Sign in Dashboard Get started
  1. Registry
  2. Packages
  3. Databricks Provider
  4. API Docs
  5. AiGatewayModelService
Viewing docs for Databricks v1.107.0
published on Tuesday, Aug 25, 2026 by Pulumi
Schema (JSON)
pulumi/pulumi-databricks

databricks.AiGatewayModelService

databricks logo databricks logo
Viewing docs for Databricks v1.107.0
published on Tuesday, Aug 25, 2026 by Pulumi
Schema (JSON)
pulumi/pulumi-databricks

    Public Beta

    API Documentation

    Create AiGatewayModelService Resource

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

    Constructor syntax

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

@overload
def AiGatewayModelService(resource_name: str,
                          opts: Optional[ResourceOptions] = None,
                          model_service_id: Optional[str] = None,
                          parent: Optional[str] = None,
                          comment: Optional[str] = None,
                          config: Optional[AiGatewayModelServiceConfigArgs] = None,
                          owner: Optional[str] = None,
                          provider_config: Optional[AiGatewayModelServiceProviderConfigArgs] = None)
    func NewAiGatewayModelService(ctx *Context, name string, args AiGatewayModelServiceArgs, opts ...ResourceOption) (*AiGatewayModelService, error)
    public AiGatewayModelService(string name, AiGatewayModelServiceArgs args, CustomResourceOptions? opts = null)
    public AiGatewayModelService(String name, AiGatewayModelServiceArgs args)
public AiGatewayModelService(String name, AiGatewayModelServiceArgs args, CustomResourceOptions options)

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


    resource "databricks_ai_gateway_model_service" "name" {
    # resource properties
}

    Parameters

    name string
    The unique name of the resource.
    args AiGatewayModelServiceArgs
    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 AiGatewayModelServiceArgs
    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 AiGatewayModelServiceArgs
    The arguments to resource properties.
    opts ResourceOption
    Bag of options to control resource's behavior.
    name string
    The unique name of the resource.
    args AiGatewayModelServiceArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    name String
    The unique name of the resource.
    args AiGatewayModelServiceArgs
    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 aiGatewayModelServiceResource = new Databricks.AiGatewayModelService("aiGatewayModelServiceResource", new()
{
    ModelServiceId = "string",
    Parent = "string",
    Comment = "string",
    Config = new Databricks.Inputs.AiGatewayModelServiceConfigArgs
    {
        InferenceTable = new Databricks.Inputs.AiGatewayModelServiceConfigInferenceTableArgs
        {
            Parent = "string",
            Disabled = false,
            IsDeleted = false,
            Table = "string",
            TableNamePrefix = "string",
        },
        RateLimits = new[]
        {
            new Databricks.Inputs.AiGatewayModelServiceConfigRateLimitArgs
            {
                Key = "string",
                RenewalPeriod = "string",
                Principal = "string",
                RequestTagKey = "string",
                RequestTagValue = "string",
                Requests = 0,
                Tokens = 0,
            },
        },
        Routing = new Databricks.Inputs.AiGatewayModelServiceConfigRoutingArgs
        {
            Destinations = new[]
            {
                new Databricks.Inputs.AiGatewayModelServiceConfigRoutingDestinationArgs
                {
                    DestinationType = "string",
                    Name = "string",
                    ExternalModelConfig = new Databricks.Inputs.AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigArgs
                    {
                        ModelProviderService = "string",
                        Target = new Databricks.Inputs.AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTargetArgs
                        {
                            Model = "string",
                            NativeApiTypes = new[]
                            {
                                "string",
                            },
                        },
                    },
                    IsDeleted = false,
                    PayPerTokenConfig = new Databricks.Inputs.AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfigArgs
                    {
                        Model = "string",
                    },
                    ProvisionedThroughputConfig = new Databricks.Inputs.AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfigArgs
                    {
                        ModelServingEndpoint = "string",
                        Model = "string",
                    },
                    TrafficPercentage = 0,
                },
            },
            Fallback = new Databricks.Inputs.AiGatewayModelServiceConfigRoutingFallbackArgs
            {
                Destinations = new[]
                {
                    new Databricks.Inputs.AiGatewayModelServiceConfigRoutingFallbackDestinationArgs
                    {
                        DestinationType = "string",
                        Name = "string",
                        ExternalModelConfig = new Databricks.Inputs.AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigArgs
                        {
                            ModelProviderService = "string",
                            Target = new Databricks.Inputs.AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTargetArgs
                            {
                                Model = "string",
                                NativeApiTypes = new[]
                                {
                                    "string",
                                },
                            },
                        },
                        IsDeleted = false,
                        PayPerTokenConfig = new Databricks.Inputs.AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfigArgs
                        {
                            Model = "string",
                        },
                        ProvisionedThroughputConfig = new Databricks.Inputs.AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfigArgs
                        {
                            ModelServingEndpoint = "string",
                            Model = "string",
                        },
                        TrafficPercentage = 0,
                    },
                },
            },
            FirstTokenTimeout = "string",
            TrafficSplitting = null,
        },
    },
    Owner = "string",
    ProviderConfig = new Databricks.Inputs.AiGatewayModelServiceProviderConfigArgs
    {
        WorkspaceId = "string",
    },
});

    example, err := databricks.NewAiGatewayModelService(ctx, "aiGatewayModelServiceResource", &databricks.AiGatewayModelServiceArgs{
	ModelServiceId: pulumi.String("string"),
	Parent:         pulumi.String("string"),
	Comment:        pulumi.String("string"),
	Config: &databricks.AiGatewayModelServiceConfigArgs{
		InferenceTable: &databricks.AiGatewayModelServiceConfigInferenceTableArgs{
			Parent:          pulumi.String("string"),
			Disabled:        pulumi.Bool(false),
			IsDeleted:       pulumi.Bool(false),
			Table:           pulumi.String("string"),
			TableNamePrefix: pulumi.String("string"),
		},
		RateLimits: databricks.AiGatewayModelServiceConfigRateLimitArray{
			&databricks.AiGatewayModelServiceConfigRateLimitArgs{
				Key:             pulumi.String("string"),
				RenewalPeriod:   pulumi.String("string"),
				Principal:       pulumi.String("string"),
				RequestTagKey:   pulumi.String("string"),
				RequestTagValue: pulumi.String("string"),
				Requests:        pulumi.Int(0),
				Tokens:          pulumi.Int(0),
			},
		},
		Routing: &databricks.AiGatewayModelServiceConfigRoutingArgs{
			Destinations: databricks.AiGatewayModelServiceConfigRoutingDestinationArray{
				&databricks.AiGatewayModelServiceConfigRoutingDestinationArgs{
					DestinationType: pulumi.String("string"),
					Name:            pulumi.String("string"),
					ExternalModelConfig: &databricks.AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigArgs{
						ModelProviderService: pulumi.String("string"),
						Target: &databricks.AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTargetArgs{
							Model: pulumi.String("string"),
							NativeApiTypes: pulumi.StringArray{
								pulumi.String("string"),
							},
						},
					},
					IsDeleted: pulumi.Bool(false),
					PayPerTokenConfig: &databricks.AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfigArgs{
						Model: pulumi.String("string"),
					},
					ProvisionedThroughputConfig: &databricks.AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfigArgs{
						ModelServingEndpoint: pulumi.String("string"),
						Model:                pulumi.String("string"),
					},
					TrafficPercentage: pulumi.Int(0),
				},
			},
			Fallback: &databricks.AiGatewayModelServiceConfigRoutingFallbackArgs{
				Destinations: databricks.AiGatewayModelServiceConfigRoutingFallbackDestinationArray{
					&databricks.AiGatewayModelServiceConfigRoutingFallbackDestinationArgs{
						DestinationType: pulumi.String("string"),
						Name:            pulumi.String("string"),
						ExternalModelConfig: &databricks.AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigArgs{
							ModelProviderService: pulumi.String("string"),
							Target: &databricks.AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTargetArgs{
								Model: pulumi.String("string"),
								NativeApiTypes: pulumi.StringArray{
									pulumi.String("string"),
								},
							},
						},
						IsDeleted: pulumi.Bool(false),
						PayPerTokenConfig: &databricks.AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfigArgs{
							Model: pulumi.String("string"),
						},
						ProvisionedThroughputConfig: &databricks.AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfigArgs{
							ModelServingEndpoint: pulumi.String("string"),
							Model:                pulumi.String("string"),
						},
						TrafficPercentage: pulumi.Int(0),
					},
				},
			},
			FirstTokenTimeout: pulumi.String("string"),
			TrafficSplitting:  &databricks.AiGatewayModelServiceConfigRoutingTrafficSplittingArgs{},
		},
	},
	Owner: pulumi.String("string"),
	ProviderConfig: &databricks.AiGatewayModelServiceProviderConfigArgs{
		WorkspaceId: pulumi.String("string"),
	},
})

