Llama 3.1 Nemotron Safety Guard 8B v3
nvidia/llama-3.1-nemotron-safety-guard-8b-v3
Safety model for policy screening, moderation, and risk-aware routing workflows
Capabilities
ReasoningNo
Tool callingNo
Structured outputNo
TemperatureFixed
AttachmentNo
Open weightsYes
Limits
Context128,000 tokens
Max inputN/A
Max output4,096 tokens
Details
Familynemotron
Knowledge cutoffN/A
Release date2025-10-28
Last updated2025-10-28
Modalities
Inputtext
Outputtext
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A