Meta
Llama Guard 4 12B
meta-llama/llama-guard-4-12b
Input
$0.18
per 1M tokens
Output
$0.18
per 1M tokens
Cached input
—
per 1M tokens
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...
- Released
- Context window
- 164K tokens
- Max output
- 16K tokens
- Input
- image, text
- Output
- text
- Reasoning
- No
Price history
No price changes since we started tracking on .
Providers on OpenRouter
3 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| DeepInfrabf16 · flexdiscount/priority tier | $0.144 | $0.144 | 164K | — | 100% |
| DeepInfrabf16 | $0.18 | $0.18 | 164K | 100% | 97.8% |
| DeepInfrabf16 · prioritydiscount/priority tier | $0.27 | $0.27 | 164K | 100% | 97.3% |