openapi: 3.1.0 info: title: Fast ACCOUNT_COSTS Databricks AI/ML Services API version: 0.1.0 tags: - name: Databricks AI/ML Services paths: /api/v1/databricks/ai-ml-services/summary: get: tags: - Databricks AI/ML Services summary: Get AI/ML services summary with trend data description: 'Get AI/ML services summary with trend data. Returns trend data for: - Model Serving (DBUs and costs) - Vector Search (DBUs and costs) - AI Gateway (DBUs and costs) Data is aggregated by the specified granularity (day, week, or month). Frontend calculates totals by summing the trend data. Query Parameters: - start_date: Start date (YYYY-MM-DD), defaults to 30 days ago - end_date: End date (YYYY-MM-DD), defaults to today - granularity: Time granularity (''day'', ''week'', ''month''), defaults to ''day'' - workspace_id: Comma-separated workspace IDs or ''all'' (default) Returns: - Array of data points with DBUs and costs per service, aggregated by granularity' operationId: get_aiml_services_summary_api_v1_databricks_ai_ml_services_summary_get security: - HTTPBearer: [] - HTTPBearer: [] parameters: - name: start_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: Start date (YYYY-MM-DD), defaults to 30 days ago title: Start Date description: Start date (YYYY-MM-DD), defaults to 30 days ago - name: end_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: End date (YYYY-MM-DD), defaults to today title: End Date description: End date (YYYY-MM-DD), defaults to today - name: granularity in: query required: false schema: type: string description: 'Time granularity: ''day'', ''week'', or ''month''' default: day title: Granularity description: 'Time granularity: ''day'', ''week'', or ''month''' - name: workspace_id in: query required: false schema: anyOf: - type: string - type: 'null' description: Comma-separated workspace IDs to filter, or 'all' title: Workspace Id description: Comma-separated workspace IDs to filter, or 'all' - name: navigationSource in: query required: false schema: anyOf: - type: string - type: 'null' title: Navigationsource - name: x-tenant in: header required: true schema: type: string title: X-Tenant responses: '200': description: Successful Response content: application/json: schema: type: array items: $ref: '#/components/schemas/AIMLServicesTrendPoint' title: Response Get Aiml Services Summary Api V1 Databricks Ai Ml Services Summary Get '403': description: Not authorized '404': description: Resource not found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/databricks/ai-ml-services/endpoints: get: tags: - Databricks AI/ML Services summary: Get unified list of AI/ML endpoints (Model Serving + Vector Search + AI Gateway) description: "Get a unified list of AI/ML endpoints for the dashboard table.\n\nEach row carries:\n\n- ``service`` — routing discriminator ('model_serving' | 'vector_search' |\n 'ai_gateway'). Used by the FE to pick the detail page on row-click; **not**\n a filter input. The legacy ``service`` query param was intentionally\n dropped (commit ad00d32) — it is no longer read here, so a stray\n ``?service=...`` is ignored rather than filtering. Use ``entity_type``\n to narrow rows.\n- ``entity_type`` — leaf type rendered in the Type column / filtered on\n via the ``entity_type`` query param.\n\nFields that don't apply to a row's service are null. Pagination is applied\nover the merged result set so the top spenders surface first.\n\nQuery Parameters:\n\n- entity_type: comma-separated leaf entity_type values (optional)\n- endpoint_name: exact endpoint name(s), repeatable, any-of match (optional)\n- start_date: Start date (YYYY-MM-DD), defaults to 30 days ago\n- end_date: End date (YYYY-MM-DD), defaults to today\n- workspace_id: Comma-separated workspace IDs or 'all' (default)\n- limit: Max rows to return (default: 50, max: 1000)\n- offset: Pagination offset (default: 0)\n- sort_by: see above\n- sort_order: 'asc' | 'desc' (default: 'desc')" operationId: get_model_serving_endpoints_api_v1_databricks_ai_ml_services_endpoints_get security: - HTTPBearer: [] - HTTPBearer: [] parameters: - name: entity_type in: query required: false schema: anyOf: - type: string - type: 'null' description: Comma-separated leaf entity_types to filter