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...
Specifications
| Provider | Meta |
|---|---|
| Intelligence Index | Not yet benchmarked |
| Context window | 163,840 tokens (164K) |
| Input price | $0.18 / 1M tokens |
| Output price | $0.18 / 1M tokens |
| Input modalities | image, text |
| Output modalities | text |
| Model ID | meta-llama/llama-guard-4-12b |
Pricing is per 1M tokens, indicative pricing via OpenRouter (updated 2026-10-05); a provider's own list price may differ. Intelligence Index via Artificial Analysis.
Frequently asked questions
How much does Llama Guard 4 12B cost?
Indicative pricing (via OpenRouter, updated 2026-10-05) is $0.18 per 1M input tokens and $0.18 per 1M output tokens. A provider's own list price may differ. On Vincony, Llama Guard 4 12B is available on credit-based pricing alongside 750+ other models.
What is Llama Guard 4 12B's context window?
Llama Guard 4 12B supports a context window of up to 163,840 tokens (164K), which is how much text it can consider at once.
Who makes Llama Guard 4 12B?
Llama Guard 4 12B is built by Meta. You can access it — and compare it against other providers' models — through Vincony's multi-model platform.
How do I use Llama Guard 4 12B?
You can use Llama Guard 4 12B directly through Meta, or via Vincony, which aggregates 750+ models (including Llama Guard 4 12B) into one interface with side-by-side comparison and credit-based pricing.