Docs Home Pulumi IaC Pulumi ESC Pulumi Insights Pulumi IDP Pulumi Cloud Packages Tutorials
  1. Packages
  2. Databricks Provider
  3. API Docs
  4. ModelServingProvisionedThroughput
Databricks v1.71.0 published on Monday, Jun 9, 2025 by Pulumi
pulumi/pulumi-databricks

databricks.ModelServingProvisionedThroughput

Explore with Pulumi AI

databricks logo
Databricks v1.71.0 published on Monday, Jun 9, 2025 by Pulumi
pulumi/pulumi-databricks

    This resource allows you to manage Foundation Model provisioned throughput endpoints in Databricks.

    This resource is currently in private preview, and only available for enrolled customers.

    This resource can only be used with a workspace-level provider!

    Example Usage

    Creating a Foundation Model provisioned throughput endpoint

    import * as pulumi from "@pulumi/pulumi";
import * as databricks from "@pulumi/databricks";

const llama = new databricks.ModelServingProvisionedThroughput("llama", {
    aiGateway: {
        usageTrackingConfig: {
            enabled: true,
        },
    },
    config: {
        servedEntities: [{
            entityName: "system.ai.llama-4-maverick",
            entityVersion: "1",
            provisionedModelUnits: 100,
        }],
    },
});

    import pulumi
import pulumi_databricks as databricks

llama = databricks.ModelServingProvisionedThroughput("llama",
    ai_gateway={
        "usage_tracking_config": {
            "enabled": True,
        },
    },
    config={
        "served_entities": [{
            "entity_name": "system.ai.llama-4-maverick",
            "entity_version": "1",
            "provisioned_model_units": 100,
        }],
    })

    package main

import (
	"github.com/pulumi/pulumi-databricks/sdk/go/databricks"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := databricks.NewModelServingProvisionedThroughput(ctx, "llama", &databricks.ModelServingProvisionedThroughputArgs{
			AiGateway: &databricks.ModelServingProvisionedThroughputAiGatewayArgs{
				UsageTrackingConfig: &databricks.ModelServingProvisionedThroughputAiGatewayUsageTrackingConfigArgs{
					Enabled: pulumi.Bool(true),
				},
			},
			Config: &databricks.ModelServingProvisionedThroughputConfigArgs{
				ServedEntities: databricks.ModelServingProvisionedThroughputConfigServedEntityArray{
					&databricks.ModelServingProvisionedThroughputConfigServedEntityArgs{
						EntityName:            pulumi.String("system.ai.llama-4-maverick"),
						EntityVersion:         pulumi.String("1"),
						ProvisionedModelUnits: pulumi.Int(100),
					},
				},
			},
		})
		if err != nil {
			return err
		}
		return nil
	})
}

    using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Databricks = Pulumi.Databricks;

return await Deployment.RunAsync(() => 
{
    var llama = new Databricks.ModelServingProvisionedThroughput("llama", new()
    {
        AiGateway = new Databricks.Inputs.ModelServingProvisionedThroughputAiGatewayArgs
        {
            UsageTrackingConfig = new Databricks.Inputs.ModelServingProvisionedThroughputAiGatewayUsageTrackingConfigArgs
            {
                Enabled = true,
            },
        },
        Config = new Databricks.Inputs.ModelServingProvisionedThroughputConfigArgs
        {
            ServedEntities = new[]
            {
                new Databricks.Inputs.ModelServingProvisionedThroughputConfigServedEntityArgs
                {
                    EntityName = "system.ai.llama-4-maverick",
                    EntityVersion = "1",
                    ProvisionedModelUnits = 100,
                },
            },
        },
    });

});

    package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.databricks.ModelServingProvisionedThroughput;
import com.pulumi.databricks.ModelServingProvisionedThroughputArgs;
import com.pulumi.databricks.inputs.ModelServingProvisionedThroughputAiGatewayArgs;
import com.pulumi.databricks.inputs.ModelServingProvisionedThroughputAiGatewayUsageTrackingConfigArgs;
import com.pulumi.databricks.inputs.ModelServingProvisionedThroughputConfigArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;

public class App {
    public static void main(String[] args) {
        Pulumi.run(App::stack);
    }

    public static void stack(Context ctx) {
        var llama = new ModelServingProvisionedThroughput("llama", ModelServingProvisionedThroughputArgs.builder()
            .aiGateway(ModelServingProvisionedThroughputAiGatewayArgs.builder()
                .usageTrackingConfig(ModelServingProvisionedThroughputAiGatewayUsageTrackingConfigArgs.builder()
                    .enabled(true)
                    .build())
                .build())
            .config(ModelServingProvisionedThroughputConfigArgs.builder()
                .servedEntities(ModelServingProvisionedThroughputConfigServedEntityArgs.builder()
                    .entityName("system.ai.llama-4-maverick")
                    .entityVersion("1")
                    .provisionedModelUnits(100)
                    .build())
                .build())
            .build());

    }
}

    resources:
  llama:
    type: databricks:ModelServingProvisionedThroughput
    properties:
      aiGateway:
        usageTrackingConfig:
          enabled: true
      config:
        servedEntities:
          - entityName: system.ai.llama-4-maverick
            entityVersion: '1'
            provisionedModelUnits: 100

    Access Control

    • databricks.Permissions can control which groups or individual users can Manage, Query or View individual serving endpoints.

    The following resources are often used in the same context:

    • databricks.ModelServing to create custom and external serving endpoints in Databricks.
    • databricks.RegisteredModel to create Models in Unity Catalog in Databricks.
    • End to end workspace management guide.
    • databricks.Directory to manage directories in Databricks Workspace.
    • databricks.MlflowModel to create models in the workspace model registry in Databricks.
    • databricks.Notebook to manage Databricks Notebooks.
    • databricks.Notebook data to export a notebook from Databricks Workspace.
    • databricks.Repo to manage Databricks Repos.

    Create ModelServingProvisionedThroughput Resource

    Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

    Constructor syntax

    new ModelServingProvisionedThroughput(name: string, args: ModelServingProvisionedThroughputArgs, opts?: CustomResourceOptions);
    @overload
def ModelServingProvisionedThroughput(resource_name: str,
                                      args: ModelServingProvisionedThroughputArgs,
                                      opts: Optional[ResourceOptions] = None)

@overload
def ModelServingProvisionedThroughput(resource_name: str,
                                      opts: Optional[ResourceOptions] = None,
                                      config: Optional[ModelServingProvisionedThroughputConfigArgs] = None,
                                      ai_gateway: Optional[ModelServingProvisionedThroughputAiGatewayArgs] = None,
                                      budget_policy_id: Optional[str] = None,
                                      name: Optional[str] = None,
                                      tags: Optional[Sequence[ModelServingProvisionedThroughputTagArgs]] = None)
    func NewModelServingProvisionedThroughput(ctx *Context, name string, args ModelServingProvisionedThroughputArgs, opts ...ResourceOption) (*ModelServingProvisionedThroughput, error)
    public ModelServingProvisionedThroughput(string name, ModelServingProvisionedThroughputArgs args, CustomResourceOptions? opts = null)
    public ModelServingProvisionedThroughput(String name, ModelServingProvisionedThroughputArgs args)
public ModelServingProvisionedThroughput(String name, ModelServingProvisionedThroughputArgs args, CustomResourceOptions options)

    type: databricks:ModelServingProvisionedThroughput
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

    Parameters

    name string
    The unique name of the resource.
    args ModelServingProvisionedThroughputArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    resource_name str
    The unique name of the resource.
    args ModelServingProvisionedThroughputArgs
    The arguments to resource properties.
    opts ResourceOptions
    Bag of options to control resource's behavior.
    ctx Context
    Context object for the current deployment.
    name string
    The unique name of the resource.
    args ModelServingProvisionedThroughputArgs
    The arguments to resource properties.
    opts ResourceOption
    Bag of options to control resource's behavior.
    name string
    The unique name of the resource.
    args ModelServingProvisionedThroughputArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    name String
    The unique name of the resource.
    args ModelServingProvisionedThroughputArgs
    The arguments to resource properties.
    options CustomResourceOptions
    Bag of options to control resource's behavior.

