AI Observatory / Model Radar
Meta / meta-llama/llama-guard-4-12b
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...
163,840
Context
16,384
Max output
$0.18 / 1M
Prompt price
2025-04-30
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Meta | Input modalities | image, text |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.18 / 1M |
| Completion price | $0.18 / 1M | Request price | N/A |
| Context length | 163,840 | Max completion tokens | 16,384 |
| Supported parameters | frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, temperature, top_k, top_p | ||
Best for
meta-llama/llama-guard-4-12b
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...
Cross-modal work
High-volume usage
vision
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.