Sign in Dashboard Get started
  1. Registry
  2. Packages
  3. Databricks Provider
  4. API Docs
  5. AiGatewayModelService
Viewing docs for Databricks v1.116.0
published on Tuesday, Oct 20, 2026 by Pulumi
Schema (JSON)
pulumi/pulumi-databricks

databricks.AiGatewayModelService

databricks logo databricks logo
Viewing docs for Databricks v1.116.0
published on Tuesday, Oct 20, 2026 by Pulumi
Schema (JSON)
pulumi/pulumi-databricks

    GA

    API Documentation

    Manages a Unity Catalog model service. A model service provides a stable endpoint that routes inference requests to one or more destinations, such as Databricks foundation models or external model provider services.

    Model services are contained in a Unity Catalog schema and governed by Unity Catalog permissions.

    Example Usage

    The following example creates a model service that sends all traffic to a Databricks foundation model:

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

const example = new databricks.AiGatewayModelService("example", {
    parent: "schemas/main.default",
    modelServiceId: "customer_support",
    comment: "Routes customer support requests",
    config: {
        routing: {
            destinations: [{
                name: "primary",
                destinationType: "DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL",
                payPerTokenConfig: {
                    model: "models/system.ai.databricks-gpt-5",
                },
                trafficPercentage: 100,
            }],
        },
    },
});

    import pulumi
import pulumi_databricks as databricks

example = databricks.AiGatewayModelService("example",
    parent="schemas/main.default",
    model_service_id="customer_support",
    comment="Routes customer support requests",
    config={
        "routing": {
            "destinations": [{
                "name": "primary",
                "destination_type": "DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL",
                "pay_per_token_config": {
                    "model": "models/system.ai.databricks-gpt-5",
                },
                "traffic_percentage": 100,
            }],
        },
    })

    package main

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

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := databricks.NewAiGatewayModelService(ctx, "example", &databricks.AiGatewayModelServiceArgs{
			Parent:         pulumi.String("schemas/main.default"),
			ModelServiceId: pulumi.String("customer_support"),
			Comment:        pulumi.String("Routes customer support requests"),
			Config: &databricks.AiGatewayModelServiceConfigArgs{
				Routing: &databricks.AiGatewayModelServiceConfigRoutingArgs{
					Destinations: databricks.AiGatewayModelServiceConfigRoutingDestinationArray{
						&databricks.AiGatewayModelServiceConfigRoutingDestinationArgs{
							Name:            pulumi.String("primary"),
							DestinationType: pulumi.String("DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL"),
							PayPerTokenConfig: &databricks.AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfigArgs{
								Model: pulumi.String("models/system.ai.databricks-gpt-5"),
							},
							TrafficPercentage: pulumi.Int(100),
						},
					},
				},
			},
		})
		if err != nil {
			return err
		}
		return nil
	})
}

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

return await Deployment.RunAsync(() => 
{
    var example = new Databricks.AiGatewayModelService("example", new()
    {
        Parent = "schemas/main.default",
        ModelServiceId = "customer_support",
        Comment = "Routes customer support requests",
        Config = new Databricks.Inputs.AiGatewayModelServiceConfigArgs
        {
            Routing = new Databricks.Inputs.AiGatewayModelServiceConfigRoutingArgs
            {
                Destinations = new[]
                {
                    new Databricks.Inputs.AiGatewayModelServiceConfigRoutingDestinationArgs
                    {
                        Name = "primary",
                        DestinationType = "DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL",
                        PayPerTokenConfig = new Databricks.Inputs.AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfigArgs
                        {
                            Model = "models/system.ai.databricks-gpt-5",
                        },
                        TrafficPercentage = 100,
                    },
                },
            },
        },
    });

});

    package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.databricks.AiGatewayModelService;
import com.pulumi.databricks.AiGatewayModelServiceArgs;
import com.pulumi.databricks.inputs.AiGatewayModelServiceConfigArgs;
import com.pulumi.databricks.inputs.AiGatewayModelServiceConfigRoutingArgs;
import com.pulumi.databricks.inputs.AiGatewayModelServiceConfigRoutingDestinationArgs;
import com.pulumi.databricks.inputs.AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfigArgs;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;