    Constructor example

    The following reference example uses placeholder values for all input properties.

    var modelServingProvisionedThroughputResource = new Databricks.ModelServingProvisionedThroughput("modelServingProvisionedThroughputResource", new()
{
    Config = new Databricks.Inputs.ModelServingProvisionedThroughputConfigArgs
    {
        ServedEntities = new[]
        {
            new Databricks.Inputs.ModelServingProvisionedThroughputConfigServedEntityArgs
            {
                EntityName = "string",
                EntityVersion = "string",
                ProvisionedModelUnits = 0,
                Name = "string",
            },
        },
        TrafficConfig = new Databricks.Inputs.ModelServingProvisionedThroughputConfigTrafficConfigArgs
        {
            Routes = new[]
            {
                new Databricks.Inputs.ModelServingProvisionedThroughputConfigTrafficConfigRouteArgs
                {
                    ServedModelName = "string",
                    TrafficPercentage = 0,
                },
            },
        },
    },
    AiGateway = new Databricks.Inputs.ModelServingProvisionedThroughputAiGatewayArgs
    {
        FallbackConfig = new Databricks.Inputs.ModelServingProvisionedThroughputAiGatewayFallbackConfigArgs
        {
            Enabled = false,
        },
        Guardrails = new Databricks.Inputs.ModelServingProvisionedThroughputAiGatewayGuardrailsArgs
        {
            Input = new Databricks.Inputs.ModelServingProvisionedThroughputAiGatewayGuardrailsInputArgs
            {
                InvalidKeywords = new[]
                {
                    "string",
                },
                Pii = new Databricks.Inputs.ModelServingProvisionedThroughputAiGatewayGuardrailsInputPiiArgs
                {
                    Behavior = "string",
                },
                Safety = false,
                ValidTopics = new[]
                {
                    "string",
                },
            },
            Output = new Databricks.Inputs.ModelServingProvisionedThroughputAiGatewayGuardrailsOutputArgs
            {
                InvalidKeywords = new[]
                {
                    "string",
                },
                Pii = new Databricks.Inputs.ModelServingProvisionedThroughputAiGatewayGuardrailsOutputPiiArgs
                {
                    Behavior = "string",
                },
                Safety = false,
                ValidTopics = new[]
                {
                    "string",
                },
            },
        },
        InferenceTableConfig = new Databricks.Inputs.ModelServingProvisionedThroughputAiGatewayInferenceTableConfigArgs
        {
            CatalogName = "string",
            Enabled = false,
            SchemaName = "string",
            TableNamePrefix = "string",
        },
        RateLimits = new[]
        {
            new Databricks.Inputs.ModelServingProvisionedThroughputAiGatewayRateLimitArgs
            {
                Calls = 0,
                RenewalPeriod = "string",
                Key = "string",
            },
        },
        UsageTrackingConfig = new Databricks.Inputs.ModelServingProvisionedThroughputAiGatewayUsageTrackingConfigArgs
        {
            Enabled = false,
        },
    },
    BudgetPolicyId = "string",
    Name = "string",
    Tags = new[]
    {
        new Databricks.Inputs.ModelServingProvisionedThroughputTagArgs
        {
            Key = "string",
            Value = "string",
        },
    },
});

    example, err := databricks.NewModelServingProvisionedThroughput(ctx, "modelServingProvisionedThroughputResource", &databricks.ModelServingProvisionedThroughputArgs{
	Config: &databricks.ModelServingProvisionedThroughputConfigArgs{
		ServedEntities: databricks.ModelServingProvisionedThroughputConfigServedEntityArray{
			&databricks.ModelServingProvisionedThroughputConfigServedEntityArgs{
				EntityName:            pulumi.String("string"),
				EntityVersion:         pulumi.String("string"),
				ProvisionedModelUnits: pulumi.Int(0),
				Name:                  pulumi.String("string"),
			},
		},
		TrafficConfig: &databricks.ModelServingProvisionedThroughputConfigTrafficConfigArgs{
			Routes: databricks.ModelServingProvisionedThroughputConfigTrafficConfigRouteArray{
				&databricks.ModelServingProvisionedThroughputConfigTrafficConfigRouteArgs{
					ServedModelName:   pulumi.String("string"),
					TrafficPercentage: pulumi.Int(0),
				},
			},
		},
	},
	AiGateway: &databricks.ModelServingProvisionedThroughputAiGatewayArgs{
		FallbackConfig: &databricks.ModelServingProvisionedThroughputAiGatewayFallbackConfigArgs{
			Enabled: pulumi.Bool(false),
		},
		Guardrails: &databricks.ModelServingProvisionedThroughputAiGatewayGuardrailsArgs{
			Input: &databricks.ModelServingProvisionedThroughputAiGatewayGuardrailsInputTypeArgs{
				InvalidKeywords: pulumi.StringArray{
					pulumi.String("string"),
				},
				Pii: &databricks.ModelServingProvisionedThroughputAiGatewayGuardrailsInputPiiArgs{
					Behavior: pulumi.String("string"),
				},
				Safety: pulumi.Bool(false),
				ValidTopics: pulumi.StringArray{
					pulumi.String("string"),
				},
			},
			Output: &databricks.ModelServingProvisionedThroughputAiGatewayGuardrailsOutputTypeArgs{
				InvalidKeywords: pulumi.StringArray{
					pulumi.String("string"),
				},
				Pii: &databricks.ModelServingProvisionedThroughputAiGatewayGuardrailsOutputPiiArgs{
					Behavior: pulumi.String("string"),
				},
				Safety: pulumi.Bool(false),
				ValidTopics: pulumi.StringArray{
					pulumi.String("string"),
				},
			},
		},
		InferenceTableConfig: &databricks.ModelServingProvisionedThroughputAiGatewayInferenceTableConfigArgs{
			CatalogName:     pulumi.String("string"),
			Enabled:         pulumi.Bool(false),
			SchemaName:      pulumi.String("string"),
			TableNamePrefix: pulumi.String("string"),
		},
		RateLimits: databricks.ModelServingProvisionedThroughputAiGatewayRateLimitArray{
			&databricks.ModelServingProvisionedThroughputAiGatewayRateLimitArgs{
				Calls:         pulumi.Int(0),
				RenewalPeriod: pulumi.String("string"),
				Key:           pulumi.String("string"),
			},
		},
		UsageTrackingConfig: &databricks.ModelServingProvisionedThroughputAiGatewayUsageTrackingConfigArgs{
			Enabled: pulumi.Bool(false),
		},
	},
	BudgetPolicyId: pulumi.String("string"),
	Name:           pulumi.String("string"),
	Tags: databricks.ModelServingProvisionedThroughputTagArray{
		&databricks.ModelServingProvisionedThroughputTagArgs{
			Key:   pulumi.String("string"),
			Value: pulumi.String("string"),
		},
	},
})

