withoutbg.com is built with Next.js, hosted on Amazon CloudFront. It measures traffic with Ahrefs Web Analytics. It sends email through Amazon SES.
| Technology | Version | First seen |
|---|---|---|
| JavaScript Frameworks & Libraries2 | ||
| 15.5.4 | 7 Nov 2026 | |
| – | 7 Nov 2026 | |
| Frontend Build Tools & CSS1 | ||
| – | 7 Nov 2026 | |
| Web Servers, Languages & Backend Frameworks1 | ||
| CDN & Hosting3 | ||
| – | 7 Nov 2026 | |
| Analytics & Tag Management1 | ||
| – | 7 Nov 2026 | |
| Transactional Email1 | ||
| – | 7 Nov 2026 | |
| Accessibility2 | ||
| – | 7 Nov 2026 | |
| Fonts & Icon Fonts3 | ||
| – | 7 Nov 2026 | |
Registration from the registry's RDAP record, the certificate the site serves, and its rank in public traffic lists.
The crew hasn’t read this site’s colors yet. We read a palette when we capture a site’s screenshot, busiest sites first. Meanwhile, browse palettes from other sites.
Counted from every stack change we've recorded: of the sites we watched running one of this site's tools, how many went on to add another. A pattern across sites, not a forecast for this one.
From what the site says about itself, and account IDs it shares with other sites.
aspmx.l.google.comalt1.aspmx.l.google.comalt2.aspmx.l.google.comalt4.aspmx.l.google.comalt3.aspmx.l.google.comns-135.awsdns-16.comns-534.awsdns-02.netns-1075.awsdns-06.orgns-1697.awsdns-20.co.ukgoogle-site-verification=5hP2I3moxdvWmIQ0RSrbbdgRE37HgUqwBPifK4MkXtAv=spf1 include:_spf.google.com include:amazonses.com ~allv=DMARC1;p=quarantine;pct=100;fo=1;rua=mailto:dmarc@withoutbg.comUser-agent: * Allow: / # Private routes (account, login, signup, checkout confirmations) are not # disallowed here on purpose: they carry a noindex meta tag, which crawlers can # only see if they are allowed to fetch the page. Sitemap: https://withoutbg.com/sitemap.xml
# withoutBG > AI background removal — Pro Model API and Open Model docs on withoutbg.com ## API (machine-readable) - OpenAPI: https://api.withoutbg.com/openapi.json - API llms.txt: https://api.withoutbg.com/llms.txt - Site OpenAPI mirror: https://withoutbg.com/openapi/pro-api.json ## Pro Model API docs - https://withoutbg.com/docs/pro-model - https://withoutbg.com/docs/pro-model.md - https://withoutbg.com/docs/pro-model/background-removal-binary.md - https://withoutbg.com/docs/pro-model/background-removal-base64.md - https://withoutbg.com/docs/pro-model/alpha-matte-binary.md - https://withoutbg.com/docs/pro-model/alpha-matte-base64.md - https://withoutbg.com/docs/pro-model/car-background-removal-binary.md - https://withoutbg.com/docs/pro-model/car-background-binary.md - https://withoutbg.com/docs/pro-model/car-layers-base64.md - https://withoutbg.com/docs/pro-model/credits.md ## Open Model docs - https://withoutbg.com/open-model - https://withoutbg.com/docs/open-model/python.md - https://withoutbg.com/docs/open-model/docker.md - https://withoutbg.com/docs/open-model/local-api.md - https://withoutbg.com/mac ## Benchmark and methodology Bench v0 scores background removal models (withoutBG and open models such as BiRefNet, IS-Net, U²-Net) against ground-truth alpha mattes on the same real photos. Metrics: MAE, MGE (edge gradient error); lower is better. Ground truth and predictions are scored at an 800 px longer side; reported numbers are per-image averages. Per-image error sums and pixel counts are published, so any subset can be recomputed. Data license: CC BY 4.0. - Benchmark page: https://withoutbg.com/benchmarks/open-background-removal - Markdown: https://withoutbg.com/benchmarks/open-background-removal.md - Scores (JSON): https://withoutbg.com/benchmarks/bench-v0/scores.json - Scores (CSV): https://withoutbg.com/benchmarks/bench-v0/scores.csv Disclosure: withoutBG Open Weights and Pro Model API are routed pipelines. A classifier sends fine strands, soft detail and transparency to withoutBG's own matting model, and hard opaque objects, flat scenes and vehicles to BiRefNet (ZhengPeng7/BiRefNet, MIT), which is part of the pipeline. Pro Model API also runs an edge refiner on the result of either branch, so its BiRefNet-routed images are refined BiRefNet output. Car endpoints add further steps (such as cast shadows) that are not part of this benchmark. The score files mark each image's route (withoutbg_route) and split every model's means by it. Compare pages are of two kinds: quantitative (both models scored against ground truth; per-image and mean metrics shown) and qualitative (no ground truth for one model, e.g. remove.bg; side-by-side outputs only, no scores). ## Product and comparisons - https://withoutbg.com/pro-model-api - https://withoutbg.com/car - https://withoutbg.com/compare - https://withoutbg.com/compare/remove-bg-alternatives - https://withoutbg.com/models
| – |
| 7 Nov 2026 |
| – |
| 7 Nov 2026 |
| – | 7 Nov 2026 |
| – |
| 7 Nov 2026 |
| – |
| 7 Nov 2026 |
| – | 7 Nov 2026 |