Test Drive

Nutanix Enterprise AI (NAI)

A Secure, Scalable Foundation for Agentic AI

Nutanix Enterprise AI (NAI) provides a unified, enterprise-grade platform to deploy, manage, and scale AI workloads across hybrid environments. As a core platform component of the Nutanix Agentic AI solution, NAI enables enterprises to streamline AI development, enforce centralized governance over agents and models, and gain visibility into token usage and costs.

NAI includes two primary products: Nutanix Agent Gateway and Nutanix Private Inference. 

  • Nutanix Agent Gateway: a centralized control layer governing traffic from agents to LLMs and from agents to Model Context Protocol (MCP) servers accessing business tools.

  • Nutanix Private Inference: simplifies LLM deployment across hybrid environments, helping teams run self-hosted models with efficient inference, predictable costs, and greater data control.

Diagram of Nutanix Enterprise AI showcasing Nutanix Agent Gateway and Nutanix Private Inference. Diagram of Nutanix Enterprise AI showcasing Nutanix Agent Gateway and Nutanix Private Inference.

Nutanix Agent Gateway 

Key Benefits 

  • Unified Governance: Centrally manage models and MCP servers in a single, controlled environment, with strict policy enforcement and full audit logging.

  • Predictable Token Economics: Monitor token usage and consumption to attribute costs and deliver predictable AI spend. 

  • Time to Value: Connect agents to external AI provider models and self-hosted models through a single API, enabling teams to move into production quickly and easily.

The Control Plane for Agentic AI

Nutanix Agent Gateway serves as the centralized control layer for Agentic AI. It provides developers with a single API to access both public cloud frontier models and private, self-hosted models. Integrating with MCP servers, the Nutanix Agent Gateway applies strict access control policies and tool-level filtering to enable agents to securely access enterprise data. Teams gain comprehensive visibility into token usage patterns and can enforce token-based rate limiting to help identify and manage unexpected spend, helping organizations deliver predictable token economics.

Nutanix Agent Gateway has native integration with Nutanix Private Inference, providing enterprises with a consistent control layer across public hosted models and private, self-hosted models. Both products share identity management, role-based access control (RBAC), and API key configurations, making it easy to transition from public hosted models to secure, private self-hosted models without changing credentials.

Diagram showing Nutanix Agent Gateway architecture and key features. Diagram showing Nutanix Agent Gateway architecture and key features.

Nutanix Private Inference 

Key Benefits 

  • Unified Governance: Help enterprises maintain data sovereignty with security and privacy controls that gives enterprises greater control over their AI workloads and data, including the ability to self-host models and keep enterprise prompts securely on-premises.

  • Predictable Token Economics: Gain more predictable, fixed-price inference by self-hosting open-weight models on your own infrastructure, reducing exposure to variable per-token charges.

  • Time to Value: Streamline model deployment and endpoint management while simplifying AI operations with user management and performance metrics.

Own Your Intelligence

Nutanix Private Inference accelerates GenAI adoption by helping enterprises deploy and manage LLMs wherever their requirements demand, spanning on-prem, cloud, and edge environments, as well as on any CNCF-certified Kubernetes environment, including Nutanix Kubernetes Platform. By leveraging open-weight models, organizations can deliver high-performance private AI while controlling cost volatility, data privacy, and data sovereignty, keeping sensitive enterprise workloads securely on-premises without per-token charges.

A curated catalog of pre-validated models from Hugging Face and NVIDIA NIM simplifies model deployment while enterprise-grade authentication and user management policies help protect access to sensitive AI workloads. Support for air-gapped and dark-site deployments helps organizations meet the requirements of highly regulated environments.

Built-in inference optimizations help maximize hardware performance across CPU- and GPU-based deployments. An intuitive interface streamlines model, endpoint, and workload management, while usage and performance dashboards and integrated OpenTelemetry export capabilities provide centralized visibility and control.

Overview diagram showing the 4-step workflow for Nutanix Private Inference. Overview diagram showing the 4-step workflow for Nutanix Private Inference.

Pricing and Licensing Terms

For more details on Nutanix Enterprise AI licensing, visit https://www.nutanix.com/products/cloud-platform/software-options#nai

Resources and Getting Started

To learn more about Nutanix Enterprise AI, visit https://www.nutanix.com/products/nutanix-enterprise-ai.  

Take Nutanix Enterprise AI for a Test Drive and explore how to manage token costs and apply governance to your AI workloads.

Get started on setting up Nutanix Enterprise AI at https://portal.nutanix.com/page/documents/list?type=software&filterKey=software&filterVal=Nutanix%20Enterprise%20AI. 

©2026 Nutanix, Inc. All rights reserved. Nutanix, the Nutanix logo and all Nutanix product and service names mentioned are registered trademarks or trademarks of Nutanix, Inc. in the United States and other countries. Kubernetes is a registered trademark of The Linux Foundation in the United States and other countries. All other brand names mentioned are for identification purposes only and may be the trademarks of their respective holder(s).