ai_gateway_model_services

Creates, updates, deletes, gets or lists an ai_gateway_model_services resource.

Overview

Name	ai_gateway_model_services
Type	Resource
Id	databricks_workspace.catalog.ai_gateway_model_services

Fields

The following fields are returned by SELECT queries:

get

Name	Datatype	Description
name	string	Resource name of the model service. Format: ``model-services/{catalog}.{schema}.{model_service}``. Each ``{...}`` component is capped at 255 characters individually. Server-derived on Create from ``parent`` + ``model_service_id``; required and immutable on Update/Get/Delete.
metastore_id	string	Metastore hosting the model service.
browse_only	boolean	Whether the caller sees only metadata available through the BROWSE privilege.
comment	string	User-provided description.
▶config	object	Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when ``config`` (or a ``config.*`` subpath) appears in ``update_mask``.
create_time	string (date-time)	When the model service was created.
created_by	string	Creator identity.
effective_owner	string	The resolved owner of the ModelService. Falls back to the caller's identity when ``owner`` is not explicitly set on creation.
etag	string	Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated ``etag`` field on the Update / Delete request; the server rejects the mutation if the stored etag differs.
owner	string	The owner of the model service. Write-only; read owner via effective_owner.
supported_api_types	array	Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time.
update_time	string (date-time)	When the model service was last modified.
updated_by	string	Identity of the last updater.

list

Name	Datatype	Description
name	string	Resource name of the model service. Format: ``model-services/{catalog}.{schema}.{model_service}``. Each ``{...}`` component is capped at 255 characters individually. Server-derived on Create from ``parent`` + ``model_service_id``; required and immutable on Update/Get/Delete.
metastore_id	string	Metastore hosting the model service.
browse_only	boolean	Whether the caller sees only metadata available through the BROWSE privilege.
comment	string	User-provided description.
▶config	object	Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when ``config`` (or a ``config.*`` subpath) appears in ``update_mask``.
create_time	string (date-time)	When the model service was created.
created_by	string	Creator identity.
effective_owner	string	The resolved owner of the ModelService. Falls back to the caller's identity when ``owner`` is not explicitly set on creation.
etag	string	Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated ``etag`` field on the Update / Delete request; the server rejects the mutation if the stored etag differs.
owner	string	The owner of the model service. Write-only; read owner via effective_owner.
supported_api_types	array	Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time.
update_time	string (date-time)	When the model service was last modified.
updated_by	string	Identity of the last updater.

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get	select	name, deployment_name	include_browse	Returns the model service identified by its resource name.
list	select	deployment_name	include_browse, page_size, page_token, parent, view	Lists the model services in a Unity Catalog schema. Provide parent as
create	insert	parent, model_service_id, deployment_name, model_service		Creates a model service in a Unity Catalog schema. A model service is a governed AI Gateway endpoint
update	update	name, update_mask, deployment_name, model_service	etag	Updates a model service. Only the fields named in update_mask are changed; the resource name is
delete	delete	name, deployment_name	etag	Deletes the model service identified by its resource name. Optionally supply an etag to make the

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
deployment_name	string	The Databricks Workspace Deployment Name (default: dbc-abcd0123-a1bc)
model_service_id	string	Leaf identifier for the model service (the unqualified name within the parent schema, e.g. "my_model_service").
name	string	Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually.
parent	string	Resource name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually.
update_mask	object	The list of fields to update. The framework validates each path against the model_service field above. Wildcard paths (paths: ["*"]) are not supported; list each field path explicitly.
etag	string	If-match precondition: when set, the delete proceeds only if the current server-side etag matches. Empty means unconditional delete.
include_browse	boolean	Whether to include model services for which the principal can only access selective metadata.
page_size	integer	Maximum number of model services to return. Defaults to 100 when unset or 0; the maximum is 1000. Use next_page_token to retrieve additional pages.
page_token	string	Opaque pagination token from a previous request.
parent	string	Resource name of the parent schema to list within, as schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually.
view	string	View selector controlling which fields are populated per row.

SELECT examples

get

Returns the model service identified by its resource name.

