Llama Guard 4 12B

JSON →
meta llm
text

A 12-billion-parameter safety classifier from Meta designed to detect harmful content and enforce content policies in LLM inputs and outputs.

context window 8K tokens
max output 8K tokens
input price $0.2 / 1M tokens
output price $0.2 / 1M tokens
json-modestreaming
releasedApr 2025
knowledge cutoffJun 2024