the rows. One of FOUNDATION_MODEL, CUSTOM_MODEL, AI_FUNCTION, EXTERNAL_MODEL, FEATURE_SPEC, VECTOR_SEARCH, AI_GATEWAY. Omit to return all rows. title: Entity Type description: Comma-separated leaf entity_types to filter the rows. One of FOUNDATION_MODEL, CUSTOM_MODEL, AI_FUNCTION, EXTERNAL_MODEL, FEATURE_SPEC, VECTOR_SEARCH, AI_GATEWAY. Omit to return all rows. - name: endpoint_name in: query required: false schema: anyOf: - type: array items: type: string - type: 'null' description: Exact endpoint name(s) to filter the rows (any-of match). Repeat the param for multiple names. Names are sourced from GET /ai-ml-services/endpoints/filters/names. Omit to return all rows. title: Endpoint Name description: Exact endpoint name(s) to filter the rows (any-of match). Repeat the param for multiple names. Names are sourced from GET /ai-ml-services/endpoints/filters/names. Omit to return all rows. - name: start_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: Start date (YYYY-MM-DD), defaults to 30 days ago title: Start Date description: Start date (YYYY-MM-DD), defaults to 30 days ago - name: end_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: End date (YYYY-MM-DD), defaults to today title: End Date description: End date (YYYY-MM-DD), defaults to today - name: workspace_id in: query required: false schema: anyOf: - type: string - type: 'null' description: Comma-separated workspace IDs to filter title: Workspace Id description: Comma-separated workspace IDs to filter - name: limit in: query required: false schema: type: integer maximum: 1000 minimum: 1 description: Max rows to return default: 50 title: Limit description: Max rows to return - name: offset in: query required: false schema: type: integer minimum: 0 description: Pagination offset default: 0 title: Offset description: Pagination offset - name: sort_by in: query required: false schema: type: string description: 'Sort field: ''endpoint_name'' | ''total_cost_usd'' | ''total_dbus'' | ''service'' | ''entity_type''' default: total_cost_usd title: Sort By description: 'Sort field: ''endpoint_name'' | ''total_cost_usd'' | ''total_dbus'' | ''service'' | ''entity_type''' - name: sort_order in: query required: false schema: type: string description: 'Sort order: ''asc'' or ''desc''' default: desc title: Sort Order description: 'Sort order: ''asc'' or ''desc''' - name: navigationSource in: query required: false schema: anyOf: - type: string - type: 'null' title: Navigationsource - name: x-tenant in: header required: true schema: type: string title: X-Tenant responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/UnifiedAIMLEndpointsListResponse' '403': description: Not authorized '404': description: Resource not found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/databricks/ai-ml-services/endpoints/filters: get: tags: - Databricks AI/ML Services summary: Get filter values for the unified AI/ML endpoints list description: "Return discrete values for the filters the list endpoint accepts.\n\nFilterable fields on ``GET /ai-ml-services/endpoints`` are:\n- ``entity_type`` — comma-separated leaf entity_type values (the seven\n types in ``_UNIFIED_VALID_ENTITY_TYPES``). The returned ``entity_types``\n lists only the leaves that actually appear on rows in the window.\n- ``workspace_id`` — distinct workspace IDs with AI/ML traffic in the\n window.\n- ``start_date`` / ``end_date`` — free-form date range, not enumerable; the\n caller passes the same window in here so both lists are scoped to it.\n- ``endpoint_name`` — exact name filter on the list endpoint. Its values are\n too numerous to enumerate up front, so they are served separately by the\n searchable, paginated ``GET /ai-ml-services/endpoints/filters/names`` rather than\n inlined here.