- Home
- AI Content Moderation Software
- Amazon Rekognition Content Moderation
Amazon Rekognition Content Moderation
Seattle, Washington, United States
What it is
Amazon Rekognition Content Moderation uses machine learning and managed APIs to automate moderation of images and videos. It identifies categories such as explicit or suggestive material, violence, drugs, tobacco, alcohol, hate symbols, gambling and disturbing content. Results include labels, confidence scores and video timestamps; a hierarchical taxonomy can help teams set detailed rules. For image analysis, customers can train a Custom Moderation adapter using as few as 20 annotated images. Low-confidence predictions can be sent through Amazon Augmented AI for review by a team or third-party reviewers. For stored-video analysis, StartContentModeration processes a video in an Amazon S3 bucket and publishes completion status to an Amazon SNS topic. The service is available through API and web, with cloud deployment. AWS bills by images or video duration processed, with no minimum fees or upfront commitments. The Free Tier lasts 12 months from account creation and includes 60 video-analysis minutes and two custom-adapter training hours per month. Images and videos may be retained to improve the service unless customers opt out; stored content is encrypted at rest using AWS KMS.
For and against
For
- Detects multiple image and video moderation categories
- Returns confidence scores and video timestamps
- Custom adapter training starts with 20 annotated images
- Low-confidence results can go to human review
- Free Tier includes monthly video and training allowances
Against
- No text or audio moderation
- Data may be stored unless customers opt out
- Free Tier lasts 12 months from account creation
- Video analysis is billed by duration processed
The verdict
Amazon Rekognition Content Moderation combines automated image and video detection with configurable rules and optional human review. Customers should account for its data-retention default and usage-based charges.
Who it suits
It suits teams moderating image or video content in social media, gaming, ecommerce, advertising, or media and entertainment. Teams that need human review or tailored image moderation can use its review workflow and custom adapter.
Plans and prices
Amazon Rekognition Custom Moderation adapter
Tiered image pricing · custom adapter can be trained with as few as 20 annotated images
Read 2 Oct 2026 · aws.amazon.com
Amazon Rekognition Free Tier
60 free video analysis minutes per month, including Content Moderation · 2 free training hours per month for a custom moderation adapter
Read 2 Oct 2026 · aws.amazon.com
Amazon Rekognition Video Content Moderation
Pay per video minute · no upfront costs or minimum fees
Read 2 Oct 2026 · aws.amazon.com
Custom Moderation adapter
adapter can train with as few as 20 annotated images · 2 free training hours/month for 12 months
Read 15 Oct 2026 · aws.amazon.com
Standard image moderation (DetectModerationLabels, Group 2)
tiered monthly image volume · no upfront fee or minimum
Read 15 Oct 2026 · aws.amazon.com
Video content moderation
60 free video-analysis minutes/month for 12 months · stored-video analysis from S3 · streaming video uses Kinesis Video Streams separately
Read 15 Oct 2026 · aws.amazon.com
On the record
- API pagination
- GetContentModeration supports MaxResults and NextToken pagination when a video produces many moderation labels.docs.aws.amazon.com · read 15 Oct 2026
- API workflow
- For stored video, StartContentModeration analyzes a video in an Amazon S3 bucket and publishes completion status to an Amazon SNS topic.docs.aws.amazon.com · read 2 Oct 2026
- Company founded
- AWS states it launched in 2006.linkedin.com · read 15 Oct 2026
- Company headquarters
- LinkedIn lists Seattle, Washington as AWS headquarters.linkedin.com · read 15 Oct 2026
- Company legal name
- The maker is Amazon Web Services (AWS), the cloud business of Amazon.com, Inc.linkedin.com · read 15 Oct 2026
- Company size
- LinkedIn lists AWS company size as 10,001+ employees.linkedin.com · read 15 Oct 2026
- Compliance
- AWS states that third-party audits cover Rekognition under SOC, PCI, FedRAMP, HIPAA, and other compliance programs.docs.aws.amazon.com · read 15 Oct 2026
- Confidence control
- Developers can set MinConfidence to trade recall for precision when filtering moderation results.aws.amazon.com · read 15 Oct 2026
- Custom models
- Custom Moderation trains an adapter on annotated images and supplies its AdapterID to DetectModerationLabels to improve results for a specific use case.docs.aws.amazon.com · read 15 Oct 2026
- Data handling
- Images and videos passed to Rekognition may be stored and used to improve the service unless the customer opts out; the stored content is encrypted at rest using AWS KMS.docs.aws.amazon.com · read 2 Oct 2026
- Deployment model
- TrustRadius classifies Amazon Rekognition as SaaS and reports no mobile application.trustradius.com · read 15 Oct 2026
- Detected categories
- The API detects adult content, violence, weapons, disturbing imagery, drugs, alcohol, tobacco, hate symbols, gambling, and rude gestures.aws.amazon.com · read 15 Oct 2026
- Detection results
- The service returns detected labels and video timestamps with confidence scores, which can be used with a hierarchical taxonomy to create granular rules.aws.amazon.com · read 2 Oct 2026
- Documentation depth
- AWS documentation covers getting started, SDK installation, images, stored video, streaming video, moderation APIs, custom adapters, and human review workflows.docs.aws.amazon.com · read 15 Oct 2026
- Hierarchical labels
- Moderation results use a three-level taxonomy with L1, L2, and L3 labels and include each label's taxonomy level.docs.aws.amazon.com · read 15 Oct 2026
- Human review
- The service integrates with Amazon Augmented AI so teams or third-party reviewers can assess low-confidence predictions.aws.amazon.com · read 2 Oct 2026
- Human review integration
- Amazon Augmented AI is integrated so human reviewers can handle a smaller set of machine-flagged content.docs.aws.amazon.com · read 15 Oct 2026
- Image API
- Images can be moderated synchronously with DetectModerationLabels or asynchronously with StartMediaAnalysisJob and GetMediaAnalysisJob.docs.aws.amazon.com · read 15 Oct 2026
