databricks.getAiGatewayModelService

Databricks v1.116.0, Oct 20 26

Viewing docs for Databricks v1.116.0
published on Tuesday, Oct 20, 2026 by Pulumi

Schema (JSON)

pulumi/pulumi-databricks

Viewing docs for Databricks v1.116.0
published on Tuesday, Oct 20, 2026 by Pulumi

Schema (JSON)

pulumi/pulumi-databricks

Example Usage

The following example retrieves the model service named customerSupport from the main.default schema:

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

const example = databricks.getAiGatewayModelService({
    name: "model-services/main.default.customer_support",
});
export const modelServiceConfig = example.then(example => example.config);

import pulumi
import pulumi_databricks as databricks

example = databricks.get_ai_gateway_model_service(name="model-services/main.default.customer_support")
pulumi.export("modelServiceConfig", example.config)

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 {
		example, err := databricks.GetAiGatewayModelService(ctx, &databricks.LookupAiGatewayModelServiceArgs{
			Name: "model-services/main.default.customer_support",
		}, nil)
		if err != nil {
			return err
		}
		ctx.Export("modelServiceConfig", example.Config)
		return nil
	})
}

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

return await Deployment.RunAsync(() => 
{
    var example = Databricks.GetAiGatewayModelService.Invoke(new()
    {
        Name = "model-services/main.default.customer_support",
    });

    return new Dictionary<string, object?>
    {
        ["modelServiceConfig"] = example.Apply(getAiGatewayModelServiceResult => getAiGatewayModelServiceResult.Config),
    };
});

package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.databricks.DatabricksFunctions;
import com.pulumi.databricks.inputs.GetAiGatewayModelServiceArgs;
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) {
        final var example = DatabricksFunctions.getAiGatewayModelService(GetAiGatewayModelServiceArgs.builder()
            .name("model-services/main.default.customer_support")
            .build());

        ctx.export("modelServiceConfig", example.config());
    }
}

variables:
  example:
    fn::invoke:
      function: databricks:getAiGatewayModelService
      arguments:
        name: model-services/main.default.customer_support
outputs:
  modelServiceConfig: ${example.config}

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

data "databricks_ai_gateway_model_service" "example" {
  name = "model-services/main.default.customer_support"
}

output "modelServiceConfig" {
  value = data.databricks_ai_gateway_model_service.example.config
}

Using getAiGatewayModelService

Two invocation forms are available. The direct form accepts plain arguments and either blocks until the result value is available, or returns a Promise-wrapped result. The output form accepts Input-wrapped arguments and returns an Output-wrapped result.

function getAiGatewayModelService(args: GetAiGatewayModelServiceArgs, opts?: InvokeOptions): Promise<GetAiGatewayModelServiceResult>
function getAiGatewayModelServiceOutput(args: GetAiGatewayModelServiceOutputArgs, opts?: InvokeOutputOptions): Output<GetAiGatewayModelServiceResult>

def get_ai_gateway_model_service(name: Optional[str] = None,
                                 provider_config: Optional[GetAiGatewayModelServiceProviderConfig] = None,
                                 opts: Optional[InvokeOptions] = None) -> GetAiGatewayModelServiceResult
def get_ai_gateway_model_service_output(name: pulumi.Input[Optional[str]] = None,
                                 provider_config: pulumi.Input[Optional[GetAiGatewayModelServiceProviderConfigArgs]] = None,
                                 opts: Optional[InvokeOutputOptions] = None) -> Output[GetAiGatewayModelServiceResult]

func LookupAiGatewayModelService(ctx *Context, args *LookupAiGatewayModelServiceArgs, opts ...InvokeOption) (*LookupAiGatewayModelServiceResult, error)
func LookupAiGatewayModelServiceOutput(ctx *Context, args *LookupAiGatewayModelServiceOutputArgs, opts ...InvokeOption) LookupAiGatewayModelServiceResultOutput

> Note: This function is named LookupAiGatewayModelService in the Go SDK.

