Safety, RAG & search · AWS vs Google Cloud
Amazon Bedrock Guardrails vs Model Armor
Bedrock Guardrails maps to Model Armor, which screens prompts and responses for prompt injection, jailbreaks, harmful content, sensitive data, and malicious URLs.
Gemini also has built-in, configurable safety filters.
Side-by-side comparison
| Aspect | Amazon Web Services | Google Cloud |
|---|---|---|
| Service | Amazon Bedrock Guardrails | Model Armor |
| Lifecycle | Generally available | Generally available |
| What it is | Content filters (hate, insults, sexual, violence, misconduct, prompt attack), denied topics, word filters, PII filters, contextual grounding checks, and Automated Reasoning checks. Also usable standalone through the ApplyGuardrail API. | Screens prompts and responses for prompt injection, jailbreaks, harmful content, sensitive data, and malicious URLs, for any model. |
| Pricing model | Charged per text unit processed by each policy type (content, denied topics, PII, grounding, Automated Reasoning). Word filters are free of charge. | Model Armor is billed by the volume of tokens screened. See the Model Armor pricing page. |
| Docs | Amazon Bedrock Guardrails docs | Model Armor docs |
| Pricing page | Amazon Bedrock Guardrails pricing | Model Armor pricing |
Key differences
- Model Armor works with any model and is configured through reusable templates.
- Gemini safety filters are configured per request and are separate from Model Armor.
- Sensitive-data screening uses Sensitive Data Protection.
Pricing summary
Pricing models only. No prices are quoted because they change by region and over time.
- AWS
- Charged per text unit processed by each policy type (content, denied topics, PII, grounding, Automated Reasoning). Word filters are free of charge. Amazon Bedrock Guardrails pricing →
- GCP
- Model Armor is billed by the volume of tokens screened. See the Model Armor pricing page. Model Armor pricing →
And on Azure?
Direct match Azure's equivalent is Foundry guardrails (content filters), Azure AI Content Safety. AWS vs Azure comparison →
FAQ
What is the Google Cloud equivalent of Amazon Bedrock Guardrails?
Bedrock Guardrails maps to Model Armor, which screens prompts and responses for prompt injection, jailbreaks, harmful content, sensitive data, and malicious URLs. Gemini also has built-in, configurable safety filters.
How does pricing compare between Amazon Bedrock Guardrails and Model Armor?
AWS: Charged per text unit processed by each policy type (content, denied topics, PII, grounding, Automated Reasoning). Word filters are free of charge. Google Cloud: Model Armor is billed by the volume of tokens screened. See the Model Armor pricing page. Check the official pricing pages for current rates.
What is the Azure equivalent?
Foundry guardrails (content filters) and Azure AI Content Safety (direct match). The Azure equivalent of Amazon Bedrock Guardrails is Foundry guardrails, which are powered by Azure AI Content Safety.