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

    public static void stack(Context ctx) {
        var example = new AiGatewayModelService("example", AiGatewayModelServiceArgs.builder()
            .parent("schemas/main.default")
            .modelServiceId("customer_support")
            .comment("Routes customer support requests")
            .config(AiGatewayModelServiceConfigArgs.builder()
                .routing(AiGatewayModelServiceConfigRoutingArgs.builder()
                    .destinations(AiGatewayModelServiceConfigRoutingDestinationArgs.builder()
                        .name("primary")
                        .destinationType("DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL")
                        .payPerTokenConfig(AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfigArgs.builder()
                            .model("models/system.ai.databricks-gpt-5")
                            .build())
                        .trafficPercentage(100)
                        .build())
                    .build())
                .build())
            .build());

    }
}

    resources:
  example:
    type: databricks:AiGatewayModelService
    properties:
      parent: schemas/main.default
      modelServiceId: customer_support
      comment: Routes customer support requests
      config:
        routing:
          destinations:
            - name: primary
              destinationType: DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL
              payPerTokenConfig:
                model: models/system.ai.databricks-gpt-5
              trafficPercentage: 100

    terraform {
  required_providers {
    databricks = {
      source = "pulumi/databricks"
    }
  }
}

resource "databricks_ai_gateway_model_service" "example" {
  lifecycle {
    create_before_destroy = true
  }
  parent           = "schemas/main.default"
  model_service_id = "customer_support"
  comment          = "Routes customer support requests"
  config = {
    routing = {
      destinations = [{
        name             = "primary"
        destination_type = "DESTINATION_TYPE_PAY_PER_TOKEN_FOUNDATION_MODEL"
        pay_per_token_config = {
          model = "models/system.ai.databricks-gpt-5"
        }
        traffic_percentage = 100
      }]
    }
  }
}

    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,
                          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",
            IsDeleted = false,
            Table = "string",
            TableNamePrefix = "string",
        },
        RateLimits = new[]
        {
            new Databricks.Inputs.AiGatewayModelServiceConfigRateLimitArgs
            {
                Key = "string",
                RenewalPeriod = "string",
                Principal = "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,
                    },
                },
            },
        },
    },
    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"),
			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"),
				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),
					},
				},
			},
		},
	},
	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"
      is_deleted        = false
      table             = "string"
      table_name_prefix = "string"
    }
    rate_limits = [{
      key            = "string"
      renewal_period = "string"
      principal      = "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
        }]
      }
    }
  }
  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")
            .isDeleted(false)
            .table("string")
            .tableNamePrefix("string")
            .build())
        .rateLimits(AiGatewayModelServiceConfigRateLimitArgs.builder()
            .key("string")
            .renewalPeriod("string")
            .principal("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())
            .build())
        .build())
    .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",
            "is_deleted": False,
            "table": "string",
            "table_name_prefix": "string",
        },
        "rate_limits": [{
            "key": "string",
            "renewal_period": "string",
            "principal": "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,
                }],
            },
        },
    },
    provider_config={
        "workspace_id": "string",
    })

    const aiGatewayModelServiceResource = new databricks.AiGatewayModelService("aiGatewayModelServiceResource", {
    modelServiceId: "string",
    parent: "string",
    comment: "string",
    config: {
        inferenceTable: {
            parent: "string",
            isDeleted: false,
            table: "string",
            tableNamePrefix: "string",
        },
        rateLimits: [{
            key: "string",
            renewalPeriod: "string",
            principal: "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,
                }],
            },
        },
    },
    providerConfig: {
        workspaceId: "string",
    },
});

