Builder

Specifies the action to take when harmful content is detected in the input. Supported values include:

Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

Specifies the action to take when harmful content is detected in the output. Supported values include:

Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

The managed word type to configure for the guardrail.