Meta: Llama Guard 4 12Bmeta-llama
Bottom Line
Meta: Llama Guard 4 12B: $0.18/1M input, $0.18/1M output, 164K context. 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...
API Pricing (per 1M tokens)
| Input | $0.18 |
| Output | $0.18 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.18 |
Specs & Performance
| Context Length | 164K |
| Max Output | 16K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | image, text → text |
More from meta-llama
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Meta: Llama Guard 4 12B API cost?
Meta: Llama Guard 4 12B costs $0.18/1M input tokens and $0.18/1M output tokens. Blended cost at a 3:1 ratio is about $0.18/1M tokens.
What is the context window of Meta: Llama Guard 4 12B?
Meta: Llama Guard 4 12B supports a 164K token context window with up to 16K output tokens.
Is Meta: Llama Guard 4 12B worth it?
Meta: Llama Guard 4 12B has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.