    var modelServingProvisionedThroughputResource = new ModelServingProvisionedThroughput("modelServingProvisionedThroughputResource", ModelServingProvisionedThroughputArgs.builder()
    .config(ModelServingProvisionedThroughputConfigArgs.builder()
        .servedEntities(ModelServingProvisionedThroughputConfigServedEntityArgs.builder()
            .entityName("string")
            .entityVersion("string")
            .provisionedModelUnits(0)
            .name("string")
            .build())
        .trafficConfig(ModelServingProvisionedThroughputConfigTrafficConfigArgs.builder()
            .routes(ModelServingProvisionedThroughputConfigTrafficConfigRouteArgs.builder()
                .servedModelName("string")
                .trafficPercentage(0)
                .build())
            .build())
        .build())
    .aiGateway(ModelServingProvisionedThroughputAiGatewayArgs.builder()
        .fallbackConfig(ModelServingProvisionedThroughputAiGatewayFallbackConfigArgs.builder()
            .enabled(false)
            .build())
        .guardrails(ModelServingProvisionedThroughputAiGatewayGuardrailsArgs.builder()
            .input(ModelServingProvisionedThroughputAiGatewayGuardrailsInputArgs.builder()
                .invalidKeywords("string")
                .pii(ModelServingProvisionedThroughputAiGatewayGuardrailsInputPiiArgs.builder()
                    .behavior("string")
                    .build())
                .safety(false)
                .validTopics("string")
                .build())
            .output(ModelServingProvisionedThroughputAiGatewayGuardrailsOutputArgs.builder()
                .invalidKeywords("string")
                .pii(ModelServingProvisionedThroughputAiGatewayGuardrailsOutputPiiArgs.builder()
                    .behavior("string")
                    .build())
                .safety(false)
                .validTopics("string")
                .build())
            .build())
        .inferenceTableConfig(ModelServingProvisionedThroughputAiGatewayInferenceTableConfigArgs.builder()
            .catalogName("string")
            .enabled(false)
            .schemaName("string")
            .tableNamePrefix("string")
            .build())
        .rateLimits(ModelServingProvisionedThroughputAiGatewayRateLimitArgs.builder()
            .calls(0)
            .renewalPeriod("string")
            .key("string")
            .build())
        .usageTrackingConfig(ModelServingProvisionedThroughputAiGatewayUsageTrackingConfigArgs.builder()
            .enabled(false)
            .build())
        .build())
    .budgetPolicyId("string")
    .name("string")
    .tags(ModelServingProvisionedThroughputTagArgs.builder()
        .key("string")
        .value("string")
        .build())
    .build());

    model_serving_provisioned_throughput_resource = databricks.ModelServingProvisionedThroughput("modelServingProvisionedThroughputResource",
    config={
        "served_entities": [{
            "entity_name": "string",
            "entity_version": "string",
            "provisioned_model_units": 0,
            "name": "string",
        }],
        "traffic_config": {
            "routes": [{
                "served_model_name": "string",
                "traffic_percentage": 0,
            }],
        },
    },
    ai_gateway={
        "fallback_config": {
            "enabled": False,
        },
        "guardrails": {
            "input": {
                "invalid_keywords": ["string"],
                "pii": {
                    "behavior": "string",
                },
                "safety": False,
                "valid_topics": ["string"],
            },
            "output": {
                "invalid_keywords": ["string"],
                "pii": {
                    "behavior": "string",
                },
                "safety": False,
                "valid_topics": ["string"],
            },
        },
        "inference_table_config": {
            "catalog_name": "string",
            "enabled": False,
            "schema_name": "string",
            "table_name_prefix": "string",
        },
        "rate_limits": [{
            "calls": 0,
            "renewal_period": "string",
            "key": "string",
        }],
        "usage_tracking_config": {
            "enabled": False,
        },
    },
    budget_policy_id="string",
    name="string",
    tags=[{
        "key": "string",
        "value": "string",
    }])

    const modelServingProvisionedThroughputResource = new databricks.ModelServingProvisionedThroughput("modelServingProvisionedThroughputResource", {
    config: {
        servedEntities: [{
            entityName: "string",
            entityVersion: "string",
            provisionedModelUnits: 0,
            name: "string",
        }],
        trafficConfig: {
            routes: [{
                servedModelName: "string",
                trafficPercentage: 0,
            }],
        },
    },
    aiGateway: {
        fallbackConfig: {
            enabled: false,
        },
        guardrails: {
            input: {
                invalidKeywords: ["string"],
                pii: {
                    behavior: "string",
                },
                safety: false,
                validTopics: ["string"],
            },
            output: {
                invalidKeywords: ["string"],
                pii: {
                    behavior: "string",
                },
                safety: false,
                validTopics: ["string"],
            },
        },
        inferenceTableConfig: {
            catalogName: "string",
            enabled: false,
            schemaName: "string",
            tableNamePrefix: "string",
        },
        rateLimits: [{
            calls: 0,
            renewalPeriod: "string",
            key: "string",
        }],
        usageTrackingConfig: {
            enabled: false,
        },
    },
    budgetPolicyId: "string",
    name: "string",
    tags: [{
        key: "string",
        value: "string",
    }],
});

    type: databricks:ModelServingProvisionedThroughput
properties:
    aiGateway:
        fallbackConfig:
            enabled: false
        guardrails:
            input:
                invalidKeywords:
                    - string
                pii:
                    behavior: string
                safety: false
                validTopics:
                    - string
            output:
                invalidKeywords:
                    - string
                pii:
                    behavior: string
                safety: false
                validTopics:
                    - string
        inferenceTableConfig:
            catalogName: string
            enabled: false
            schemaName: string
            tableNamePrefix: string
        rateLimits:
            - calls: 0
              key: string
              renewalPeriod: string
        usageTrackingConfig:
            enabled: false
    budgetPolicyId: string
    config:
        servedEntities:
            - entityName: string
              entityVersion: string
              name: string
              provisionedModelUnits: 0
        trafficConfig:
            routes:
                - servedModelName: string
                  trafficPercentage: 0
    name: string
    tags:
        - key: string
          value: string

    ModelServingProvisionedThroughput Resource Properties

    To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.

    Inputs

    In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.