    resource "databricks_ai_gateway_model_service" "aiGatewayModelServiceResource" {
  lifecycle {
    create_before_destroy = true
  }
  model_service_id = "string"
  parent           = "string"
  comment          = "string"
  config = {
    inference_table = {
      parent            = "string"
      disabled          = false
      is_deleted        = false
      table             = "string"
      table_name_prefix = "string"
    }
    rate_limits = [{
      key               = "string"
      renewal_period    = "string"
      principal         = "string"
      request_tag_key   = "string"
      request_tag_value = "string"
      requests          = 0
      tokens            = 0
    }]
    routing = {
      destinations = [{
        destination_type = "string"
        name             = "string"
        external_model_config = {
          model_provider_service = "string"
          target = {
            model            = "string"
            native_api_types = ["string"]
          }
        }
        is_deleted = false
        pay_per_token_config = {
          model = "string"
        }
        provisioned_throughput_config = {
          model_serving_endpoint = "string"
          model                  = "string"
        }
        traffic_percentage = 0
      }]
      fallback = {
        destinations = [{
          destination_type = "string"
          name             = "string"
          external_model_config = {
            model_provider_service = "string"
            target = {
              model            = "string"
              native_api_types = ["string"]
            }
          }
          is_deleted = false
          pay_per_token_config = {
            model = "string"
          }
          provisioned_throughput_config = {
            model_serving_endpoint = "string"
            model                  = "string"
          }
          traffic_percentage = 0
        }]
      }
      first_token_timeout = "string"
      traffic_splitting   = {}
    }
  }
  owner = "string"
  provider_config = {
    workspace_id = "string"
  }
}

    var aiGatewayModelServiceResource = new AiGatewayModelService("aiGatewayModelServiceResource", AiGatewayModelServiceArgs.builder()
    .modelServiceId("string")
    .parent("string")
    .comment("string")
    .config(AiGatewayModelServiceConfigArgs.builder()
        .inferenceTable(AiGatewayModelServiceConfigInferenceTableArgs.builder()
            .parent("string")
            .disabled(false)
            .isDeleted(false)
            .table("string")
            .tableNamePrefix("string")
            .build())
        .rateLimits(AiGatewayModelServiceConfigRateLimitArgs.builder()
            .key("string")
            .renewalPeriod("string")
            .principal("string")
            .requestTagKey("string")
            .requestTagValue("string")
            .requests(0)
            .tokens(0)
            .build())
        .routing(AiGatewayModelServiceConfigRoutingArgs.builder()
            .destinations(AiGatewayModelServiceConfigRoutingDestinationArgs.builder()
                .destinationType("string")
                .name("string")
                .externalModelConfig(AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigArgs.builder()
                    .modelProviderService("string")
                    .target(AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTargetArgs.builder()
                        .model("string")
                        .nativeApiTypes("string")
                        .build())
                    .build())
                .isDeleted(false)
                .payPerTokenConfig(AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfigArgs.builder()
                    .model("string")
                    .build())
                .provisionedThroughputConfig(AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfigArgs.builder()
                    .modelServingEndpoint("string")
                    .model("string")
                    .build())
                .trafficPercentage(0)
                .build())
            .fallback(AiGatewayModelServiceConfigRoutingFallbackArgs.builder()
                .destinations(AiGatewayModelServiceConfigRoutingFallbackDestinationArgs.builder()
                    .destinationType("string")
                    .name("string")
                    .externalModelConfig(AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigArgs.builder()
                        .modelProviderService("string")
                        .target(AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTargetArgs.builder()
                            .model("string")
                            .nativeApiTypes("string")
                            .build())
                        .build())
                    .isDeleted(false)
                    .payPerTokenConfig(AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfigArgs.builder()
                        .model("string")
                        .build())
                    .provisionedThroughputConfig(AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfigArgs.builder()
                        .modelServingEndpoint("string")
                        .model("string")
                        .build())
                    .trafficPercentage(0)
                    .build())
                .build())
            .firstTokenTimeout("string")
            .trafficSplitting(AiGatewayModelServiceConfigRoutingTrafficSplittingArgs.builder()
                .build())
            .build())
        .build())
    .owner("string")
    .providerConfig(AiGatewayModelServiceProviderConfigArgs.builder()
        .workspaceId("string")
        .build())
    .build());

    ai_gateway_model_service_resource = databricks.AiGatewayModelService("aiGatewayModelServiceResource",
    model_service_id="string",
    parent="string",
    comment="string",
    config={
        "inference_table": {
            "parent": "string",
            "disabled": False,
            "is_deleted": False,
            "table": "string",
            "table_name_prefix": "string",
        },
        "rate_limits": [{
            "key": "string",
            "renewal_period": "string",
            "principal": "string",
            "request_tag_key": "string",
            "request_tag_value": "string",
            "requests": 0,
            "tokens": 0,
        }],
        "routing": {
            "destinations": [{
                "destination_type": "string",
                "name": "string",
                "external_model_config": {
                    "model_provider_service": "string",
                    "target": {
                        "model": "string",
                        "native_api_types": ["string"],
                    },
                },
                "is_deleted": False,
                "pay_per_token_config": {
                    "model": "string",
                },
                "provisioned_throughput_config": {
                    "model_serving_endpoint": "string",
                    "model": "string",
                },
                "traffic_percentage": 0,
            }],
            "fallback": {
                "destinations": [{
                    "destination_type": "string",
                    "name": "string",
                    "external_model_config": {
                        "model_provider_service": "string",
                        "target": {
                            "model": "string",
                            "native_api_types": ["string"],
                        },
                    },
                    "is_deleted": False,
                    "pay_per_token_config": {
                        "model": "string",
                    },
                    "provisioned_throughput_config": {
                        "model_serving_endpoint": "string",
                        "model": "string",
                    },
                    "traffic_percentage": 0,
                }],
            },
            "first_token_timeout": "string",
            "traffic_splitting": {},
        },
    },
    owner="string",
    provider_config={
        "workspace_id": "string",
    })

