How to create an OVHCloud AI Endpoints API key to use in Ozeki AI Gateway

This guide demonstrates how to create an OVHCloud API key and configure it in Ozeki AI Gateway. You'll learn how to access the OVHCloud Manager platform, generate a new API key for AI Endpoints, and set up OVHCloud as a provider in your gateway. By following these steps, you can connect your Ozeki AI Gateway to OVHCloud's AI model inference platform and access a variety of open-source and commercial AI models. 

API URL: https://oai.endpoints.kepler.ai.cloud.ovh.net/v1
Example API Key: ovhcloud-abcde...
Default model: gpt-oss-120b

What is an OVHCloud AI Endpoints API key?

An OVHCloud API key is a unique authentication credential that allows applications to access AI models through the AI Endpoints platform. The platform provides access to a wide range of open-source and commercial AI models with flexible pricing. When configuring OVHCloud as a provider in Ozeki AI Gateway, you need this API key to establish the connection between your gateway and the AI services.

Overview
Overview

Steps to follow

  1. Navigate to OVHCloud Manager
  2. Choose cloud project
  3. Navigate to AI Endpoints
  4. Create new API key
  5. Copy API key
  6. Open Providers page in Ozeki AI Gateway
  7. Create provider

How to create an OVHCloud AI Endpoints API key video

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

Step 0 - Install Ozeki AI Gateway

Before configuring OVHCloud 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 OVHCloud Manager

Open your web browser and navigate to the OVHCloud Manager. Sign in with your account credentials or create a new account if needed. The manager platform provides access to all services including AI Endpoints, cloud computing resources, and project management tools (Figure 1).

Open OVHCloud Manager website
Figure 1 - Navigate to OVHCloud Manager

Step 2 - Choose cloud project

Select your Public Cloud project from the project list. If you don't have a project yet, you'll need to create one first. The project serves as the container for your resources including AI Endpoints and API keys (Figure 2).

Choose cloud project
Figure 2 - Choose your cloud project

Step 3 - Navigate to AI Endpoints

In the left sidebar menu, locate and click on "AI Endpoints" under the AI & Machine Learning section. This page displays your configuration and allows you to manage API keys for accessing the AI model inference services (Figure 3).

Navigate to AI Endpoints
Figure 3 - Navigate to AI Endpoints section

Step 4 - Create new API key

On the AI Endpoints page, click the "Create an new API key" button to begin the API key creation process. This initiates the key generation workflow where you'll configure the settings for your new authentication credential (Figure 4).

Create new API key
Figure 4 - Create new API key

Enter a descriptive name for your API key, such as "OzekiAIGateway". You may also configure a key expiry date. Review the configuration settings and click the "Create" button to create your authentication credential (Figure 5).

Enter details and generate key
Figure 5 - Enter details and generate key

Step 5 - Copy API key

After generation, the platform 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 the AI Endpoints services and models (Figure 6).

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 6 - 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 7).

Open Providers page
Figure 7 - 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 (Figure 8).

Add new provider
Figure 8 - Click add new provider button

Fill in the configuration form with your connection information. Enter the provider name, select "OpenAI compatible" as the type, paste the endpoint URL (https://oai.endpoints.kepler.ai.cloud.ovh.net/v1), and add your API key. Select your preferred model from the dropdown list. The platform offers a variety of models including open-source options like gpt-oss-120b and commercial models. You can browse the complete model catalog at the OVHCloud AI Endpoints Catalog to see available models, pricing, and specifications. Click "Create" to save the configuration (Figure 9). 

https://oai.endpoints.kepler.ai.cloud.ovh.net/v1

Enter details and create provider
Figure 9 - Enter provider details and create

After successful creation, the provider is added to Ozeki AI Gateway. The provider now appears in the list, confirming that your gateway can route requests to the AI services. You can now create routes that allow users to access the AI models through your gateway (Figure 10).

Provider created
Figure 10 - Provider created successfully

To sum it up

You have successfully created an OVHCloud API key and configured it as a provider in Ozeki AI Gateway. Your gateway can now communicate with the platform and access a wide range of AI models including both open-source and commercial options.

More information