[GH-ISSUE #148] Unable to configure Azure OpenAI #93

New issue

Open

opened 2026-03-03 13:58:49 +03:00 by kerem · 2 comments

kerem commented

2026-03-03 13:58:49 +03:00

Owner

Originally created by @Greybird on GitHub (Jan 12, 2026).
Original GitHub issue: https://github.com/Kuingsmile/word-GPT-Plus/issues/148

Hello,

I struggle to setup Azure OpenAI API provider.

Especially, I'm unclear about the endpoint format to use.
Its scheme is:
https://<resourcename>.openai.azure.com/openai/deployments/<deploymentname>/chat/completions?api-version=<apiversion>
I understand that I should put <deploymentname> in Deploy name and <apiversion> in API Version, but I was unable to find a content for endpoint that would result in something else than 'Something went wrong, check DevTools`.

Could you provide guidance ?

Thanks,

Originally created by @Greybird on GitHub (Jan 12, 2026). Original GitHub issue: https://github.com/Kuingsmile/word-GPT-Plus/issues/148 Hello, I struggle to setup Azure OpenAI API provider. Especially, I'm unclear about the endpoint format to use. Its scheme is: `https://<resourcename>.openai.azure.com/openai/deployments/<deploymentname>/chat/completions?api-version=<apiversion>` I understand that I should put `<deploymentname>` in `Deploy name` and `<apiversion>` in `API Version`, but I was unable to find a content for `endpoint` that would result in something else than 'Something went wrong, check DevTools`. Could you provide guidance ? Thanks,

kerem commented

2026-03-03 13:58:50 +03:00

Author

Owner

@Kuingsmile commented on GitHub (Jan 29, 2026):

Check this

interface AzureOpenAIInput {
  /**
   * API version to use when making requests to Azure OpenAI.
   */
  azureOpenAIApiVersion?: string;
  /**
   * API key to use when making requests to Azure OpenAI.
   */
  azureOpenAIApiKey?: string;
  /**
   * Azure OpenAI API instance name to use when making requests to Azure OpenAI.
   * this is the name of the instance you created in the Azure portal.
   * e.g. "my-openai-instance"
   * this will be used in the endpoint URL: https://my-openai-instance.openai.azure.com/openai/deployments/{DeploymentName}/
   */
  azureOpenAIApiInstanceName?: string;
  /**
   * Azure OpenAI API deployment name to use for completions when making requests to Azure OpenAI.
   * This is the name of the deployment you created in the Azure portal.
   * e.g. "my-openai-deployment"
   * this will be used in the endpoint URL: https://{InstanceName}.openai.azure.com/openai/deployments/my-openai-deployment/
   */
  azureOpenAIApiDeploymentName?: string;
  /**
   * Azure OpenAI API deployment name to use for embedding when making requests to Azure OpenAI.
   * This is the name of the deployment you created in the Azure portal.
   * This will fallback to azureOpenAIApiDeploymentName if not provided.
   * e.g. "my-openai-deployment"
   * this will be used in the endpoint URL: https://{InstanceName}.openai.azure.com/openai/deployments/my-openai-deployment/
   */
  azureOpenAIApiEmbeddingsDeploymentName?: string;
  /**
   * Azure OpenAI API deployment name to use for completions when making requests to Azure OpenAI.
   * Completions are only available for gpt-3.5-turbo and text-davinci-003 deployments.
   * This is the name of the deployment you created in the Azure portal.
   * This will fallback to azureOpenAIApiDeploymentName if not provided.
   * e.g. "my-openai-deployment"
   * this will be used in the endpoint URL: https://{InstanceName}.openai.azure.com/openai/deployments/my-openai-deployment/
   */
  azureOpenAIApiCompletionsDeploymentName?: string;
  /**
   * Custom base url for Azure OpenAI API. This is useful in case you have a deployment in another region.
   * e.g. setting this value to "https://westeurope.api.cognitive.microsoft.com/openai/deployments"
   * will be result in the endpoint URL: https://westeurope.api.cognitive.microsoft.com/openai/deployments/{DeploymentName}/
   */
  azureOpenAIBasePath?: string;
  /**
   * Custom endpoint for Azure OpenAI API. This is useful in case you have a deployment in another region.
   * e.g. setting this value to "https://westeurope.api.cognitive.microsoft.com/"
   * will be result in the endpoint URL: https://westeurope.api.cognitive.microsoft.com/openai/deployments/{DeploymentName}/
   */
  azureOpenAIEndpoint?: string;
  /**
   * A function that returns an access token for Microsoft Entra (formerly known as Azure Active Directory),
   * which will be invoked on every request.
   */
  azureADTokenProvider?: () => Promise<string>;
}