public static class GetAiGatewayModelService 
{
    public static Task<GetAiGatewayModelServiceResult> InvokeAsync(GetAiGatewayModelServiceArgs args, InvokeOptions? opts = null)
    public static Output<GetAiGatewayModelServiceResult> Invoke(GetAiGatewayModelServiceInvokeArgs args, InvokeOptions? opts = null)
    public static Output<GetAiGatewayModelServiceResult> Invoke(GetAiGatewayModelServiceInvokeArgs args, InvokeOutputOptions opts)
}

public static CompletableFuture<GetAiGatewayModelServiceResult> getAiGatewayModelService(GetAiGatewayModelServiceArgs args, InvokeOptions options)
public static Output<GetAiGatewayModelServiceResult> getAiGatewayModelService(GetAiGatewayModelServiceArgs args, InvokeOptions options)
public static Output<GetAiGatewayModelServiceResult> getAiGatewayModelService(GetAiGatewayModelServiceArgs args, InvokeOutputOptions options)

fn::invoke:
  function: databricks:index/getAiGatewayModelService:getAiGatewayModelService
  arguments:
    # arguments dictionary

data "databricks_get_ai_gateway_model_service" "name" {
    # arguments
}

The following arguments are supported:

Name string: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
ProviderConfig GetAiGatewayModelServiceProviderConfig: Configure the provider for management through account provider.

Name string: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
ProviderConfig GetAiGatewayModelServiceProviderConfig: Configure the provider for management through account provider.

name string: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
provider_config object: Configure the provider for management through account provider.

name String: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
providerConfig GetAiGatewayModelServiceProviderConfig: Configure the provider for management through account provider.

name string: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
providerConfig GetAiGatewayModelServiceProviderConfig: Configure the provider for management through account provider.

name str: 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
provider_config GetAiGatewayModelServiceProviderConfig: Configure the provider for management through account provider.

name String: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
providerConfig Property Map: Configure the provider for management through account provider.

getAiGatewayModelService Result

The following output properties are available:

Comment string: (string) - User-provided description
Config GetAiGatewayModelServiceConfig: (ModelServiceConfig) - 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
Name string: (string) - User-facing label for this destination, used in routing references
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
ProviderConfig GetAiGatewayModelServiceProviderConfig

Comment string: (string) - User-provided description
Config GetAiGatewayModelServiceConfig: (ModelServiceConfig) - 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
Name string: (string) - User-facing label for this destination, used in routing references
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
ProviderConfig GetAiGatewayModelServiceProviderConfig

comment string: (string) - User-provided description
config object: (ModelServiceConfig) - 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
name string: (string) - User-facing label for this destination, used in routing references
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
provider_config object

comment String: (string) - User-provided description
config GetAiGatewayModelServiceConfig: (ModelServiceConfig) - 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
name String: (string) - User-facing label for this destination, used in routing references
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
providerConfig GetAiGatewayModelServiceProviderConfig

comment string: (string) - User-provided description
config GetAiGatewayModelServiceConfig: (ModelServiceConfig) - 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
name string: (string) - User-facing label for this destination, used in routing references
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
providerConfig GetAiGatewayModelServiceProviderConfig

comment str: (string) - User-provided description
config GetAiGatewayModelServiceConfig: (ModelServiceConfig) - 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
name str: (string) - User-facing label for this destination, used in routing references
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
provider_config GetAiGatewayModelServiceProviderConfig

comment String: (string) - User-provided description
config Property Map: (ModelServiceConfig) - 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
name String: (string) - User-facing label for this destination, used in routing references
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
providerConfig Property Map

Supporting Types

GetAiGatewayModelServiceConfig

InferenceTable GetAiGatewayModelServiceConfigInferenceTable: (InferenceTableConfig) - Inference table configuration for payload logging
RateLimits List<GetAiGatewayModelServiceConfigRateLimit>: (list of RateLimit) - Rate limits applied to requests routed through this model service
Routing GetAiGatewayModelServiceConfigRouting: (ModelServiceConfigRoutingConfig) - Routing configuration: destinations and fallback

InferenceTable GetAiGatewayModelServiceConfigInferenceTable: (InferenceTableConfig) - Inference table configuration for payload logging
RateLimits []GetAiGatewayModelServiceConfigRateLimit: (list of RateLimit) - Rate limits applied to requests routed through this model service
Routing GetAiGatewayModelServiceConfigRouting: (ModelServiceConfigRoutingConfig) - Routing configuration: destinations and fallback

inference_table object: (InferenceTableConfig) - Inference table configuration for payload logging
rate_limits list(object): (list of RateLimit) - Rate limits applied to requests routed through this model service
routing object: (ModelServiceConfigRoutingConfig) - Routing configuration: destinations and fallback

inferenceTable GetAiGatewayModelServiceConfigInferenceTable: (InferenceTableConfig) - Inference table configuration for payload logging
rateLimits List<GetAiGatewayModelServiceConfigRateLimit>: (list of RateLimit) - Rate limits applied to requests routed through this model service
routing GetAiGatewayModelServiceConfigRouting: (ModelServiceConfigRoutingConfig) - Routing configuration: destinations and fallback

