- Sign into Azure OpenAI Studio at https://oai.azure.com.
- Choose the subscription and the Azure OpenAI resource to work with and select Use resource.
- Under Management select Deployments.
- Select Create new deployment and configure the following fields:
Field Description Select a model Model availability varies by region. For a list of available models per region, see model summary table and region availability at https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#model-summary-table-and-region-availability. Deployment name Choose a name carefully. The deployment name is used in your code to call the model by using the client libraries and the REST APIs. Advanced options (Optional) You can set optional advanced settings, as needed for your resource.
- For the Content Filter, assign a content filter to your deployment.
- For the Tokens per Minute Rate Limit, adjust the Tokens per Minute (TPM) to set the effective rate limit for your deployment. You can modify this value at any time by using the quotas menu: https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/quota?tabs=rest.
- Select a model from the dropdown list.
- Enter a deployment name to help you identify the model.
- For your first deployment, leave the Advanced options set to the defaults. Select Create.
The deployments table shows a new entry that corresponds to your newly created model. When the deployment completes, your model deployment status changes to succeeded.