    const aiGatewayModelServiceResource = new databricks.AiGatewayModelService("aiGatewayModelServiceResource", {
    modelServiceId: "string",
    parent: "string",
    comment: "string",
    config: {
        inferenceTable: {
            parent: "string",
            disabled: false,
            isDeleted: false,
            table: "string",
            tableNamePrefix: "string",
        },
        rateLimits: [{
            key: "string",
            renewalPeriod: "string",
            principal: "string",
            requestTagKey: "string",
            requestTagValue: "string",
            requests: 0,
            tokens: 0,
        }],
        routing: {
            destinations: [{
                destinationType: "string",
                name: "string",
                externalModelConfig: {
                    modelProviderService: "string",
                    target: {
                        model: "string",
                        nativeApiTypes: ["string"],
                    },
                },
                isDeleted: false,
                payPerTokenConfig: {
                    model: "string",
                },
                provisionedThroughputConfig: {
                    modelServingEndpoint: "string",
                    model: "string",
                },
                trafficPercentage: 0,
            }],
            fallback: {
                destinations: [{
                    destinationType: "string",
                    name: "string",
                    externalModelConfig: {
                        modelProviderService: "string",
                        target: {
                            model: "string",
                            nativeApiTypes: ["string"],
                        },
                    },
                    isDeleted: false,
                    payPerTokenConfig: {
                        model: "string",
                    },
                    provisionedThroughputConfig: {
                        modelServingEndpoint: "string",
                        model: "string",
                    },
                    trafficPercentage: 0,
                }],
            },
            firstTokenTimeout: "string",
            trafficSplitting: {},
        },
    },
    owner: "string",
    providerConfig: {
        workspaceId: "string",
    },
});

    type: databricks:AiGatewayModelService
properties:
    comment: string
    config:
        inferenceTable:
            disabled: false
            isDeleted: false
            parent: string
            table: string
            tableNamePrefix: string
        rateLimits:
            - key: string
              principal: string
              renewalPeriod: string
              requestTagKey: string
              requestTagValue: string
              requests: 0
              tokens: 0
        routing:
            destinations:
                - destinationType: string
                  externalModelConfig:
                    modelProviderService: string
                    target:
                        model: string
                        nativeApiTypes:
                            - string
                  isDeleted: false
                  name: string
                  payPerTokenConfig:
                    model: string
                  provisionedThroughputConfig:
                    model: string
                    modelServingEndpoint: string
                  trafficPercentage: 0
            fallback:
                destinations:
                    - destinationType: string
                      externalModelConfig:
                        modelProviderService: string
                        target:
                            model: string
                            nativeApiTypes:
                                - string
                      isDeleted: false
                      name: string
                      payPerTokenConfig:
                        model: string
                      provisionedThroughputConfig:
                        model: string
                        modelServingEndpoint: string
                      trafficPercentage: 0
            firstTokenTimeout: string
            trafficSplitting: {}
    modelServiceId: string
    owner: string
    parent: string
    providerConfig:
        workspaceId: string

    AiGatewayModelService 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 AiGatewayModelService resource accepts the following input properties:

    ModelServiceId string
    Name for the model service, e.g. "myModelService"
    Parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    Comment string
    User-provided description
    Config AiGatewayModelServiceConfig
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    Owner string
    The owner of the model service. Write-only; read owner via effective_owner
    ProviderConfig AiGatewayModelServiceProviderConfig
    Configure the provider for management through account provider.
    ModelServiceId string
    Name for the model service, e.g. "myModelService"
    Parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    Comment string
    User-provided description
    Config AiGatewayModelServiceConfigArgs
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    Owner string
    The owner of the model service. Write-only; read owner via effective_owner
    ProviderConfig AiGatewayModelServiceProviderConfigArgs
    Configure the provider for management through account provider.
    model_service_id string
    Name for the model service, e.g. "myModelService"
    parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    comment string
    User-provided description
    config object
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    owner string
    The owner of the model service. Write-only; read owner via effective_owner
    provider_config object
    Configure the provider for management through account provider.
    modelServiceId String
    Name for the model service, e.g. "myModelService"
    parent String
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    comment String
    User-provided description
    config AiGatewayModelServiceConfig
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    owner String
    The owner of the model service. Write-only; read owner via effective_owner
    providerConfig AiGatewayModelServiceProviderConfig
    Configure the provider for management through account provider.
    modelServiceId string
    Name for the model service, e.g. "myModelService"
    parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    comment string
    User-provided description
    config AiGatewayModelServiceConfig
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    owner string
    The owner of the model service. Write-only; read owner via effective_owner
    providerConfig AiGatewayModelServiceProviderConfig
    Configure the provider for management through account provider.
    model_service_id str
    Name for the model service, e.g. "myModelService"
    parent str
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    comment str
    User-provided description
    config AiGatewayModelServiceConfigArgs
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    owner str
    The owner of the model service. Write-only; read owner via effective_owner
    provider_config AiGatewayModelServiceProviderConfigArgs
    Configure the provider for management through account provider.
    modelServiceId String
    Name for the model service, e.g. "myModelService"
    parent String
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    comment String
    User-provided description
    config Property Map
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    owner String
    The owner of the model service. Write-only; read owner via effective_owner
    providerConfig Property Map
    Configure the provider for management through account provider.

    Outputs

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

    CreateTime string
    (string) - When the model service was created
    CreatedBy string
    (string) - Creator identity
    EffectiveOwner string
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    Etag string
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    Id string
    The provider-assigned unique ID for this managed resource.
    MetastoreId string
    (string) - Metastore hosting the model service
    Name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    SupportedApiTypes List<string>
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    UpdateTime string
    (string) - When the model service was last modified
    UpdatedBy string
    (string) - Identity of the last updater
    CreateTime string
    (string) - When the model service was created
    CreatedBy string
    (string) - Creator identity
    EffectiveOwner string
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    Etag string
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    Id string
    The provider-assigned unique ID for this managed resource.
    MetastoreId string
    (string) - Metastore hosting the model service
    Name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    SupportedApiTypes []string
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    UpdateTime string
    (string) - When the model service was last modified
    UpdatedBy string
    (string) - Identity of the last updater
    create_time string
    (string) - When the model service was created
    created_by string
    (string) - Creator identity
    effective_owner string
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    etag string
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    id string
    The provider-assigned unique ID for this managed resource.
    metastore_id string
    (string) - Metastore hosting the model service
    name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    supported_api_types list(string)
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    update_time string
    (string) - When the model service was last modified
    updated_by string
    (string) - Identity of the last updater
    createTime String
    (string) - When the model service was created
    createdBy String
    (string) - Creator identity
    effectiveOwner String
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    etag String
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    id String
    The provider-assigned unique ID for this managed resource.
    metastoreId String
    (string) - Metastore hosting the model service
    name String
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    supportedApiTypes List<String>
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    updateTime String
    (string) - When the model service was last modified
    updatedBy String
    (string) - Identity of the last updater
    createTime string
    (string) - When the model service was created
    createdBy string
    (string) - Creator identity
    effectiveOwner string
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    etag string
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    id string
    The provider-assigned unique ID for this managed resource.
    metastoreId string
    (string) - Metastore hosting the model service
    name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    supportedApiTypes string[]
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    updateTime string
    (string) - When the model service was last modified
    updatedBy string
    (string) - Identity of the last updater
    create_time str
    (string) - When the model service was created
    created_by str
    (string) - Creator identity
    effective_owner str
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    etag str
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    id str
    The provider-assigned unique ID for this managed resource.
    metastore_id str
    (string) - Metastore hosting the model service
    name str
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    supported_api_types Sequence[str]
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    update_time str
    (string) - When the model service was last modified
    updated_by str
    (string) - Identity of the last updater
    createTime String
    (string) - When the model service was created
    createdBy String
    (string) - Creator identity
    effectiveOwner String
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    etag String
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    id String
    The provider-assigned unique ID for this managed resource.
    metastoreId String
    (string) - Metastore hosting the model service
    name String
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    supportedApiTypes List<String>
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    updateTime String
    (string) - When the model service was last modified
    updatedBy String
    (string) - Identity of the last updater

