Amazon Rekognition Content Moderation

C tier on AI Image Recognition SoftwareScore 6.9 · #6 of 35

Android app: Not listed
Free plan: Yes
Paid plans from: $0.10/mo
Runs on: api, Web

aws.amazon.com

Summary

Amazon Rekognition Content Moderation uses machine learning and managed APIs to automate moderation of images and videos. It detects categories that include explicit or suggestive content, violence, drugs, tobacco, alcohol, hate symbols, gambling, and disturbing content. Results provide labels, confidence scores, and timestamps for video, which can support rules organized by a hierarchical taxonomy. Customers can train a Custom Moderation adapter for image analysis with as few as 20 annotated images. The service can connect low-confidence predictions to Amazon Augmented AI for review by teams or third-party reviewers. For stored video, the StartContentModeration API analyzes a video in an Amazon S3 bucket and publishes completion status to an Amazon SNS topic. AWS bills according to images or video duration processed, with no minimum fee or upfront commitment. The Free Tier lasts 12 months from account creation and includes 60 video-analysis minutes per month and two custom-adapter training hours per month. Images and videos passed to the service may be stored and used to improve it unless customers opt out; stored content is encrypted at rest using AWS KMS.

Who it is for

This service suits teams moderating image and video content in areas such as social media, gaming, ecommerce, advertising, and media and entertainment. It also fits teams that need human review for low-confidence results or image rules tailored with a custom adapter.

What is good

Detects multiple image and video moderation categories.
Results include labels, confidence scores, and video timestamps.
Custom adapter training can use as few as 20 images.
Low-confidence predictions can go to human review.
No minimum fees or upfront commitments.

What to know first

Text moderation is not supported.
Free Tier lasts 12 months from account creation.
Content may be stored and used for service improvement unless customers opt out.
Charges depend on images or video duration processed.

Verdict

Amazon Rekognition Content Moderation combines managed image and video detection with custom adapters and optional human review. Consider its usage-based charges and content-handling terms when planning a moderation workflow.

Amazon Rekognition Content Moderation plans and pricing

All plans

Amazon Rekognition Free Tier Free Free Tier lasts 12 months from account creation 60 free video analysis minutes per month, including Content Moderation · 2 free training hours per month for a custom moderation adapter aws.amazon.com · 2 Oct 2026

Amazon Rekognition Custom Moderation adapter Free $0.0012 per image for the first 1 million images in the US East (N. Virginia) example; training is $5 per hour Tiered image pricing · custom adapter can be trained with as few as 20 annotated images aws.amazon.com · 2 Oct 2026

Amazon Rekognition Video Content Moderation $0.10/mo $0.10/min for stored video analysis in the us-east-1 example Pay per video minute · no upfront costs or minimum fees aws.amazon.com · 2 Oct 2026

Compared on AI image recognition software

Free plan: Noaws.amazon.com
Text moderation: Noaws.amazon.com
Image moderation: Yesaws.amazon.com
Audio moderation: Noaws.amazon.com
Video moderation: Yesaws.amazon.com
Custom policies: Yesaws.amazon.com
Human review workflow: Yesaws.amazon.com
Deployment options: cloudaws.amazon.com

Facts

Purpose: Amazon Rekognition Content Moderation automates image and video moderation workflows with machine learning and managed APIs.aws.amazon.com · 2 Oct 2026
Moderation categories: It detects categories including explicit or suggestive content, violence, drugs, tobacco, alcohol, hate symbols, gambling, and disturbing content.aws.amazon.com · 2 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 · 2 Oct 2026
Custom models: Amazon Rekognition Custom Moderation lets customers train an adapter with as few as 20 annotated images for image analysis tasks tailored to their use case.aws.amazon.com · 2 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 · 2 Oct 2026
Integrations: The product page describes using Amazon S3 to store uploaded content and Amazon Augmented AI for human review.aws.amazon.com · 2 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 · 2 Oct 2026
Security: Amazon Rekognition API endpoints support HTTPS, and its documentation says communications are encrypted using TLS.docs.aws.amazon.com · 2 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 · 2 Oct 2026
Compliance: Third-party auditors assess Amazon Rekognition as part of multiple AWS compliance programs, while customers remain responsible for evaluating their own compliance obligations.docs.aws.amazon.com · 2 Oct 2026
Use cases: AWS describes use cases including social media, gaming, ecommerce, advertising, and media and entertainment.aws.amazon.com · 2 Oct 2026
Scaling and billing: AWS says the service processes from a few to millions of images and videos, charges based on images or video duration processed, and has no minimum fees, licenses, or upfront commitments.aws.amazon.com · 2 Oct 2026