How to create a DeepInfra API key to use in Ozeki AI Gateway
This guide demonstrates how to create a DeepInfra API key and configure it in Ozeki AI Gateway. You'll learn how to access the DeepInfra platform, generate a new API key, and set up DeepInfra as a provider in your gateway. By following these steps, you can connect your Ozeki AI Gateway to DeepInfra's extensive collection of open-source AI models.
API URL: https://api.deepinfra.com/v1/openai Example API Key: abc123... Default model: openai/gpt-oss-120b
What is a DeepInfra API key?
A DeepInfra API key is a unique authentication credential that allows applications to access a wide range of open-source AI models through the DeepInfra platform. DeepInfra specializes in hosting and serving popular open-source models from providers like Meta, Mistral, and others. When configuring DeepInfra as a provider in Ozeki AI Gateway, you need this API key to establish the connection between your gateway and DeepInfra's services.
Steps to follow
- Open DeepInfra dashboard
- Navigate to API keys
- Create key
- Name and generate key
- Copy API key
- Open Providers page in Ozeki AI Gateway
- Create provider
How to create a DeepInfra API key video
The following video shows how to create a DeepInfra API key and configure it in Ozeki AI Gateway step-by-step. The video covers accessing the DeepInfra platform, generating credentials, and setting up the provider in your gateway.
Step 0 - Install Ozeki AI Gateway
Before configuring DeepInfra 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 - Open DeepInfra dashboard
Open your web browser and navigate to the DeepInfra dashboard. Sign in with your account credentials or create a new account if needed. The dashboard provides access to model deployment, API management, and authentication settings (Figure 1).
Step 2 - Navigate to API keys
In the DeepInfra dashboard, locate and click on "API Keys" in the navigation menu. This section allows you to manage authentication credentials for accessing hosted models through API requests (Figure 2).
Step 3 - Create key
On the API keys page, click the "New API Key" button to create a key. This initiates the generation workflow where you'll configure the credential with a descriptive name (Figure 3).
Step 4 - Name and generate key
Enter a descriptive name for your credential, such as "Ozeki AI Gateway". A clear naming convention helps identify which keys are used by which applications or services. Click the "Generate API Key" button to create your authentication token (Figure 4).
Step 5 - Copy API key
After generation completes, DeepInfra displays the complete credential value. Click the copy button to transfer it to your clipboard. Store this token securely as it provides access to your DeepInfra account and available models (Figure 5).
The API key is only shown once during creation. Make sure to copy and securely store the key before closing this window.
Step 6 - Open Providers page in Ozeki AI Gateway
Launch the Ozeki AI Gateway web interface and navigate to the Providers page. This is where you'll configure DeepInfra as a new provider using the credential you just created (Figure 6).
Step 7 - Create provider
Click the "New" button to begin the provider creation process. This opens a form where you'll enter the connection details for DeepInfra (Figure 7).
Fill in the configuration form with your DeepInfra information. Enter the provider name, select "OpenAI compatible" as the type, paste the endpoint URL (https://api.deepinfra.com/v1/openai), and add your authentication token. Select your preferred model from the dropdown list, then click "Create" to save the configuration (Figure 8).
https://api.deepinfra.com/v1/openai
After clicking "Create", DeepInfra is added to Ozeki AI Gateway. The provider now appears in the list, confirming that your gateway can route requests to DeepInfra services. You can now create routes that allow users to access open-source models through your gateway (Figure 9).
Final thoughts
You have successfully created a DeepInfra API key and configured it as a provider in Ozeki AI Gateway. Your gateway can now communicate with DeepInfra's platform and access a diverse collection of open-source AI models. This setup allows you to manage DeepInfra access for multiple users and applications from a centralized point.