Add the Docs MCP to your AI coding tool to get help building with Respan. No API key needed.
Azure OpenAI requires three credentials: API key, API base URL (also called base_url or endpoint), and API version. Make sure you have all three from your Azure Portal before proceeding.
Before integrating Azure OpenAI with Respan, ensure you have:
Visit your Azure Portal OpenAI Service.
You will see your deployments. Choose the deployment you want to use.

Click on the “Endpoints” link to view your API base URL.
The API base URL is also called endpoint or base_url. For OpenAI, this would be https://api.openai.com, but for Azure it’s unique to your resource (e.g., https://your-resource.openai.azure.com/).

Click on the “Manage Keys” link to view your API keys. You can use either Key 1 or Key 2.
Pick an API version from the available Azure OpenAI versions.
2024-10-21 (recommended)2024-08-01-preview2024-06-012024-02-01There are 2 ways to add your Azure OpenAI credentials to your requests:
Fill in the three required Azure OpenAI credentials:
Your Azure OpenAI API key from the Azure Portal.
Your Azure OpenAI endpoint URL (also called base_url or endpoint).
The api_base (synonyms: base_url, endpoint) is the base URL for your Azure OpenAI resource.
Examples:
https://your-resource.openai.azure.com/https://api.openai.comYou can find this in your Azure Portal under “Endpoints”.
Your Azure OpenAI API version (e.g., 2024-10-21). See available versions.

Azure allows custom deployment names. You need to map your deployment name so Respan knows which Azure deployment to call.
Important: When testing the model, use the format azure/{your-deployment-name} in the model test input.
For example:
gpt-4o, use: azure/gpt-4omy-gpt4-deployment, use: azure/my-gpt4-deployment
You can limit which models use these credentials. Leave empty to apply your credentials for all Azure OpenAI models.
To specify models:
azure/gpt-4o)Enter to add the model
If your Azure deployment name differs from the standard model name, use model_name_map to specify the mapping.
Example: If you deployed gpt-4o with a custom name like my-gpt4-prod, map it like this:
model_name_map only works when your credentials are valid.You can override credentials for individual models without changing the default credentials.
You can add multiple Azure deployments and load balance between them for better availability and cost optimization.
Learn more: Load Balancing Guide
Important: When testing in the model playground:
azure/your-deployment-name (e.g., azure/gpt-4o)azure/gpt-4o as an example for Azure modelsazure/{deployment-name} format (e.g., azure/gpt-4o)Cause: Your deployment name doesn’t match what’s configured in Azure.
Solution:
model_name_map to map the standard model name to your custom deployment nameazure/ prefix (e.g., azure/gpt-4o)Cause: One or more of your Azure credentials are incorrect.
Solution:
api_key in Azure Portal → Manage Keysapi_base matches your resource endpoint exactly (including trailing slash)api_version is a valid versionIssue: The “Model test call” input field is for specifying which model to test, not the message.
Correct usage:
azure/gpt-4o (the model identifier with azure/ prefix)The placeholder should be dynamic and show azure/gpt-4o for Azure providers, not just gpt-4o.
Credential validation is not currently supported. Make sure your credentials are correct before making requests to avoid errors.
azure_deepseek/deepseek-v3azure_deepseek/deepseek-chatazure_deepseek/deepseek-reasonerazure_deepseek/deepseek-r1azure/o1azure/o3azure/o3-miniazure/o4-miniazure/gpt-4azure/gpt-4-32kazure/gpt-4-1106-previewazure/gpt-4-vision-previewazure/gpt-4oazure/gpt-4o-miniazure/gpt-4o-2024-08-06azure/gpt-4.1azure/gpt-4.1-miniazure/gpt-4.1-nanoazure/gpt-5azure/gpt-5-miniazure/gpt-35-turboYou can find the complete and up-to-date list here.