@Kuingsmile commented on GitHub (Jan 29, 2026): Check this ```javascript interface AzureOpenAIInput { /** * API version to use when making requests to Azure OpenAI. */ azureOpenAIApiVersion?: string; /** * API key to use when making requests to Azure OpenAI. */ azureOpenAIApiKey?: string; /** * Azure OpenAI API instance name to use when making requests to Azure OpenAI. * this is the name of the instance you created in the Azure portal. * e.g. "my-openai-instance" * this will be used in the endpoint URL: https://my-openai-instance.openai.azure.com/openai/deployments/{DeploymentName}/ */ azureOpenAIApiInstanceName?: string; /** * Azure OpenAI API deployment name to use for completions when making requests to Azure OpenAI. * This is the name of the deployment you created in the Azure portal. * e.g. "my-openai-deployment" * this will be used in the endpoint URL: https://{InstanceName}.openai.azure.com/openai/deployments/my-openai-deployment/ */ azureOpenAIApiDeploymentName?: string; /** * Azure OpenAI API deployment name to use for embedding when making requests to Azure OpenAI. * This is the name of the deployment you created in the Azure portal. * This will fallback to azureOpenAIApiDeploymentName if not provided. * e.g. "my-openai-deployment" * this will be used in the endpoint URL: https://{InstanceName}.openai.azure.com/openai/deployments/my-openai-deployment/ */ azureOpenAIApiEmbeddingsDeploymentName?: string; /** * Azure OpenAI API deployment name to use for completions when making requests to Azure OpenAI. * Completions are only available for gpt-3.5-turbo and text-davinci-003 deployments. * This is the name of the deployment you created in the Azure portal. * This will fallback to azureOpenAIApiDeploymentName if not provided. * e.g. "my-openai-deployment" * this will be used in the endpoint URL: https://{InstanceName}.openai.azure.com/openai/deployments/my-openai-deployment/ */ azureOpenAIApiCompletionsDeploymentName?: string; /** * Custom base url for Azure OpenAI API. This is useful in case you have a deployment in another region. * e.g. setting this value to "https://westeurope.api.cognitive.microsoft.com/openai/deployments" * will be result in the endpoint URL: https://westeurope.api.cognitive.microsoft.com/openai/deployments/{DeploymentName}/ */ azureOpenAIBasePath?: string; /** * Custom endpoint for Azure OpenAI API. This is useful in case you have a deployment in another region. * e.g. setting this value to "https://westeurope.api.cognitive.microsoft.com/" * will be result in the endpoint URL: https://westeurope.api.cognitive.microsoft.com/openai/deployments/{DeploymentName}/ */ azureOpenAIEndpoint?: string; /** * A function that returns an access token for Microsoft Entra (formerly known as Azure Active Directory), * which will be invoked on every request. */ azureADTokenProvider?: () => Promise<string>; } ```

kerem commented

2026-03-03 13:58:50 +03:00

Author

Owner

@kauttoj commented on GitHub (Jan 31, 2026):

In this settings interface, you have 8 parameters (ApiVersion, ApiKey, ApiInstanceName, DeploymentName, EmbeddingsDeploymentName, CompletionsDeploymentName, BasePath, Endpoint). But in the plug-in settings we have only 4 parameters (API key, endpoint, deploy name, API version). This is very confusing.

Anyway, this is what worked for me:

endpoint: https://.openai.azure.com
Deploy name: gpt-5.2 [I always use the exact model name, you might have different]
API version: 2025-04-01-preview

@kauttoj commented on GitHub (Jan 31, 2026): In this settings interface, you have 8 parameters (ApiVersion, ApiKey, ApiInstanceName, DeploymentName, EmbeddingsDeploymentName, CompletionsDeploymentName, BasePath, Endpoint). But in the plug-in settings we have only 4 parameters (API key, endpoint, deploy name, API version). This is very confusing. Anyway, this is what worked for me: endpoint: https://<your deployment>.openai.azure.com Deploy name: gpt-5.2 [I always use the exact model name, you might have different] API version: 2025-04-01-preview