databricks.AiGatewayModelProviderService

Databricks v1.107.0, Aug 25 26

Viewing docs for Databricks v1.107.0
published on Tuesday, Aug 25, 2026 by Pulumi

Schema (JSON)

pulumi/pulumi-databricks

Viewing docs for Databricks v1.107.0
published on Tuesday, Aug 25, 2026 by Pulumi

Schema (JSON)

pulumi/pulumi-databricks

Create AiGatewayModelProviderService Resource

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

Constructor syntax

new AiGatewayModelProviderService(name: string, args: AiGatewayModelProviderServiceArgs, opts?: CustomResourceOptions);

@overload
def AiGatewayModelProviderService(resource_name: str,
                                  args: AiGatewayModelProviderServiceArgs,
                                  opts: Optional[ResourceOptions] = None)

@overload
def AiGatewayModelProviderService(resource_name: str,
                                  opts: Optional[ResourceOptions] = None,
                                  model_provider_service_id: Optional[str] = None,
                                  parent: Optional[str] = None,
                                  comment: Optional[str] = None,
                                  config: Optional[AiGatewayModelProviderServiceConfigArgs] = None,
                                  owner: Optional[str] = None,
                                  provider_config: Optional[AiGatewayModelProviderServiceProviderConfigArgs] = None)

func NewAiGatewayModelProviderService(ctx *Context, name string, args AiGatewayModelProviderServiceArgs, opts ...ResourceOption) (*AiGatewayModelProviderService, error)

public AiGatewayModelProviderService(string name, AiGatewayModelProviderServiceArgs args, CustomResourceOptions? opts = null)

public AiGatewayModelProviderService(String name, AiGatewayModelProviderServiceArgs args)
public AiGatewayModelProviderService(String name, AiGatewayModelProviderServiceArgs args, CustomResourceOptions options)

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

resource "databricks_ai_gateway_model_provider_service" "name" {
    # resource properties
}

Parameters

name string: The unique name of the resource.
args AiGatewayModelProviderServiceArgs: The arguments to resource properties.
opts CustomResourceOptions: Bag of options to control resource's behavior.

resource_name str: The unique name of the resource.
args AiGatewayModelProviderServiceArgs: The arguments to resource properties.
opts ResourceOptions: Bag of options to control resource's behavior.

ctx Context: Context object for the current deployment.
name string: The unique name of the resource.
args AiGatewayModelProviderServiceArgs: The arguments to resource properties.
opts ResourceOption: Bag of options to control resource's behavior.

name string: The unique name of the resource.
args AiGatewayModelProviderServiceArgs: The arguments to resource properties.
opts CustomResourceOptions: Bag of options to control resource's behavior.

name String: The unique name of the resource.
args AiGatewayModelProviderServiceArgs: The arguments to resource properties.
options CustomResourceOptions: Bag of options to control resource's behavior.

Constructor example

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

var aiGatewayModelProviderServiceResource = new Databricks.AiGatewayModelProviderService("aiGatewayModelProviderServiceResource", new()
{
    ModelProviderServiceId = "string",
    Parent = "string",
    Comment = "string",
    Config = new Databricks.Inputs.AiGatewayModelProviderServiceConfigArgs
    {
        AllowAllTargets = false,
        AmazonBedrock = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAmazonBedrockArgs
        {
            Direct = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAmazonBedrockDirectArgs
            {
                AwsAccessKey = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeyArgs
                {
                    AccessKeyId = "string",
                    SecretAccessKey = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeySecretAccessKeyArgs
                    {
                        Plaintext = "string",
                    },
                },
                Region = "string",
                ServiceCredential = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAmazonBedrockDirectServiceCredentialArgs
                {
                    Name = "string",
                },
            },
        },
        Anthropic = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAnthropicArgs
        {
            Direct = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAnthropicDirectArgs
            {
                ApiKey = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAnthropicDirectApiKeyArgs
                {
                    Plaintext = "string",
                },
            },
            Relayed = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAnthropicRelayedArgs
            {
                PlanType = "string",
            },
        },
        AzureOpenai = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAzureOpenaiArgs
        {
            Direct = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAzureOpenaiDirectArgs
            {
                ApiKey = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAzureOpenaiDirectApiKeyArgs
                {
                    Plaintext = "string",
                },
                BaseUrl = "string",
                EntraServicePrincipal = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalArgs
                {
                    ClientId = "string",
                    ClientSecret = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalClientSecretArgs
                    {
                        Plaintext = "string",
                    },
                    TenantId = "string",
                },
                ServiceCredential = new Databricks.Inputs.AiGatewayModelProviderServiceConfigAzureOpenaiDirectServiceCredentialArgs
                {
                    Name = "string",
                },
            },
        },
        Custom = new Databricks.Inputs.AiGatewayModelProviderServiceConfigCustomArgs
        {
            Direct = new Databricks.Inputs.AiGatewayModelProviderServiceConfigCustomDirectArgs
            {
                ApiKey = new Databricks.Inputs.AiGatewayModelProviderServiceConfigCustomDirectApiKeyArgs
                {
                    Plaintext = "string",
                },
                BaseUrl = "string",
            },
        },
        ForwardHeaders = false,
        ForwardQueryParameters = false,
        ForwardUnmanagedPaths = false,
        GeminiEnterprise = new Databricks.Inputs.AiGatewayModelProviderServiceConfigGeminiEnterpriseArgs
        {
            Direct = new Databricks.Inputs.AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectArgs
            {
                ApiKey = new Databricks.Inputs.AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectApiKeyArgs
                {
                    Plaintext = "string",
                },
                ProjectId = "string",
                Region = "string",
            },
        },
        InferenceTable = new Databricks.Inputs.AiGatewayModelProviderServiceConfigInferenceTableArgs
        {
            Parent = "string",
            Disabled = false,
            IsDeleted = false,
            Table = "string",
            TableNamePrefix = "string",
        },
        MicrosoftFoundry = new Databricks.Inputs.AiGatewayModelProviderServiceConfigMicrosoftFoundryArgs
        {
            Direct = new Databricks.Inputs.AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectArgs
            {
                ApiKey = new Databricks.Inputs.AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectApiKeyArgs
                {
                    Plaintext = "string",
                },
                BaseUrl = "string",
                EntraServicePrincipal = new Databricks.Inputs.AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalArgs
                {
                    ClientId = "string",
                    ClientSecret = new Databricks.Inputs.AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalClientSecretArgs
                    {
                        Plaintext = "string",
                    },
                    TenantId = "string",
                },
                ServiceCredential = new Databricks.Inputs.AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectServiceCredentialArgs
                {
                    Name = "string",
                },
            },
        },
        Openai = new Databricks.Inputs.AiGatewayModelProviderServiceConfigOpenaiArgs
        {
            Direct = new Databricks.Inputs.AiGatewayModelProviderServiceConfigOpenaiDirectArgs
            {
                ApiKey = new Databricks.Inputs.AiGatewayModelProviderServiceConfigOpenaiDirectApiKeyArgs
                {
                    Plaintext = "string",
                },
                BaseUrl = "string",
                Organization = "string",
            },
        },
        ProviderType = "string",
        RateLimits = new[]
        {
            new Databricks.Inputs.AiGatewayModelProviderServiceConfigRateLimitArgs
            {
                Key = "string",
                RenewalPeriod = "string",
                Principal = "string",
                RequestTagKey = "string",
                RequestTagValue = "string",
                Requests = 0,
                Tokens = 0,
            },
        },
        Targets = new[]
        {
            new Databricks.Inputs.AiGatewayModelProviderServiceConfigTargetArgs
            {
                Model = "string",
                NativeApiTypes = new[]
                {
                    "string",
                },
            },
        },
    },
    Owner = "string",
    ProviderConfig = new Databricks.Inputs.AiGatewayModelProviderServiceProviderConfigArgs
    {
        WorkspaceId = "string",
    },
});