\n\nNote: ``service`` is a row-level routing discriminator, not a filter\ninput, so it is intentionally absent from this response." operationId: get_aiml_endpoint_filters_api_v1_databricks_ai_ml_services_endpoints_filters_get security: - HTTPBearer: [] - HTTPBearer: [] parameters: - name: start_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: Start date (YYYY-MM-DD), defaults to 30 days ago title: Start Date description: Start date (YYYY-MM-DD), defaults to 30 days ago - name: end_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: End date (YYYY-MM-DD), defaults to today title: End Date description: End date (YYYY-MM-DD), defaults to today - name: navigationSource in: query required: false schema: anyOf: - type: string - type: 'null' title: Navigationsource - name: x-tenant in: header required: true schema: type: string title: X-Tenant responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/AIMLEndpointsFilterOptions' '403': description: Not authorized '404': description: Resource not found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/databricks/ai-ml-services/endpoints/filters/names: get: tags: - Databricks AI/ML Services summary: Get searchable, paginated endpoint names for the name filter description: 'Return distinct endpoint names for the name-filter dropdown. The full name set is too large to ship at once, so the FE searches server-side and pages through matches. Names are scoped to the same window (and optional workspace) as the list, so the dropdown never offers a name that can''t appear on the table.' operationId: get_aiml_endpoint_names_api_v1_databricks_ai_ml_services_endpoints_filters_names_get security: - HTTPBearer: [] - HTTPBearer: [] parameters: - name: search in: query required: false schema: anyOf: - type: string - type: 'null' description: Case-insensitive substring to match endpoint names title: Search description: Case-insensitive substring to match endpoint names - name: start_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: Start date (YYYY-MM-DD), defaults to 30 days ago title: Start Date description: Start date (YYYY-MM-DD), defaults to 30 days ago - name: end_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: End date (YYYY-MM-DD), defaults to today title: End Date description: End date (YYYY-MM-DD), defaults to today - name: workspace_id in: query required: false schema: anyOf: - type: string - type: 'null' description: Workspace ID to scope names to title: Workspace Id description: Workspace ID to scope names to - name: page in: query required: false schema: type: integer minimum: 1 description: Page number (1-indexed) default: 1 title: Page description: Page number (1-indexed) - name: size in: query required: false schema: type: integer maximum: 100 minimum: 1 description: Items per page default: 20 title: Size description: Items per page - name: navigationSource in: query required: false schema: anyOf: - type: string - type: 'null' title: Navigationsource - name: x-tenant in: header required: true schema: type: string title: X-Tenant responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/AIMLEndpointNamesResponse' '403': description: Not authorized '404': description: Resource not found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/databricks/ai-ml-services/endpoints/{endpoint_name}: get: tags: - Databricks AI/ML Services summary: Get endpoint detail (Model Serving, Vector Search or AI Gateway) description: 'Get detailed metrics for a specific endpoint. Path Parameters: - endpoint_name: Endpoint name (required) Query Parameters: - service: ''model_serving'' | ''vector_search'' | ''ai_gateway'' (required) - start_date: Start date (YYYY-MM-DD), defaults to 30 days ago - end_date: End date (YYYY-MM-DD), defaults to today Returns detailed metrics shaped per service. AI Gateway detail mirrors Vector Search (cost / DBUs / activity window) plus first_seen and last_activity; no per-request or token counts.' operationId: get_endpoint_detail_api_v1_databricks_ai_ml_services_endpoints__endpoint_name__get security: - HTTPBearer: [] - HTTPBearer: [] parameters: - name: endpoint_name in: path required: true schema: type: string title: Endpoint Name - name: service in: query required: true schema: type: string description: 'Service type: ''model_serving'' | ''vector_search'' | ''ai_gateway''' title: Service description: 'Service type: ''model_serving'' | ''vector_search'' | ''ai_gateway''' - name: start_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: Start date (YYYY-MM-DD), defaults to 30 days ago title: Start Date description: Start date (YYYY-MM-DD), defaults to 30 days ago - name: end_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: