Detector24 vs Amazon Rekognition
Amazon Rekognition Content Moderation is the moderation primitive inside AWS: image moderation from $0.0010 per image, stored video at $0.10 per minute, a ten-category taxonomy, a 99.9% uptime SLA and the AWS compliance programme, with text moderation handled separately by Amazon Comprehend in English only. Detector24 is a standalone API covering image, video, text in 95+ languages and audio, plus AI-generated content, deepfake and threat detection, with per-model published prices, 100 free moderations a month and content deleted after analysis.
Information last reviewed September 7, 2026. Compared: Detector24’s published plans against Amazon Rekognition Content Moderation as publicly priced for US East (N. Virginia) on aws.amazon.com, in USD.
Still shortlisting? See all alternatives to Amazon Rekognition, including services we do not sell.
Where Detector24 and Amazon Rekognition differ
One API versus three AWS services
Rekognition moderates images and stored video; text toxicity lives in Amazon Comprehend and is English only per its docs; AI-generated image or deepfake detection is not stated in Rekognition’s materials. Detector24 covers image, video, text in 95+ languages and audio in one API, with AI image, deepfake, AI music, AI voice and threat detection as products in the same catalogue.
Your inputs and their models
AWS states Rekognition may store and use image and video inputs to improve Rekognition and other Amazon machine-learning technologies unless you opt out through an AWS Organizations AI services opt-out policy. Detector24 no human reviewers in the loop; images are automatically deleted after analysis with no long-term storage; data residency options available. Rekognition’s moderation calls themselves are non-storage operations where no input bytes persist.
Per-image tiers versus per-model prices
Rekognition publishes clear tiers: $0.0010 per image for the first million a month, falling to $0.00025 per image above 35 million, and $0.10 per minute of stored video, with a 12-month free tier of 1,000 images and 60 video minutes a month. Detector24 publishes per-model prices with basic moderation from $0.00007 per check on higher-tier plans, from a $99 or $599 monthly minimum, with 100 free moderations every month. Compare at your own volume.
AWS brings the compliance programme and the SLA
Rekognition is in scope for SOC 1, 2 and 3, PCI DSS, FedRAMP, HIPAA eligibility and a long ISO list including 27001, 27017, 27018 and 27701, carries a 99.9% monthly uptime SLA, supports PrivateLink and FIPS endpoints, and ships SDKs in 13 languages. Detector24 states AICPA SOC, ISO 27001, PCI DSS, CSA STAR Level One, GDPR-compliant handling; if FedRAMP or HIPAA eligibility is a hard requirement, Rekognition has the paperwork.
Detector24 and Amazon Rekognition, side by side
| Attribute | Detector24 | Amazon Rekognition |
|---|---|---|
| Modalities | Image, video and live-stream, text and audio moderation, plus AI-generated image detection, deepfake detection, AI music and AI voice detection, and threat detection | Images (DetectModerationLabels) and stored video (StartContentModeration); streaming video moderation not stated and Streaming Video is no longer available to new customers from 30 April 2026; text via Amazon Comprehend toxicity detection, English only; AI-generated or deepfake detection not stated |
| Categories | Image moderation across 25+ categories including NSFW, violence and hate symbols; text moderation in 95+ languages with PII and threat detection | Three-level taxonomy with ten top-level categories: Explicit, Non-Explicit Nudity, Swimwear or Underwear, Violence, Visually Disturbing, Drugs and Tobacco, Alcohol, Rude Gestures, Gambling, Hate Symbols; docs state it does not detect CSAM |
| Public pricing | Free tier with 100 moderations a month; Core from a $99 monthly minimum; Forensic from a $599 monthly minimum; per-model, per-request prices published on the pricing page, with basic content moderation from $0.00007 per check on higher-tier plans. No setup fees. | US East: $0.0010 per image for the first 1 million, $0.0008 for the next 4 million, $0.0006 for the next 30 million, $0.00025 above 35 million; stored video $0.10 per minute; custom moderation adapters from $0.0012 per image and $5 per training hour |
| Free tier | 100 free moderations a month on the free tier | 12 months from account creation: 1,000 images a month for Group 1 and Group 2 APIs and 60 minutes of video analysis a month |
| Stated speed | Under 150 ms for image moderation, under 100 ms for text, under 500 ms for video with sub-second live-stream checks, and under 300 ms for audio, as stated on each product page | Latency figures not stated in the materials we reviewed; SLA credits apply when monthly uptime falls below 99.9%; default 50 transactions a second for DetectModerationLabels in us-east-1 |
| Stated accuracy | 98.5% accuracy stated for image moderation on detector24.ai | “Automatically flagging up to 95% of unsafe content”, with humans reviewing “typically 1-5% of the total volume”; AWS recommends measuring accuracy on your own data sets; no independent benchmark cited |
| Submitted content handling | No human reviewers in the loop; images are automatically deleted after analysis with no long-term storage; data residency options available | Moderation calls are non-storage operations; AWS may use inputs to improve Rekognition and other Amazon AI services unless you opt out via an AWS Organizations policy; deletion requests through AWS Support; data residency by region not stated for moderation specifically |
| Certifications stated | AICPA SOC, ISO 27001, PCI DSS, CSA STAR Level One, GDPR-compliant handling | In scope for SOC 1, 2 and 3, PCI DSS and 3DS, FedRAMP, HIPAA eligible, ISO/IEC 27001:2022, 27017, 27018, 27701, 22301, 20000-1, 9001 and CSA STAR CCM v4.0 |
| Human review and custom rules | None: fully automated, with per-model confidence thresholds you configure | Amazon A2I integration for human review via confidence-range or random-sampling triggers; Custom Moderation adapters trained on your annotated images, expiring 60 to 90 days after a new base model |
Third-party details on this page reflect what each provider publicly stated on the review date shown above and may have changed since. Statements about what Amazon Rekognition offers reflect its public materials on the review date; absence of a feature from those materials does not prove it is unavailable.