SELECT
name,
metastore_id,
browse_only,
comment,
config,
create_time,
created_by,
effective_owner,
etag,
owner,
supported_api_types,
update_time,
updated_by
FROM databricks_workspace.catalog.ai_gateway_model_services
WHERE name = '{{ name }}' -- required
AND deployment_name = '{{ deployment_name }}' -- required
AND include_browse = '{{ include_browse }}'
;

list

Lists the model services in a Unity Catalog schema. Provide parent as

SELECT
name,
metastore_id,
browse_only,
comment,
config,
create_time,
created_by,
effective_owner,
etag,
owner,
supported_api_types,
update_time,
updated_by
FROM databricks_workspace.catalog.ai_gateway_model_services
WHERE deployment_name = '{{ deployment_name }}' -- required
AND include_browse = '{{ include_browse }}'
AND page_size = '{{ page_size }}'
AND page_token = '{{ page_token }}'
AND parent = '{{ parent }}'
AND view = '{{ view }}'
;

INSERT examples

create

Creates a model service in a Unity Catalog schema. A model service is a governed AI Gateway endpoint

INSERT INTO databricks_workspace.catalog.ai_gateway_model_services (
model_service,
parent,
model_service_id,
deployment_name
)
SELECT 
'{{ model_service }}' /* required */,
'{{ parent }}',
'{{ model_service_id }}',
'{{ deployment_name }}'
RETURNING
name,
metastore_id,
browse_only,
comment,
config,
create_time,
created_by,
effective_owner,
etag,
owner,
supported_api_types,
update_time,
updated_by
;

Manifest

# Description fields are for documentation purposes
- name: ai_gateway_model_services
props:
  - name: parent
    value: "{{ parent }}"
    description: Required parameter for the ai_gateway_model_services resource.
  - name: model_service_id
    value: "{{ model_service_id }}"
    description: Required parameter for the ai_gateway_model_services resource.
  - name: deployment_name
    value: "{{ deployment_name }}"
    description: Required parameter for the ai_gateway_model_services resource.
  - name: model_service
    description: |
      The model service to create. The server populates ``name`` from ``parent`` + ``model_service_id``; clients should leave it unset.
    value:
      browse_only: {{ browse_only }}
      comment: "{{ comment }}"
      config:
        inference_table:
          parent: "{{ parent }}"
          disabled: {{ disabled }}
          is_deleted: {{ is_deleted }}
          table: "{{ table }}"
          table_name_prefix: "{{ table_name_prefix }}"
        rate_limits:
          - key: "{{ key }}"
            renewal_period: "{{ renewal_period }}"
            principal: "{{ principal }}"
            request_tag_key: "{{ request_tag_key }}"
            request_tag_value: "{{ request_tag_value }}"
            requests: {{ requests }}
            tokens: {{ tokens }}
        routing:
          destinations:
            - name: "{{ name }}"
              destination_type: "{{ destination_type }}"
              external_model_config:
                model_provider_service: "{{ model_provider_service }}"
                target: "{{ target }}"
              is_deleted: {{ is_deleted }}
              pay_per_token_config:
                model: "{{ model }}"
              provisioned_throughput_config:
                model_serving_endpoint: "{{ model_serving_endpoint }}"
                model: "{{ model }}"
              traffic_percentage: {{ traffic_percentage }}
          fallback:
            destinations:
              - name: "{{ name }}"
                destination_type: "{{ destination_type }}"
                external_model_config:
                  model_provider_service: "{{ model_provider_service }}"
                  target: "{{ target }}"
                is_deleted: {{ is_deleted }}
                pay_per_token_config:
                  model: "{{ model }}"
                provisioned_throughput_config:
                  model_serving_endpoint: "{{ model_serving_endpoint }}"
                  model: "{{ model }}"
                traffic_percentage: {{ traffic_percentage }}
          first_token_timeout: "{{ first_token_timeout }}"
          traffic_splitting: "{{ traffic_splitting }}"
      create_time: "{{ create_time }}"
      created_by: "{{ created_by }}"
      effective_owner: "{{ effective_owner }}"
      etag: "{{ etag }}"
      metastore_id: "{{ metastore_id }}"
      name: "{{ name }}"
      owner: "{{ owner }}"
      supported_api_types:
        - "{{ supported_api_types }}"
      update_time: "{{ update_time }}"
      updated_by: "{{ updated_by }}"

UPDATE examples

update

Updates a model service. Only the fields named in update_mask are changed; the resource name is

UPDATE databricks_workspace.catalog.ai_gateway_model_services
SET 
model_service = '{{ model_service }}'
WHERE 
name = '{{ name }}' --required
AND update_mask = '{{ update_mask }}' --required
AND deployment_name = '{{ deployment_name }}' --required
AND model_service = '{{ model_service }}' --required
AND etag = '{{ etag}}'
RETURNING
name,
metastore_id,
browse_only,
comment,
config,
create_time,
created_by,
effective_owner,
etag,
owner,
supported_api_types,
update_time,
updated_by;

DELETE examples

delete

Deletes the model service identified by its resource name. Optionally supply an etag to make the

DELETE FROM databricks_workspace.catalog.ai_gateway_model_services
WHERE name = '{{ name }}' --required
AND deployment_name = '{{ deployment_name }}' --required
AND etag = '{{ etag }}'
;