inferenceTable GetAiGatewayModelServiceConfigInferenceTable: (InferenceTableConfig) - Inference table configuration for payload logging
rateLimits GetAiGatewayModelServiceConfigRateLimit[]: (list of RateLimit) - Rate limits applied to requests routed through this model service
routing GetAiGatewayModelServiceConfigRouting: (ModelServiceConfigRoutingConfig) - Routing configuration: destinations and fallback

inference_table GetAiGatewayModelServiceConfigInferenceTable: (InferenceTableConfig) - Inference table configuration for payload logging
rate_limits Sequence[GetAiGatewayModelServiceConfigRateLimit]: (list of RateLimit) - Rate limits applied to requests routed through this model service
routing GetAiGatewayModelServiceConfigRouting: (ModelServiceConfigRoutingConfig) - Routing configuration: destinations and fallback

inferenceTable Property Map: (InferenceTableConfig) - Inference table configuration for payload logging
rateLimits List<Property Map>: (list of RateLimit) - Rate limits applied to requests routed through this model service
routing Property Map: (ModelServiceConfigRoutingConfig) - Routing configuration: destinations and fallback

GetAiGatewayModelServiceConfigInferenceTable

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
Parent string: (string) - Parent Unity Catalog schema where the inference table is created, in the form schemas/{catalog}.{schema}. Required when configuring an inference table. After the inference table is created, this field cannot be changed
Table string: (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
TableNamePrefix string: (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

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
Parent string: (string) - Parent Unity Catalog schema where the inference table is created, in the form schemas/{catalog}.{schema}. Required when configuring an inference table. After the inference table is created, this field cannot be changed
Table string: (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
TableNamePrefix string: (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

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
parent string: (string) - Parent Unity Catalog schema where the inference table is created, in the form schemas/{catalog}.{schema}. Required when configuring an inference table. After the inference table is created, this field cannot be changed
table string: (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
table_name_prefix string: (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

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
parent String: (string) - Parent Unity Catalog schema where the inference table is created, in the form schemas/{catalog}.{schema}. Required when configuring an inference table. After the inference table is created, this field cannot be changed
table String: (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
tableNamePrefix String: (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

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
parent string: (string) - Parent Unity Catalog schema where the inference table is created, in the form schemas/{catalog}.{schema}. Required when configuring an inference table. After the inference table is created, this field cannot be changed
table string: (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
tableNamePrefix string: (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

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
parent str: (string) - Parent Unity Catalog schema where the inference table is created, in the form schemas/{catalog}.{schema}. Required when configuring an inference table. After the inference table is created, this field cannot be changed
table str: (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
table_name_prefix str: (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

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
parent String: (string) - Parent Unity Catalog schema where the inference table is created, in the form schemas/{catalog}.{schema}. Required when configuring an inference table. After the inference table is created, this field cannot be changed
table String: (string) - Resolved UC table for payload logs. Format: tables/{catalog}.{schema}.{table}
tableNamePrefix String: (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

GetAiGatewayModelServiceConfigRateLimit

Key string: (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: (string) - Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
Principal string: (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: (integer) - Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
Tokens int: (integer) - Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests

Key string: (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: (string) - Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
Principal string: (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: (integer) - Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
Tokens int: (integer) - Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests

key string: (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: (string) - Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
principal string: (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: (integer) - Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
tokens number: (integer) - Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests

key String: (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: (string) - Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
principal String: (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: (integer) - Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
tokens Integer: (integer) - Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests

key string: (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: (string) - Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
principal string: (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: (integer) - Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
tokens number: (integer) - Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests

key str: (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 str: (string) - Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
principal str: (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: (integer) - Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
tokens int: (integer) - Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests

key String: (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: (string) - Renewal period. Possible values are: RATE_LIMIT_RENEWAL_PERIOD_HOUR, RATE_LIMIT_RENEWAL_PERIOD_MINUTE
principal String: (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: (integer) - Maximum requests allowed in one renewal period. Leave unset for no request limit. Set to 0 to deny all requests
tokens Number: (integer) - Maximum tokens allowed in one renewal period. Leave unset for no token limit. Set to 0 to deny all requests

GetAiGatewayModelServiceConfigRouting

Destinations List<GetAiGatewayModelServiceConfigRoutingDestination>: (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported
Fallback GetAiGatewayModelServiceConfigRoutingFallback: (ModelServiceConfigFallbackConfig) - Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order

