ADI Services are services made available to you by Databricks that can be integrated into your Azure Databricks environment. Standard data residency settings apply to ADI Services.
OpenAI and Gemini models are available through ADI Services.
In addition to the models already available to you through Azure Databricks Foundation Model APIs, the following models can be made available through ADI Services as a Databricks-hosted endpoint:
Deprecation notice: The OpenAI GPT Codex models (GPT-5.2 Codex, GPT-5.1 Codex Max, and GPT-5.1 Codex Mini) will be retired on July 16, 2026. See Retired models for the recommended replacement models and guidance for how to migrate during deprecation.
These models can be used for real-time inference or batch inference workloads using Foundation Model APIs pay-per-token. They also support Function calling and Structured output.
Access to these models requires ADI Services eligibility and enablement.
Reach out to your Azure Databricks account teams to understand eligibility criteria and pricing details.
Follow these steps to access these models:
HIPAA and related regulations require organizations that handle protected health information (PHI) to meet specific safeguards. When a covered entity or business associate uses a cloud service provider like Databricks, the cloud service provider is also considered a business associate.
As a result, when you use ADI Services with HIPAA regulated data, you agree to Databricks' Business Associate Agreement (BAA) in the absence of a separately implemented version. To read the Databricks BAA, see Business Associate Agreement.
This table below lists models in the ADI Services that are subject to separate model terms. These links are provided for your convenience. You are responsible for ensuring compliance with applicable model terms and any applicable use policies.
|
Model |
Terms and policies |
|
OpenAI GPT-5.4 mini |
|
|
OpenAI GPT-5.4 nano |
|
|
OpenAI GPT-5.3 Codex |
|
|
OpenAI GPT-5.2 Codex |
|