Where we agree with AWS: measure accuracy on your own data
AWS’s developer guide tells customers to measure Rekognition’s accuracy on their own data sets rather than trust a headline figure, and offers adapters so you can tune the model to your content. That is sound advice for any vendor on this page, Detector24 included. Detector24 states 98.5% accuracy for image moderation on its site; AWS states it flags up to 95% of unsafe content. Neither number replaces a test on your uploads.
The structural difference is scope. Rekognition is one primitive in a very large catalogue: images and stored video here, English text toxicity in Comprehend, no stated AI-generated or deepfake detection, and streaming video withdrawn for new customers in April 2026. Detector24 is a narrower company with a wider moderation catalogue: image, video, live stream, text in 95+ languages, audio, and AI-generated content, deepfake, AI music, AI voice and threat detection through one API.
The last difference is what your uploads become. AWS may use image and video inputs to improve its services unless you opt out at the organisation level, and the moderation calls themselves persist nothing. Detector24 deletes after analysis and does not offer a training opt-in on customer content. If you are already inside AWS with an opt-out policy in place, that gap closes; if you are not, it is worth reading twice.
Detector24 fits you if
- You need text moderation in more than English, or audio moderation, in the same API as images
- AI-generated image, deepfake, AI music or AI voice detection is part of your requirement
- Content must be deleted after analysis with no training use
- You want stated latency figures and a free tier that renews every month
Amazon Rekognition may fit you if
- You are already on AWS and want moderation inside your existing IAM, VPC and billing
- FedRAMP, HIPAA eligibility or the full AWS ISO list is a hard requirement
- You want a contractual 99.9% uptime SLA and SDKs in 13 languages
- Custom moderation adapters and Amazon A2I human review fit your workflow
Common questions
If you need more than image and stored-video moderation, yes. Detector24 covers image, video, text in 95+ languages and audio, adds AI-generated content, deepfake and threat detection, publishes per-model prices, and gives every account 100 free moderations a month on the free tier. Rekognition offers deeper AWS integration, a 99.9% SLA and the AWS compliance programme.
How we compared
This comparison is based on publicly available information from Amazon Rekognition’s official website, pricing page and documentation, and on Detector24’s own published pricing and features, as reviewed on September 7, 2026. Features, pricing and availability may change at any time. Please verify current details directly with each provider before purchasing.
Nothing on this page is legal advice. Which moderation setup satisfies the UK Online Safety Act, the EU Digital Services Act, US state laws or any platform policy depends on your service and your regulator’s guidance. Confirm your obligations with qualified counsel.
Sources
- Amazon Rekognition content moderation feature page (verified September 7, 2026)
- Amazon Rekognition pricing (verified September 7, 2026)
- Rekognition developer guide: moderating content (taxonomy) (verified September 7, 2026)
- Rekognition developer guide: availability changes (streaming video, bulk analysis) (verified September 7, 2026)
- Amazon Comprehend: toxicity detection (English only) (verified September 7, 2026)
- Amazon Rekognition FAQ (data use, accuracy) (verified September 7, 2026)
- Rekognition developer guide: storage and non-storage operations (verified September 7, 2026)
- Amazon Rekognition SLA (verified September 7, 2026)
- AWS services in scope (compliance programmes) (verified September 7, 2026)
- Rekognition developer guide: Amazon A2I integration (verified September 7, 2026)
- Detector24 pricing (our own published claims) (verified September 7, 2026)
Detector24 is an independent service operated by Bynn Intelligence Inc. and is not affiliated with, sponsored by, or endorsed by Amazon Rekognition. All third-party names and trademarks are the property of their respective owners and are used only to identify the products being compared.
Related comparisons
Run the models on your own content
100 free moderations a month on the free tier. The same API, dashboard and model catalogue as the paid plans.