> 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/1.10.1/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.

# 1.10.1

## Docs

- [Release Notes](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/release-notes.md): This is the first release of 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 trus
- [Getting Started with Safety Guard Multilingual NIM](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/getting-started.md): Before you begin, refer to Support Matrix for software and hardware requirements.
- [Prompt Templates](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/prompt-template.md): Llama 3.1 Nemotron Safety Guard Multilingual 8B V1 NIM performs content safety checks for user input and LLM response output. The checks can ensure that the dialog input and output are consistent with
- [Integrating with NeMo Guardrails](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/integrate-guardrails.md): NeMo Guardrails uses the LangChain ChatNVIDIA connector to connect to a locally running NIM microservice like Llama 3.1 Nemotron Safety Guard Multilingual 8B V1 NIM. The content safety microservice ex
- [Configuration](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/configuration.md): Llama 3.1 Nemotron Safety Guard Multilingual 8B V1 NIM is packaged as a container. You can set environment variables and specify command-line arguments to configure the microservice.
- [Air Gap Deployment](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/air-gapped.md): The microservice supports serving models in an air gap system–also known as air wall, air-gapping, or disconnected network.
- [Llama 3.1 Nemotron Safety Guard Multilingual 8B V1 NIM Performance](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/performance.md): NVIDIA used the genai-perf tool to benchmark the performance of the microservice. You can find more information about the tool in .
- [Support Matrix](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/support-matrix.md): CUDA 12.9 is configured in the microservice container.
- [Observability](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/observability.md): Llama 3.1 Nemotron Safety Guard Multilingual 8B V1 NIM supports exporting metrics and traces in an OpenTelemetry-compatible format. Additionally, the microservice and its underlying NVIDIA Triton Infe
- [Troubleshooting Llama 3.1 Nemotron Safety Guard Multilingual 8B V1 NIM](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/troubleshooting.md): Safety Guard Multilingual NIM has no known issues, but shares some underlying technology with NVIDIA NIM for LLMs.

## API Docs

- API Reference [OpenAI-compatible chat endpoint](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/api-reference/create-chat-completion-v-1-chat-completions-post.md)
- API Reference [OpenAI-compatible completions endpoint](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/api-reference/create-completion-v-1-completions-post.md)
- API Reference [Service ready check](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/api-reference/health-v-1-health-ready-get.md)
- API Reference [Service liveness check](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/api-reference/health-ready-v-1-health-live-get.md)
- API Reference [List available models](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/api-reference/show-available-models-v-1-models-get.md)
- API Reference [Metadata](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/api-reference/metadata-v-1-metadata-get.md)
- API Reference [Returns version information about this NIM](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/api-reference/show-version-v-1-version-get.md)
- API Reference [Metrics](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/api-reference/metrics-v-1-metrics-get.md)
- API Reference [License](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/api-reference/license-v-1-license-get.md)
- API Reference [Manifest](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/1.10.1/api-reference/manifest-v-1-manifest-get.md)

## OpenAPI Specification

The raw OpenAPI 3.1 specification for this API is available at:
- [OpenAPI JSON](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/openapi.json)
- [OpenAPI YAML](https://docs.nvidia.com/nim/llama-3-1-nemotron-safety-guard-8b/openapi.yaml)


> **Note:** This page contains both a page directory (above) and the landing page content (below). The page directory is generated for agent use and does not appear on the landing page.

> 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/1.10.1/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 [](/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](/prompt-template).
Refer to [Integrating with NeMo Guardrails](/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).