Destinations []GetAiGatewayModelServiceConfigRoutingDestination: (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported
Fallback GetAiGatewayModelServiceConfigRoutingFallback: (ModelServiceConfigFallbackConfig) - Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order

destinations list(object): (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported
fallback object: (ModelServiceConfigFallbackConfig) - Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order

destinations List<GetAiGatewayModelServiceConfigRoutingDestination>: (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported
fallback GetAiGatewayModelServiceConfigRoutingFallback: (ModelServiceConfigFallbackConfig) - Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order

destinations GetAiGatewayModelServiceConfigRoutingDestination[]: (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported
fallback GetAiGatewayModelServiceConfigRoutingFallback: (ModelServiceConfigFallbackConfig) - Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order

destinations Sequence[GetAiGatewayModelServiceConfigRoutingDestination]: (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported
fallback GetAiGatewayModelServiceConfigRoutingFallback: (ModelServiceConfigFallbackConfig) - Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order

destinations List<Property Map>: (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported
fallback Property Map: (ModelServiceConfigFallbackConfig) - Fallback routing applied after a primary destination fails. Fallback destinations are tried in the listed order

GetAiGatewayModelServiceConfigRoutingDestination

DestinationType string: (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
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
Name string: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
ExternalModelConfig GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfig: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
PayPerTokenConfig GetAiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
ProvisionedThroughputConfig GetAiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
TrafficPercentage int: (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: (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
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
Name string: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
ExternalModelConfig GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfig: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
PayPerTokenConfig GetAiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
ProvisionedThroughputConfig GetAiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
TrafficPercentage int: (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

destination_type string: (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
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
name string: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
external_model_config object: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
pay_per_token_config object: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
provisioned_throughput_config object: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
traffic_percentage number: (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: (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
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
name String: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
externalModelConfig GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfig: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
payPerTokenConfig GetAiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
provisionedThroughputConfig GetAiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
trafficPercentage Integer: (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: (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
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
name string: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
externalModelConfig GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfig: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
payPerTokenConfig GetAiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
provisionedThroughputConfig GetAiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
trafficPercentage number: (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

destination_type str: (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
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
name str: 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 GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfig: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
pay_per_token_config GetAiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
provisioned_throughput_config GetAiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
traffic_percentage int: (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: (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
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
name String: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
externalModelConfig Property Map: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
payPerTokenConfig Property Map: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
provisionedThroughputConfig Property Map: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
trafficPercentage Number: (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

GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfig

ModelProviderService string: (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 GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget: (ModelProviderServiceConfigModelTargetConfig) - 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: (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 GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget: (ModelProviderServiceConfigModelTargetConfig) - 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: (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: (ModelProviderServiceConfigModelTargetConfig) - 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: (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 GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget: (ModelProviderServiceConfigModelTargetConfig) - 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: (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 GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget: (ModelProviderServiceConfigModelTargetConfig) - 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: (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 GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget: (ModelProviderServiceConfigModelTargetConfig) - 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: (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: (ModelProviderServiceConfigModelTargetConfig) - 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

GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget

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>: (list of 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: (list of 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): (list of 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>: (list of 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[]: (list of 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]: (list of 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>: (list of 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

GetAiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig

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

GetAiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig

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: (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: (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: (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: (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: (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 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_serving_endpoint str: (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: (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

GetAiGatewayModelServiceConfigRoutingFallback

Destinations List<GetAiGatewayModelServiceConfigRoutingFallbackDestination>: (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported

Destinations []GetAiGatewayModelServiceConfigRoutingFallbackDestination: (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported

destinations list(object): (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported

destinations List<GetAiGatewayModelServiceConfigRoutingFallbackDestination>: (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported

destinations GetAiGatewayModelServiceConfigRoutingFallbackDestination[]: (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported

destinations Sequence[GetAiGatewayModelServiceConfigRoutingFallbackDestination]: (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported

destinations List<Property Map>: (list of ModelServiceConfigDestinationConfig) - Primary routing destinations. At most 10 are allowed. At least one is required on Create. On Update, provide this list when replacing the full config or updating config.routing.destinations; other granular routing updates do not require resending destinations. The intermediate config.routing mask path is not supported