    type: databricks:AiGatewayModelService
properties:
    comment: string
    config:
        inferenceTable:
            isDeleted: false
            parent: string
            table: string
            tableNamePrefix: string
        rateLimits:
            - key: string
              principal: string
              renewalPeriod: 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
    modelServiceId: 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
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    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
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    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
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    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
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    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
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    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
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    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
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    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) - Time the model service was created
    CreatedBy string
    (string) - Creator identity
    EffectiveOwner string
    (string) - Owner of the model service
    Etag string
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    UpdateTime string
    (string) - Time the model service was last modified
    UpdatedBy string
    (string) - Identity of the last updater
    CreateTime string
    (string) - Time the model service was created
    CreatedBy string
    (string) - Creator identity
    EffectiveOwner string
    (string) - Owner of the model service
    Etag string
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    UpdateTime string
    (string) - Time the model service was last modified
    UpdatedBy string
    (string) - Identity of the last updater
    create_time string
    (string) - Time the model service was created
    created_by string
    (string) - Creator identity
    effective_owner string
    (string) - Owner of the model service
    etag string
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    update_time string
    (string) - Time the model service was last modified
    updated_by string
    (string) - Identity of the last updater
    createTime String
    (string) - Time the model service was created
    createdBy String
    (string) - Creator identity
    effectiveOwner String
    (string) - Owner of the model service
    etag String
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    updateTime String
    (string) - Time the model service was last modified
    updatedBy String
    (string) - Identity of the last updater
    createTime string
    (string) - Time the model service was created
    createdBy string
    (string) - Creator identity
    effectiveOwner string
    (string) - Owner of the model service
    etag string
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    updateTime string
    (string) - Time the model service was last modified
    updatedBy string
    (string) - Identity of the last updater
    create_time str
    (string) - Time the model service was created
    created_by str
    (string) - Creator identity
    effective_owner str
    (string) - Owner of the model service
    etag str
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    update_time str
    (string) - Time the model service was last modified
    updated_by str
    (string) - Identity of the last updater
    createTime String
    (string) - Time the model service was created
    createdBy String
    (string) - Creator identity
    effectiveOwner String
    (string) - Owner of the model service
    etag String
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    updateTime String
    (string) - Time 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,
        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
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    CreateTime string
    (string) - Time the model service was created
    CreatedBy string
    (string) - Creator identity
    EffectiveOwner string
    (string) - Owner of the model service
    Etag string
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    UpdateTime string
    (string) - Time the model service was last modified
    UpdatedBy string
    (string) - Identity of the last updater
    Comment string
    User-provided description
    Config AiGatewayModelServiceConfigArgs
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    CreateTime string
    (string) - Time the model service was created
    CreatedBy string
    (string) - Creator identity
    EffectiveOwner string
    (string) - Owner of the model service
    Etag string
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    UpdateTime string
    (string) - Time the model service was last modified
    UpdatedBy string
    (string) - Identity of the last updater
    comment string
    User-provided description
    config object
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    create_time string
    (string) - Time the model service was created
    created_by string
    (string) - Creator identity
    effective_owner string
    (string) - Owner of the model service
    etag string
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    update_time string
    (string) - Time the model service was last modified
    updated_by string
    (string) - Identity of the last updater
    comment String
    User-provided description
    config AiGatewayModelServiceConfig
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    createTime String
    (string) - Time the model service was created
    createdBy String
    (string) - Creator identity
    effectiveOwner String
    (string) - Owner of the model service
    etag String
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    updateTime String
    (string) - Time the model service was last modified
    updatedBy String
    (string) - Identity of the last updater
    comment string
    User-provided description
    config AiGatewayModelServiceConfig
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    createTime string
    (string) - Time the model service was created
    createdBy string
    (string) - Creator identity
    effectiveOwner string
    (string) - Owner of the model service
    etag string
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    updateTime string
    (string) - Time the model service was last modified
    updatedBy string
    (string) - Identity of the last updater
    comment str
    User-provided description
    config AiGatewayModelServiceConfigArgs
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    create_time str
    (string) - Time the model service was created
    created_by str
    (string) - Creator identity
    effective_owner str
    (string) - Owner of the model service
    etag str
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    update_time str
    (string) - Time the model service was last modified
    updated_by str
    (string) - Identity of the last updater
    comment String
    User-provided description
    config Property Map
    Destinations, routing, rate limits, and payload logging configuration. Required on Create. On Update, provide this field when updateMask contains config or one of its subpaths
    createTime String
    (string) - Time the model service was created
    createdBy String
    (string) - Creator identity
    effectiveOwner String
    (string) - Owner of the model service
    etag String
    (string) - Optimistic concurrency token returned on every read. To make an Update or Delete conditional, pass the last-read value in that request's etag field. In REST responses, this value is a base64 string; URL-encode it when setting the etag query parameter
    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
    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) - API types supported across this service's destinations, such as openai/v1/chat/completions, openai/v1/embeddings, and mlflow/v1/chat/completions. Derived from the backing models and providers at read time
    updateTime String
    (string) - Time the model service was last modified
    updatedBy String
    (string) - Identity of the last updater

