> This page is for version 1.10.1.
> For other versions, use one of these documentation indexes:
> - 1.14.0 (default): https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.14.0/llms.txt
> - 1.10.1: https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/_mcp/server.

# Llama 3.1 Nemotron Safety Guard Multilingual 8B V1 NIM

> The microservice serves a GPU-accelerated LLM model that performs multilingual content moderation for building trustworthy LLM applications rather than a general-knowledge LLM. The LLM model detects h

## About the Microservice

The microservice serves a GPU-accelerated LLM model that performs multilingual content moderation for building trustworthy LLM applications rather than a general-knowledge LLM.
The LLM model detects harmful content in user messages or bot responses in the following languages:

* Arabic

* Chinese

* English

* French

* German

* Hindi

* Japanese

* Spanish

* Thai

The model is a content safety model trained by NVIDIA from the [Nemotron Content Safety Dataset Multilingual V1](https://huggingface.co/datasets/nvidia/Nemotron-Content-Safety-Dataset-Multilingual-v1) and cultural adaptation techniques.
The dataset has a commercially friendly license and is publicly available to permit community analysis and development.

## Audience and Best Use

One audience for the microservice is developers who develop their own code and want to integrate multilingual content safety to their application.
These developers typically have experience with the OpenAI API specification and libraries such as LangChain.
The unique prompt template and extracting the safe and unsafe response are shown in the [](/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/getting-started#classifying-safe-and-unsafe-content) section of the Getting Started page.

Another audience for the microservice want to integrate the multilingual content safety container with NVIDIA NeMo Guardrails.
This audience might want to understand how to customize the [Prompt Templates](/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/prompt-template).
Refer to [Integrating with NeMo Guardrails](/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/integrate-guardrails) for an introduction and a reference to detailed steps in the NeMo Guardrails documentation.

## License

| Component                                              | Artifact Type                                                                                                                                  | Artifact Licenses                                                                                                                                                                                                                                                                                 |
| ------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Llama 3.1 Nemotron Safety Guard Multilingual 8B V1 NIM | [Container](https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/llama-3.1-nemotron-safety-guard-multilingual-8b-v1?version=1.10.1) | [NVIDIA Software License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/) and the [Product-Specific Terms for NVIDIA AI Products](https://www.nvidia.com/en-us/agreements/enterprise-software/product-specific-terms-for-ai-products/). |
| Llama Nemotron Safety Guard Multilingual 8B V1         | Model                                                                                                                                          | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). [Llama 3.1 Community License Agreement](https://www.llama.com/llama3_1/license/). Built with Llama.                                                                          |

## Related Information

* [CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications](https://arxiv.org/abs/2508.01710), arXiv:2508.01710.

* [Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails](https://arxiv.org/abs/2501.09004), arXiv:2501.09004.

* [Nemotron Content Safety Dataset Multilingual V1](https://huggingface.co/datasets/nvidia/Nemotron-Content-Safety-Dataset-Multilingual-v1) on Hugging Face Hub.

* The microservice is based on [NVIDIA NIM for LLMs](https://docs.nvidia.com/nim/large-language-models/latest/introduction.html).