    The ModelServingProvisionedThroughput resource accepts the following input properties:

    Config ModelServingProvisionedThroughputConfig
    The model serving endpoint configuration.
    AiGateway ModelServingProvisionedThroughputAiGateway
    A block with AI Gateway configuration for the serving endpoint. Note: only external model endpoints are supported as of now.
    BudgetPolicyId string
    The Budget Policy ID set for this serving endpoint.
    Name string
    The name of the model serving endpoint. This field is required and must be unique across a workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores. NOTE: Changing this name will delete the existing endpoint and create a new endpoint with the updated name.
    Tags List<ModelServingProvisionedThroughputTag>
    Tags to be attached to the serving endpoint and automatically propagated to billing logs.
    Config ModelServingProvisionedThroughputConfigArgs
    The model serving endpoint configuration.
    AiGateway ModelServingProvisionedThroughputAiGatewayArgs
    A block with AI Gateway configuration for the serving endpoint. Note: only external model endpoints are supported as of now.
    BudgetPolicyId string
    The Budget Policy ID set for this serving endpoint.
    Name string
    The name of the model serving endpoint. This field is required and must be unique across a workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores. NOTE: Changing this name will delete the existing endpoint and create a new endpoint with the updated name.
    Tags []ModelServingProvisionedThroughputTagArgs
    Tags to be attached to the serving endpoint and automatically propagated to billing logs.
    config ModelServingProvisionedThroughputConfig
    The model serving endpoint configuration.
    aiGateway ModelServingProvisionedThroughputAiGateway
    A block with AI Gateway configuration for the serving endpoint. Note: only external model endpoints are supported as of now.
    budgetPolicyId String
    The Budget Policy ID set for this serving endpoint.
    name String
    The name of the model serving endpoint. This field is required and must be unique across a workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores. NOTE: Changing this name will delete the existing endpoint and create a new endpoint with the updated name.
    tags List<ModelServingProvisionedThroughputTag>
    Tags to be attached to the serving endpoint and automatically propagated to billing logs.
    config ModelServingProvisionedThroughputConfig
    The model serving endpoint configuration.
    aiGateway ModelServingProvisionedThroughputAiGateway
    A block with AI Gateway configuration for the serving endpoint. Note: only external model endpoints are supported as of now.
    budgetPolicyId string
    The Budget Policy ID set for this serving endpoint.
    name string
    The name of the model serving endpoint. This field is required and must be unique across a workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores. NOTE: Changing this name will delete the existing endpoint and create a new endpoint with the updated name.
    tags ModelServingProvisionedThroughputTag[]
    Tags to be attached to the serving endpoint and automatically propagated to billing logs.
    config ModelServingProvisionedThroughputConfigArgs
    The model serving endpoint configuration.
    ai_gateway ModelServingProvisionedThroughputAiGatewayArgs
    A block with AI Gateway configuration for the serving endpoint. Note: only external model endpoints are supported as of now.
    budget_policy_id str
    The Budget Policy ID set for this serving endpoint.
    name str
    The name of the model serving endpoint. This field is required and must be unique across a workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores. NOTE: Changing this name will delete the existing endpoint and create a new endpoint with the updated name.
    tags Sequence[ModelServingProvisionedThroughputTagArgs]
    Tags to be attached to the serving endpoint and automatically propagated to billing logs.
    config Property Map
    The model serving endpoint configuration.
    aiGateway Property Map
    A block with AI Gateway configuration for the serving endpoint. Note: only external model endpoints are supported as of now.
    budgetPolicyId String
    The Budget Policy ID set for this serving endpoint.
    name String
    The name of the model serving endpoint. This field is required and must be unique across a workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores. NOTE: Changing this name will delete the existing endpoint and create a new endpoint with the updated name.
    tags List<Property Map>
    Tags to be attached to the serving endpoint and automatically propagated to billing logs.

    Outputs

    All input properties are implicitly available as output properties. Additionally, the ModelServingProvisionedThroughput resource produces the following output properties:

    Id string
    The provider-assigned unique ID for this managed resource.
    ServingEndpointId string
    Unique identifier of the serving endpoint primarily used to set permissions and refer to this instance for other operations.
    Id string
    The provider-assigned unique ID for this managed resource.
    ServingEndpointId string
    Unique identifier of the serving endpoint primarily used to set permissions and refer to this instance for other operations.
    id String
    The provider-assigned unique ID for this managed resource.
    servingEndpointId String
    Unique identifier of the serving endpoint primarily used to set permissions and refer to this instance for other operations.
    id string
    The provider-assigned unique ID for this managed resource.
    servingEndpointId string
    Unique identifier of the serving endpoint primarily used to set permissions and refer to this instance for other operations.
    id str
    The provider-assigned unique ID for this managed resource.
    serving_endpoint_id str
    Unique identifier of the serving endpoint primarily used to set permissions and refer to this instance for other operations.
    id String
    The provider-assigned unique ID for this managed resource.
    servingEndpointId String
    Unique identifier of the serving endpoint primarily used to set permissions and refer to this instance for other operations.

    Look up Existing ModelServingProvisionedThroughput Resource

    Get an existing ModelServingProvisionedThroughput resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.

