ADC

AI gateway

February 23, 2026

Contributed by:

Generative AI is a branch of artificial intelligence that is designed to produce content like text, images, video, and software code. Unlike earlier AI systems that primarily focused on tasks like classification or prediction, generative AI is built to create outputs that resemble human creativity, drawing on patterns it has learned from vast amounts of data.

Large Language Models (LLMs) are advanced AI systems built to process, generate, and reason with human language. They are trained on massive amounts of text data such as books, articles, code, and online content. LLMs use deep learning methods, most notably transformer-based architectures, to learn patterns and structures of language. The deep learning methods enable them to perform a wide range of tasks: answering questions, summarizing information, producing code, translating across languages, and holding natural conversations. Large Language Models are increasingly being embedded into enterprise workflows and customer-facing solutions. Modern-day enterprises are increasingly using LLMs to:

Customer Support: Power intelligent chatbots and virtual assistants to provide faster and natural responses to user queries.
Knowledge Management: Summarize documents and extract insights from organizational knowledge bases.
Developer Productivity: Assist with code generation, debugging, and documentation for accelerated software delivery.
Business Operations: Automate repetitive tasks such as drafting emails, generating reports, or translating communications.

An AI gateway is the control plane and traffic manager for AI-powered applications. Just as traditional API gateways manage REST and RPC traffic, an AI gateway is purpose-built to handle LLM (Large Language Model) and AI inference traffic. It provides a unified layer for routing, security, observability, and policy enforcement across diverse AI services.

NetScaler’s AI Gateway extends its proven expertise in application delivery, security, and performance optimization into the AI domain, thus ensuring enterprises can safely and efficiently operationalize AI workloads.

AI Gateway currently supports the OpenAI Chat Completions API.

Ai gateway overview

Prerequisites

Enable features and mode.

enable ns mode FR L3 Edge USNIP 

enable ns feature WL SP LB CS SSL AAA REWRITE RESPONDER AppFlow CH APIGateway
<!--NeedCopy-->

Add a subnet IP address. This IP address is used to connect to the backend services (Azure OpenAI Instances in this example).
```
add ns ip <IPAddress> <netmask> -type SNIP

```

The official version of this content is in English. Some of the Cloud Software Group documentation content is machine translated for your convenience only. Cloud Software Group has no control over machine-translated content, which may contain errors, inaccuracies or unsuitable language. No warranty of any kind, either expressed or implied, is made as to the accuracy, reliability, suitability, or correctness of any translations made from the English original into any other language, or that your Cloud Software Group product or service conforms to any machine translated content, and any warranty provided under the applicable end user license agreement or terms of service, or any other agreement with Cloud Software Group, that the product or service conforms with any documentation shall not apply to the extent that such documentation has been machine translated. Cloud Software Group will not be held responsible for any damage or issues that may arise from using machine-translated content.

Was this helpful

NetScaler Secure Deployment Guide

AI gateway

February 23, 2026

Contributed by:

February 23, 2026

Contributed by:

AI gateway

Prerequisites

In this article