    Look up Existing AiGatewayModelService Resource

    Get an existing AiGatewayModelService 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?: AiGatewayModelServiceState, opts?: CustomResourceOptions): AiGatewayModelService
    @staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        comment: Optional[str] = None,
        config: Optional[AiGatewayModelServiceConfigArgs] = None,
        create_time: Optional[str] = None,
        created_by: Optional[str] = None,
        effective_owner: Optional[str] = None,
        etag: Optional[str] = None,
        metastore_id: Optional[str] = None,
        model_service_id: Optional[str] = None,
        name: Optional[str] = None,
        owner: Optional[str] = None,
        parent: Optional[str] = None,
        provider_config: Optional[AiGatewayModelServiceProviderConfigArgs] = None,
        supported_api_types: Optional[Sequence[str]] = None,
        update_time: Optional[str] = None,
        updated_by: Optional[str] = None) -> AiGatewayModelService
    func GetAiGatewayModelService(ctx *Context, name string, id IDInput, state *AiGatewayModelServiceState, opts ...ResourceOption) (*AiGatewayModelService, error)
    public static AiGatewayModelService Get(string name, Input<string> id, AiGatewayModelServiceState? state, CustomResourceOptions? opts = null)
    public static AiGatewayModelService get(String name, Output<String> id, AiGatewayModelServiceState state, CustomResourceOptions options)
    resources:  _:    type: databricks:AiGatewayModelService    get:      id: ${id}
    import {
  to = databricks_ai_gateway_model_service.example
  id = "${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:
    Comment string
    User-provided description
    Config AiGatewayModelServiceConfig
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    CreateTime string
    (string) - When the model service was created
    CreatedBy string
    (string) - Creator identity
    EffectiveOwner string
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    Etag string
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    MetastoreId string
    (string) - Metastore hosting the model service
    ModelServiceId string
    Name for the model service, e.g. "myModelService"
    Name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    Owner string
    The owner of the model service. Write-only; read owner via effective_owner
    Parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    ProviderConfig AiGatewayModelServiceProviderConfig
    Configure the provider for management through account provider.
    SupportedApiTypes List<string>
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    UpdateTime string
    (string) - When the model service was last modified
    UpdatedBy string
    (string) - Identity of the last updater
    Comment string
    User-provided description
    Config AiGatewayModelServiceConfigArgs
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    CreateTime string
    (string) - When the model service was created
    CreatedBy string
    (string) - Creator identity
    EffectiveOwner string
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    Etag string
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    MetastoreId string
    (string) - Metastore hosting the model service
    ModelServiceId string
    Name for the model service, e.g. "myModelService"
    Name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    Owner string
    The owner of the model service. Write-only; read owner via effective_owner
    Parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    ProviderConfig AiGatewayModelServiceProviderConfigArgs
    Configure the provider for management through account provider.
    SupportedApiTypes []string
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    UpdateTime string
    (string) - When the model service was last modified
    UpdatedBy string
    (string) - Identity of the last updater
    comment string
    User-provided description
    config object
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    create_time string
    (string) - When the model service was created
    created_by string
    (string) - Creator identity
    effective_owner string
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    etag string
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    metastore_id string
    (string) - Metastore hosting the model service
    model_service_id string
    Name for the model service, e.g. "myModelService"
    name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    owner string
    The owner of the model service. Write-only; read owner via effective_owner
    parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    provider_config object
    Configure the provider for management through account provider.
    supported_api_types list(string)
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    update_time string
    (string) - When the model service was last modified
    updated_by string
    (string) - Identity of the last updater
    comment String
    User-provided description
    config AiGatewayModelServiceConfig
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    createTime String
    (string) - When the model service was created
    createdBy String
    (string) - Creator identity
    effectiveOwner String
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    etag String
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    metastoreId String
    (string) - Metastore hosting the model service
    modelServiceId String
    Name for the model service, e.g. "myModelService"
    name String
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    owner String
    The owner of the model service. Write-only; read owner via effective_owner
    parent String
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    providerConfig AiGatewayModelServiceProviderConfig
    Configure the provider for management through account provider.
    supportedApiTypes List<String>
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    updateTime String
    (string) - When the model service was last modified
    updatedBy String
    (string) - Identity of the last updater
    comment string
    User-provided description
    config AiGatewayModelServiceConfig
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    createTime string
    (string) - When the model service was created
    createdBy string
    (string) - Creator identity
    effectiveOwner string
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    etag string
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    metastoreId string
    (string) - Metastore hosting the model service
    modelServiceId string
    Name for the model service, e.g. "myModelService"
    name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    owner string
    The owner of the model service. Write-only; read owner via effective_owner
    parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    providerConfig AiGatewayModelServiceProviderConfig
    Configure the provider for management through account provider.
    supportedApiTypes string[]
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    updateTime string
    (string) - When the model service was last modified
    updatedBy string
    (string) - Identity of the last updater
    comment str
    User-provided description
    config AiGatewayModelServiceConfigArgs
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    create_time str
    (string) - When the model service was created
    created_by str
    (string) - Creator identity
    effective_owner str
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    etag str
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    metastore_id str
    (string) - Metastore hosting the model service
    model_service_id str
    Name for the model service, e.g. "myModelService"
    name str
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    owner str
    The owner of the model service. Write-only; read owner via effective_owner
    parent str
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    provider_config AiGatewayModelServiceProviderConfigArgs
    Configure the provider for management through account provider.
    supported_api_types Sequence[str]
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    update_time str
    (string) - When the model service was last modified
    updated_by str
    (string) - Identity of the last updater
    comment String
    User-provided description
    config Property Map
    Operational configuration: destinations, routing, rate limits, inference table. Required on CreateModelService; on UpdateModelService it is required only when config (or a config.* subpath) appears in updateMask
    createTime String
    (string) - When the model service was created
    createdBy String
    (string) - Creator identity
    effectiveOwner String
    (string) - The resolved owner of the ModelService. Falls back to the caller's identity when owner is not explicitly set on creation
    etag String
    (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
    metastoreId String
    (string) - Metastore hosting the model service
    modelServiceId String
    Name for the model service, e.g. "myModelService"
    name String
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    owner String
    The owner of the model service. Write-only; read owner via effective_owner
    parent String
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    providerConfig Property Map
    Configure the provider for management through account provider.
    supportedApiTypes List<String>
    (list of string) - Unified API types this endpoint supports (e.g. "chat", "embeddings", "completions"). Derived from the destinations' backing models / providers at read time
    updateTime String
    (string) - When the model service was last modified
    updatedBy String
    (string) - Identity of the last updater