    public static get(name: string, id: Input<ID>, state?: ModelServingProvisionedThroughputState, opts?: CustomResourceOptions): ModelServingProvisionedThroughput
    @staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        ai_gateway: Optional[ModelServingProvisionedThroughputAiGatewayArgs] = None,
        budget_policy_id: Optional[str] = None,
        config: Optional[ModelServingProvisionedThroughputConfigArgs] = None,
        name: Optional[str] = None,
        serving_endpoint_id: Optional[str] = None,
        tags: Optional[Sequence[ModelServingProvisionedThroughputTagArgs]] = None) -> ModelServingProvisionedThroughput
    func GetModelServingProvisionedThroughput(ctx *Context, name string, id IDInput, state *ModelServingProvisionedThroughputState, opts ...ResourceOption) (*ModelServingProvisionedThroughput, error)
    public static ModelServingProvisionedThroughput Get(string name, Input<string> id, ModelServingProvisionedThroughputState? state, CustomResourceOptions? opts = null)
    public static ModelServingProvisionedThroughput get(String name, Output<String> id, ModelServingProvisionedThroughputState state, CustomResourceOptions options)
    resources:  _:    type: databricks:ModelServingProvisionedThroughput    get:      id: ${id}
    name
    The unique name of the resulting resource.
    id
    The unique provider ID of the resource to lookup.
    state
    Any extra arguments used during the lookup.
    opts
    A bag of options that control this resource's behavior.
    resource_name
    The unique name of the resulting resource.
    id
    The unique provider ID of the resource to lookup.
    name
    The unique name of the resulting resource.
    id
    The unique provider ID of the resource to lookup.
    state
    Any extra arguments used during the lookup.
    opts
    A bag of options that control this resource's behavior.
    name
    The unique name of the resulting resource.
    id
    The unique provider ID of the resource to lookup.
    state
    Any extra arguments used during the lookup.
    opts
    A bag of options that control this resource's behavior.
    name
    The unique name of the resulting resource.
    id
    The unique provider ID of the resource to lookup.
    state
    Any extra arguments used during the lookup.
    opts
    A bag of options that control this resource's behavior.
    The following state arguments are supported:
    AiGateway ModelServingProvisionedThroughputAiGateway
    A block with AI Gateway configuration for the serving endpoint. Note: only external model endpoints are supported as of now.
    BudgetPolicyId string
    The Budget Policy ID set for this serving endpoint.
    Config ModelServingProvisionedThroughputConfig
    The model serving endpoint configuration.
    Name string
    The name of the model serving endpoint. This field is required and must be unique across a workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores. NOTE: Changing this name will delete the existing endpoint and create a new endpoint with the updated name.
    ServingEndpointId string
    Unique identifier of the serving endpoint primarily used to set permissions and refer to this instance for other operations.
    Tags List<ModelServingProvisionedThroughputTag>
    Tags to be attached to the serving endpoint and automatically propagated to billing logs.
    AiGateway ModelServingProvisionedThroughputAiGatewayArgs
    A block with AI Gateway configuration for the serving endpoint. Note: only external model endpoints are supported as of now.
    BudgetPolicyId string
    The Budget Policy ID set for this serving endpoint.
    Config ModelServingProvisionedThroughputConfigArgs
    The model serving endpoint configuration.
    Name string
    The name of the model serving endpoint. This field is required and must be unique across a workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores. NOTE: Changing this name will delete the existing endpoint and create a new endpoint with the updated name.
    ServingEndpointId string
    Unique identifier of the serving endpoint primarily used to set permissions and refer to this instance for other operations.
    Tags []ModelServingProvisionedThroughputTagArgs
    Tags to be attached to the serving endpoint and automatically propagated to billing logs.
    aiGateway ModelServingProvisionedThroughputAiGateway
    A block with AI Gateway configuration for the serving endpoint. Note: only external model endpoints are supported as of now.
    budgetPolicyId String
    The Budget Policy ID set for this serving endpoint.
    config ModelServingProvisionedThroughputConfig
    The model serving endpoint configuration.
    name String
    The name of the model serving endpoint. This field is required and must be unique across a workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores. NOTE: Changing this name will delete the existing endpoint and create a new endpoint with the updated name.
    servingEndpointId String
    Unique identifier of the serving endpoint primarily used to set permissions and refer to this instance for other operations.
    tags List<ModelServingProvisionedThroughputTag>
    Tags to be attached to the serving endpoint and automatically propagated to billing logs.
    aiGateway ModelServingProvisionedThroughputAiGateway
    A block with AI Gateway configuration for the serving endpoint. Note: only external model endpoints are supported as of now.
    budgetPolicyId string
    The Budget Policy ID set for this serving endpoint.
    config ModelServingProvisionedThroughputConfig
    The model serving endpoint configuration.
    name string
    The name of the model serving endpoint. This field is required and must be unique across a workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores. NOTE: Changing this name will delete the existing endpoint and create a new endpoint with the updated name.
    servingEndpointId string
    Unique identifier of the serving endpoint primarily used to set permissions and refer to this instance for other operations.
    tags ModelServingProvisionedThroughputTag[]
    Tags to be attached to the serving endpoint and automatically propagated to billing logs.
    ai_gateway ModelServingProvisionedThroughputAiGatewayArgs
    A block with AI Gateway configuration for the serving endpoint. Note: only external model endpoints are supported as of now.
    budget_policy_id str
    The Budget Policy ID set for this serving endpoint.
    config ModelServingProvisionedThroughputConfigArgs
    The model serving endpoint configuration.
    name str
    The name of the model serving endpoint. This field is required and must be unique across a workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores. NOTE: Changing this name will delete the existing endpoint and create a new endpoint with the updated name.
    serving_endpoint_id str
    Unique identifier of the serving endpoint primarily used to set permissions and refer to this instance for other operations.
    tags Sequence[ModelServingProvisionedThroughputTagArgs]
    Tags to be attached to the serving endpoint and automatically propagated to billing logs.
    aiGateway Property Map
    A block with AI Gateway configuration for the serving endpoint. Note: only external model endpoints are supported as of now.
    budgetPolicyId String
    The Budget Policy ID set for this serving endpoint.
    config Property Map
    The model serving endpoint configuration.
    name String
    The name of the model serving endpoint. This field is required and must be unique across a workspace. An endpoint name can consist of alphanumeric characters, dashes, and underscores. NOTE: Changing this name will delete the existing endpoint and create a new endpoint with the updated name.
    servingEndpointId String
    Unique identifier of the serving endpoint primarily used to set permissions and refer to this instance for other operations.
    tags List<Property Map>
    Tags to be attached to the serving endpoint and automatically propagated to billing logs.

    Supporting Types

    ModelServingProvisionedThroughputAiGateway, ModelServingProvisionedThroughputAiGatewayArgs

    FallbackConfig ModelServingProvisionedThroughputAiGatewayFallbackConfig
    Guardrails ModelServingProvisionedThroughputAiGatewayGuardrails
    Block with configuration for AI Guardrails to prevent unwanted data and unsafe data in requests and responses. Consists of the following attributes:
    InferenceTableConfig ModelServingProvisionedThroughputAiGatewayInferenceTableConfig
    Block describing the configuration of usage tracking. Consists of the following attributes:
    RateLimits List<ModelServingProvisionedThroughputAiGatewayRateLimit>
    Block describing rate limits for AI gateway. For details see the description of rate_limits block above.
    UsageTrackingConfig ModelServingProvisionedThroughputAiGatewayUsageTrackingConfig
    Block with configuration for payload logging using inference tables. For details see the description of auto_capture_config block above.
    FallbackConfig ModelServingProvisionedThroughputAiGatewayFallbackConfig
    Guardrails ModelServingProvisionedThroughputAiGatewayGuardrails
    Block with configuration for AI Guardrails to prevent unwanted data and unsafe data in requests and responses. Consists of the following attributes:
    InferenceTableConfig ModelServingProvisionedThroughputAiGatewayInferenceTableConfig
    Block describing the configuration of usage tracking. Consists of the following attributes:
    RateLimits []ModelServingProvisionedThroughputAiGatewayRateLimit
    Block describing rate limits for AI gateway. For details see the description of rate_limits block above.
    UsageTrackingConfig ModelServingProvisionedThroughputAiGatewayUsageTrackingConfig
    Block with configuration for payload logging using inference tables. For details see the description of auto_capture_config block above.
    fallbackConfig ModelServingProvisionedThroughputAiGatewayFallbackConfig
    guardrails ModelServingProvisionedThroughputAiGatewayGuardrails
    Block with configuration for AI Guardrails to prevent unwanted data and unsafe data in requests and responses. Consists of the following attributes:
    inferenceTableConfig ModelServingProvisionedThroughputAiGatewayInferenceTableConfig
    Block describing the configuration of usage tracking. Consists of the following attributes:
    rateLimits List<ModelServingProvisionedThroughputAiGatewayRateLimit>
    Block describing rate limits for AI gateway. For details see the description of rate_limits block above.
    usageTrackingConfig ModelServingProvisionedThroughputAiGatewayUsageTrackingConfig
    Block with configuration for payload logging using inference tables. For details see the description of auto_capture_config block above.
    fallbackConfig ModelServingProvisionedThroughputAiGatewayFallbackConfig
    guardrails ModelServingProvisionedThroughputAiGatewayGuardrails
    Block with configuration for AI Guardrails to prevent unwanted data and unsafe data in requests and responses. Consists of the following attributes:
    inferenceTableConfig ModelServingProvisionedThroughputAiGatewayInferenceTableConfig
    Block describing the configuration of usage tracking. Consists of the following attributes:
    rateLimits ModelServingProvisionedThroughputAiGatewayRateLimit[]
    Block describing rate limits for AI gateway. For details see the description of rate_limits block above.
    usageTrackingConfig ModelServingProvisionedThroughputAiGatewayUsageTrackingConfig
    Block with configuration for payload logging using inference tables. For details see the description of auto_capture_config block above.
    fallback_config ModelServingProvisionedThroughputAiGatewayFallbackConfig
    guardrails ModelServingProvisionedThroughputAiGatewayGuardrails
    Block with configuration for AI Guardrails to prevent unwanted data and unsafe data in requests and responses. Consists of the following attributes:
    inference_table_config ModelServingProvisionedThroughputAiGatewayInferenceTableConfig
    Block describing the configuration of usage tracking. Consists of the following attributes:
    rate_limits Sequence[ModelServingProvisionedThroughputAiGatewayRateLimit]
    Block describing rate limits for AI gateway. For details see the description of rate_limits block above.
    usage_tracking_config ModelServingProvisionedThroughputAiGatewayUsageTrackingConfig
    Block with configuration for payload logging using inference tables. For details see the description of auto_capture_config block above.
    fallbackConfig Property Map
    guardrails Property Map
    Block with configuration for AI Guardrails to prevent unwanted data and unsafe data in requests and responses. Consists of the following attributes:
    inferenceTableConfig Property Map
    Block describing the configuration of usage tracking. Consists of the following attributes:
    rateLimits List<Property Map>
    Block describing rate limits for AI gateway. For details see the description of rate_limits block above.
    usageTrackingConfig Property Map
    Block with configuration for payload logging using inference tables. For details see the description of auto_capture_config block above.

