Skip to main content

Model provider services in Unity Catalog

Beta

This feature is in Beta. Account admins can manage access to this feature from the account console Previews page. See Manage Databricks previews.

A model provider service is a Unity Catalog securable that represents an external model provider — such as OpenAI, Anthropic, or Amazon Bedrock — together with its connection details and credentials. A model provider service enables you to register a provider once, govern access to it with Unity Catalog privileges, and query it through Unity AI Gateway without exposing the underlying credentials.

What is a model provider service?

A model provider service lives in a Unity Catalog catalog and schema and uses a three-part name, such as main.default.openai_prod. It holds:

  • The provider type (for example, OpenAI or Amazon Bedrock).
  • The connection configuration for that provider, such as an endpoint base URL or cloud region.
  • The provider credentials, which Databricks encrypts and stores. Databricks does not return credentials on read.

Because a model provider service is a Unity Catalog securable, you manage it the same way you manage other governed objects:

  • Grant and revoke access with Unity Catalog privileges.
  • Discover it in Catalog Explorer alongside your other data and AI assets.
  • Configure Unity AI Gateway features such as rate limits and inference tables on it.

Callers query a model provider service directly through Unity AI Gateway by referencing its name, and they don't see the stored credentials. A model provider service can also supply the external provider that a model service routes to, giving administrators a single, governed chokepoint for provider credentials.

Supported providers

A model provider service supports the following external providers and authentication methods.

Provider

Authentication

OpenAI

API key

Azure OpenAI

API key, or Microsoft Entra ID Databricks service principal (tenant ID, client ID, and client secret)

Anthropic

API key

Amazon Bedrock

AWS access key pair (access key ID and secret access key)

Microsoft Foundry

API key, or Microsoft Entra ID Databricks service principal (tenant ID, client ID, and client secret)

Google Gemini Enterprise

API key, with GCP project ID and region

Custom

Bearer token, with an endpoint base URL

Why govern external providers in Unity Catalog?

Without a central registry, every team that uses an external model embeds its own provider credentials in application code or notebooks. Model provider services move that configuration into Unity Catalog so you can:

  • Define a provider once. Register the credentials and connection details in one place, then let many users and model services share it without ever handling the secret.
  • Govern access with Unity Catalog privileges. Use the same GRANT and REVOKE statements you use for other securables to govern who can query each provider.
  • Query across workspaces. A model provider service is available in any workspace that shares its metastore.
  • Track usage and cost. Unity AI Gateway records usage for queries that route through a model provider service. See Model usage for Unity AI Gateway services.

Privileges

The following Unity Catalog privileges apply to model provider services. A principal also needs USE CATALOG and USE SCHEMA on the parent catalog and schema.

Privilege

Grants the ability to

CREATE SERVICE (on the schema)

Create a model provider service in the schema.

CREATE CONNECTION (on the schema)

Store inline credentials when creating a model provider service. Creating a service with inline credentials provisions a Unity Catalog connection, which requires this privilege.

EXECUTE

Query the model provider service through Unity AI Gateway.

READ_METADATA

View the model provider service and its configuration without querying it.

MANAGE

Edit, delete, and grant access to the model provider service.

For how to grant and revoke these privileges, see Discover and govern access to model provider services.

Beta scope

During Beta:

  • Account admins must enable the Unity AI Gateway preview before you can create or query model provider services. See Manage Databricks previews.
  • Model provider services support only the providers and authentication methods listed in Supported providers.

Next steps