llama-3.1-nemotron-safety-guard-8b-v3 API
About
Process massive datasets with llama-3.1-nemotron-safety-guard-8b-v3, featuring an expansive 128K context window for long-document analysis. This model delivers available completely free of charge, open weights architecture. Access llama-3.1-nemotron-safety-guard-8b-v3 via the Nvidia API with up to 4K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
No
Structured Output
No
Tool Use
No
WeightsOpen
Temperature
Fixed
Attachment
Not Supported
Limits
Context Window
128K
Tokens
Input Limit
128K
Tokens
Max Output
4K
Tokens
Pricing
Standard (per 1M tokens)
Input
Free
Output
Free
Frequently Asked Questions
llama-3.1-nemotron-safety-guard-8b-v3 by Nvidia costs Free per 1M input tokens and Free per 1M output tokens.
Model Details
ID
nvidia/llama-3_1-nemotron-safety-guard-8b-v3
Provider
NvidiaFamily
Release Date
Oct 28, 2025
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
NVIDIA_API_KEY
API Base URL
https://integrate.api.nvidia.com/v1