Review Llama Guard 4 12B on key metrics including price, context length, throughput, and model features.
AuthorMeta Llama
Context Length163.8k
Supports Tools
Llama Guard 4 is a multimodal content safety classifier derived from Llama 4 Scout, fine-tuned for both prompt and response classification. It supports content moderation for English and multiple languages, including mixed text-and-image prompts. The model is aligned with the MLCommons hazards taxonomy and is integrated into the Llama Moderations API for robust safety classification in text and images.