Amazon Bedrock Guardrails now supports Standard tier for contextual grounding checks
News
Amazon Bedrock Guardrails now offers a Standard tier for contextual grounding checks that detects and filters hallucinations by verifying model responses are grounded in reference sources.
- Standard tier supports conversational content and reasoning responses, unlike Classic tier
- Scores differently worded responses with same meaning more consistently
- Provides comprehensive language support matching Standard tier for content filters
- Same pricing as Classic tier; requires cross-Region inference with guardrail profile
- Available in 11 AWS Regions including US, Europe, and Asia Pacific
The Standard tier enables contextual grounding checks for conversational applications while maintaining existing guardrails on Classic tier by default.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Dec 3
2024
2024
Amazon Bedrock Guardrails now supports Automated Reasoning checks (Preview)
Apr 23
2024
2024
Guardrails for Amazon Bedrock now available with new safety filters and privacy controls
Jun 17
2026
2026
Amazon Bedrock AgentCore now supports Bedrock Guardrails in policy
Oct 3
2024
2024
Implement model-independent safety measures with Amazon Bedrock Guardrails
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.