    Supporting Types

    AiGatewayModelServiceConfig, AiGatewayModelServiceConfigArgs

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

    AiGatewayModelServiceConfigInferenceTable, AiGatewayModelServiceConfigInferenceTableArgs

    Parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    IsDeleted bool
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    Table string
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    TableNamePrefix string
    Prefix used to form the inference table's registered name. AI Gateway appends _payload; for example, tableNamePrefix = "orders" creates ordersPayload. If unset, the prefix defaults to the service name. Read table from the response for the resulting resource name. After the inference table is created, this field cannot be changed
    Parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    IsDeleted bool
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    Table string
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    TableNamePrefix string
    Prefix used to form the inference table's registered name. AI Gateway appends _payload; for example, tableNamePrefix = "orders" creates ordersPayload. If unset, the prefix defaults to the service name. Read table from the response for the resulting resource name. After the inference table is created, this field cannot be changed
    parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    is_deleted bool
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    table string
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    table_name_prefix string
    Prefix used to form the inference table's registered name. AI Gateway appends _payload; for example, tableNamePrefix = "orders" creates ordersPayload. If unset, the prefix defaults to the service name. Read table from the response for the resulting resource name. After the inference table is created, this field cannot be changed
    parent String
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    isDeleted Boolean
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    table String
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    tableNamePrefix String
    Prefix used to form the inference table's registered name. AI Gateway appends _payload; for example, tableNamePrefix = "orders" creates ordersPayload. If unset, the prefix defaults to the service name. Read table from the response for the resulting resource name. After the inference table is created, this field cannot be changed
    parent string
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    isDeleted boolean
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    table string
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    tableNamePrefix string
    Prefix used to form the inference table's registered name. AI Gateway appends _payload; for example, tableNamePrefix = "orders" creates ordersPayload. If unset, the prefix defaults to the service name. Read table from the response for the resulting resource name. After the inference table is created, this field cannot be changed
    parent str
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    is_deleted bool
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    table str
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    table_name_prefix str
    Prefix used to form the inference table's registered name. AI Gateway appends _payload; for example, tableNamePrefix = "orders" creates ordersPayload. If unset, the prefix defaults to the service name. Read table from the response for the resulting resource name. After the inference table is created, this field cannot be changed
    parent String
    Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
    isDeleted Boolean
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    table String
    (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
    tableNamePrefix String
    Prefix used to form the inference table's registered name. AI Gateway appends _payload; for example, tableNamePrefix = "orders" creates ordersPayload. If unset, the prefix defaults to the service name. Read table from the response for the resulting resource name. After the inference table is created, this field cannot be changed

