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 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.

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 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 numerous Google Cloud services including Gemini platform to act as an AI firewall.