Meta: Llama Guard 4 12B
Review
Meta's Llama Guard 4 12B is a safety-classification model designed for content moderation rather than general business tasks, with vision support and affordable pricing. It has no general benchmark data and is not suited to typical content generation or reasoning workflows.
Assessment date: April 16, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Performance Profile
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..
Capabilities
Architecture
| Modality | Text + Image → Text |
| Tokenizer | Other |
| Parameters | 12B |
How does Meta: Llama Guard 4 12B stack up?
Compare side-by-side with other legacy models.
Model Information
| OpenRouter ID |
meta-llama/llama-guard-4-12b
|
| Provider | meta-llama |
| Release Date | April 30, 2025 |
| Context Length | 163,840 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.18 | $0.000180 |
| Output | $0.18 | $0.000180 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
