Model Armor
Protect AI prompts, responses, and agent interactions
Runtime security for generative and agentic AI, Model Armor provides comprehensive protections against prompt injection, sensitive data leaks, and harmful content.
Model Armor offers a free tier; try it today.
Features
LLM-AI model threat detection
Proactively identifies and blocks sophisticated prompt injection and jailbreaking techniques designed to manipulate or compromise LLMs. It also detects and neutralizes malicious URLs embedded in prompts or responses before they can cause harm.
Granular content safety
Provides fine-grained control of harmful, unethical, or undesirable content, such as hate speech, harassment, sexually explicit material, and dangerous topics. Use adjustable confidence thresholds to allow organizations to precisely tune enforcement based on specific application context, user base, and risk tolerance.
Integrated sensitive data protection
Integrated with Google Cloud's Sensitive Data Protection service and specifically adapted for the unpredictability of AI-generated text. Model Armor helps prevent the leakage of personal identifiable information (PII), financial information, credentials, and custom-defined sensitive data types in both prompts and model responses.
Malware detection and safe browsing
Detects malicious files, malware, and unsafe URLs within AI prompts and responses. Stop embedded threats like indirect prompt injection where safe and legitimate prompts may be contaminated with malicious files and URLs.
Model and cloud agnostic deployment
Model Armor protects all LLMs (including Gemini, OpenAI, Anthropic, Llama, and more) via a REST API allowing developers to use it with any cloud or infrastructure. It also offers no-code in-line protection integrated with Vertex AI scalable model deployments or network service extensions and Apigee API gateways to act as an AI firewall.
How It Works
Model Armor screens AI prompts, responses, and agent interactions to provide runtime security for AI, constantly protecting from threats. It uses a hybrid defense in-depth approach that combines rules-based controls, ML models, and powerful AI reasoning models to provide adaptive defenses.
Model Armor screens AI prompts, responses, and agent interactions to provide runtime security for AI, constantly protecting from threats. It uses a hybrid defense in-depth approach that combines rules-based controls, ML models, and powerful AI reasoning models to provide adaptive defenses.
Common Uses
Secure customer service chatbot
Protecting customer-facing AI applications
LLM-powered chatbots are fundamental for businesses, but they pose risks like inadvertently leaking sensitive customer PII, providing incorrect policy information, or damaging brand reputation with offensive responses. Model Armor helps mitigate these threats.
Learning resources
Protecting customer-facing AI applications
LLM-powered chatbots are fundamental for businesses, but they pose risks like inadvertently leaking sensitive customer PII, providing incorrect policy information, or damaging brand reputation with offensive responses. Model Armor helps mitigate these threats.
Secure knowledge management AI agents
Brand-safe content generation
Pricing
| Model Armor pricing | Pay-as-you-go and subscription options. | |
|---|---|---|
| Package | Tier | Pricing |
Model Armor standalone | Free tier | Free for up to 2 million tokens/month |
Additional usage over 2 million tokens | $0.10 per additional 1 million tokens | |
SCC Premium (Organization-level) - Pay-as-you-go | Free tier | Free for up to 2 million tokens/month |
Additional usage over 2 million tokens | $0.10 per additional 1 million tokens | |
SCC Premium (Project-level) - Pay-as-you-go | Free tier | Free for up to 2 million tokens/month |
Additional usage over 2 million tokens | $0.10 per additional 1 million tokens | |
SCC Enterprise - subscription only | Included with subscription | 3 billion tokens/month |
Additional usage over 3 billion tokens | $0.10 per additional 1 million tokens | |
See additional Model Armor pricing details here.
Model Armor pricing
Pay-as-you-go and subscription options.
Model Armor standalone
Free tier
Free for up to 2 million tokens/month
Additional usage over 2 million tokens
$0.10 per additional 1 million tokens
SCC Premium (Organization-level) -
Pay-as-you-go
Free tier
Free for up to 2 million tokens/month
Additional usage over 2 million tokens
$0.10 per additional 1 million tokens
SCC Premium (Project-level) -
Pay-as-you-go
Free tier
Free for up to 2 million tokens/month
Additional usage over 2 million tokens
$0.10 per additional 1 million tokens
SCC Enterprise - subscription only
Included with subscription
3 billion tokens/month
Additional usage over 3 billion tokens
$0.10 per additional 1 million tokens
See additional Model Armor pricing details here.
