(Optional) Static headers sent with every request. Variable expansion is supported.

Deployments

Required
Choose whether the model will use Chat Completions API or Responses API. Responses API offers more capabilities such as retrieving the reasoning summary.
Indicate if this is a reasoning model.
Use the pricing from a given OpenAI model, or enter a custom pricing
In $/1k tokens
In $/1k tokens
In $/1k tokens

Fine-tuning

Enable to allow models from this connection in the fine-tuning recipe.
Its credentials are used to deploy fine-tuned models with Azure Management API
You need to input a resource group and a subscription id if you want to be able to deploy your Azure Open AI models.

Fine-tunable models

Required
Required