    ModelServingProvisionedThroughputAiGatewayFallbackConfig, ModelServingProvisionedThroughputAiGatewayFallbackConfigArgs

    Enabled bool
    boolean flag specifying if usage tracking is enabled.
    Enabled bool
    boolean flag specifying if usage tracking is enabled.
    enabled Boolean
    boolean flag specifying if usage tracking is enabled.
    enabled boolean
    boolean flag specifying if usage tracking is enabled.
    enabled bool
    boolean flag specifying if usage tracking is enabled.
    enabled Boolean
    boolean flag specifying if usage tracking is enabled.

    ModelServingProvisionedThroughputAiGatewayGuardrails, ModelServingProvisionedThroughputAiGatewayGuardrailsArgs

    Input ModelServingProvisionedThroughputAiGatewayGuardrailsInput
    A block with configuration for input guardrail filters:
    Output ModelServingProvisionedThroughputAiGatewayGuardrailsOutput
    A block with configuration for output guardrail filters. Has the same structure as input block.
    Input ModelServingProvisionedThroughputAiGatewayGuardrailsInputType
    A block with configuration for input guardrail filters:
    Output ModelServingProvisionedThroughputAiGatewayGuardrailsOutputType
    A block with configuration for output guardrail filters. Has the same structure as input block.
    input ModelServingProvisionedThroughputAiGatewayGuardrailsInput
    A block with configuration for input guardrail filters:
    output ModelServingProvisionedThroughputAiGatewayGuardrailsOutput
    A block with configuration for output guardrail filters. Has the same structure as input block.
    input ModelServingProvisionedThroughputAiGatewayGuardrailsInput
    A block with configuration for input guardrail filters:
    output ModelServingProvisionedThroughputAiGatewayGuardrailsOutput
    A block with configuration for output guardrail filters. Has the same structure as input block.
    input ModelServingProvisionedThroughputAiGatewayGuardrailsInput
    A block with configuration for input guardrail filters:
    output ModelServingProvisionedThroughputAiGatewayGuardrailsOutput
    A block with configuration for output guardrail filters. Has the same structure as input block.
    input Property Map
    A block with configuration for input guardrail filters:
    output Property Map
    A block with configuration for output guardrail filters. Has the same structure as input block.

    ModelServingProvisionedThroughputAiGatewayGuardrailsInput, ModelServingProvisionedThroughputAiGatewayGuardrailsInputArgs

    InvalidKeywords List<string>
    List of invalid keywords. AI guardrail uses keyword or string matching to decide if the keyword exists in the request or response content.
    Pii ModelServingProvisionedThroughputAiGatewayGuardrailsInputPii
    Block with configuration for guardrail PII filter:
    Safety bool
    the boolean flag that indicates whether the safety filter is enabled.
    ValidTopics List<string>
    The list of allowed topics. Given a chat request, this guardrail flags the request if its topic is not in the allowed topics.
    InvalidKeywords []string
    List of invalid keywords. AI guardrail uses keyword or string matching to decide if the keyword exists in the request or response content.
    Pii ModelServingProvisionedThroughputAiGatewayGuardrailsInputPii
    Block with configuration for guardrail PII filter:
    Safety bool
    the boolean flag that indicates whether the safety filter is enabled.
    ValidTopics []string
    The list of allowed topics. Given a chat request, this guardrail flags the request if its topic is not in the allowed topics.
    invalidKeywords List<String>
    List of invalid keywords. AI guardrail uses keyword or string matching to decide if the keyword exists in the request or response content.
    pii ModelServingProvisionedThroughputAiGatewayGuardrailsInputPii
    Block with configuration for guardrail PII filter:
    safety Boolean
    the boolean flag that indicates whether the safety filter is enabled.
    validTopics List<String>
    The list of allowed topics. Given a chat request, this guardrail flags the request if its topic is not in the allowed topics.
    invalidKeywords string[]
    List of invalid keywords. AI guardrail uses keyword or string matching to decide if the keyword exists in the request or response content.
    pii ModelServingProvisionedThroughputAiGatewayGuardrailsInputPii
    Block with configuration for guardrail PII filter:
    safety boolean
    the boolean flag that indicates whether the safety filter is enabled.
    validTopics string[]
    The list of allowed topics. Given a chat request, this guardrail flags the request if its topic is not in the allowed topics.
    invalid_keywords Sequence[str]
    List of invalid keywords. AI guardrail uses keyword or string matching to decide if the keyword exists in the request or response content.
    pii ModelServingProvisionedThroughputAiGatewayGuardrailsInputPii
    Block with configuration for guardrail PII filter:
    safety bool
    the boolean flag that indicates whether the safety filter is enabled.
    valid_topics Sequence[str]
    The list of allowed topics. Given a chat request, this guardrail flags the request if its topic is not in the allowed topics.
    invalidKeywords List<String>
    List of invalid keywords. AI guardrail uses keyword or string matching to decide if the keyword exists in the request or response content.
    pii Property Map
    Block with configuration for guardrail PII filter:
    safety Boolean
    the boolean flag that indicates whether the safety filter is enabled.
    validTopics List<String>
    The list of allowed topics. Given a chat request, this guardrail flags the request if its topic is not in the allowed topics.

