How to create an Nvidia NIM API key to use in Ozeki AI Gateway

This guide demonstrates how to create an Nvidia NIM API key and configure it in Ozeki AI Gateway. You'll learn how to access the Nvidia NIM platform, generate a new API key, and set up Nvidia NIM as a provider in your gateway. By following these steps, you can connect your Ozeki AI Gateway to Nvidia's high-performance AI model inference platform powered by Nvidia GPUs. 

API URL: https://integrate.api.nvidia.com/v1/
Example API Key: nvapi-abcde...
Default model: openai/gpt-oss-120b

What is an Nvidia NIM API key?

An Nvidia NIM API key is a unique authentication credential that allows applications to access AI models through the Nvidia NIM (NVIDIA Inference Microservices) platform. Nvidia NIM provides optimized AI model inference leveraging Nvidia GPU technology for high performance and efficiency. When configuring Nvidia NIM as a provider in Ozeki AI Gateway, you need this API key to establish the connection between your gateway and Nvidia NIM's services.

Overview
Overview

Steps to follow

  1. Navigate to Nvidia NIM website
  2. Open account key management page
  3. Create new API key
  4. Enter details and create key
  5. Copy API key
  6. Open Providers page in Ozeki AI Gateway
  7. Create provider

How to create an Nvidia NIM API key video

The following video shows how to create an Nvidia NIM API key and configure it in Ozeki AI Gateway step-by-step. The video covers accessing the Nvidia Build platform, generating credentials, and setting up the provider in your gateway.

Step 0 - Install Ozeki AI Gateway

Before configuring Nvidia NIM as a provider, ensure Ozeki AI Gateway is installed and running on your system. If you haven't installed Ozeki AI Gateway yet, follow our Installation on Linux guide or Installation on Windows guide to complete the initial setup.

Step 1 - Navigate to Nvidia NIM website

Open your web browser and navigate to the Nvidia Build platform. Sign in with your Nvidia account credentials or create a new account if needed. The Nvidia Build platform provides access to AI model inference services, API management, and GPU-accelerated computing resources (Figure 1).

Navigate to Nvidia NIM website
Figure 1 - Navigate to Nvidia NIM website

Step 2 - Open account key management page

After signing in, navigate to the API key management page. This page allows you to create, view, and manage your API keys for accessing Nvidia NIM services and models (Figure 2).

Open account key management page
Figure 2 - Open account key management page

Step 3 - Create new API key

On the key management page, click the "Generate API Key" button to begin the API key creation process. This initiates the key generation workflow where you'll configure the settings and permissions for your new credential (Figure 3).

Create new API key
Figure 3 - Create new API key

Step 4 - Enter details and create key

Enter a descriptive name for your API key, such as "Ozeki AI Gateway". Configure the expiration settings for the key - you can choose to set a specific expiration date or create a key that doesn't expire. Setting an appropriate expiration date is recommended for security best practices. Click the Generate Key button to create your authentication credential (Figure 4).

Enter details and create key
Figure 4 - Enter details and create key

Step 5 - Copy API key

After generation, Nvidia NIM displays the complete API key value. Click the copy button to transfer it to your clipboard. Store this key securely as it provides access to your Nvidia NIM account and AI model inference services (Figure 5).

The API key is only shown once during creation. Make sure to copy and securely store the key before closing this window.

Copy API key
Figure 5 - Copy API key

Step 6 - Open Providers page in Ozeki AI Gateway

Open the Ozeki AI Gateway web interface and navigate to the Providers page. The Providers page displays all configured AI model connections and allows you to add new providers (Figure 6).

Open Providers page
Figure 6 - Open Providers page in Ozeki AI Gateway

Step 7 - Create provider

Click the "New" button on the Providers page to begin creating a provider configuration. This opens a form where you'll specify the connection details for Nvidia NIM (Figure 7).

Add new provider
Figure 7 - Click add new provider button

Fill in the configuration form with your Nvidia NIM information. Enter the provider name, select "OpenAI compatible" as the type, paste the endpoint URL (https://integrate.api.nvidia.com/v1/), and add your API key. Select your preferred model from the dropdown list, then click "Create" to save the configuration (Figure 8). 

https://integrate.api.nvidia.com/v1/

Enter details and create provider
Figure 8 - Enter Nvidia NIM provider details and create

After successful creation, Nvidia NIM is added to Ozeki AI Gateway. The provider now appears in the list, confirming that your gateway can route requests to Nvidia NIM services. You can now create routes that allow users to access Nvidia's GPU-accelerated AI models through your gateway (Figure 9).

Provider created
Figure 9 - Nvidia NIM provider created successfully

To sum it up

You have successfully created an Nvidia NIM API key and configured it as a provider in Ozeki AI Gateway. Your gateway can now communicate with Nvidia's platform and access various AI models with GPU-accelerated inference for high performance. This setup allows you to manage Nvidia NIM access for multiple users and applications from a centralized point while leveraging Nvidia's powerful GPU technology for AI model inference.

More information