    Supporting Types

    AiGatewayModelServiceConfig, AiGatewayModelServiceConfigArgs

    InferenceTable AiGatewayModelServiceConfigInferenceTable
    Inference table config for payload logging
    RateLimits List<AiGatewayModelServiceConfigRateLimit>
    Rate limits applied to requests routed through this model service
    Routing AiGatewayModelServiceConfigRouting
    Routing configuration: destinations, routing strategy, and fallback
    InferenceTable AiGatewayModelServiceConfigInferenceTable
    Inference table config for payload logging
    RateLimits []AiGatewayModelServiceConfigRateLimit
    Rate limits applied to requests routed through this model service
    Routing AiGatewayModelServiceConfigRouting
    Routing configuration: destinations, routing strategy, and fallback
    inference_table object
    Inference table config for payload logging
    rate_limits list(object)
    Rate limits applied to requests routed through this model service
    routing object
    Routing configuration: destinations, routing strategy, and fallback
    inferenceTable AiGatewayModelServiceConfigInferenceTable
    Inference table config for payload logging
    rateLimits List<AiGatewayModelServiceConfigRateLimit>
    Rate limits applied to requests routed through this model service
    routing AiGatewayModelServiceConfigRouting
    Routing configuration: destinations, routing strategy, and fallback
    inferenceTable AiGatewayModelServiceConfigInferenceTable
    Inference table config for payload logging
    rateLimits AiGatewayModelServiceConfigRateLimit[]
    Rate limits applied to requests routed through this model service
    routing AiGatewayModelServiceConfigRouting
    Routing configuration: destinations, routing strategy, and fallback
    inference_table AiGatewayModelServiceConfigInferenceTable
    Inference table config for payload logging
    rate_limits Sequence[AiGatewayModelServiceConfigRateLimit]
    Rate limits applied to requests routed through this model service
    routing AiGatewayModelServiceConfigRouting
    Routing configuration: destinations, routing strategy, and fallback
    inferenceTable Property Map
    Inference table config for payload logging
    rateLimits List<Property Map>
    Rate limits applied to requests routed through this model service
    routing Property Map
    Routing configuration: destinations, routing strategy, and fallback

    AiGatewayModelServiceConfigInferenceTable, AiGatewayModelServiceConfigInferenceTableArgs

    Parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    Disabled bool
    Indicates whether payload logging is disabled (opt-out). Unset means that payload logging is active (the on-by-default state coincides with the proto zero-value, so the server never fills this field for a client that leaves it unset). Set disabled = true to pause runtime logging while keeping the sub-message attached (preserving parent and tableNamePrefix for a later flip back to active). parent remains required either way
    IsDeleted bool
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    Table string
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    TableNamePrefix string
    Prefix for the inference-table's UC-registered name. The actual leaf name UC stores is <table_name_prefix>_payload; the _payload suffix is appended automatically. To find the actual UC table after Create, read the table field on the response. Defaults to <model_service_name>_payload when unset. Set at create time and immutable thereafter; changing it on an existing service is rejected
    Parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    Disabled bool
    Indicates whether payload logging is disabled (opt-out). Unset means that payload logging is active (the on-by-default state coincides with the proto zero-value, so the server never fills this field for a client that leaves it unset). Set disabled = true to pause runtime logging while keeping the sub-message attached (preserving parent and tableNamePrefix for a later flip back to active). parent remains required either way
    IsDeleted bool
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    Table string
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    TableNamePrefix string
    Prefix for the inference-table's UC-registered name. The actual leaf name UC stores is <table_name_prefix>_payload; the _payload suffix is appended automatically. To find the actual UC table after Create, read the table field on the response. Defaults to <model_service_name>_payload when unset. Set at create time and immutable thereafter; changing it on an existing service is rejected
    parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    disabled bool
    Indicates whether payload logging is disabled (opt-out). Unset means that payload logging is active (the on-by-default state coincides with the proto zero-value, so the server never fills this field for a client that leaves it unset). Set disabled = true to pause runtime logging while keeping the sub-message attached (preserving parent and tableNamePrefix for a later flip back to active). parent remains required either way
    is_deleted bool
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    table string
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    table_name_prefix string
    Prefix for the inference-table's UC-registered name. The actual leaf name UC stores is <table_name_prefix>_payload; the _payload suffix is appended automatically. To find the actual UC table after Create, read the table field on the response. Defaults to <model_service_name>_payload when unset. Set at create time and immutable thereafter; changing it on an existing service is rejected
    parent String
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    disabled Boolean
    Indicates whether payload logging is disabled (opt-out). Unset means that payload logging is active (the on-by-default state coincides with the proto zero-value, so the server never fills this field for a client that leaves it unset). Set disabled = true to pause runtime logging while keeping the sub-message attached (preserving parent and tableNamePrefix for a later flip back to active). parent remains required either way
    isDeleted Boolean
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    table String
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    tableNamePrefix String
    Prefix for the inference-table's UC-registered name. The actual leaf name UC stores is <table_name_prefix>_payload; the _payload suffix is appended automatically. To find the actual UC table after Create, read the table field on the response. Defaults to <model_service_name>_payload when unset. Set at create time and immutable thereafter; changing it on an existing service is rejected
    parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    disabled boolean
    Indicates whether payload logging is disabled (opt-out). Unset means that payload logging is active (the on-by-default state coincides with the proto zero-value, so the server never fills this field for a client that leaves it unset). Set disabled = true to pause runtime logging while keeping the sub-message attached (preserving parent and tableNamePrefix for a later flip back to active). parent remains required either way
    isDeleted boolean
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    table string
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    tableNamePrefix string
    Prefix for the inference-table's UC-registered name. The actual leaf name UC stores is <table_name_prefix>_payload; the _payload suffix is appended automatically. To find the actual UC table after Create, read the table field on the response. Defaults to <model_service_name>_payload when unset. Set at create time and immutable thereafter; changing it on an existing service is rejected
    parent str
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    disabled bool
    Indicates whether payload logging is disabled (opt-out). Unset means that payload logging is active (the on-by-default state coincides with the proto zero-value, so the server never fills this field for a client that leaves it unset). Set disabled = true to pause runtime logging while keeping the sub-message attached (preserving parent and tableNamePrefix for a later flip back to active). parent remains required either way
    is_deleted bool
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    table str
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    table_name_prefix str
    Prefix for the inference-table's UC-registered name. The actual leaf name UC stores is <table_name_prefix>_payload; the _payload suffix is appended automatically. To find the actual UC table after Create, read the table field on the response. Defaults to <model_service_name>_payload when unset. Set at create time and immutable thereafter; changing it on an existing service is rejected
    parent String
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    disabled Boolean
    Indicates whether payload logging is disabled (opt-out). Unset means that payload logging is active (the on-by-default state coincides with the proto zero-value, so the server never fills this field for a client that leaves it unset). Set disabled = true to pause runtime logging while keeping the sub-message attached (preserving parent and tableNamePrefix for a later flip back to active). parent remains required either way
    isDeleted Boolean
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    table String
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    tableNamePrefix String
    Prefix for the inference-table's UC-registered name. The actual leaf name UC stores is <table_name_prefix>_payload; the _payload suffix is appended automatically. To find the actual UC table after Create, read the table field on the response. Defaults to <model_service_name>_payload when unset. Set at create time and immutable thereafter; changing it on an existing service is rejected

