Models / Meta
Moderation

Llama Guard 4 12B

Multimodal safety model from Llama 4 Scout, classifying text and images for safe LLM prompts and responses.

This model is not available on Together’s Serverless API.

  • Model provider
    Meta
  • Type
    Moderation
  • Main use cases
    Moderation
  • Parameters
    12B
  • Context length
    1M
  • Input price

    $0.20 / 1M tokens

  • Output price

    $0.20 / 1M tokens

  • Input modalities
    Text
    Image
  • Output modalities
    Text
  • Released
    April 23, 2025
  • External link
  • Category
    Moderation