End date (YYYY-MM-DD), defaults to today title: End Date description: End date (YYYY-MM-DD), defaults to today - name: navigationSource in: query required: false schema: anyOf: - type: string - type: 'null' title: Navigationsource - name: x-tenant in: header required: true schema: type: string title: X-Tenant responses: '200': description: Successful Response content: application/json: schema: {} '403': description: Not authorized '404': description: Endpoint not found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/databricks/ai-ml-services/endpoints/{endpoint_name}/trend: get: tags: - Databricks AI/ML Services summary: Get endpoint trend (Model Serving, Vector Search or AI Gateway) description: "Get trend data for a specific endpoint.\n\nPath Parameters:\n- endpoint_name: Endpoint name (required)\n\nQuery Parameters:\n- service: 'model_serving' | 'vector_search' | 'ai_gateway' (required)\n- start_date: Start date (YYYY-MM-DD), defaults to 30 days ago\n- end_date: End date (YYYY-MM-DD), defaults to today\n- granularity: 'day', 'week', 'month', or 'auto' (default: auto)\n\nReturns:\n- Array of trend data points (direct array, no wrapper object). For\n Vector Search and AI Gateway this is ``{date, dbus, cost_usd}`` — one\n row per bucket where billing usage exists (no zero-fill)." operationId: get_endpoint_trend_api_v1_databricks_ai_ml_services_endpoints__endpoint_name__trend_get security: - HTTPBearer: [] - HTTPBearer: [] parameters: - name: endpoint_name in: path required: true schema: type: string title: Endpoint Name - name: service in: query required: true schema: type: string description: 'Service type: ''model_serving'' | ''vector_search'' | ''ai_gateway''' title: Service description: 'Service type: ''model_serving'' | ''vector_search'' | ''ai_gateway''' - name: start_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: Start date (YYYY-MM-DD), defaults to 30 days ago title: Start Date description: Start date (YYYY-MM-DD), defaults to 30 days ago - name: end_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: End date (YYYY-MM-DD), defaults to today title: End Date description: End date (YYYY-MM-DD), defaults to today - name: granularity in: query required: false schema: type: string description: 'Time granularity: ''day'', ''week'', ''month'', or ''auto'' (auto-detect based on date range)' default: auto title: Granularity description: 'Time granularity: ''day'', ''week'', ''month'', or ''auto'' (auto-detect based on date range)' - name: navigationSource in: query required: false schema: anyOf: - type: string - type: 'null' title: Navigationsource - name: x-tenant in: header required: true schema: type: string title: X-Tenant responses: '200': description: Successful Response content: application/json: schema: {} '403': description: Not authorized '404': description: Resource not found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/databricks/ai-ml-services/endpoints/{endpoint_name}/callers: get: tags: - Databricks AI/ML Services summary: Get jobs/queries calling a model serving endpoint description: 'Get list of jobs/queries that are calling a model serving endpoint. This endpoint identifies the source of model serving endpoint calls by analyzing: - Query history for AI function calls (ai_classify, ai_summarize, etc.) - Job information from query_source metadata - Notebook IDs for notebook-based calls Path Parameters: - endpoint_name: Endpoint name (required) Query Parameters: - start_date: Start date (YYYY-MM-DD), defaults to 30 days ago - end_date: End date (YYYY-MM-DD), defaults to today - limit: Max rows to return (default: 50, max: 1000) - offset: Pagination offset (default: 0) Returns: - callers: List of jobs/queries with call frequency metrics - pagination: Pagination info (total, limit, offset)' operationId: get_endpoint_callers_api_v1_databricks_ai_ml_services_endpoints__endpoint_name__callers_get security: - HTTPBearer: [] - HTTPBearer: [] parameters: - name: endpoint_name in: path required: true schema: type: string title: Endpoint Name - name: start_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: Start date (YYYY-MM-DD), defaults to 30 days ago title: Start Date description: