Meta (Llama) · Chat · meta-llama/llama-guard-4-12b
Llama Guard 4 12B
Short answer
Llama Guard 4 12B is listed by Meta (Llama) and is marked new, not yet reviewed. Llama Guard 4 12B is listed at $0.18 input and $0.18 output per million tokens, with a 163,840-token context window. In: image, text. Out: text. Tools: Not listed. Open weights: Yes.
New, not yet reviewed
Tools: Not listed.
- in image
- in text
- out text
- open weights
Facts
| Fact | Value | Source |
|---|---|---|
| Release date | 30 Apr 2025 | OpenRouter field created. This is the listing date the feed publishes. Checked 20 Nov 2026. |
| Context window | 163,840 tokens | OpenRouter field context_length. Checked 20 Nov 2026. |
| Max output | 16,384 tokens | OpenRouter field top_provider.max_completion_tokens. Checked 20 Nov 2026. |
| Input price | $0.18 per million tokens. Published per-token rate 0.00000018. | OpenRouter field pricing.prompt, USD per token, multiplied by 1,000,000. Checked 20 Nov 2026. |
| Output price | $0.18 per million tokens. Published per-token rate 0.00000018. | OpenRouter field pricing.completion, USD per token, multiplied by 1,000,000. Checked 20 Nov 2026. |
| Batch input price | No batch route listed | Sibling OpenRouter id ending in :batch, field pricing.prompt. Checked 20 Nov 2026. |
| Batch output price | No batch route listed | Sibling OpenRouter id ending in :batch, field pricing.completion. Checked 20 Nov 2026. |
| Input modalities | image, text | OpenRouter field architecture.input_modalities. Checked 20 Nov 2026. |
| Output modalities | text | OpenRouter field architecture.output_modalities. Checked 20 Nov 2026. |
| Tools | Not listed | OpenRouter field supported_parameters contains tools. Checked 20 Nov 2026. |
| Open weights | Yes — meta-llama/Llama-Guard-4-12B | OpenRouter field hugging_face_id. Empty means no public weights id is listed, which is not a legal opinion. Checked 20 Nov 2026. |
| Knowledge cutoff | 2024-08-31 | OpenRouter field knowledge_cutoff. Checked 20 Nov 2026. |
| Reasoning | Unknown | OpenRouter field reasoning. Missing means unknown, not unsupported. Checked 20 Nov 2026. |
Listing blurb
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...
No third-party index was included for this model in the feed. The Best Model For does not fill that gap.
Questions
How much does Llama Guard 4 12B cost?
Llama Guard 4 12B is listed at $0.18 input and $0.18 output per million tokens, with a 163,840-token context window. No batch route is listed. Other price fields, if any, are on this page and are not converted.
Does Llama Guard 4 12B have open weights?
The feed lists a Hugging Face id: meta-llama/Llama-Guard-4-12B. That is what The Best Model For means by open weights.
What is Llama Guard 4 12B good for?
The Best Model For has not reviewed this model. The safe default is a small sample of the real task, not a production queue.