example, err := databricks.NewAiGatewayModelProviderService(ctx, "aiGatewayModelProviderServiceResource", &databricks.AiGatewayModelProviderServiceArgs{
	ModelProviderServiceId: pulumi.String("string"),
	Parent:                 pulumi.String("string"),
	Comment:                pulumi.String("string"),
	Config: &databricks.AiGatewayModelProviderServiceConfigArgs{
		AllowAllTargets: pulumi.Bool(false),
		AmazonBedrock: &databricks.AiGatewayModelProviderServiceConfigAmazonBedrockArgs{
			Direct: &databricks.AiGatewayModelProviderServiceConfigAmazonBedrockDirectArgs{
				AwsAccessKey: &databricks.AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeyArgs{
					AccessKeyId: pulumi.String("string"),
					SecretAccessKey: &databricks.AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeySecretAccessKeyArgs{
						Plaintext: pulumi.String("string"),
					},
				},
				Region: pulumi.String("string"),
				ServiceCredential: &databricks.AiGatewayModelProviderServiceConfigAmazonBedrockDirectServiceCredentialArgs{
					Name: pulumi.String("string"),
				},
			},
		},
		Anthropic: &databricks.AiGatewayModelProviderServiceConfigAnthropicArgs{
			Direct: &databricks.AiGatewayModelProviderServiceConfigAnthropicDirectArgs{
				ApiKey: &databricks.AiGatewayModelProviderServiceConfigAnthropicDirectApiKeyArgs{
					Plaintext: pulumi.String("string"),
				},
			},
			Relayed: &databricks.AiGatewayModelProviderServiceConfigAnthropicRelayedArgs{
				PlanType: pulumi.String("string"),
			},
		},
		AzureOpenai: &databricks.AiGatewayModelProviderServiceConfigAzureOpenaiArgs{
			Direct: &databricks.AiGatewayModelProviderServiceConfigAzureOpenaiDirectArgs{
				ApiKey: &databricks.AiGatewayModelProviderServiceConfigAzureOpenaiDirectApiKeyArgs{
					Plaintext: pulumi.String("string"),
				},
				BaseUrl: pulumi.String("string"),
				EntraServicePrincipal: &databricks.AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalArgs{
					ClientId: pulumi.String("string"),
					ClientSecret: &databricks.AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalClientSecretArgs{
						Plaintext: pulumi.String("string"),
					},
					TenantId: pulumi.String("string"),
				},
				ServiceCredential: &databricks.AiGatewayModelProviderServiceConfigAzureOpenaiDirectServiceCredentialArgs{
					Name: pulumi.String("string"),
				},
			},
		},
		Custom: &databricks.AiGatewayModelProviderServiceConfigCustomArgs{
			Direct: &databricks.AiGatewayModelProviderServiceConfigCustomDirectArgs{
				ApiKey: &databricks.AiGatewayModelProviderServiceConfigCustomDirectApiKeyArgs{
					Plaintext: pulumi.String("string"),
				},
				BaseUrl: pulumi.String("string"),
			},
		},
		ForwardHeaders:         pulumi.Bool(false),
		ForwardQueryParameters: pulumi.Bool(false),
		ForwardUnmanagedPaths:  pulumi.Bool(false),
		GeminiEnterprise: &databricks.AiGatewayModelProviderServiceConfigGeminiEnterpriseArgs{
			Direct: &databricks.AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectArgs{
				ApiKey: &databricks.AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectApiKeyArgs{
					Plaintext: pulumi.String("string"),
				},
				ProjectId: pulumi.String("string"),
				Region:    pulumi.String("string"),
			},
		},
		InferenceTable: &databricks.AiGatewayModelProviderServiceConfigInferenceTableArgs{
			Parent:          pulumi.String("string"),
			Disabled:        pulumi.Bool(false),
			IsDeleted:       pulumi.Bool(false),
			Table:           pulumi.String("string"),
			TableNamePrefix: pulumi.String("string"),
		},
		MicrosoftFoundry: &databricks.AiGatewayModelProviderServiceConfigMicrosoftFoundryArgs{
			Direct: &databricks.AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectArgs{
				ApiKey: &databricks.AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectApiKeyArgs{
					Plaintext: pulumi.String("string"),
				},
				BaseUrl: pulumi.String("string"),
				EntraServicePrincipal: &databricks.AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalArgs{
					ClientId: pulumi.String("string"),
					ClientSecret: &databricks.AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalClientSecretArgs{
						Plaintext: pulumi.String("string"),
					},
					TenantId: pulumi.String("string"),
				},
				ServiceCredential: &databricks.AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectServiceCredentialArgs{
					Name: pulumi.String("string"),
				},
			},
		},
		Openai: &databricks.AiGatewayModelProviderServiceConfigOpenaiArgs{
			Direct: &databricks.AiGatewayModelProviderServiceConfigOpenaiDirectArgs{
				ApiKey: &databricks.AiGatewayModelProviderServiceConfigOpenaiDirectApiKeyArgs{
					Plaintext: pulumi.String("string"),
				},
				BaseUrl:      pulumi.String("string"),
				Organization: pulumi.String("string"),
			},
		},
		ProviderType: pulumi.String("string"),
		RateLimits: databricks.AiGatewayModelProviderServiceConfigRateLimitArray{
			&databricks.AiGatewayModelProviderServiceConfigRateLimitArgs{
				Key:             pulumi.String("string"),
				RenewalPeriod:   pulumi.String("string"),
				Principal:       pulumi.String("string"),
				RequestTagKey:   pulumi.String("string"),
				RequestTagValue: pulumi.String("string"),
				Requests:        pulumi.Int(0),
				Tokens:          pulumi.Int(0),
			},
		},
		Targets: databricks.AiGatewayModelProviderServiceConfigTargetArray{
			&databricks.AiGatewayModelProviderServiceConfigTargetArgs{
				Model: pulumi.String("string"),
				NativeApiTypes: pulumi.StringArray{
					pulumi.String("string"),
				},
			},
		},
	},
	Owner: pulumi.String("string"),
	ProviderConfig: &databricks.AiGatewayModelProviderServiceProviderConfigArgs{
		WorkspaceId: pulumi.String("string"),
	},
})

resource "databricks_ai_gateway_model_provider_service" "aiGatewayModelProviderServiceResource" {
  lifecycle {
    create_before_destroy = true
  }
  model_provider_service_id = "string"
  parent                    = "string"
  comment                   = "string"
  config = {
    allow_all_targets = false
    amazon_bedrock = {
      direct = {
        aws_access_key = {
          access_key_id = "string"
          secret_access_key = {
            plaintext = "string"
          }
        }
        region = "string"
        service_credential = {
          name = "string"
        }
      }
    }
    anthropic = {
      direct = {
        api_key = {
          plaintext = "string"
        }
      }
      relayed = {
        plan_type = "string"
      }
    }
    azure_openai = {
      direct = {
        api_key = {
          plaintext = "string"
        }
        base_url = "string"
        entra_service_principal = {
          client_id = "string"
          client_secret = {
            plaintext = "string"
          }
          tenant_id = "string"
        }
        service_credential = {
          name = "string"
        }
      }
    }
    custom = {
      direct = {
        api_key = {
          plaintext = "string"
        }
        base_url = "string"
      }
    }
    forward_headers          = false
    forward_query_parameters = false
    forward_unmanaged_paths  = false
    gemini_enterprise = {
      direct = {
        api_key = {
          plaintext = "string"
        }
        project_id = "string"
        region     = "string"
      }
    }
    inference_table = {
      parent            = "string"
      disabled          = false
      is_deleted        = false
      table             = "string"
      table_name_prefix = "string"
    }
    microsoft_foundry = {
      direct = {
        api_key = {
          plaintext = "string"
        }
        base_url = "string"
        entra_service_principal = {
          client_id = "string"
          client_secret = {
            plaintext = "string"
          }
          tenant_id = "string"
        }
        service_credential = {
          name = "string"
        }
      }
    }
    openai = {
      direct = {
        api_key = {
          plaintext = "string"
        }
        base_url     = "string"
        organization = "string"
      }
    }
    provider_type = "string"
    rate_limits = [{
      key               = "string"
      renewal_period    = "string"
      principal         = "string"
      request_tag_key   = "string"
      request_tag_value = "string"
      requests          = 0
      tokens            = 0
    }]
    targets = [{
      model            = "string"
      native_api_types = ["string"]
    }]
  }
  owner = "string"
  provider_config = {
    workspace_id = "string"
  }
}

var aiGatewayModelProviderServiceResource = new AiGatewayModelProviderService("aiGatewayModelProviderServiceResource", AiGatewayModelProviderServiceArgs.builder()
    .modelProviderServiceId("string")
    .parent("string")
    .comment("string")
    .config(AiGatewayModelProviderServiceConfigArgs.builder()
        .allowAllTargets(false)
        .amazonBedrock(AiGatewayModelProviderServiceConfigAmazonBedrockArgs.builder()
            .direct(AiGatewayModelProviderServiceConfigAmazonBedrockDirectArgs.builder()
                .awsAccessKey(AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeyArgs.builder()
                    .accessKeyId("string")
                    .secretAccessKey(AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeySecretAccessKeyArgs.builder()
                        .plaintext("string")
                        .build())
                    .build())
                .region("string")
                .serviceCredential(AiGatewayModelProviderServiceConfigAmazonBedrockDirectServiceCredentialArgs.builder()
                    .name("string")
                    .build())
                .build())
            .build())
        .anthropic(AiGatewayModelProviderServiceConfigAnthropicArgs.builder()
            .direct(AiGatewayModelProviderServiceConfigAnthropicDirectArgs.builder()
                .apiKey(AiGatewayModelProviderServiceConfigAnthropicDirectApiKeyArgs.builder()
                    .plaintext("string")
                    .build())
                .build())
            .relayed(AiGatewayModelProviderServiceConfigAnthropicRelayedArgs.builder()
                .planType("string")
                .build())
            .build())
        .azureOpenai(AiGatewayModelProviderServiceConfigAzureOpenaiArgs.builder()
            .direct(AiGatewayModelProviderServiceConfigAzureOpenaiDirectArgs.builder()
                .apiKey(AiGatewayModelProviderServiceConfigAzureOpenaiDirectApiKeyArgs.builder()
                    .plaintext("string")
                    .build())
                .baseUrl("string")
                .entraServicePrincipal(AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalArgs.builder()
                    .clientId("string")
                    .clientSecret(AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalClientSecretArgs.builder()
                        .plaintext("string")
                        .build())
                    .tenantId("string")
                    .build())
                .serviceCredential(AiGatewayModelProviderServiceConfigAzureOpenaiDirectServiceCredentialArgs.builder()
                    .name("string")
                    .build())
                .build())
            .build())
        .custom(AiGatewayModelProviderServiceConfigCustomArgs.builder()
            .direct(AiGatewayModelProviderServiceConfigCustomDirectArgs.builder()
                .apiKey(AiGatewayModelProviderServiceConfigCustomDirectApiKeyArgs.builder()
                    .plaintext("string")
                    .build())
                .baseUrl("string")
                .build())
            .build())
        .forwardHeaders(false)
        .forwardQueryParameters(false)
        .forwardUnmanagedPaths(false)
        .geminiEnterprise(AiGatewayModelProviderServiceConfigGeminiEnterpriseArgs.builder()
            .direct(AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectArgs.builder()
                .apiKey(AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectApiKeyArgs.builder()
                    .plaintext("string")
                    .build())
                .projectId("string")
                .region("string")
                .build())
            .build())
        .inferenceTable(AiGatewayModelProviderServiceConfigInferenceTableArgs.builder()
            .parent("string")
            .disabled(false)
            .isDeleted(false)
            .table("string")
            .tableNamePrefix("string")
            .build())
        .microsoftFoundry(AiGatewayModelProviderServiceConfigMicrosoftFoundryArgs.builder()
            .direct(AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectArgs.builder()
                .apiKey(AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectApiKeyArgs.builder()
                    .plaintext("string")
                    .build())
                .baseUrl("string")
                .entraServicePrincipal(AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalArgs.builder()
                    .clientId("string")
                    .clientSecret(AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalClientSecretArgs.builder()
                        .plaintext("string")
                        .build())
                    .tenantId("string")
                    .build())
                .serviceCredential(AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectServiceCredentialArgs.builder()
                    .name("string")
                    .build())
                .build())
            .build())
        .openai(AiGatewayModelProviderServiceConfigOpenaiArgs.builder()
            .direct(AiGatewayModelProviderServiceConfigOpenaiDirectArgs.builder()
                .apiKey(AiGatewayModelProviderServiceConfigOpenaiDirectApiKeyArgs.builder()
                    .plaintext("string")
                    .build())
                .baseUrl("string")
                .organization("string")
                .build())
            .build())
        .providerType("string")
        .rateLimits(AiGatewayModelProviderServiceConfigRateLimitArgs.builder()
            .key("string")
            .renewalPeriod("string")
            .principal("string")
            .requestTagKey("string")
            .requestTagValue("string")
            .requests(0)
            .tokens(0)
            .build())
        .targets(AiGatewayModelProviderServiceConfigTargetArgs.builder()
            .model("string")
            .nativeApiTypes("string")
            .build())
        .build())
    .owner("string")
    .providerConfig(AiGatewayModelProviderServiceProviderConfigArgs.builder()
        .workspaceId("string")
        .build())
    .build());