Start date (YYYY-MM-DD), defaults to 30 days ago - name: end_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: End date (YYYY-MM-DD), defaults to today title: End Date description: End date (YYYY-MM-DD), defaults to today - name: limit in: query required: false schema: type: integer maximum: 1000 minimum: 1 description: Max rows to return default: 50 title: Limit description: Max rows to return - name: offset in: query required: false schema: type: integer minimum: 0 description: Pagination offset default: 0 title: Offset description: Pagination offset - name: navigationSource in: query required: false schema: anyOf: - type: string - type: 'null' title: Navigationsource - name: x-tenant in: header required: true schema: type: string title: X-Tenant responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/EndpointCallersListResponse' '403': description: Not authorized '404': description: Resource not found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/databricks/ai-ml-services/endpoints/{endpoint_name}/usage-breakdown: get: tags: - Databricks AI/ML Services summary: Get AI function usage breakdown by source description: 'Get usage breakdown for an AI function endpoint. Shows how the AI function is being invoked: via MV refresh, notebooks, jobs, SQL queries, DDL, or ad-hoc queries. Path Parameters: - endpoint_name: AI function endpoint name (e.g., databricks-ai-summarize) Query Parameters: - start_date: Start date (YYYY-MM-DD), defaults to 30 days ago - end_date: End date (YYYY-MM-DD), defaults to today Returns: - usage: List of usage sources with type, identity, request count, and last used' operationId: get_ai_function_usage_breakdown_api_v1_databricks_ai_ml_services_endpoints__endpoint_name__usage_breakdown_get security: - HTTPBearer: [] - HTTPBearer: [] parameters: - name: endpoint_name in: path required: true schema: type: string title: Endpoint Name - name: start_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: Start date (YYYY-MM-DD), defaults to 30 days ago title: Start Date description: Start date (YYYY-MM-DD), defaults to 30 days ago - name: end_date in: query required: false schema: anyOf: - type: string format: date - type: 'null' description: End date (YYYY-MM-DD), defaults to today title: End Date description: End date (YYYY-MM-DD), defaults to today - name: navigationSource in: query required: false schema: anyOf: - type: string - type: 'null' title: Navigationsource - name: x-tenant in: header required: true schema: type: string title: X-Tenant responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/AIFunctionUsageBreakdownResponse' '403': description: Not authorized '404': description: Resource not found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: AIMLEndpointsFilterOptions: properties: entity_types: items: type: string type: array title: Entity Types description: 'Distinct entity_types appearing on rows in the window. Subset of the seven leaf types: FOUNDATION_MODEL, CUSTOM_MODEL, AI_FUNCTION, EXTERNAL_MODEL, FEATURE_SPEC, VECTOR_SEARCH, AI_GATEWAY.' workspace_ids: items: type: string type: array title: Workspace Ids description: Distinct workspace IDs that have AI/ML usage in the window type: object title: AIMLEndpointsFilterOptions description: 'Discrete filter values for the unified AI/ML endpoints list. Only fields that are actually filterable on ``GET /ai-ml-services/endpoints`` are returned. ``start_date`` / ``end_date`` are a free-form date range and therefore not enumerable here; the caller still passes them in to scope ``entity_types`` and ``workspace_ids`` to rows with traffic in the window.' ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError AIFunctionUsageItem: properties: usage_type: type: string title: Usage Type description: 'Type of usage: ''MV Refresh'', ''Notebook'', ''SQL Query'', ''Job'', ''DDL'', ''Ad-hoc''' usage_identity: type: string title: Usage Identity description: 'Identity of the usage source: MV name, notebook ID, job ID, etc.' job_name: anyOf: - type: string - type: 'null' title: Job Name description: Resolved job name from dbx_job_inventory (for Job type) executed_by: anyOf: - type: string - type: 'null' title: Executed By description: User who executed the query source_identifier: anyOf: - type: string - type: 'null' title: Source Identifier description: 'Best available identifier: statement_id, job_id, notebook_id, etc.' total_requests: type: integer title: Total Requests description: Total number of invocations default: 0 days_active: type: integer title: Days Active description: Number of distinct days with activity default: 0 last_used: anyOf: - type: string - type: 'null' title: Last Used description: Most recent invocation timestamp type: object required: - usage_type - usage_identity title: AIFunctionUsageItem description: A usage source for an AI function endpoint. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError UnifiedAIMLEndpointsListResponse: properties: endpoints: items: $ref: '#/components/schemas/UnifiedAIMLEndpointItem' type: array title: Endpoints description: Mixed list of model serving, vector search and AI gateway endpoints pagination: $ref: '#/components/schemas/app__schemas__databricks__ai_services__PaginationInfo' description: Pagination info type: object required: - pagination title: UnifiedAIMLEndpointsListResponse description: Response for the unified AI/ML endpoints list. UnifiedAIMLEndpointItem: properties: service: type: string title: Service description: 'Routing discriminator: ''model_serving'' | ''vector_search'' | ''ai_gateway''' entity_type: anyOf: - type: string - type: 'null' title: Entity Type description: Leaf type used for the Type column / filter. One of the five model_serving entity types, 'VECTOR_SEARCH', or 'AI_GATEWAY'. Null when a model_serving endpoint has no served_entities row (rendered as '-' by the FE) — we don't guess a type. endpoint_name: type: string title: Endpoint Name description: Endpoint name endpoint_id: anyOf: - type: string - type: 'null' title: Endpoint Id description: Endpoint ID total_dbus: type: number title: Total Dbus description: Total DBUs consumed default: 0 total_cost_usd: type: number title: Total Cost Usd description: Total cost in USD default: 0 created_by: anyOf: - type: string - type: 'null' title: Created By description: Creator email (model_serving) total_requests: anyOf: - type: integer - type: 'null' title: Total Requests description: Total requests (model_serving) total_tokens: anyOf: - type: integer - type: 'null' title: Total Tokens description: Total tokens (model_serving) unique_users: anyOf: - type: integer - type: 'null' title: Unique Users description: Unique users (model_serving) days_active: anyOf: - type: integer - type: 'null' title: Days Active description: Days with activity (vector_search / ai_gateway) first_seen: anyOf: - type: string - type: 'null' title: First Seen description: First seen date (vector_search / ai_gateway) last_activity: anyOf: - type: string - type: 'null' title: Last Activity description: Last activity date (vector_search / ai_gateway) type: object required: - service - endpoint_name title: UnifiedAIMLEndpointItem description: "Unified endpoint row covering Model Serving, Vector Search and AI Gateway.\n\n``entity_type`` is the single leaf-level discriminator the table renders in\nits Type column and the FE filters on:\n\n- Model Serving rows: one of ``FOUNDATION_MODEL``, ``CUSTOM_MODEL``,\n ``AI_FUNCTION``, ``EXTERNAL_MODEL``, ``FEATURE_SPEC``.\n- Vector Search rows: ``VECTOR_SEARCH``.\n- AI Gateway rows: ``AI_GATEWAY``.\n\n``service`` stays on each row as the routing discriminator the FE uses on\nrow-click (model-serving / vector-search / ai-gateway detail pages); it is\nno longer a filter input. Fields that don't apply to a row's service are\nnull." AIFunctionUsageBreakdownResponse: properties: usage: items: $ref: '#/components/schemas/AIFunctionUsageItem' type: array title: Usage description: List of usage sources type: object title: AIFunctionUsageBreakdownResponse description: Response for AI function usage breakdown. EndpointCallerItem: properties: job_id: anyOf: - type: string - type: 'null' title: Job Id description: Job ID from Lakeflow/Workflows job_name: anyOf: - type: string - type: 'null' title: Job Name description: Job name notebook_id: anyOf: - type: string - type: 'null' title: Notebook Id description: Notebook ID if called from notebook