    AiGatewayModelServiceConfigRateLimit, AiGatewayModelServiceConfigRateLimitArgs

    Key string
    Scope key. Determines whether principal is required. Possible values are: RATE_LIMIT_KEY_REQUEST_TAG, RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_SERVICE_PRINCIPAL, RATE_LIMIT_KEY_USER, RATE_LIMIT_KEY_USER_DEFAULT, RATE_LIMIT_KEY_USER_GROUP
    RenewalPeriod string
    Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
    Principal string
    Principal this limit applies to: user email, group name, or service principal application ID. Required unless key is RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_USER_DEFAULT, or RATE_LIMIT_KEY_REQUEST_TAG (which must not set a principal)
    RequestTagKey string
    Request tag key this limit applies to. Required when key is RATE_LIMIT_KEY_REQUEST_TAG, forbidden otherwise
    RequestTagValue string
    Request tag value this limit applies to. Only valid when key is RATE_LIMIT_KEY_REQUEST_TAG. Leave unset to apply the limit to every value of requestTagKey (an any-value default); a set value is a specific override for that value
    Requests int
    Max requests allowed within a renewal period. Leave unset for no request limit
    Tokens int
    Max tokens allowed within a renewal period. Leave unset for no token limit
    Key string
    Scope key. Determines whether principal is required. Possible values are: RATE_LIMIT_KEY_REQUEST_TAG, RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_SERVICE_PRINCIPAL, RATE_LIMIT_KEY_USER, RATE_LIMIT_KEY_USER_DEFAULT, RATE_LIMIT_KEY_USER_GROUP
    RenewalPeriod string
    Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
    Principal string
    Principal this limit applies to: user email, group name, or service principal application ID. Required unless key is RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_USER_DEFAULT, or RATE_LIMIT_KEY_REQUEST_TAG (which must not set a principal)
    RequestTagKey string
    Request tag key this limit applies to. Required when key is RATE_LIMIT_KEY_REQUEST_TAG, forbidden otherwise
    RequestTagValue string
    Request tag value this limit applies to. Only valid when key is RATE_LIMIT_KEY_REQUEST_TAG. Leave unset to apply the limit to every value of requestTagKey (an any-value default); a set value is a specific override for that value
    Requests int
    Max requests allowed within a renewal period. Leave unset for no request limit
    Tokens int
    Max tokens allowed within a renewal period. Leave unset for no token limit
    key string
    Scope key. Determines whether principal is required. Possible values are: RATE_LIMIT_KEY_REQUEST_TAG, RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_SERVICE_PRINCIPAL, RATE_LIMIT_KEY_USER, RATE_LIMIT_KEY_USER_DEFAULT, RATE_LIMIT_KEY_USER_GROUP
    renewal_period string
    Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
    principal string
    Principal this limit applies to: user email, group name, or service principal application ID. Required unless key is RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_USER_DEFAULT, or RATE_LIMIT_KEY_REQUEST_TAG (which must not set a principal)
    request_tag_key string
    Request tag key this limit applies to. Required when key is RATE_LIMIT_KEY_REQUEST_TAG, forbidden otherwise
    request_tag_value string
    Request tag value this limit applies to. Only valid when key is RATE_LIMIT_KEY_REQUEST_TAG. Leave unset to apply the limit to every value of requestTagKey (an any-value default); a set value is a specific override for that value
    requests number
    Max requests allowed within a renewal period. Leave unset for no request limit
    tokens number
    Max tokens allowed within a renewal period. Leave unset for no token limit
    key String
    Scope key. Determines whether principal is required. Possible values are: RATE_LIMIT_KEY_REQUEST_TAG, RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_SERVICE_PRINCIPAL, RATE_LIMIT_KEY_USER, RATE_LIMIT_KEY_USER_DEFAULT, RATE_LIMIT_KEY_USER_GROUP
    renewalPeriod String
    Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
    principal String
    Principal this limit applies to: user email, group name, or service principal application ID. Required unless key is RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_USER_DEFAULT, or RATE_LIMIT_KEY_REQUEST_TAG (which must not set a principal)
    requestTagKey String
    Request tag key this limit applies to. Required when key is RATE_LIMIT_KEY_REQUEST_TAG, forbidden otherwise
    requestTagValue String
    Request tag value this limit applies to. Only valid when key is RATE_LIMIT_KEY_REQUEST_TAG. Leave unset to apply the limit to every value of requestTagKey (an any-value default); a set value is a specific override for that value
    requests Integer
    Max requests allowed within a renewal period. Leave unset for no request limit
    tokens Integer
    Max tokens allowed within a renewal period. Leave unset for no token limit
    key string
    Scope key. Determines whether principal is required. Possible values are: RATE_LIMIT_KEY_REQUEST_TAG, RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_SERVICE_PRINCIPAL, RATE_LIMIT_KEY_USER, RATE_LIMIT_KEY_USER_DEFAULT, RATE_LIMIT_KEY_USER_GROUP
    renewalPeriod string
    Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
    principal string
    Principal this limit applies to: user email, group name, or service principal application ID. Required unless key is RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_USER_DEFAULT, or RATE_LIMIT_KEY_REQUEST_TAG (which must not set a principal)
    requestTagKey string
    Request tag key this limit applies to. Required when key is RATE_LIMIT_KEY_REQUEST_TAG, forbidden otherwise
    requestTagValue string
    Request tag value this limit applies to. Only valid when key is RATE_LIMIT_KEY_REQUEST_TAG. Leave unset to apply the limit to every value of requestTagKey (an any-value default); a set value is a specific override for that value
    requests number
    Max requests allowed within a renewal period. Leave unset for no request limit
    tokens number
    Max tokens allowed within a renewal period. Leave unset for no token limit
    key str
    Scope key. Determines whether principal is required. Possible values are: RATE_LIMIT_KEY_REQUEST_TAG, RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_SERVICE_PRINCIPAL, RATE_LIMIT_KEY_USER, RATE_LIMIT_KEY_USER_DEFAULT, RATE_LIMIT_KEY_USER_GROUP
    renewal_period str
    Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
    principal str
    Principal this limit applies to: user email, group name, or service principal application ID. Required unless key is RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_USER_DEFAULT, or RATE_LIMIT_KEY_REQUEST_TAG (which must not set a principal)
    request_tag_key str
    Request tag key this limit applies to. Required when key is RATE_LIMIT_KEY_REQUEST_TAG, forbidden otherwise
    request_tag_value str
    Request tag value this limit applies to. Only valid when key is RATE_LIMIT_KEY_REQUEST_TAG. Leave unset to apply the limit to every value of requestTagKey (an any-value default); a set value is a specific override for that value
    requests int
    Max requests allowed within a renewal period. Leave unset for no request limit
    tokens int
    Max tokens allowed within a renewal period. Leave unset for no token limit
    key String
    Scope key. Determines whether principal is required. Possible values are: RATE_LIMIT_KEY_REQUEST_TAG, RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_SERVICE_PRINCIPAL, RATE_LIMIT_KEY_USER, RATE_LIMIT_KEY_USER_DEFAULT, RATE_LIMIT_KEY_USER_GROUP
    renewalPeriod String
    Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
    principal String
    Principal this limit applies to: user email, group name, or service principal application ID. Required unless key is RATE_LIMIT_KEY_SERVICE, RATE_LIMIT_KEY_USER_DEFAULT, or RATE_LIMIT_KEY_REQUEST_TAG (which must not set a principal)
    requestTagKey String
    Request tag key this limit applies to. Required when key is RATE_LIMIT_KEY_REQUEST_TAG, forbidden otherwise
    requestTagValue String
    Request tag value this limit applies to. Only valid when key is RATE_LIMIT_KEY_REQUEST_TAG. Leave unset to apply the limit to every value of requestTagKey (an any-value default); a set value is a specific override for that value
    requests Number
    Max requests allowed within a renewal period. Leave unset for no request limit
    tokens Number
    Max tokens allowed within a renewal period. Leave unset for no token limit