ai_gateway_model_provider_service_resource = databricks.AiGatewayModelProviderService("aiGatewayModelProviderServiceResource",
    model_provider_service_id="string",
    parent="string",
    comment="string",
    config={
        "allow_all_targets": False,
        "amazon_bedrock": {
            "direct": {
                "aws_access_key": {
                    "access_key_id": "string",
                    "secret_access_key": {
                        "plaintext": "string",
                    },
                },
                "region": "string",
                "service_credential": {
                    "name": "string",
                },
            },
        },
        "anthropic": {
            "direct": {
                "api_key": {
                    "plaintext": "string",
                },
            },
            "relayed": {
                "plan_type": "string",
            },
        },
        "azure_openai": {
            "direct": {
                "api_key": {
                    "plaintext": "string",
                },
                "base_url": "string",
                "entra_service_principal": {
                    "client_id": "string",
                    "client_secret": {
                        "plaintext": "string",
                    },
                    "tenant_id": "string",
                },
                "service_credential": {
                    "name": "string",
                },
            },
        },
        "custom": {
            "direct": {
                "api_key": {
                    "plaintext": "string",
                },
                "base_url": "string",
            },
        },
        "forward_headers": False,
        "forward_query_parameters": False,
        "forward_unmanaged_paths": False,
        "gemini_enterprise": {
            "direct": {
                "api_key": {
                    "plaintext": "string",
                },
                "project_id": "string",
                "region": "string",
            },
        },
        "inference_table": {
            "parent": "string",
            "disabled": False,
            "is_deleted": False,
            "table": "string",
            "table_name_prefix": "string",
        },
        "microsoft_foundry": {
            "direct": {
                "api_key": {
                    "plaintext": "string",
                },
                "base_url": "string",
                "entra_service_principal": {
                    "client_id": "string",
                    "client_secret": {
                        "plaintext": "string",
                    },
                    "tenant_id": "string",
                },
                "service_credential": {
                    "name": "string",
                },
            },
        },
        "openai": {
            "direct": {
                "api_key": {
                    "plaintext": "string",
                },
                "base_url": "string",
                "organization": "string",
            },
        },
        "provider_type": "string",
        "rate_limits": [{
            "key": "string",
            "renewal_period": "string",
            "principal": "string",
            "request_tag_key": "string",
            "request_tag_value": "string",
            "requests": 0,
            "tokens": 0,
        }],
        "targets": [{
            "model": "string",
            "native_api_types": ["string"],
        }],
    },
    owner="string",
    provider_config={
        "workspace_id": "string",
    })

const aiGatewayModelProviderServiceResource = new databricks.AiGatewayModelProviderService("aiGatewayModelProviderServiceResource", {
    modelProviderServiceId: "string",
    parent: "string",
    comment: "string",
    config: {
        allowAllTargets: false,
        amazonBedrock: {
            direct: {
                awsAccessKey: {
                    accessKeyId: "string",
                    secretAccessKey: {
                        plaintext: "string",
                    },
                },
                region: "string",
                serviceCredential: {
                    name: "string",
                },
            },
        },
        anthropic: {
            direct: {
                apiKey: {
                    plaintext: "string",
                },
            },
            relayed: {
                planType: "string",
            },
        },
        azureOpenai: {
            direct: {
                apiKey: {
                    plaintext: "string",
                },
                baseUrl: "string",
                entraServicePrincipal: {
                    clientId: "string",
                    clientSecret: {
                        plaintext: "string",
                    },
                    tenantId: "string",
                },
                serviceCredential: {
                    name: "string",
                },
            },
        },
        custom: {
            direct: {
                apiKey: {
                    plaintext: "string",
                },
                baseUrl: "string",
            },
        },
        forwardHeaders: false,
        forwardQueryParameters: false,
        forwardUnmanagedPaths: false,
        geminiEnterprise: {
            direct: {
                apiKey: {
                    plaintext: "string",
                },
                projectId: "string",
                region: "string",
            },
        },
        inferenceTable: {
            parent: "string",
            disabled: false,
            isDeleted: false,
            table: "string",
            tableNamePrefix: "string",
        },
        microsoftFoundry: {
            direct: {
                apiKey: {
                    plaintext: "string",
                },
                baseUrl: "string",
                entraServicePrincipal: {
                    clientId: "string",
                    clientSecret: {
                        plaintext: "string",
                    },
                    tenantId: "string",
                },
                serviceCredential: {
                    name: "string",
                },
            },
        },
        openai: {
            direct: {
                apiKey: {
                    plaintext: "string",
                },
                baseUrl: "string",
                organization: "string",
            },
        },
        providerType: "string",
        rateLimits: [{
            key: "string",
            renewalPeriod: "string",
            principal: "string",
            requestTagKey: "string",
            requestTagValue: "string",
            requests: 0,
            tokens: 0,
        }],
        targets: [{
            model: "string",
            nativeApiTypes: ["string"],
        }],
    },
    owner: "string",
    providerConfig: {
        workspaceId: "string",
    },
});

type: databricks:AiGatewayModelProviderService
properties:
    comment: string
    config:
        allowAllTargets: false
        amazonBedrock:
            direct:
                awsAccessKey:
                    accessKeyId: string
                    secretAccessKey:
                        plaintext: string
                region: string
                serviceCredential:
                    name: string
        anthropic:
            direct:
                apiKey:
                    plaintext: string
            relayed:
                planType: string
        azureOpenai:
            direct:
                apiKey:
                    plaintext: string
                baseUrl: string
                entraServicePrincipal:
                    clientId: string
                    clientSecret:
                        plaintext: string
                    tenantId: string
                serviceCredential:
                    name: string
        custom:
            direct:
                apiKey:
                    plaintext: string
                baseUrl: string
        forwardHeaders: false
        forwardQueryParameters: false
        forwardUnmanagedPaths: false
        geminiEnterprise:
            direct:
                apiKey:
                    plaintext: string
                projectId: string
                region: string
        inferenceTable:
            disabled: false
            isDeleted: false
            parent: string
            table: string
            tableNamePrefix: string
        microsoftFoundry:
            direct:
                apiKey:
                    plaintext: string
                baseUrl: string
                entraServicePrincipal:
                    clientId: string
                    clientSecret:
                        plaintext: string
                    tenantId: string
                serviceCredential:
                    name: string
        openai:
            direct:
                apiKey:
                    plaintext: string
                baseUrl: string
                organization: string
        providerType: string
        rateLimits:
            - key: string
              principal: string
              renewalPeriod: string
              requestTagKey: string
              requestTagValue: string
              requests: 0
              tokens: 0
        targets:
            - model: string
              nativeApiTypes:
                - string
    modelProviderServiceId: string
    owner: string
    parent: string
    providerConfig:
        workspaceId: string

AiGatewayModelProviderService Resource Properties

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

Inputs

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

The AiGatewayModelProviderService resource accepts the following input properties:

ModelProviderServiceId string: Name for the model provider service, e.g. "openaiProd"
Parent string: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
Comment string: User-provided description
Config AiGatewayModelProviderServiceConfig: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
Owner string: The owner of the model provider service. Write-only; read owner via effective_owner
ProviderConfig AiGatewayModelProviderServiceProviderConfig: Configure the provider for management through account provider.

ModelProviderServiceId string: Name for the model provider service, e.g. "openaiProd"
Parent string: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
Comment string: User-provided description
Config AiGatewayModelProviderServiceConfigArgs: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
Owner string: The owner of the model provider service. Write-only; read owner via effective_owner
ProviderConfig AiGatewayModelProviderServiceProviderConfigArgs: Configure the provider for management through account provider.

model_provider_service_id string: Name for the model provider service, e.g. "openaiProd"
parent string: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
comment string: User-provided description
config object: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
owner string: The owner of the model provider service. Write-only; read owner via effective_owner
provider_config object: Configure the provider for management through account provider.

modelProviderServiceId String: Name for the model provider service, e.g. "openaiProd"
parent String: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
comment String: User-provided description
config AiGatewayModelProviderServiceConfig: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
owner String: The owner of the model provider service. Write-only; read owner via effective_owner
providerConfig AiGatewayModelProviderServiceProviderConfig: Configure the provider for management through account provider.

modelProviderServiceId string: Name for the model provider service, e.g. "openaiProd"
parent string: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
comment string: User-provided description
config AiGatewayModelProviderServiceConfig: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
owner string: The owner of the model provider service. Write-only; read owner via effective_owner
providerConfig AiGatewayModelProviderServiceProviderConfig: Configure the provider for management through account provider.

model_provider_service_id str: Name for the model provider service, e.g. "openaiProd"
parent str: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
comment str: User-provided description
config AiGatewayModelProviderServiceConfigArgs: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
owner str: The owner of the model provider service. Write-only; read owner via effective_owner
provider_config AiGatewayModelProviderServiceProviderConfigArgs: Configure the provider for management through account provider.

modelProviderServiceId String: Name for the model provider service, e.g. "openaiProd"
parent String: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
comment String: User-provided description
config Property Map: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
owner String: The owner of the model provider service. Write-only; read owner via effective_owner
providerConfig Property Map: Configure the provider for management through account provider.