executed_by: anyOf: - type: string - type: 'null' title: Executed By description: User who executed the query (for direct queries) caller_type: type: string title: Caller Type description: 'Type of caller: ''job'', ''notebook'', or ''query''' query_count: type: integer title: Query Count description: Total number of queries/invocations default: 0 unique_queries: type: integer title: Unique Queries description: Number of unique query statements default: 0 first_execution: anyOf: - type: string - type: 'null' title: First Execution description: First execution timestamp last_execution: anyOf: - type: string - type: 'null' title: Last Execution description: Last execution timestamp days_active: type: integer title: Days Active description: Number of days with activity default: 0 avg_queries_per_day: type: number title: Avg Queries Per Day description: Average queries per active day default: 0 cost_per_inference: type: number title: Cost Per Inference description: Estimated cost per inference in the endpoint currency. The endpoint's billed cost is allocated to this caller by its share of tokens, then divided by its invocations; falls back to the flat endpoint rate (endpoint cost / total invocations) when token counts are unavailable. default: 0 type: object required: - caller_type title: EndpointCallerItem description: A job or query that calls the model serving endpoint. EndpointCallersListResponse: properties: callers: items: $ref: '#/components/schemas/EndpointCallerItem' type: array title: Callers description: List of callers (jobs/queries) pagination: $ref: '#/components/schemas/app__schemas__databricks__ai_services__PaginationInfo' description: Pagination info type: object required: - pagination title: EndpointCallersListResponse description: Response for listing jobs/queries calling an endpoint. AIMLServicesTrendPoint: properties: date: type: string title: Date description: Date in YYYY-MM-DD format total_dbus: type: number title: Total Dbus description: Total DBUs across all services default: 0 total_cost_usd: type: number title: Total Cost Usd description: Total cost in USD across all services default: 0 model_serving_dbus: type: number title: Model Serving Dbus description: Model serving DBUs default: 0 model_serving_cost_usd: type: number title: Model Serving Cost Usd description: Model serving cost in USD default: 0 vector_search_dbus: type: number title: Vector Search Dbus description: Vector search DBUs default: 0 vector_search_cost_usd: type: number title: Vector Search Cost Usd description: Vector search cost in USD default: 0 ai_gateway_dbus: type: number title: Ai Gateway Dbus description: AI Gateway DBUs default: 0 ai_gateway_cost_usd: type: number title: Ai Gateway Cost Usd description: AI Gateway cost in USD default: 0 type: object required: - date title: AIMLServicesTrendPoint description: Single data point for AI/ML services daily trend. app__schemas__databricks__ai_services__PaginationInfo: properties: total: type: integer title: Total description: Total number of items limit: type: integer title: Limit description: Items per page offset: type: integer title: Offset description: Current offset type: object required: - total - limit - offset title: PaginationInfo description: Pagination information. AIMLEndpointNamesResponse: properties: items: items: type: string type: array title: Items description: Distinct endpoint names on this page page: type: integer title: Page description: Current page number (1-indexed) default: 1 size: type: integer title: Size description: Items per page default: 20 total: type: integer title: Total description: Total number of matching names default: 0 total_pages: type: integer title: Total Pages description: Total number of pages default: 1 type: object title: AIMLEndpointNamesResponse description: 'Paginated, searchable list of distinct endpoint names. Backs the endpoint-name filter dropdown: the full set of names is too large to ship at once, so the FE searches server-side (substring ``search``) and pages through matches. The selected name(s) are then sent back to ``GET /ai-ml-services/endpoints`` as the exact ``endpoint_name`` filter.' securitySchemes: HTTPBearer: type: http scheme: bearer