    ModelServingProvisionedThroughputAiGatewayGuardrailsInputPii, ModelServingProvisionedThroughputAiGatewayGuardrailsInputPiiArgs

    Behavior string
    a string that describes the behavior for PII filter. Currently only BLOCK value is supported.
    Behavior string
    a string that describes the behavior for PII filter. Currently only BLOCK value is supported.
    behavior String
    a string that describes the behavior for PII filter. Currently only BLOCK value is supported.
    behavior string
    a string that describes the behavior for PII filter. Currently only BLOCK value is supported.
    behavior str
    a string that describes the behavior for PII filter. Currently only BLOCK value is supported.
    behavior String
    a string that describes the behavior for PII filter. Currently only BLOCK value is supported.

    ModelServingProvisionedThroughputAiGatewayGuardrailsOutput, ModelServingProvisionedThroughputAiGatewayGuardrailsOutputArgs

    InvalidKeywords List<string>
    List of invalid keywords. AI guardrail uses keyword or string matching to decide if the keyword exists in the request or response content.
    Pii ModelServingProvisionedThroughputAiGatewayGuardrailsOutputPii
    Block with configuration for guardrail PII filter:
    Safety bool
    the boolean flag that indicates whether the safety filter is enabled.
    ValidTopics List<string>
    The list of allowed topics. Given a chat request, this guardrail flags the request if its topic is not in the allowed topics.
    InvalidKeywords []string
    List of invalid keywords. AI guardrail uses keyword or string matching to decide if the keyword exists in the request or response content.
    Pii ModelServingProvisionedThroughputAiGatewayGuardrailsOutputPii
    Block with configuration for guardrail PII filter:
    Safety bool
    the boolean flag that indicates whether the safety filter is enabled.
    ValidTopics []string
    The list of allowed topics. Given a chat request, this guardrail flags the request if its topic is not in the allowed topics.
    invalidKeywords List<String>
    List of invalid keywords. AI guardrail uses keyword or string matching to decide if the keyword exists in the request or response content.
    pii ModelServingProvisionedThroughputAiGatewayGuardrailsOutputPii
    Block with configuration for guardrail PII filter:
    safety Boolean
    the boolean flag that indicates whether the safety filter is enabled.
    validTopics List<String>
    The list of allowed topics. Given a chat request, this guardrail flags the request if its topic is not in the allowed topics.
    invalidKeywords string[]
    List of invalid keywords. AI guardrail uses keyword or string matching to decide if the keyword exists in the request or response content.
    pii ModelServingProvisionedThroughputAiGatewayGuardrailsOutputPii
    Block with configuration for guardrail PII filter:
    safety boolean
    the boolean flag that indicates whether the safety filter is enabled.
    validTopics string[]
    The list of allowed topics. Given a chat request, this guardrail flags the request if its topic is not in the allowed topics.
    invalid_keywords Sequence[str]
    List of invalid keywords. AI guardrail uses keyword or string matching to decide if the keyword exists in the request or response content.
    pii ModelServingProvisionedThroughputAiGatewayGuardrailsOutputPii
    Block with configuration for guardrail PII filter:
    safety bool
    the boolean flag that indicates whether the safety filter is enabled.
    valid_topics Sequence[str]
    The list of allowed topics. Given a chat request, this guardrail flags the request if its topic is not in the allowed topics.
    invalidKeywords List<String>
    List of invalid keywords. AI guardrail uses keyword or string matching to decide if the keyword exists in the request or response content.
    pii Property Map
    Block with configuration for guardrail PII filter:
    safety Boolean
    the boolean flag that indicates whether the safety filter is enabled.
    validTopics List<String>
    The list of allowed topics. Given a chat request, this guardrail flags the request if its topic is not in the allowed topics.

    ModelServingProvisionedThroughputAiGatewayGuardrailsOutputPii, ModelServingProvisionedThroughputAiGatewayGuardrailsOutputPiiArgs

    Behavior string
    a string that describes the behavior for PII filter. Currently only BLOCK value is supported.
    Behavior string
    a string that describes the behavior for PII filter. Currently only BLOCK value is supported.
    behavior String
    a string that describes the behavior for PII filter. Currently only BLOCK value is supported.
    behavior string
    a string that describes the behavior for PII filter. Currently only BLOCK value is supported.
    behavior str
    a string that describes the behavior for PII filter. Currently only BLOCK value is supported.
    behavior String
    a string that describes the behavior for PII filter. Currently only BLOCK value is supported.

    ModelServingProvisionedThroughputAiGatewayInferenceTableConfig, ModelServingProvisionedThroughputAiGatewayInferenceTableConfigArgs

    CatalogName string
    Enabled bool
    boolean flag specifying if usage tracking is enabled.
    SchemaName string
    TableNamePrefix string
    CatalogName string
    Enabled bool
    boolean flag specifying if usage tracking is enabled.
    SchemaName string
    TableNamePrefix string
    catalogName String
    enabled Boolean
    boolean flag specifying if usage tracking is enabled.
    schemaName String
    tableNamePrefix String
    catalogName string
    enabled boolean
    boolean flag specifying if usage tracking is enabled.
    schemaName string
    tableNamePrefix string
    catalog_name str
    enabled bool
    boolean flag specifying if usage tracking is enabled.
    schema_name str
    table_name_prefix str
    catalogName String
    enabled Boolean
    boolean flag specifying if usage tracking is enabled.
    schemaName String
    tableNamePrefix String

    ModelServingProvisionedThroughputAiGatewayRateLimit, ModelServingProvisionedThroughputAiGatewayRateLimitArgs

    Calls int
    RenewalPeriod string
    Key string
    The key field for a tag.
    Calls int
    RenewalPeriod string
    Key string
    The key field for a tag.
    calls Integer
    renewalPeriod String
    key String
    The key field for a tag.
    calls number
    renewalPeriod string
    key string
    The key field for a tag.
    calls int
    renewal_period str
    key str
    The key field for a tag.
    calls Number
    renewalPeriod String
    key String
    The key field for a tag.

    ModelServingProvisionedThroughputAiGatewayUsageTrackingConfig, ModelServingProvisionedThroughputAiGatewayUsageTrackingConfigArgs

    Enabled bool
    boolean flag specifying if usage tracking is enabled.
    Enabled bool
    boolean flag specifying if usage tracking is enabled.
    enabled Boolean
    boolean flag specifying if usage tracking is enabled.
    enabled boolean
    boolean flag specifying if usage tracking is enabled.
    enabled bool
    boolean flag specifying if usage tracking is enabled.
    enabled Boolean
    boolean flag specifying if usage tracking is enabled.