    AiGatewayModelServiceConfigRouting, AiGatewayModelServiceConfigRoutingArgs

    Destinations List<AiGatewayModelServiceConfigRoutingDestination>
    Fallback AiGatewayModelServiceConfigRoutingFallback
    Fallback routing config, applied after primary destinations fail
    FirstTokenTimeout string
    Timeout for the first token of a streaming response. If a destination does not return its first token within this duration, AI Gateway aborts the attempt and fails over to the next destination. Applies to streaming requests only. Leave unset for no first-token timeout
    TrafficSplitting AiGatewayModelServiceConfigRoutingTrafficSplitting
    Marker message selecting request-based traffic splitting. Traffic is distributed according to each destination's trafficPercentage value; no configuration lives on this message itself
    Destinations []AiGatewayModelServiceConfigRoutingDestination
    Fallback AiGatewayModelServiceConfigRoutingFallback
    Fallback routing config, applied after primary destinations fail
    FirstTokenTimeout string
    Timeout for the first token of a streaming response. If a destination does not return its first token within this duration, AI Gateway aborts the attempt and fails over to the next destination. Applies to streaming requests only. Leave unset for no first-token timeout
    TrafficSplitting AiGatewayModelServiceConfigRoutingTrafficSplitting
    Marker message selecting request-based traffic splitting. Traffic is distributed according to each destination's trafficPercentage value; no configuration lives on this message itself
    destinations list(object)
    fallback object
    Fallback routing config, applied after primary destinations fail
    first_token_timeout string
    Timeout for the first token of a streaming response. If a destination does not return its first token within this duration, AI Gateway aborts the attempt and fails over to the next destination. Applies to streaming requests only. Leave unset for no first-token timeout
    traffic_splitting object
    Marker message selecting request-based traffic splitting. Traffic is distributed according to each destination's trafficPercentage value; no configuration lives on this message itself
    destinations List<AiGatewayModelServiceConfigRoutingDestination>
    fallback AiGatewayModelServiceConfigRoutingFallback
    Fallback routing config, applied after primary destinations fail
    firstTokenTimeout String
    Timeout for the first token of a streaming response. If a destination does not return its first token within this duration, AI Gateway aborts the attempt and fails over to the next destination. Applies to streaming requests only. Leave unset for no first-token timeout
    trafficSplitting AiGatewayModelServiceConfigRoutingTrafficSplitting
    Marker message selecting request-based traffic splitting. Traffic is distributed according to each destination's trafficPercentage value; no configuration lives on this message itself
    destinations AiGatewayModelServiceConfigRoutingDestination[]
    fallback AiGatewayModelServiceConfigRoutingFallback
    Fallback routing config, applied after primary destinations fail
    firstTokenTimeout string
    Timeout for the first token of a streaming response. If a destination does not return its first token within this duration, AI Gateway aborts the attempt and fails over to the next destination. Applies to streaming requests only. Leave unset for no first-token timeout
    trafficSplitting AiGatewayModelServiceConfigRoutingTrafficSplitting
    Marker message selecting request-based traffic splitting. Traffic is distributed according to each destination's trafficPercentage value; no configuration lives on this message itself
    destinations Sequence[AiGatewayModelServiceConfigRoutingDestination]
    fallback AiGatewayModelServiceConfigRoutingFallback
    Fallback routing config, applied after primary destinations fail
    first_token_timeout str
    Timeout for the first token of a streaming response. If a destination does not return its first token within this duration, AI Gateway aborts the attempt and fails over to the next destination. Applies to streaming requests only. Leave unset for no first-token timeout
    traffic_splitting AiGatewayModelServiceConfigRoutingTrafficSplitting
    Marker message selecting request-based traffic splitting. Traffic is distributed according to each destination's trafficPercentage value; no configuration lives on this message itself
    destinations List<Property Map>
    fallback Property Map
    Fallback routing config, applied after primary destinations fail
    firstTokenTimeout String
    Timeout for the first token of a streaming response. If a destination does not return its first token within this duration, AI Gateway aborts the attempt and fails over to the next destination. Applies to streaming requests only. Leave unset for no first-token timeout
    trafficSplitting Property Map
    Marker message selecting request-based traffic splitting. Traffic is distributed according to each destination's trafficPercentage value; no configuration lives on this message itself

    AiGatewayModelServiceConfigRoutingDestination, AiGatewayModelServiceConfigRoutingDestinationArgs

    DestinationType string
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    Name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    ExternalModelConfig AiGatewayModelServiceConfigRoutingDestinationExternalModelConfig
    IsDeleted bool
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    PayPerTokenConfig AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig
    ProvisionedThroughputConfig AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig
    TrafficPercentage int
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig
    DestinationType string
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    Name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    ExternalModelConfig AiGatewayModelServiceConfigRoutingDestinationExternalModelConfig
    IsDeleted bool
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    PayPerTokenConfig AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig
    ProvisionedThroughputConfig AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig
    TrafficPercentage int
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig
    destination_type string
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    external_model_config object
    is_deleted bool
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    pay_per_token_config object
    provisioned_throughput_config object
    traffic_percentage number
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig
    destinationType String
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    name String
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    externalModelConfig AiGatewayModelServiceConfigRoutingDestinationExternalModelConfig
    isDeleted Boolean
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    payPerTokenConfig AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig
    provisionedThroughputConfig AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig
    trafficPercentage Integer
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig
    destinationType string
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    externalModelConfig AiGatewayModelServiceConfigRoutingDestinationExternalModelConfig
    isDeleted boolean
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    payPerTokenConfig AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig
    provisionedThroughputConfig AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig
    trafficPercentage number
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig
    destination_type str
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    name str
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    external_model_config AiGatewayModelServiceConfigRoutingDestinationExternalModelConfig
    is_deleted bool
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    pay_per_token_config AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig
    provisioned_throughput_config AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig
    traffic_percentage int
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig
    destinationType String
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    name String
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    externalModelConfig Property Map
    isDeleted Boolean
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    payPerTokenConfig Property Map
    provisionedThroughputConfig Property Map
    trafficPercentage Number
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig

    AiGatewayModelServiceConfigRoutingDestinationExternalModelConfig, AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigArgs

    ModelProviderService string
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    Target AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time
    ModelProviderService string
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    Target AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time
    model_provider_service string
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    target object
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time
    modelProviderService String
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    target AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time
    modelProviderService string
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    target AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time
    model_provider_service str
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    target AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time
    modelProviderService String
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    target Property Map
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time

    AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget, AiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTargetArgs

    Model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    NativeApiTypes List<string>
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope
    Model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    NativeApiTypes []string
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope
    model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    native_api_types list(string)
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope
    model String
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    nativeApiTypes List<String>
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope
    model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    nativeApiTypes string[]
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope
    model str
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    native_api_types Sequence[str]
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope
    model String
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    nativeApiTypes List<String>
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope

    AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig, AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfigArgs

    Model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    Model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model String
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model str
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model String
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time

    AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig, AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfigArgs

    ModelServingEndpoint string
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    Model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    ModelServingEndpoint string
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    Model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model_serving_endpoint string
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    modelServingEndpoint String
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    model String
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    modelServingEndpoint string
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model_serving_endpoint str
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    model str
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    modelServingEndpoint String
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    model String
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time

    AiGatewayModelServiceConfigRoutingFallback, AiGatewayModelServiceConfigRoutingFallbackArgs

    AiGatewayModelServiceConfigRoutingFallbackDestination, AiGatewayModelServiceConfigRoutingFallbackDestinationArgs

    DestinationType string
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    Name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    ExternalModelConfig AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig
    IsDeleted bool
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    PayPerTokenConfig AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig
    ProvisionedThroughputConfig AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig
    TrafficPercentage int
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig
    DestinationType string
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    Name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    ExternalModelConfig AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig
    IsDeleted bool
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    PayPerTokenConfig AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig
    ProvisionedThroughputConfig AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig
    TrafficPercentage int
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig
    destination_type string
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    external_model_config object
    is_deleted bool
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    pay_per_token_config object
    provisioned_throughput_config object
    traffic_percentage number
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig
    destinationType String
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    name String
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    externalModelConfig AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig
    isDeleted Boolean
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    payPerTokenConfig AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig
    provisionedThroughputConfig AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig
    trafficPercentage Integer
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig
    destinationType string
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    name string
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    externalModelConfig AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig
    isDeleted boolean
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    payPerTokenConfig AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig
    provisionedThroughputConfig AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig
    trafficPercentage number
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig
    destination_type str
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    name str
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    external_model_config AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig
    is_deleted bool
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    pay_per_token_config AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig
    provisioned_throughput_config AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig
    traffic_percentage int
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig
    destinationType String
    Backing-model category. Determines which oneof variant is populated. Possible values are: DESTINATION_TYPE_EXTERNAL_FOUNDATION_MODEL, DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL, DESTINATION_TYPE_PROVISIONED_THROUGHPUT_FOUNDATION_MODEL
    name String
    (string) - Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
    externalModelConfig Property Map
    isDeleted Boolean
    (boolean) - True when the destination's backing UC entity (MODEL for foundation-model destinations, MODEL_PROVIDER_SERVICE for external destinations) has been deleted but the destination row still references it. The dangling destination is surfaced (not silently dropped) so callers can see the broken routing. Inference traffic through this destination fails closed (BAD_REQUEST / FAILED_PRECONDITION)
    payPerTokenConfig Property Map
    provisionedThroughputConfig Property Map
    trafficPercentage Number
    Share of traffic sent to this destination, 0-100. Optional on fallback destinations; see FallbackConfig

    AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig, AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigArgs

    ModelProviderService string
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    Target AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time
    ModelProviderService string
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    Target AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time
    model_provider_service string
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    target object
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time
    modelProviderService String
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    target AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time
    modelProviderService string
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    target AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time
    model_provider_service str
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    target AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time
    modelProviderService String
    Resource name of the governed ModelProviderService that owns provider auth and provider-specific configuration. The referenced ModelProviderService also carries the provider type, so this message does not surface it directly. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually
    target Property Map
    Routing target for the destination: the provider-side model selected from the referenced ModelProviderService's targets catalog, plus the unified API types the platform should translate to/from at request time

    AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget, AiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTargetArgs

    Model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    NativeApiTypes List<string>
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope
    Model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    NativeApiTypes []string
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope
    model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    native_api_types list(string)
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope
    model String
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    nativeApiTypes List<String>
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope
    model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    nativeApiTypes string[]
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope
    model str
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    native_api_types Sequence[str]
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope
    model String
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    nativeApiTypes List<String>
    Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope

    AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig, AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfigArgs

    Model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    Model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model String
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model str
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model String
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time

    AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig, AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfigArgs

    ModelServingEndpoint string
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    Model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    ModelServingEndpoint string
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    Model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model_serving_endpoint string
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    modelServingEndpoint String
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    model String
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    modelServingEndpoint string
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    model string
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    model_serving_endpoint str
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    model str
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time
    modelServingEndpoint String
    Name of the backing Model Serving endpoint serving the provisioned- throughput foundation model, as the AIP-122 typed resource name serving-endpoints/{name}. The same UC model can be served on multiple Model Serving endpoints (different throughput / region / config); the caller picks which one this destination routes to. The endpoint must exist at create time
    model String
    (string) - UC model FQN of the model served by the backing endpoint (e.g., system.ai.databricks-claude-opus-4-6). Resolved from Model Serving at Create/Update time

    AiGatewayModelServiceProviderConfig, AiGatewayModelServiceProviderConfigArgs

    WorkspaceId string
    Workspace ID which the resource belongs to. This workspace must be part of the account which the provider is configured with.
    WorkspaceId string
    Workspace ID which the resource belongs to. This workspace must be part of the account which the provider is configured with.
    workspace_id string
    Workspace ID which the resource belongs to. This workspace must be part of the account which the provider is configured with.
    workspaceId String
    Workspace ID which the resource belongs to. This workspace must be part of the account which the provider is configured with.
    workspaceId string
    Workspace ID which the resource belongs to. This workspace must be part of the account which the provider is configured with.
    workspace_id str
    Workspace ID which the resource belongs to. This workspace must be part of the account which the provider is configured with.
    workspaceId String
    Workspace ID which the resource belongs to. This workspace must be part of the account which the provider is configured with.

    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 logo
    Viewing docs for Databricks v1.107.0
    published on Tuesday, Aug 25, 2026 by Pulumi
    Schema (JSON)
    pulumi/pulumi-databricks

      Try Pulumi Cloud free.
      Your team will thank you.

      Start free trial