Llama Guard 4 12Bon Krater.ai
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
Released April 30, 2025
Specifications
Llama Guard 4 12B at a glance
Context
1M tokens
Max output
16.4K tokens
Input
Image, Text
Output
Text
Input price
$0.18 / 1M
Output price
$0.18 / 1M
Knowledge cutoff
2024-08-31
Capabilities
What it is good at
Catalog capabilities
- Accepts image input
- Generates text responses
Good for
Compare
Compare Llama Guard 4 12B
Llama Guard 4 12B vs Llama 4 Scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B.
Open comparisonLlama Guard 4 12B vs Llama 4 Maverick
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward
Open comparisonLlama Guard 4 12B vs Llama 3.1 8B Instruct
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors.
Open comparisonFAQ
Questions about Llama Guard 4 12B
Clear answers based on the model catalog and Krater access.
Use Llama Guard 4 12B in your API
Connect with Krater's unified API.
Ready to use Llama Guard 4 12B?
Access leading models in one focused workspace.