meta-llama/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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrabf16 | $0.180 | $0.180 | 164K | 100% |
| Together | $0.200 | $0.200 | 1.0M | 100% |
Llama Guard 4 12B costs $0.180 per million input tokens and $0.180 per million output tokens via OpenRouter, making it 90th cheapest of 298 paid models.
Llama Guard 4 12B generates around 18 tokens per second with 120ms time-to-first-token (p50), the 268th fastest tracked model.
Llama Guard 4 12B supports a 164K-token context window and can output up to 16K tokens. It accepts image, text input.