Outputs

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

CreateTime string: (string) - When the provider service was created
CreatedBy string: (string) - Creator identity
EffectiveOwner string: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
Etag string: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
Id string: The provider-assigned unique ID for this managed resource.
MetastoreId string: (string) - Metastore hosting the provider service
Name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
UpdateTime string: (string) - When the provider service was last modified
UpdatedBy string: (string) - Identity of the last updater

CreateTime string: (string) - When the provider service was created
CreatedBy string: (string) - Creator identity
EffectiveOwner string: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
Etag string: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
Id string: The provider-assigned unique ID for this managed resource.
MetastoreId string: (string) - Metastore hosting the provider service
Name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
UpdateTime string: (string) - When the provider service was last modified
UpdatedBy string: (string) - Identity of the last updater

create_time string: (string) - When the provider service was created
created_by string: (string) - Creator identity
effective_owner string: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
etag string: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
id string: The provider-assigned unique ID for this managed resource.
metastore_id string: (string) - Metastore hosting the provider service
name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
update_time string: (string) - When the provider service was last modified
updated_by string: (string) - Identity of the last updater

createTime String: (string) - When the provider service was created
createdBy String: (string) - Creator identity
effectiveOwner String: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
etag String: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
id String: The provider-assigned unique ID for this managed resource.
metastoreId String: (string) - Metastore hosting the provider service
name String: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
updateTime String: (string) - When the provider service was last modified
updatedBy String: (string) - Identity of the last updater

createTime string: (string) - When the provider service was created
createdBy string: (string) - Creator identity
effectiveOwner string: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
etag string: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
id string: The provider-assigned unique ID for this managed resource.
metastoreId string: (string) - Metastore hosting the provider service
name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
updateTime string: (string) - When the provider service was last modified
updatedBy string: (string) - Identity of the last updater

create_time str: (string) - When the provider service was created
created_by str: (string) - Creator identity
effective_owner str: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
etag str: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
id str: The provider-assigned unique ID for this managed resource.
metastore_id str: (string) - Metastore hosting the provider service
name str: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
update_time str: (string) - When the provider service was last modified
updated_by str: (string) - Identity of the last updater

createTime String: (string) - When the provider service was created
createdBy String: (string) - Creator identity
effectiveOwner String: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
etag String: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
id String: The provider-assigned unique ID for this managed resource.
metastoreId String: (string) - Metastore hosting the provider service
name String: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
updateTime String: (string) - When the provider service was last modified
updatedBy String: (string) - Identity of the last updater

Look up Existing AiGatewayModelProviderService Resource

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

public static get(name: string, id: Input<ID>, state?: AiGatewayModelProviderServiceState, opts?: CustomResourceOptions): AiGatewayModelProviderService

@staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        comment: Optional[str] = None,
        config: Optional[AiGatewayModelProviderServiceConfigArgs] = None,
        create_time: Optional[str] = None,
        created_by: Optional[str] = None,
        effective_owner: Optional[str] = None,
        etag: Optional[str] = None,
        metastore_id: Optional[str] = None,
        model_provider_service_id: Optional[str] = None,
        name: Optional[str] = None,
        owner: Optional[str] = None,
        parent: Optional[str] = None,
        provider_config: Optional[AiGatewayModelProviderServiceProviderConfigArgs] = None,
        update_time: Optional[str] = None,
        updated_by: Optional[str] = None) -> AiGatewayModelProviderService

func GetAiGatewayModelProviderService(ctx *Context, name string, id IDInput, state *AiGatewayModelProviderServiceState, opts ...ResourceOption) (*AiGatewayModelProviderService, error)

public static AiGatewayModelProviderService Get(string name, Input<string> id, AiGatewayModelProviderServiceState? state, CustomResourceOptions? opts = null)

public static AiGatewayModelProviderService get(String name, Output<String> id, AiGatewayModelProviderServiceState state, CustomResourceOptions options)

resources:  _:    type: databricks:AiGatewayModelProviderService    get:      id: ${id}

import {
  to = databricks_ai_gateway_model_provider_service.example
  id = "${id}"
}

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

resource_name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

name: The unique name of the resulting resource.
id: The unique provider ID of the resource to lookup.
state: Any extra arguments used during the lookup.
opts: A bag of options that control this resource's behavior.

The following state arguments are supported:

Comment string: User-provided description
Config AiGatewayModelProviderServiceConfig: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
CreateTime string: (string) - When the provider service was created
CreatedBy string: (string) - Creator identity
EffectiveOwner string: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
Etag string: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
MetastoreId string: (string) - Metastore hosting the provider service
ModelProviderServiceId string: Name for the model provider service, e.g. "openaiProd"
Name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
Owner string: The owner of the model provider service. Write-only; read owner via effective_owner
Parent string: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
ProviderConfig AiGatewayModelProviderServiceProviderConfig: Configure the provider for management through account provider.
UpdateTime string: (string) - When the provider service was last modified
UpdatedBy string: (string) - Identity of the last updater

Comment string: User-provided description
Config AiGatewayModelProviderServiceConfigArgs: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
CreateTime string: (string) - When the provider service was created
CreatedBy string: (string) - Creator identity
EffectiveOwner string: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
Etag string: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
MetastoreId string: (string) - Metastore hosting the provider service
ModelProviderServiceId string: Name for the model provider service, e.g. "openaiProd"
Name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
Owner string: The owner of the model provider service. Write-only; read owner via effective_owner
Parent string: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
ProviderConfig AiGatewayModelProviderServiceProviderConfigArgs: Configure the provider for management through account provider.
UpdateTime string: (string) - When the provider service was last modified
UpdatedBy string: (string) - Identity of the last updater

comment string: User-provided description
config object: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
create_time string: (string) - When the provider service was created
created_by string: (string) - Creator identity
effective_owner string: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
etag string: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
metastore_id string: (string) - Metastore hosting the provider service
model_provider_service_id string: Name for the model provider service, e.g. "openaiProd"
name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
owner string: The owner of the model provider service. Write-only; read owner via effective_owner
parent string: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
provider_config object: Configure the provider for management through account provider.
update_time string: (string) - When the provider service was last modified
updated_by string: (string) - Identity of the last updater

comment String: User-provided description
config AiGatewayModelProviderServiceConfig: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
createTime String: (string) - When the provider service was created
createdBy String: (string) - Creator identity
effectiveOwner String: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
etag String: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
metastoreId String: (string) - Metastore hosting the provider service
modelProviderServiceId String: Name for the model provider service, e.g. "openaiProd"
name String: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
owner String: The owner of the model provider service. Write-only; read owner via effective_owner
parent String: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
providerConfig AiGatewayModelProviderServiceProviderConfig: Configure the provider for management through account provider.
updateTime String: (string) - When the provider service was last modified
updatedBy String: (string) - Identity of the last updater

comment string: User-provided description
config AiGatewayModelProviderServiceConfig: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
createTime string: (string) - When the provider service was created
createdBy string: (string) - Creator identity
effectiveOwner string: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
etag string: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
metastoreId string: (string) - Metastore hosting the provider service
modelProviderServiceId string: Name for the model provider service, e.g. "openaiProd"
name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
owner string: The owner of the model provider service. Write-only; read owner via effective_owner
parent string: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
providerConfig AiGatewayModelProviderServiceProviderConfig: Configure the provider for management through account provider.
updateTime string: (string) - When the provider service was last modified
updatedBy string: (string) - Identity of the last updater

comment str: User-provided description
config AiGatewayModelProviderServiceConfigArgs: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
create_time str: (string) - When the provider service was created
created_by str: (string) - Creator identity
effective_owner str: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
etag str: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
metastore_id str: (string) - Metastore hosting the provider service
model_provider_service_id str: Name for the model provider service, e.g. "openaiProd"
name str: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
owner str: The owner of the model provider service. Write-only; read owner via effective_owner
parent str: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
provider_config AiGatewayModelProviderServiceProviderConfigArgs: Configure the provider for management through account provider.
update_time str: (string) - When the provider service was last modified
updated_by str: (string) - Identity of the last updater

comment String: User-provided description
config Property Map: Behavioral configuration: provider connection, model catalog, and passthrough policy. See ModelProviderServiceConfig for the per-field contract. Required on CreateModelProviderService; on Update it is required only when config (or a config.* subpath) appears in updateMask
createTime String: (string) - When the provider service was created
createdBy String: (string) - Creator identity
effectiveOwner String: (string) - The resolved owner of the model provider service. Falls back to the caller's identity when owner is not explicitly set on creation
etag String: (string) - Optimistic concurrency control token. Server-generated from the entity's state and returned on every read. To use it as an if-match precondition on a mutation, echo the last-read value back via the dedicated etag field on the Update / Delete request; the server rejects the mutation if the stored etag differs
metastoreId String: (string) - Metastore hosting the provider service
modelProviderServiceId String: Name for the model provider service, e.g. "openaiProd"
name String: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete
owner String: The owner of the model provider service. Write-only; read owner via effective_owner
parent String: Name of the parent schema. Format: schemas/{catalog}.{schema}. Each {...} component is capped at 255 characters individually
providerConfig Property Map: Configure the provider for management through account provider.
updateTime String: (string) - When the provider service was last modified
updatedBy String: (string) - Identity of the last updater