    AiGatewayModelServiceConfigRateLimit, AiGatewayModelServiceConfigRateLimitArgs

    Key string
    Scope of the rate limit. Depending on this value, the limit applies to a principal, the service as a whole, or each user by default. Possible values are: 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 when key applies to a user, group, or service principal; otherwise it must be unset
    Requests int
    Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
    Tokens int
    Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests
    Key string
    Scope of the rate limit. Depending on this value, the limit applies to a principal, the service as a whole, or each user by default. Possible values are: 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 when key applies to a user, group, or service principal; otherwise it must be unset
    Requests int
    Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
    Tokens int
    Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests
    key string
    Scope of the rate limit. Depending on this value, the limit applies to a principal, the service as a whole, or each user by default. Possible values are: 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 when key applies to a user, group, or service principal; otherwise it must be unset
    requests number
    Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
    tokens number
    Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests
    key String
    Scope of the rate limit. Depending on this value, the limit applies to a principal, the service as a whole, or each user by default. Possible values are: 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 when key applies to a user, group, or service principal; otherwise it must be unset
    requests Integer
    Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
    tokens Integer
    Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests
    key string
    Scope of the rate limit. Depending on this value, the limit applies to a principal, the service as a whole, or each user by default. Possible values are: 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 when key applies to a user, group, or service principal; otherwise it must be unset
    requests number
    Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
    tokens number
    Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests
    key str
    Scope of the rate limit. Depending on this value, the limit applies to a principal, the service as a whole, or each user by default. Possible values are: 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 when key applies to a user, group, or service principal; otherwise it must be unset
    requests int
    Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
    tokens int
    Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests
    key String
    Scope of the rate limit. Depending on this value, the limit applies to a principal, the service as a whole, or each user by default. Possible values are: 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 when key applies to a user, group, or service principal; otherwise it must be unset
    requests Number
    Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
    tokens Number
    Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests

    AiGatewayModelServiceConfigRouting, AiGatewayModelServiceConfigRoutingArgs

    Destinations List<AiGatewayModelServiceConfigRoutingDestination>
    Fallback AiGatewayModelServiceConfigRoutingFallback
    Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order
    Destinations []AiGatewayModelServiceConfigRoutingDestination
    Fallback AiGatewayModelServiceConfigRoutingFallback
    Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order
    destinations list(object)
    fallback object
    Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order
    destinations List<AiGatewayModelServiceConfigRoutingDestination>
    fallback AiGatewayModelServiceConfigRoutingFallback
    Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order
    destinations AiGatewayModelServiceConfigRoutingDestination[]
    fallback AiGatewayModelServiceConfigRoutingFallback
    Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order
    destinations Sequence[AiGatewayModelServiceConfigRoutingDestination]
    fallback AiGatewayModelServiceConfigRoutingFallback
    Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order
    destinations List<Property Map>
    fallback Property Map
    Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order

    AiGatewayModelServiceConfigRoutingDestination, AiGatewayModelServiceConfigRoutingDestinationArgs

    DestinationType string
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    IsDeleted bool
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    PayPerTokenConfig AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig
    Configuration for a pay-per-token Databricks foundation model
    ProvisionedThroughputConfig AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig
    Configuration for a provisioned-throughput Databricks foundation model
    TrafficPercentage int
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field
    DestinationType string
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    IsDeleted bool
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    PayPerTokenConfig AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig
    Configuration for a pay-per-token Databricks foundation model
    ProvisionedThroughputConfig AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig
    Configuration for a provisioned-throughput Databricks foundation model
    TrafficPercentage int
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field
    destination_type string
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    is_deleted bool
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    pay_per_token_config object
    Configuration for a pay-per-token Databricks foundation model
    provisioned_throughput_config object
    Configuration for a provisioned-throughput Databricks foundation model
    traffic_percentage number
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field
    destinationType String
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    isDeleted Boolean
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    payPerTokenConfig AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig
    Configuration for a pay-per-token Databricks foundation model
    provisionedThroughputConfig AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig
    Configuration for a provisioned-throughput Databricks foundation model
    trafficPercentage Integer
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field
    destinationType string
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    isDeleted boolean
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    payPerTokenConfig AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig
    Configuration for a pay-per-token Databricks foundation model
    provisionedThroughputConfig AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig
    Configuration for a provisioned-throughput Databricks foundation model
    trafficPercentage number
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field
    destination_type str
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    is_deleted bool
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    pay_per_token_config AiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig
    Configuration for a pay-per-token Databricks foundation model
    provisioned_throughput_config AiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig
    Configuration for a provisioned-throughput Databricks foundation model
    traffic_percentage int
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field
    destinationType String
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    isDeleted Boolean
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    payPerTokenConfig Property Map
    Configuration for a pay-per-token Databricks foundation model
    provisionedThroughputConfig Property Map
    Configuration for a provisioned-throughput Databricks foundation model
    trafficPercentage Number
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field

