Llama Guard 4 12B
META-LLAMA Developer Architecture Profile
Intelligence (ELO)1054Chatbot Arena Verified
Max Context Limit163,840Max Out: 16,384 tokens
Prompt CachingStandardNo Cache Discount
Standard API / 1M$0.36Blended Standard Rate
Model Capabilities & Contract SLAs
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...
Granular Pricing Matrix
Input Tokens (Standard Prompt)$0.18 / 1M
Output Tokens (Completion)$0.18 / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine MatchupLlama Guard 4 12B vs OpenAI: GPT-6 Luna (batch)VS Engine MatchupLlama Guard 4 12B vs OpenAI: gpt-oss-120b (batch)VS Engine MatchupLlama Guard 4 12B vs Google: Gemma 3 12BVS Engine MatchupLlama Guard 4 12B vs Meta: Muse Spark 1.2 ContributorVS Engine MatchupLlama Guard 4 12B vs NVIDIA: Nemotron 3.5 Content Safety (free)VS Engine MatchupLlama Guard 4 12B vs Reka Edge