Supporting Types

AiGatewayModelProviderServiceConfig, AiGatewayModelProviderServiceConfigArgs

AllowAllTargets bool

When true, accepts any model exposed by the upstream provider; targets is not required and does not restrict routability. When false, only models listed in targets are routable

AmazonBedrock AiGatewayModelProviderServiceConfigAmazonBedrock

Anthropic AiGatewayModelProviderServiceConfigAnthropic

AzureOpenai AiGatewayModelProviderServiceConfigAzureOpenai

Custom AiGatewayModelProviderServiceConfigCustom

ForwardHeaders bool

Whether to forward incoming request headers to the upstream provider. Applies to managed (multi-model) requests as well as passthrough requests served by this provider service. Governance-level decision by the provider service owner; not selectable per inference call

ForwardQueryParameters bool

Whether to forward incoming request query parameters to the upstream provider. Same trust-boundary semantics as forwardHeaders

ForwardUnmanagedPaths bool

Whether to forward request paths that fall outside this service's managed API set to the upstream provider as opaque passthrough. When true, requests addressed to subpaths not recognized by the managed API surface are proxied to the upstream provider over the same provider connection. When false, only managed-API paths are served. Governance-level decision by the provider service owner; expanding this expands the trust boundary that the ModelProviderService exposes

GeminiEnterprise AiGatewayModelProviderServiceConfigGeminiEnterprise

InferenceTable AiGatewayModelProviderServiceConfigInferenceTable

Inference table configuration for payload logging when this provider service is invoked directly. When it is invoked through a model service, the model service's own inference table captures the invocation instead. Mirrors ModelServiceConfig.inference_table / AgentServiceConfig.inference_table

MicrosoftFoundry AiGatewayModelProviderServiceConfigMicrosoftFoundry

Openai AiGatewayModelProviderServiceConfigOpenai

ProviderType string

Provider type discriminator. Required at create time; immutable after. Determines which variant of the provider oneof must be set. May not be changed via Update; attempts to include config.provider_type in UpdateModelProviderServiceRequest.update_mask are rejected.

Required on CreateModelProviderService and immutable thereafter. Possible values are: EXTERNAL_MODEL_PROVIDER_TYPE_AMAZON_BEDROCK, EXTERNAL_MODEL_PROVIDER_TYPE_ANTHROPIC, EXTERNAL_MODEL_PROVIDER_TYPE_AZURE_OPENAI, EXTERNAL_MODEL_PROVIDER_TYPE_CUSTOM, EXTERNAL_MODEL_PROVIDER_TYPE_GEMINI_ENTERPRISE, EXTERNAL_MODEL_PROVIDER_TYPE_MICROSOFT_FOUNDRY, EXTERNAL_MODEL_PROVIDER_TYPE_OPENAI

RateLimits List<AiGatewayModelProviderServiceConfigRateLimit>

Rate limits applied when this provider service is invoked directly. When it is invoked through a model service, the model service's own rateLimits apply instead. Mirrors ModelServiceConfig.rate_limits / McpServiceConfig.rate_limits

Targets List<AiGatewayModelProviderServiceConfigTarget>

Routing targets this provider service exposes (provider-side model identifier + unified API types per entry). Required (>=1) when allowAllTargets = false; optional and additive when allowAllTargets = true. References from ExternalModelConfig.target must match an entry here unless allowAllTargets = true

AllowAllTargets bool

When true, accepts any model exposed by the upstream provider; targets is not required and does not restrict routability. When false, only models listed in targets are routable

AmazonBedrock AiGatewayModelProviderServiceConfigAmazonBedrock

Anthropic AiGatewayModelProviderServiceConfigAnthropic

AzureOpenai AiGatewayModelProviderServiceConfigAzureOpenai

Custom AiGatewayModelProviderServiceConfigCustom

ForwardHeaders bool

ForwardQueryParameters bool

Whether to forward incoming request query parameters to the upstream provider. Same trust-boundary semantics as forwardHeaders

ForwardUnmanagedPaths bool

GeminiEnterprise AiGatewayModelProviderServiceConfigGeminiEnterprise

InferenceTable AiGatewayModelProviderServiceConfigInferenceTable

MicrosoftFoundry AiGatewayModelProviderServiceConfigMicrosoftFoundry

Openai AiGatewayModelProviderServiceConfigOpenai

ProviderType string

RateLimits []AiGatewayModelProviderServiceConfigRateLimit

Targets []AiGatewayModelProviderServiceConfigTarget

allow_all_targets bool

When true, accepts any model exposed by the upstream provider; targets is not required and does not restrict routability. When false, only models listed in targets are routable

amazon_bedrock object

anthropic object

azure_openai object

custom object

forward_headers bool

forward_query_parameters bool

Whether to forward incoming request query parameters to the upstream provider. Same trust-boundary semantics as forwardHeaders

forward_unmanaged_paths bool

gemini_enterprise object

inference_table object

microsoft_foundry object

openai object

provider_type string

rate_limits list(object)

targets list(object)

allowAllTargets Boolean

When true, accepts any model exposed by the upstream provider; targets is not required and does not restrict routability. When false, only models listed in targets are routable

amazonBedrock AiGatewayModelProviderServiceConfigAmazonBedrock

anthropic AiGatewayModelProviderServiceConfigAnthropic

azureOpenai AiGatewayModelProviderServiceConfigAzureOpenai

custom AiGatewayModelProviderServiceConfigCustom

forwardHeaders Boolean

forwardQueryParameters Boolean

Whether to forward incoming request query parameters to the upstream provider. Same trust-boundary semantics as forwardHeaders

forwardUnmanagedPaths Boolean

geminiEnterprise AiGatewayModelProviderServiceConfigGeminiEnterprise

inferenceTable AiGatewayModelProviderServiceConfigInferenceTable

microsoftFoundry AiGatewayModelProviderServiceConfigMicrosoftFoundry

openai AiGatewayModelProviderServiceConfigOpenai

providerType String

rateLimits List<AiGatewayModelProviderServiceConfigRateLimit>

targets List<AiGatewayModelProviderServiceConfigTarget>

allowAllTargets boolean

When true, accepts any model exposed by the upstream provider; targets is not required and does not restrict routability. When false, only models listed in targets are routable

amazonBedrock AiGatewayModelProviderServiceConfigAmazonBedrock

anthropic AiGatewayModelProviderServiceConfigAnthropic

azureOpenai AiGatewayModelProviderServiceConfigAzureOpenai

custom AiGatewayModelProviderServiceConfigCustom

forwardHeaders boolean

forwardQueryParameters boolean

Whether to forward incoming request query parameters to the upstream provider. Same trust-boundary semantics as forwardHeaders

forwardUnmanagedPaths boolean

geminiEnterprise AiGatewayModelProviderServiceConfigGeminiEnterprise

inferenceTable AiGatewayModelProviderServiceConfigInferenceTable

microsoftFoundry AiGatewayModelProviderServiceConfigMicrosoftFoundry

openai AiGatewayModelProviderServiceConfigOpenai

providerType string

rateLimits AiGatewayModelProviderServiceConfigRateLimit[]

targets AiGatewayModelProviderServiceConfigTarget[]

allow_all_targets bool

When true, accepts any model exposed by the upstream provider; targets is not required and does not restrict routability. When false, only models listed in targets are routable

amazon_bedrock AiGatewayModelProviderServiceConfigAmazonBedrock

anthropic AiGatewayModelProviderServiceConfigAnthropic

azure_openai AiGatewayModelProviderServiceConfigAzureOpenai

custom AiGatewayModelProviderServiceConfigCustom

forward_headers bool

forward_query_parameters bool

Whether to forward incoming request query parameters to the upstream provider. Same trust-boundary semantics as forwardHeaders

forward_unmanaged_paths bool

gemini_enterprise AiGatewayModelProviderServiceConfigGeminiEnterprise

inference_table AiGatewayModelProviderServiceConfigInferenceTable

microsoft_foundry AiGatewayModelProviderServiceConfigMicrosoftFoundry

openai AiGatewayModelProviderServiceConfigOpenai

provider_type str

rate_limits Sequence[AiGatewayModelProviderServiceConfigRateLimit]

targets Sequence[AiGatewayModelProviderServiceConfigTarget]

allowAllTargets Boolean

When true, accepts any model exposed by the upstream provider; targets is not required and does not restrict routability. When false, only models listed in targets are routable

amazonBedrock Property Map

anthropic Property Map

azureOpenai Property Map

custom Property Map

forwardHeaders Boolean

forwardQueryParameters Boolean

Whether to forward incoming request query parameters to the upstream provider. Same trust-boundary semantics as forwardHeaders

forwardUnmanagedPaths Boolean

geminiEnterprise Property Map

inferenceTable Property Map

microsoftFoundry Property Map

openai Property Map

providerType String

rateLimits List<Property Map>

targets List<Property Map>

AiGatewayModelProviderServiceConfigAmazonBedrock, AiGatewayModelProviderServiceConfigAmazonBedrockArgs

Direct AiGatewayModelProviderServiceConfigAmazonBedrockDirect

Direct AiGatewayModelProviderServiceConfigAmazonBedrockDirect

direct object

direct AiGatewayModelProviderServiceConfigAmazonBedrockDirect

direct AiGatewayModelProviderServiceConfigAmazonBedrockDirect

direct AiGatewayModelProviderServiceConfigAmazonBedrockDirect

direct Property Map

AiGatewayModelProviderServiceConfigAmazonBedrockDirect, AiGatewayModelProviderServiceConfigAmazonBedrockDirectArgs

AwsAccessKey AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKey: AWS access-key-pair auth. Mutually exclusive with serviceCredential
Region string
ServiceCredential AiGatewayModelProviderServiceConfigAmazonBedrockDirectServiceCredential

