Amazon Bedrock Guardrails

Amazon Bedrock Guardrails is a cloud service for applying checks to model interactions. Listed capabilities include prompt injection defense, output guardrails, PII redaction, and secrets detection. Controls include text and image content filters, denied-topic rules, sensitive-information filters, word filters, and contextual grounding checks. Separate InvokeGuardrailChecks options cover content filters, prompt attacks, and sensitive-information filters; content-filter and prompt-attack checks are specified for text only. The service is web-based and has no free plan. Listed prices include $0.15 a month for text content filters on Standard and Classic tiers, and $0.15 a month for denied topics. Sensitive-information filters and contextual grounding checks each cost $0.10 a month. Image content filters, regular-expression sensitive-information filters, and word filters are listed at free. InvokeGuardrailChecks content filters cost $0.07 a month, prompt-attack checks cost $0.08 a month, and sensitive-information checks cost $0.10 a month.

It suits users seeking cloud-based checks for model inputs and outputs, including content filtering, sensitive-information handling, and prompt-injection defense. Readers should consider the individual listed charges because there is no free plan.