Skip to content

Azure OpenAI

This section explains how to add and configure an Azure OpenAI model in AskSenseOps.

Prerequisites

Before configuring the model, ensure that you have:

  • An Azure OpenAI resource or deployment that you can access.
  • An API key for authentication.
  • The model name or deployment details required by your Azure OpenAI setup.

Adding an Azure OpenAI Model

  1. Open AskSenseOps.
  2. Navigate to the model configuration section.
  3. Click Add Model.
  4. Enter the model details described below.
  5. Test the configuration and save the model.

Basic Info

Field Description Required
Display Name Enter a name to identify the model in AskSenseOps, such as GPT-4.1 Mini. Yes
Provider Select Azure OpenAI. Yes

Credentials

Field Description Required
API Key Enter the API key associated with your Azure OpenAI resource or deployment. Yes

Model Configuration

Field Description Required
Model Name / ID Enter the model identifier, such as gpt-4.1-mini. Yes
Endpoint URL Enter the endpoint URL for your Azure OpenAI setup. No
Deployment Name Enter the name of the deployed model in Azure OpenAI. Yes
API Version Enter the API version required by your Azure OpenAI endpoint. Yes

The Endpoint URL field includes guidance for selecting the API based on the endpoint path:

  • Paths ending in /anthropic are used for Claude on Azure AI Foundry.
  • Paths ending in /models are used for other Azure AI Foundry models.
  • Paths ending in /openai/v1 are used for the Azure OpenAI v1 API.
  • Other endpoint paths use the classic deployments API.

Custom Headers

Custom headers are optional and can be used when a gateway requires additional authentication or routing headers.

  1. Under Custom Headers (Optional), click + Add.
  2. Enter the required header name and value.
  3. Add additional headers if needed.

Examples shown in the interface include x-openai-token, x-fabrix-client, and x-llm-model-id for gateway integrations.

If a custom header carries the authentication token, the API Key field can be left empty.

Testing and Saving the Model

After entering the configuration details:

  1. Review the display name, provider, credentials, and model configuration.
  2. Click Test to verify the model configuration.
  3. If the test succeeds, click Save Model to save the configuration.

If the test fails, verify the API key, model identifier, deployment name, API version, and endpoint URL.