    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed
    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed
    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed
    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed
    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed
    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed
    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed

    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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    IsDeleted bool
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    PayPerTokenConfig AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig
    Configuration for a pay-per-token Databricks foundation model
    ProvisionedThroughputConfig AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig
    Configuration for a provisioned-throughput Databricks foundation model
    TrafficPercentage int
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field
    DestinationType string
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    IsDeleted bool
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    PayPerTokenConfig AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig
    Configuration for a pay-per-token Databricks foundation model
    ProvisionedThroughputConfig AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig
    Configuration for a provisioned-throughput Databricks foundation model
    TrafficPercentage int
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field
    destination_type string
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    is_deleted bool
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    pay_per_token_config object
    Configuration for a pay-per-token Databricks foundation model
    provisioned_throughput_config object
    Configuration for a provisioned-throughput Databricks foundation model
    traffic_percentage number
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field
    destinationType String
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    isDeleted Boolean
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    payPerTokenConfig AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig
    Configuration for a pay-per-token Databricks foundation model
    provisionedThroughputConfig AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig
    Configuration for a provisioned-throughput Databricks foundation model
    trafficPercentage Integer
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field
    destinationType string
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    isDeleted boolean
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    payPerTokenConfig AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig
    Configuration for a pay-per-token Databricks foundation model
    provisionedThroughputConfig AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig
    Configuration for a provisioned-throughput Databricks foundation model
    trafficPercentage number
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field
    destination_type str
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    is_deleted bool
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    pay_per_token_config AiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig
    Configuration for a pay-per-token Databricks foundation model
    provisioned_throughput_config AiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig
    Configuration for a provisioned-throughput Databricks foundation model
    traffic_percentage int
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field
    destinationType String
    Backing-model category. Provide the matching type-specific configuration and leave the other type-specific configurations unset. 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
    Configuration for an external model reached through a model provider service
    isDeleted Boolean
    (boolean) - Whether the destination's backing model or model provider service has been deleted. The destination remains visible so you can identify the broken dependency. Requests cannot use this destination until the backing resource is restored or the destination is replaced
    payPerTokenConfig Property Map
    Configuration for a pay-per-token Databricks foundation model
    provisionedThroughputConfig Property Map
    Configuration for a provisioned-throughput Databricks foundation model
    trafficPercentage Number
    Percentage of primary traffic sent to this destination, from 0 to 100. Required when there is more than one primary destination, in which case the primary percentages must sum to 100; a single primary destination receives all traffic. Fallback destinations are ordered and do not use this field

    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed
    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed
    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed
    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed
    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed
    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed
    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 supported by this model, such as openai/v1/chat/completions. At least one value is required. AI Gateway uses these values to translate requests and responses. At most 64 entries of 256 characters each are allowed

    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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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, in the form serving-endpoints/{name}. The same Unity Catalog model can be served on multiple Model Serving endpoints with different throughput, regions, or configurations. The caller selects the endpoint to which this destination routes. 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 v1.116.0
    published on Tuesday, Oct 20, 2026 by Pulumi
    Schema (JSON)
    pulumi/pulumi-databricks

      Try Pulumi Cloud free.
      Your team will thank you.

      Start free trial