Deploy custom security & safety controls that align with your application needs and responsible AI guidelines, leveraging open NVIDIA Nemotron models.

Run Anywhere

nvidiallama-3.1-nemoguard-8b-topic-control

Topic control model to keep conversations focused on approved topics, avoiding inappropriate content.

LLM safetySafety and moderationdialogue safetynemo guardrailsnemotron

Run Anywhere

nvidianemoguard-jailbreak-detect

Industry leading jailbreak classification model for protection from adversarial attempts

LLM SafetyNIMPrompt InjectionSafety and Moderationllm securitynemo guardrailsnemotron

Run Anywhere

nvidiallama-3.1-nemoguard-8b-content-safety

Leading content safety model for enhancing the safety and moderation capabilities of LLMs

LLM safetySafety and moderationdialogue safetynemo guardrailsnemotron

nvidiallama-3.1-nemotron-safety-guard-8b-v3

Leading multilingual content safety model for enhancing the safety and moderation capabilities of LLMs

content moderationllm safetymultilingual content safetymultilingual guard modelnemoguard

Recognize content produced by popular models and AI platforms to detect plagiarism or prevent misinformation.

Run Anywhere

hivedeepfake-image-detection

Advanced AI model detects faces and identifies deep fake images.

AI safetyContent moderationcomputer visiondeep fake detection

Run Anywhere

hiveai-generated-image-detection

Robust image classification model for detecting and managing AI-generated content.

AI safetyContent moderationcomputer visionimage classification