GetAiGatewayModelServiceConfigRoutingFallbackDestination

DestinationType string: (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
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
Name string: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
ExternalModelConfig GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
PayPerTokenConfig GetAiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
ProvisionedThroughputConfig GetAiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
TrafficPercentage int: (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: (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
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
Name string: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
ExternalModelConfig GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
PayPerTokenConfig GetAiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
ProvisionedThroughputConfig GetAiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
TrafficPercentage int: (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

destination_type string: (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
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
name string: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
external_model_config object: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
pay_per_token_config object: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
provisioned_throughput_config object: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
traffic_percentage number: (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: (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
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
name String: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
externalModelConfig GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
payPerTokenConfig GetAiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
provisionedThroughputConfig GetAiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
trafficPercentage Integer: (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: (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
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
name string: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
externalModelConfig GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
payPerTokenConfig GetAiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
provisionedThroughputConfig GetAiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
trafficPercentage number: (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

destination_type str: (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
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
name str: 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 GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
pay_per_token_config GetAiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
provisioned_throughput_config GetAiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
traffic_percentage int: (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: (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
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
name String: Resource name of the model service. Format: model-services/{catalog}.{schema}.{model_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelServiceId; required and immutable on Update/Get/Delete
externalModelConfig Property Map: (ModelServiceConfigExternalModelConfig) - Configuration for an external model reached through a model provider service
payPerTokenConfig Property Map: (ModelServiceConfigPayPerTokenConfig) - Configuration for a pay-per-token Databricks foundation model
provisionedThroughputConfig Property Map: (ModelServiceConfigProvisionedThroughputConfig) - Configuration for a provisioned-throughput Databricks foundation model
trafficPercentage Number: (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

GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig

ModelProviderService string: (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 GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget: (ModelProviderServiceConfigModelTargetConfig) - 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: (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 GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget: (ModelProviderServiceConfigModelTargetConfig) - 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: (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: (ModelProviderServiceConfigModelTargetConfig) - 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: (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 GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget: (ModelProviderServiceConfigModelTargetConfig) - 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: (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 GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget: (ModelProviderServiceConfigModelTargetConfig) - 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: (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 GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget: (ModelProviderServiceConfigModelTargetConfig) - 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: (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: (ModelProviderServiceConfigModelTargetConfig) - 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

GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget

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>: (list of 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: (list of 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): (list of 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>: (list of 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[]: (list of 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]: (list of 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>: (list of 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

GetAiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig

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

GetAiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig

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: (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: (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: (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: (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: (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 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_serving_endpoint str: (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: (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

GetAiGatewayModelServiceProviderConfig

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.

Viewing docs for Databricks v1.116.0
published on Tuesday, Oct 20, 2026 by Pulumi

Schema (JSON)

pulumi/pulumi-databricks

databricks.getAiGatewayModelService

On this page

On this page

Example Usage

Using getAiGatewayModelService

getAiGatewayModelService Result

Supporting Types

GetAiGatewayModelServiceConfig

GetAiGatewayModelServiceConfigInferenceTable

GetAiGatewayModelServiceConfigRateLimit

GetAiGatewayModelServiceConfigRouting

GetAiGatewayModelServiceConfigRoutingDestination

GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfig

GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget

GetAiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig

GetAiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig

GetAiGatewayModelServiceConfigRoutingFallback

GetAiGatewayModelServiceConfigRoutingFallbackDestination

GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig

GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget

GetAiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig

GetAiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig

GetAiGatewayModelServiceProviderConfig

Package Details

On this page

On this page

Try Pulumi Cloud free.
Your team will thank you.

databricks.getAiGatewayModelService

On this page

On this page

Example Usage

Using getAiGatewayModelService

getAiGatewayModelService Result

Supporting Types

GetAiGatewayModelServiceConfig

GetAiGatewayModelServiceConfigInferenceTable

GetAiGatewayModelServiceConfigRateLimit

GetAiGatewayModelServiceConfigRouting

GetAiGatewayModelServiceConfigRoutingDestination

GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfig

GetAiGatewayModelServiceConfigRoutingDestinationExternalModelConfigTarget

GetAiGatewayModelServiceConfigRoutingDestinationPayPerTokenConfig

GetAiGatewayModelServiceConfigRoutingDestinationProvisionedThroughputConfig

GetAiGatewayModelServiceConfigRoutingFallback

GetAiGatewayModelServiceConfigRoutingFallbackDestination

GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfig

GetAiGatewayModelServiceConfigRoutingFallbackDestinationExternalModelConfigTarget

GetAiGatewayModelServiceConfigRoutingFallbackDestinationPayPerTokenConfig

GetAiGatewayModelServiceConfigRoutingFallbackDestinationProvisionedThroughputConfig

GetAiGatewayModelServiceProviderConfig

Package Details

On this page

On this page

Try Pulumi Cloud free.Your team will thank you.

Try Pulumi Cloud free.
Your team will thank you.