Amazon Bedrock Guardrails now supports Standard tier for contextual grounding checks

Amazon Bedrock Guardrails Standard Tier for Contextual Grounding Checks

Amazon Bedrock Guardrails now offers a Standard tier for contextual grounding checks, which detect and filter hallucinations by ensuring model responses are grounded in your reference source and relevant to the user's query. This tier is more robust than the Classic tier, supporting responses that include reasoning or conversational content, scoring differently worded responses with the same meaning more consistently, and providing more comprehensive language support.

What to do

• Choose the Standard tier for each guardrail in the Amazon Bedrock console or API.
• Existing guardrails will retain the Classic tier until changed.
• Use cross-Region inference with a guardrail profile to access the Standard tier.

Availability

The Standard tier is available in the following AWS Regions: US East (N. Virginia), US East (Ohio), US West (N. California), US West (Oregon), Europe (Frankfurt), Europe (Ireland), Europe (Milan), Europe (Paris), Europe (Spain), Europe (Stockholm), and Asia Pacific (Tokyo).

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.