AwsAccessKey AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKey: AWS access-key-pair auth. Mutually exclusive with serviceCredential
Region string
ServiceCredential AiGatewayModelProviderServiceConfigAmazonBedrockDirectServiceCredential

aws_access_key object: AWS access-key-pair auth. Mutually exclusive with serviceCredential
region string
service_credential object

awsAccessKey AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKey: AWS access-key-pair auth. Mutually exclusive with serviceCredential
region String
serviceCredential AiGatewayModelProviderServiceConfigAmazonBedrockDirectServiceCredential

awsAccessKey AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKey: AWS access-key-pair auth. Mutually exclusive with serviceCredential
region string
serviceCredential AiGatewayModelProviderServiceConfigAmazonBedrockDirectServiceCredential

aws_access_key AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKey: AWS access-key-pair auth. Mutually exclusive with serviceCredential
region str
service_credential AiGatewayModelProviderServiceConfigAmazonBedrockDirectServiceCredential

awsAccessKey Property Map: AWS access-key-pair auth. Mutually exclusive with serviceCredential
region String
serviceCredential Property Map

AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKey, AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeyArgs

AccessKeyId string: AWS access key ID. Required on Create when using access-key auth. Treated as username-equivalent (not a secret value): round-trips on reads and is scrubbed from audit logs
SecretAccessKey AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeySecretAccessKey: AWS secret access key paired with accessKeyId. Required on Create when using access-key auth. Supplied as inline plaintext via ProviderSecret.plaintext

AccessKeyId string: AWS access key ID. Required on Create when using access-key auth. Treated as username-equivalent (not a secret value): round-trips on reads and is scrubbed from audit logs
SecretAccessKey AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeySecretAccessKey: AWS secret access key paired with accessKeyId. Required on Create when using access-key auth. Supplied as inline plaintext via ProviderSecret.plaintext

access_key_id string: AWS access key ID. Required on Create when using access-key auth. Treated as username-equivalent (not a secret value): round-trips on reads and is scrubbed from audit logs
secret_access_key object: AWS secret access key paired with accessKeyId. Required on Create when using access-key auth. Supplied as inline plaintext via ProviderSecret.plaintext

accessKeyId String: AWS access key ID. Required on Create when using access-key auth. Treated as username-equivalent (not a secret value): round-trips on reads and is scrubbed from audit logs
secretAccessKey AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeySecretAccessKey: AWS secret access key paired with accessKeyId. Required on Create when using access-key auth. Supplied as inline plaintext via ProviderSecret.plaintext

accessKeyId string: AWS access key ID. Required on Create when using access-key auth. Treated as username-equivalent (not a secret value): round-trips on reads and is scrubbed from audit logs
secretAccessKey AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeySecretAccessKey: AWS secret access key paired with accessKeyId. Required on Create when using access-key auth. Supplied as inline plaintext via ProviderSecret.plaintext

access_key_id str: AWS access key ID. Required on Create when using access-key auth. Treated as username-equivalent (not a secret value): round-trips on reads and is scrubbed from audit logs
secret_access_key AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeySecretAccessKey: AWS secret access key paired with accessKeyId. Required on Create when using access-key auth. Supplied as inline plaintext via ProviderSecret.plaintext

accessKeyId String: AWS access key ID. Required on Create when using access-key auth. Treated as username-equivalent (not a secret value): round-trips on reads and is scrubbed from audit logs
secretAccessKey Property Map: AWS secret access key paired with accessKeyId. Required on Create when using access-key auth. Supplied as inline plaintext via ProviderSecret.plaintext

AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeySecretAccessKey, AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeySecretAccessKeyArgs

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext str: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

AiGatewayModelProviderServiceConfigAmazonBedrockDirectServiceCredential, AiGatewayModelProviderServiceConfigAmazonBedrockDirectServiceCredentialArgs

Name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

Name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name String: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name str: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name String: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

AiGatewayModelProviderServiceConfigAnthropic, AiGatewayModelProviderServiceConfigAnthropicArgs

Direct AiGatewayModelProviderServiceConfigAnthropicDirect
Relayed AiGatewayModelProviderServiceConfigAnthropicRelayed: Relayed (credential-less) form: no Anthropic credential is stored. Each inference request instead carries the caller's own OAuth token, which the platform forwards to Anthropic on outbound requests. Mutually exclusive with direct; no apiKey is required or persisted

Direct AiGatewayModelProviderServiceConfigAnthropicDirect
Relayed AiGatewayModelProviderServiceConfigAnthropicRelayed: Relayed (credential-less) form: no Anthropic credential is stored. Each inference request instead carries the caller's own OAuth token, which the platform forwards to Anthropic on outbound requests. Mutually exclusive with direct; no apiKey is required or persisted

direct object
relayed object: Relayed (credential-less) form: no Anthropic credential is stored. Each inference request instead carries the caller's own OAuth token, which the platform forwards to Anthropic on outbound requests. Mutually exclusive with direct; no apiKey is required or persisted

direct AiGatewayModelProviderServiceConfigAnthropicDirect
relayed AiGatewayModelProviderServiceConfigAnthropicRelayed: Relayed (credential-less) form: no Anthropic credential is stored. Each inference request instead carries the caller's own OAuth token, which the platform forwards to Anthropic on outbound requests. Mutually exclusive with direct; no apiKey is required or persisted

direct AiGatewayModelProviderServiceConfigAnthropicDirect
relayed AiGatewayModelProviderServiceConfigAnthropicRelayed: Relayed (credential-less) form: no Anthropic credential is stored. Each inference request instead carries the caller's own OAuth token, which the platform forwards to Anthropic on outbound requests. Mutually exclusive with direct; no apiKey is required or persisted

direct AiGatewayModelProviderServiceConfigAnthropicDirect
relayed AiGatewayModelProviderServiceConfigAnthropicRelayed: Relayed (credential-less) form: no Anthropic credential is stored. Each inference request instead carries the caller's own OAuth token, which the platform forwards to Anthropic on outbound requests. Mutually exclusive with direct; no apiKey is required or persisted

direct Property Map
relayed Property Map: Relayed (credential-less) form: no Anthropic credential is stored. Each inference request instead carries the caller's own OAuth token, which the platform forwards to Anthropic on outbound requests. Mutually exclusive with direct; no apiKey is required or persisted

AiGatewayModelProviderServiceConfigAnthropicDirect, AiGatewayModelProviderServiceConfigAnthropicDirectArgs

ApiKey AiGatewayModelProviderServiceConfigAnthropicDirectApiKey

ApiKey AiGatewayModelProviderServiceConfigAnthropicDirectApiKey

api_key object

apiKey AiGatewayModelProviderServiceConfigAnthropicDirectApiKey

apiKey AiGatewayModelProviderServiceConfigAnthropicDirectApiKey

api_key AiGatewayModelProviderServiceConfigAnthropicDirectApiKey

apiKey Property Map

AiGatewayModelProviderServiceConfigAnthropicDirectApiKey, AiGatewayModelProviderServiceConfigAnthropicDirectApiKeyArgs

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext str: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

AiGatewayModelProviderServiceConfigAnthropicRelayed, AiGatewayModelProviderServiceConfigAnthropicRelayedArgs

PlanType string: Which Anthropic subscription tier the relayed token belongs to. Optional; when unset the MPS gets the full governance surface (see TEAM_ENTERPRISE). Immutable after Create, so the tier cannot be flipped in place. Possible values are: ANTHROPIC_RELAYED_PLAN_TYPE_MAX, ANTHROPIC_RELAYED_PLAN_TYPE_TEAM_ENTERPRISE

PlanType string: Which Anthropic subscription tier the relayed token belongs to. Optional; when unset the MPS gets the full governance surface (see TEAM_ENTERPRISE). Immutable after Create, so the tier cannot be flipped in place. Possible values are: ANTHROPIC_RELAYED_PLAN_TYPE_MAX, ANTHROPIC_RELAYED_PLAN_TYPE_TEAM_ENTERPRISE

plan_type string: Which Anthropic subscription tier the relayed token belongs to. Optional; when unset the MPS gets the full governance surface (see TEAM_ENTERPRISE). Immutable after Create, so the tier cannot be flipped in place. Possible values are: ANTHROPIC_RELAYED_PLAN_TYPE_MAX, ANTHROPIC_RELAYED_PLAN_TYPE_TEAM_ENTERPRISE

planType String: Which Anthropic subscription tier the relayed token belongs to. Optional; when unset the MPS gets the full governance surface (see TEAM_ENTERPRISE). Immutable after Create, so the tier cannot be flipped in place. Possible values are: ANTHROPIC_RELAYED_PLAN_TYPE_MAX, ANTHROPIC_RELAYED_PLAN_TYPE_TEAM_ENTERPRISE

planType string: Which Anthropic subscription tier the relayed token belongs to. Optional; when unset the MPS gets the full governance surface (see TEAM_ENTERPRISE). Immutable after Create, so the tier cannot be flipped in place. Possible values are: ANTHROPIC_RELAYED_PLAN_TYPE_MAX, ANTHROPIC_RELAYED_PLAN_TYPE_TEAM_ENTERPRISE

plan_type str: Which Anthropic subscription tier the relayed token belongs to. Optional; when unset the MPS gets the full governance surface (see TEAM_ENTERPRISE). Immutable after Create, so the tier cannot be flipped in place. Possible values are: ANTHROPIC_RELAYED_PLAN_TYPE_MAX, ANTHROPIC_RELAYED_PLAN_TYPE_TEAM_ENTERPRISE

planType String: Which Anthropic subscription tier the relayed token belongs to. Optional; when unset the MPS gets the full governance surface (see TEAM_ENTERPRISE). Immutable after Create, so the tier cannot be flipped in place. Possible values are: ANTHROPIC_RELAYED_PLAN_TYPE_MAX, ANTHROPIC_RELAYED_PLAN_TYPE_TEAM_ENTERPRISE

