Meta: Llama Guard 4 12B
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...
Everything else
| Max output | 16K |
|---|---|
| Input / 1M | $0.18 |
| Output / 1M | $0.18 |
| Cache read / 1M | — |
| Cache write / 1M | — |
| 1M in + 1M out | $0.36 |
| Takes | image, text |
| Returns | text |
| Tools | no |
| Reasoning | no |
| Open weights | yes |
| Released | 2025-04-30 |
| Knowledge cutoff | 2024-08-31 |
| Retires | — |
| Catalog id | meta-llama/llama-guard-4-12b |
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.