Amazon Bedrock Guardrails image content filters provide industry-leading safeguards, helping customer block up to 88% of harmful multimodal content: Generally available today

Amazon Bedrock Guardrails has announced the general availability of image content filters, providing comprehensive content moderation for generative AI applications across both text and image modalities.

• Enables blocking up to 88% of harmful multimodal content
• Offers six distinct policy types, including content, topic, and sensitive information filters
• Supports configurable moderation with adjustable thresholds
• Available in multiple AWS regions including US East, US West, Europe, and Asia Pacific
• Can be integrated across foundation models, self-hosted, and third-party models

The new capability helps organizations enhance brand safety by preventing harmful or unwanted content without requiring manual moderation or custom safeguard development.