    ModelServingProvisionedThroughputConfig, ModelServingProvisionedThroughputConfigArgs

    ServedEntities List<ModelServingProvisionedThroughputConfigServedEntity>
    A list of served entities for the endpoint to serve.
    TrafficConfig ModelServingProvisionedThroughputConfigTrafficConfig
    A single block represents the traffic split configuration amongst the served models.
    ServedEntities []ModelServingProvisionedThroughputConfigServedEntity
    A list of served entities for the endpoint to serve.
    TrafficConfig ModelServingProvisionedThroughputConfigTrafficConfig
    A single block represents the traffic split configuration amongst the served models.
    servedEntities List<ModelServingProvisionedThroughputConfigServedEntity>
    A list of served entities for the endpoint to serve.
    trafficConfig ModelServingProvisionedThroughputConfigTrafficConfig
    A single block represents the traffic split configuration amongst the served models.
    servedEntities ModelServingProvisionedThroughputConfigServedEntity[]
    A list of served entities for the endpoint to serve.
    trafficConfig ModelServingProvisionedThroughputConfigTrafficConfig
    A single block represents the traffic split configuration amongst the served models.
    served_entities Sequence[ModelServingProvisionedThroughputConfigServedEntity]
    A list of served entities for the endpoint to serve.
    traffic_config ModelServingProvisionedThroughputConfigTrafficConfig
    A single block represents the traffic split configuration amongst the served models.
    servedEntities List<Property Map>
    A list of served entities for the endpoint to serve.
    trafficConfig Property Map
    A single block represents the traffic split configuration amongst the served models.

    ModelServingProvisionedThroughputConfigServedEntity, ModelServingProvisionedThroughputConfigServedEntityArgs

    EntityName string
    The full path of the UC model to be served, given in the form of catalog_name.schema_name.model_name.
    EntityVersion string
    The version of the model in UC to be served.
    ProvisionedModelUnits int
    The number of model units to be provisioned.
    Name string
    The name of a served entity. It must be unique across an endpoint. A served entity name can consist of alphanumeric characters, dashes, and underscores. If not specified for an external model, this field will be created from the entity_name and entity_version
    EntityName string
    The full path of the UC model to be served, given in the form of catalog_name.schema_name.model_name.
    EntityVersion string
    The version of the model in UC to be served.
    ProvisionedModelUnits int
    The number of model units to be provisioned.
    Name string
    The name of a served entity. It must be unique across an endpoint. A served entity name can consist of alphanumeric characters, dashes, and underscores. If not specified for an external model, this field will be created from the entity_name and entity_version
    entityName String
    The full path of the UC model to be served, given in the form of catalog_name.schema_name.model_name.
    entityVersion String
    The version of the model in UC to be served.
    provisionedModelUnits Integer
    The number of model units to be provisioned.
    name String
    The name of a served entity. It must be unique across an endpoint. A served entity name can consist of alphanumeric characters, dashes, and underscores. If not specified for an external model, this field will be created from the entity_name and entity_version
    entityName string
    The full path of the UC model to be served, given in the form of catalog_name.schema_name.model_name.
    entityVersion string
    The version of the model in UC to be served.
    provisionedModelUnits number
    The number of model units to be provisioned.
    name string
    The name of a served entity. It must be unique across an endpoint. A served entity name can consist of alphanumeric characters, dashes, and underscores. If not specified for an external model, this field will be created from the entity_name and entity_version
    entity_name str
    The full path of the UC model to be served, given in the form of catalog_name.schema_name.model_name.
    entity_version str
    The version of the model in UC to be served.
    provisioned_model_units int
    The number of model units to be provisioned.
    name str
    The name of a served entity. It must be unique across an endpoint. A served entity name can consist of alphanumeric characters, dashes, and underscores. If not specified for an external model, this field will be created from the entity_name and entity_version
    entityName String
    The full path of the UC model to be served, given in the form of catalog_name.schema_name.model_name.
    entityVersion String
    The version of the model in UC to be served.
    provisionedModelUnits Number
    The number of model units to be provisioned.
    name String
    The name of a served entity. It must be unique across an endpoint. A served entity name can consist of alphanumeric characters, dashes, and underscores. If not specified for an external model, this field will be created from the entity_name and entity_version

    ModelServingProvisionedThroughputConfigTrafficConfig, ModelServingProvisionedThroughputConfigTrafficConfigArgs

    Routes List<ModelServingProvisionedThroughputConfigTrafficConfigRoute>
    Each block represents a route that defines traffic to each served entity. Each served_entity block needs to have a corresponding routes block.
    Routes []ModelServingProvisionedThroughputConfigTrafficConfigRoute
    Each block represents a route that defines traffic to each served entity. Each served_entity block needs to have a corresponding routes block.
    routes List<ModelServingProvisionedThroughputConfigTrafficConfigRoute>
    Each block represents a route that defines traffic to each served entity. Each served_entity block needs to have a corresponding routes block.
    routes ModelServingProvisionedThroughputConfigTrafficConfigRoute[]
    Each block represents a route that defines traffic to each served entity. Each served_entity block needs to have a corresponding routes block.
    routes Sequence[ModelServingProvisionedThroughputConfigTrafficConfigRoute]
    Each block represents a route that defines traffic to each served entity. Each served_entity block needs to have a corresponding routes block.
    routes List<Property Map>
    Each block represents a route that defines traffic to each served entity. Each served_entity block needs to have a corresponding routes block.

    ModelServingProvisionedThroughputConfigTrafficConfigRoute, ModelServingProvisionedThroughputConfigTrafficConfigRouteArgs

    ServedModelName string
    TrafficPercentage int
    The percentage of endpoint traffic to send to this route. It must be an integer between 0 and 100 inclusive.
    ServedModelName string
    TrafficPercentage int
    The percentage of endpoint traffic to send to this route. It must be an integer between 0 and 100 inclusive.
    servedModelName String
    trafficPercentage Integer
    The percentage of endpoint traffic to send to this route. It must be an integer between 0 and 100 inclusive.
    servedModelName string
    trafficPercentage number
    The percentage of endpoint traffic to send to this route. It must be an integer between 0 and 100 inclusive.
    served_model_name str
    traffic_percentage int
    The percentage of endpoint traffic to send to this route. It must be an integer between 0 and 100 inclusive.
    servedModelName String
    trafficPercentage Number
    The percentage of endpoint traffic to send to this route. It must be an integer between 0 and 100 inclusive.

    ModelServingProvisionedThroughputTag, ModelServingProvisionedThroughputTagArgs

    Key string
    The key field for a tag.
    Value string
    The value field for a tag.
    Key string
    The key field for a tag.
    Value string
    The value field for a tag.
    key String
    The key field for a tag.
    value String
    The value field for a tag.
    key string
    The key field for a tag.
    value string
    The value field for a tag.
    key str
    The key field for a tag.
    value str
    The value field for a tag.
    key String
    The key field for a tag.
    value String
    The value field for a tag.

    Import

    The model serving provisioned throughput resource can be imported using the name of the endpoint:

    hcl

    import {

    to = databricks_model_serving_provisioned_throughput.this

    id = “”

    }

    $ pulumi import databricks:index/modelServingProvisionedThroughput:ModelServingProvisionedThroughput Alternatively, when using Pulumi version 1.4 or earlier, import using the command:

    bash

    $ pulumi import databricks:index/modelServingProvisionedThroughput:ModelServingProvisionedThroughput this <model-serving-endpoint-name>

    To learn more about importing existing cloud resources, see Importing resources.

    Package Details

    Repository
    databricks pulumi/pulumi-databricks
    License
    Apache-2.0
    Notes
    This Pulumi package is based on the databricks Terraform Provider.
    databricks logo
    Databricks v1.71.0 published on Monday, Jun 9, 2025 by Pulumi
    pulumi/pulumi-databricks