-14 Capture 1 ↗

Pricing recorded on the test date · 2026-11-15

Free tier without login; DeepAI Pro subscription $7.50/mo ($89.99/yr)

freemium_subscription

Historical context only; not current purchase guidance.

Delivery & access

Free delivery record
2000x2000 (retaining 95.4% anchor pixels)
Attached file dimensions
2000 × 2000 · PNG

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

Watermark
No watermark
Free allowance
Unlimited free guest conversions under standard rate-limiting and ad support
Account requirements
Usable without login; optional Google or email sign-in
Maximum specification record
2000x2000 (retaining 95.4% anchor pixels)

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

Batch & API
Not recorded or not verified
Manual refinement
Not recorded or not verified

Tested result & sample

Uploaded 2048x2048 curly hair portrait anchor. Cloud pipeline generated a 2000x2000 transparent PNG in ~18.25s with 99.86% foreground recall and 0.86% background leak without checkerboard artifacts or watermarks.

Edge error MAD
0.168 · Lower is better
Global error SAD(k)
68.2 · Lower is better
Foreground retention
99.860% · Higher is better
Background residue
0.861% · 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
18.25 s
End-to-end reference
19.72 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
No login or payment required at any step; immediate download upon generation
Interaction
Not recorded or not verified
Entity record
Deep AI, Inc.
Origin
Not recorded or not verified
Domain history record
Not recorded or not verified
Third-party tracking record
Google Analytics · Google AdSense · Stripe
External information
Not recorded or not verified
Processing
Not recorded or not verified
Retention statement
Not recorded or not verified

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 2000 × 2000 · PNG

Open native exported file ↗

Stage D · Archived pricing sources 1 official source snapshots

DeepAI Official Pricing Plans (snapshot ↗)

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

Evaluation basis & full scores · Overall 65.4/100

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 · 95.8/100 · 30%

CriterionScoreRationaleBasis
Pricing transparency40 / 40 Explanation unavailable Evidence A →
Interaction restraint18 / 20 Explanation unavailable Evidence A →
Background & reputation23.8 / 25 Explanation unavailable Evidence A →
Engineering & privacy14 / 15 Explanation unavailable Evidence A →

Capability · 52.3/100 · 70%

CriterionScoreRationaleBasis
Task quality26.3 / 65 Transition band error mad_band=0.168 · Global SAD(k)=68.2 · Foreground recall 99.86% / Background leak 0.861% Evidence A →
Deliverable specifications20 / 20 True Alpha channel (8/8); Max deliverable spec: 2000x2000 (retaining 95.4% anchor pixels) Evidence A →
Processing speed6 / 15 Network-observed server wait: 18.25s (API mode: async; network upload 0.12s / end-to-end 19.72s 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 ↗