AiGatewayModelProviderServiceConfigAzureOpenai, AiGatewayModelProviderServiceConfigAzureOpenaiArgs

Direct AiGatewayModelProviderServiceConfigAzureOpenaiDirect

Direct AiGatewayModelProviderServiceConfigAzureOpenaiDirect

direct object

direct AiGatewayModelProviderServiceConfigAzureOpenaiDirect

direct AiGatewayModelProviderServiceConfigAzureOpenaiDirect

direct AiGatewayModelProviderServiceConfigAzureOpenaiDirect

direct Property Map

AiGatewayModelProviderServiceConfigAzureOpenaiDirect, AiGatewayModelProviderServiceConfigAzureOpenaiDirectArgs

ApiKey AiGatewayModelProviderServiceConfigAzureOpenaiDirectApiKey
BaseUrl string
EntraServicePrincipal AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipal
ServiceCredential AiGatewayModelProviderServiceConfigAzureOpenaiDirectServiceCredential

ApiKey AiGatewayModelProviderServiceConfigAzureOpenaiDirectApiKey
BaseUrl string
EntraServicePrincipal AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipal
ServiceCredential AiGatewayModelProviderServiceConfigAzureOpenaiDirectServiceCredential

api_key object
base_url string
entra_service_principal object
service_credential object

apiKey AiGatewayModelProviderServiceConfigAzureOpenaiDirectApiKey
baseUrl String
entraServicePrincipal AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipal
serviceCredential AiGatewayModelProviderServiceConfigAzureOpenaiDirectServiceCredential

apiKey AiGatewayModelProviderServiceConfigAzureOpenaiDirectApiKey
baseUrl string
entraServicePrincipal AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipal
serviceCredential AiGatewayModelProviderServiceConfigAzureOpenaiDirectServiceCredential

api_key AiGatewayModelProviderServiceConfigAzureOpenaiDirectApiKey
base_url str
entra_service_principal AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipal
service_credential AiGatewayModelProviderServiceConfigAzureOpenaiDirectServiceCredential

apiKey Property Map
baseUrl String
entraServicePrincipal Property Map
serviceCredential Property Map

AiGatewayModelProviderServiceConfigAzureOpenaiDirectApiKey, AiGatewayModelProviderServiceConfigAzureOpenaiDirectApiKeyArgs

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext str: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipal, AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalArgs

ClientId string: Entra ID client (application) ID. Required on Create
ClientSecret AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalClientSecret: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
TenantId string: Entra ID (Azure AD) tenant ID. Required on Create

ClientId string: Entra ID client (application) ID. Required on Create
ClientSecret AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalClientSecret: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
TenantId string: Entra ID (Azure AD) tenant ID. Required on Create

client_id string: Entra ID client (application) ID. Required on Create
client_secret object: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
tenant_id string: Entra ID (Azure AD) tenant ID. Required on Create

clientId String: Entra ID client (application) ID. Required on Create
clientSecret AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalClientSecret: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
tenantId String: Entra ID (Azure AD) tenant ID. Required on Create

clientId string: Entra ID client (application) ID. Required on Create
clientSecret AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalClientSecret: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
tenantId string: Entra ID (Azure AD) tenant ID. Required on Create

client_id str: Entra ID client (application) ID. Required on Create
client_secret AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalClientSecret: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
tenant_id str: Entra ID (Azure AD) tenant ID. Required on Create

clientId String: Entra ID client (application) ID. Required on Create
clientSecret Property Map: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
tenantId String: Entra ID (Azure AD) tenant ID. Required on Create

AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalClientSecret, AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalClientSecretArgs

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext str: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

AiGatewayModelProviderServiceConfigAzureOpenaiDirectServiceCredential, AiGatewayModelProviderServiceConfigAzureOpenaiDirectServiceCredentialArgs

Name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

Name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name String: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name str: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name String: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

AiGatewayModelProviderServiceConfigCustom, AiGatewayModelProviderServiceConfigCustomArgs

Direct AiGatewayModelProviderServiceConfigCustomDirect

Direct AiGatewayModelProviderServiceConfigCustomDirect

direct object

direct AiGatewayModelProviderServiceConfigCustomDirect

direct AiGatewayModelProviderServiceConfigCustomDirect

direct AiGatewayModelProviderServiceConfigCustomDirect

direct Property Map

AiGatewayModelProviderServiceConfigCustomDirect, AiGatewayModelProviderServiceConfigCustomDirectArgs

ApiKey AiGatewayModelProviderServiceConfigCustomDirectApiKey
BaseUrl string

ApiKey AiGatewayModelProviderServiceConfigCustomDirectApiKey
BaseUrl string

api_key object
base_url string

apiKey AiGatewayModelProviderServiceConfigCustomDirectApiKey
baseUrl String

apiKey AiGatewayModelProviderServiceConfigCustomDirectApiKey
baseUrl string

api_key AiGatewayModelProviderServiceConfigCustomDirectApiKey
base_url str

apiKey Property Map
baseUrl String

AiGatewayModelProviderServiceConfigCustomDirectApiKey, AiGatewayModelProviderServiceConfigCustomDirectApiKeyArgs

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext str: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

AiGatewayModelProviderServiceConfigGeminiEnterprise, AiGatewayModelProviderServiceConfigGeminiEnterpriseArgs

Direct AiGatewayModelProviderServiceConfigGeminiEnterpriseDirect

Direct AiGatewayModelProviderServiceConfigGeminiEnterpriseDirect

direct object

direct AiGatewayModelProviderServiceConfigGeminiEnterpriseDirect

direct AiGatewayModelProviderServiceConfigGeminiEnterpriseDirect

direct AiGatewayModelProviderServiceConfigGeminiEnterpriseDirect

direct Property Map

AiGatewayModelProviderServiceConfigGeminiEnterpriseDirect, AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectArgs

ApiKey AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectApiKey
ProjectId string: GCP project ID hosting the Gemini Enterprise endpoint. Required on Create
Region string

ApiKey AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectApiKey
ProjectId string: GCP project ID hosting the Gemini Enterprise endpoint. Required on Create
Region string

api_key object
project_id string: GCP project ID hosting the Gemini Enterprise endpoint. Required on Create
region string

apiKey AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectApiKey
projectId String: GCP project ID hosting the Gemini Enterprise endpoint. Required on Create
region String

apiKey AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectApiKey
projectId string: GCP project ID hosting the Gemini Enterprise endpoint. Required on Create
region string

api_key AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectApiKey
project_id str: GCP project ID hosting the Gemini Enterprise endpoint. Required on Create
region str

apiKey Property Map
projectId String: GCP project ID hosting the Gemini Enterprise endpoint. Required on Create
region String

AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectApiKey, AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectApiKeyArgs

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext str: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

AiGatewayModelProviderServiceConfigInferenceTable, AiGatewayModelProviderServiceConfigInferenceTableArgs

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

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

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

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

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

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

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

AiGatewayModelProviderServiceConfigMicrosoftFoundry, AiGatewayModelProviderServiceConfigMicrosoftFoundryArgs

Direct AiGatewayModelProviderServiceConfigMicrosoftFoundryDirect

Direct AiGatewayModelProviderServiceConfigMicrosoftFoundryDirect

direct object

direct AiGatewayModelProviderServiceConfigMicrosoftFoundryDirect

direct AiGatewayModelProviderServiceConfigMicrosoftFoundryDirect

direct AiGatewayModelProviderServiceConfigMicrosoftFoundryDirect

direct Property Map

AiGatewayModelProviderServiceConfigMicrosoftFoundryDirect, AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectArgs

ApiKey AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectApiKey
BaseUrl string
EntraServicePrincipal AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipal
ServiceCredential AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectServiceCredential

ApiKey AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectApiKey
BaseUrl string
EntraServicePrincipal AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipal
ServiceCredential AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectServiceCredential

api_key object
base_url string
entra_service_principal object
service_credential object

apiKey AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectApiKey
baseUrl String
entraServicePrincipal AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipal
serviceCredential AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectServiceCredential

apiKey AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectApiKey
baseUrl string
entraServicePrincipal AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipal
serviceCredential AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectServiceCredential

api_key AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectApiKey
base_url str
entra_service_principal AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipal
service_credential AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectServiceCredential

apiKey Property Map
baseUrl String
entraServicePrincipal Property Map
serviceCredential Property Map

AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectApiKey, AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectApiKeyArgs

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext str: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipal, AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalArgs

ClientId string: Entra ID client (application) ID. Required on Create
ClientSecret AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalClientSecret: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
TenantId string: Entra ID (Azure AD) tenant ID. Required on Create

ClientId string: Entra ID client (application) ID. Required on Create
ClientSecret AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalClientSecret: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
TenantId string: Entra ID (Azure AD) tenant ID. Required on Create

client_id string: Entra ID client (application) ID. Required on Create
client_secret object: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
tenant_id string: Entra ID (Azure AD) tenant ID. Required on Create

clientId String: Entra ID client (application) ID. Required on Create
clientSecret AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalClientSecret: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
tenantId String: Entra ID (Azure AD) tenant ID. Required on Create

clientId string: Entra ID client (application) ID. Required on Create
clientSecret AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalClientSecret: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
tenantId string: Entra ID (Azure AD) tenant ID. Required on Create

client_id str: Entra ID client (application) ID. Required on Create
client_secret AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalClientSecret: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
tenant_id str: Entra ID (Azure AD) tenant ID. Required on Create

clientId String: Entra ID client (application) ID. Required on Create
clientSecret Property Map: Entra ID client secret. Supplied as inline plaintext via ProviderSecret.plaintext
tenantId String: Entra ID (Azure AD) tenant ID. Required on Create

AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalClientSecret, AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalClientSecretArgs

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext str: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectServiceCredential, AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectServiceCredentialArgs

