Llama-Guard-3-8B · deepinfra
Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.
Entrada, $/1M $0.055
Salida, $/1M $0.055
Contexto 131 072
Acepta —
Última comprobación 04.11.2026 12:00:14 UTC
Fuente —
Alertas de precio
API
Este tipo de modelo no tiene un formato de solicitud común: consulta la documentación del proveedor.
Source: AI Rate Card, https://airatecard.com/es/c/offer%3Adeepinfra%7Cmeta-llama/Llama-Guard-3-8B, prices checked 2026-11-04
Datos técnicos
ID: offer:deepinfra|meta-llama/Llama-Guard-3-8B