Name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

Name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name String: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name string: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name str: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

name String: (string) - Resource name of the provider service. Format: model-provider-services/{catalog}.{schema}.{model_provider_service}. Each {...} component is capped at 255 characters individually. Server-derived on Create from parent + modelProviderServiceId; required and immutable on Update/Get/Delete

AiGatewayModelProviderServiceConfigOpenai, AiGatewayModelProviderServiceConfigOpenaiArgs

Direct AiGatewayModelProviderServiceConfigOpenaiDirect

Direct AiGatewayModelProviderServiceConfigOpenaiDirect

direct object

direct AiGatewayModelProviderServiceConfigOpenaiDirect

direct AiGatewayModelProviderServiceConfigOpenaiDirect

direct AiGatewayModelProviderServiceConfigOpenaiDirect

direct Property Map

AiGatewayModelProviderServiceConfigOpenaiDirect, AiGatewayModelProviderServiceConfigOpenaiDirectArgs

ApiKey AiGatewayModelProviderServiceConfigOpenaiDirectApiKey
BaseUrl string
Organization string: Optional OpenAI organization ID. When set, the platform forwards it as the OpenAI-Organization header

ApiKey AiGatewayModelProviderServiceConfigOpenaiDirectApiKey
BaseUrl string
Organization string: Optional OpenAI organization ID. When set, the platform forwards it as the OpenAI-Organization header

api_key object
base_url string
organization string: Optional OpenAI organization ID. When set, the platform forwards it as the OpenAI-Organization header

apiKey AiGatewayModelProviderServiceConfigOpenaiDirectApiKey
baseUrl String
organization String: Optional OpenAI organization ID. When set, the platform forwards it as the OpenAI-Organization header

apiKey AiGatewayModelProviderServiceConfigOpenaiDirectApiKey
baseUrl string
organization string: Optional OpenAI organization ID. When set, the platform forwards it as the OpenAI-Organization header

api_key AiGatewayModelProviderServiceConfigOpenaiDirectApiKey
base_url str
organization str: Optional OpenAI organization ID. When set, the platform forwards it as the OpenAI-Organization header

apiKey Property Map
baseUrl String
organization String: Optional OpenAI organization ID. When set, the platform forwards it as the OpenAI-Organization header

AiGatewayModelProviderServiceConfigOpenaiDirectApiKey, AiGatewayModelProviderServiceConfigOpenaiDirectApiKeyArgs

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

Plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext string: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext str: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

plaintext String: Inline plaintext credential. INPUT_ONLY: the value never round-trips on reads. Get and List responses omit plaintext; the field's presence in the read shape only indicates that a secret is configured

AiGatewayModelProviderServiceConfigRateLimit, AiGatewayModelProviderServiceConfigRateLimitArgs

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

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

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

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

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

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

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

AiGatewayModelProviderServiceConfigTarget, AiGatewayModelProviderServiceConfigTargetArgs

Model string: Provider-side model identifier (e.g. "gpt-5", "claude-opus-4-7"). This is a string on the LLM provider's side, not a UC entity. The UC governance hook for external destinations is the ModelProviderService referenced by ExternalModelConfig.model_provider_service, not the model itself
NativeApiTypes List<string>: Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope

Model string: Provider-side model identifier (e.g. "gpt-5", "claude-opus-4-7"). This is a string on the LLM provider's side, not a UC entity. The UC governance hook for external destinations is the ModelProviderService referenced by ExternalModelConfig.model_provider_service, not the model itself
NativeApiTypes []string: Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope

model string: Provider-side model identifier (e.g. "gpt-5", "claude-opus-4-7"). This is a string on the LLM provider's side, not a UC entity. The UC governance hook for external destinations is the ModelProviderService referenced by ExternalModelConfig.model_provider_service, not the model itself
native_api_types list(string): Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope

model String: Provider-side model identifier (e.g. "gpt-5", "claude-opus-4-7"). This is a string on the LLM provider's side, not a UC entity. The UC governance hook for external destinations is the ModelProviderService referenced by ExternalModelConfig.model_provider_service, not the model itself
nativeApiTypes List<String>: Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope

model string: Provider-side model identifier (e.g. "gpt-5", "claude-opus-4-7"). This is a string on the LLM provider's side, not a UC entity. The UC governance hook for external destinations is the ModelProviderService referenced by ExternalModelConfig.model_provider_service, not the model itself
nativeApiTypes string[]: Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope

model str: Provider-side model identifier (e.g. "gpt-5", "claude-opus-4-7"). This is a string on the LLM provider's side, not a UC entity. The UC governance hook for external destinations is the ModelProviderService referenced by ExternalModelConfig.model_provider_service, not the model itself
native_api_types Sequence[str]: Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope

model String: Provider-side model identifier (e.g. "gpt-5", "claude-opus-4-7"). This is a string on the LLM provider's side, not a UC entity. The UC governance hook for external destinations is the ModelProviderService referenced by ExternalModelConfig.model_provider_service, not the model itself
nativeApiTypes List<String>: Provider-native API types the model supports (e.g. "openai/v1/chat/completions"). Used by the platform for request/response translation from the unified API type. At most 64 entries of at most 256 characters each; the list is persisted into the destination binding's bounded storage envelope

AiGatewayModelProviderServiceProviderConfig, AiGatewayModelProviderServiceProviderConfigArgs

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 v1.107.0
published on Tuesday, Aug 25, 2026 by Pulumi

Schema (JSON)

pulumi/pulumi-databricks

databricks.AiGatewayModelProviderService

On this page

On this page

Create AiGatewayModelProviderService Resource

Constructor syntax

Parameters

Constructor example

AiGatewayModelProviderService Resource Properties

Inputs

Outputs

Look up Existing AiGatewayModelProviderService Resource

Supporting Types

AiGatewayModelProviderServiceConfig, AiGatewayModelProviderServiceConfigArgs

AiGatewayModelProviderServiceConfigAmazonBedrock, AiGatewayModelProviderServiceConfigAmazonBedrockArgs

AiGatewayModelProviderServiceConfigAmazonBedrockDirect, AiGatewayModelProviderServiceConfigAmazonBedrockDirectArgs

AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKey, AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeyArgs

AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeySecretAccessKey, AiGatewayModelProviderServiceConfigAmazonBedrockDirectAwsAccessKeySecretAccessKeyArgs

AiGatewayModelProviderServiceConfigAmazonBedrockDirectServiceCredential, AiGatewayModelProviderServiceConfigAmazonBedrockDirectServiceCredentialArgs

AiGatewayModelProviderServiceConfigAnthropic, AiGatewayModelProviderServiceConfigAnthropicArgs

AiGatewayModelProviderServiceConfigAnthropicDirect, AiGatewayModelProviderServiceConfigAnthropicDirectArgs

AiGatewayModelProviderServiceConfigAnthropicDirectApiKey, AiGatewayModelProviderServiceConfigAnthropicDirectApiKeyArgs

AiGatewayModelProviderServiceConfigAnthropicRelayed, AiGatewayModelProviderServiceConfigAnthropicRelayedArgs

AiGatewayModelProviderServiceConfigAzureOpenai, AiGatewayModelProviderServiceConfigAzureOpenaiArgs

AiGatewayModelProviderServiceConfigAzureOpenaiDirect, AiGatewayModelProviderServiceConfigAzureOpenaiDirectArgs

AiGatewayModelProviderServiceConfigAzureOpenaiDirectApiKey, AiGatewayModelProviderServiceConfigAzureOpenaiDirectApiKeyArgs

AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipal, AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalArgs

AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalClientSecret, AiGatewayModelProviderServiceConfigAzureOpenaiDirectEntraServicePrincipalClientSecretArgs

AiGatewayModelProviderServiceConfigAzureOpenaiDirectServiceCredential, AiGatewayModelProviderServiceConfigAzureOpenaiDirectServiceCredentialArgs

AiGatewayModelProviderServiceConfigCustom, AiGatewayModelProviderServiceConfigCustomArgs

AiGatewayModelProviderServiceConfigCustomDirect, AiGatewayModelProviderServiceConfigCustomDirectArgs

AiGatewayModelProviderServiceConfigCustomDirectApiKey, AiGatewayModelProviderServiceConfigCustomDirectApiKeyArgs

AiGatewayModelProviderServiceConfigGeminiEnterprise, AiGatewayModelProviderServiceConfigGeminiEnterpriseArgs

AiGatewayModelProviderServiceConfigGeminiEnterpriseDirect, AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectArgs

AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectApiKey, AiGatewayModelProviderServiceConfigGeminiEnterpriseDirectApiKeyArgs

AiGatewayModelProviderServiceConfigInferenceTable, AiGatewayModelProviderServiceConfigInferenceTableArgs

AiGatewayModelProviderServiceConfigMicrosoftFoundry, AiGatewayModelProviderServiceConfigMicrosoftFoundryArgs

AiGatewayModelProviderServiceConfigMicrosoftFoundryDirect, AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectArgs

AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectApiKey, AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectApiKeyArgs

AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipal, AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalArgs

AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalClientSecret, AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectEntraServicePrincipalClientSecretArgs

AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectServiceCredential, AiGatewayModelProviderServiceConfigMicrosoftFoundryDirectServiceCredentialArgs

AiGatewayModelProviderServiceConfigOpenai, AiGatewayModelProviderServiceConfigOpenaiArgs

AiGatewayModelProviderServiceConfigOpenaiDirect, AiGatewayModelProviderServiceConfigOpenaiDirectArgs

AiGatewayModelProviderServiceConfigOpenaiDirectApiKey, AiGatewayModelProviderServiceConfigOpenaiDirectApiKeyArgs

AiGatewayModelProviderServiceConfigRateLimit, AiGatewayModelProviderServiceConfigRateLimitArgs

AiGatewayModelProviderServiceConfigTarget, AiGatewayModelProviderServiceConfigTargetArgs

AiGatewayModelProviderServiceProviderConfig, AiGatewayModelProviderServiceProviderConfigArgs

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.