Endpoint

volcenginecc v0.0.35, May 14 26

Viewing docs for volcenginecc v0.0.35
published on Thursday, May 14, 2026 by Volcengine

Schema (JSON)

volcengine/pulumi-volcenginecc

Viewing docs for volcenginecc v0.0.35
published on Thursday, May 14, 2026 by Volcengine

Schema (JSON)

volcengine/pulumi-volcenginecc

When using large language models for inference services, the inference endpoint is the key entry point for model invocation. Developers can initiate API/SDK inference requests to the large model simply by specifying the ID, enabling quick access and flexible invocation. The system provides a unified API invocation method, call monitoring, rate limiting strategies, and security mechanisms to ensure stability and security during inference

Example Usage

Example coming soon!

Example coming soon!

Example coming soon!

Example coming soon!

Example coming soon!

resources:
  endpointDemo:
    type: volcenginecc:ark:Endpoint
    name: EndpointDemo
    properties:
      name: EndpointDemo
      description: endpoint description
      modelReference:
        foundation_model:
          name: doubao-1-5-thinking-***
          modelVersion: '250428'
      tags:
        - key: env
          value: test
      projectName: default
      rateLimit:
        tpm: 5
        rpm: 10

Example coming soon!

Create Endpoint Resource

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

Constructor syntax

new Endpoint(name: string, args: EndpointArgs, opts?: CustomResourceOptions);

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

@overload
def Endpoint(resource_name: str,
             opts: Optional[ResourceOptions] = None,
             model_reference: Optional[EndpointModelReferenceArgs] = None,
             name: Optional[str] = None,
             description: Optional[str] = None,
             model_unit_id: Optional[str] = None,
             moderation: Optional[EndpointModerationArgs] = None,
             project_name: Optional[str] = None,
             rate_limit: Optional[EndpointRateLimitArgs] = None,
             tags: Optional[Sequence[EndpointTagArgs]] = None)

func NewEndpoint(ctx *Context, name string, args EndpointArgs, opts ...ResourceOption) (*Endpoint, error)

public Endpoint(string name, EndpointArgs args, CustomResourceOptions? opts = null)

public Endpoint(String name, EndpointArgs args)
public Endpoint(String name, EndpointArgs args, CustomResourceOptions options)

type: volcenginecc:ark:Endpoint
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

resource "volcenginecc_ark_endpoint" "name" {
    # resource properties
}

Parameters

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

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

name String: The unique name of the resource.
args EndpointArgs: 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 endpointResource = new Volcenginecc.Ark.Endpoint("endpointResource", new()
{
    ModelReference = new Volcenginecc.Ark.Inputs.EndpointModelReferenceArgs
    {
        CustomModelId = "string",
        FoundationModel = new Volcenginecc.Ark.Inputs.EndpointModelReferenceFoundationModelArgs
        {
            ModelVersion = "string",
            Name = "string",
        },
    },
    Name = "string",
    Description = "string",
    ModelUnitId = "string",
    Moderation = new Volcenginecc.Ark.Inputs.EndpointModerationArgs
    {
        Strategy = "string",
    },
    ProjectName = "string",
    RateLimit = new Volcenginecc.Ark.Inputs.EndpointRateLimitArgs
    {
        Rpm = 0,
        Tpm = 0,
    },
    Tags = new[]
    {
        new Volcenginecc.Ark.Inputs.EndpointTagArgs
        {
            Key = "string",
            Value = "string",
        },
    },
});

example, err := ark.NewEndpoint(ctx, "endpointResource", &ark.EndpointArgs{
	ModelReference: &ark.EndpointModelReferenceArgs{
		CustomModelId: pulumi.String("string"),
		FoundationModel: &ark.EndpointModelReferenceFoundationModelArgs{
			ModelVersion: pulumi.String("string"),
			Name:         pulumi.String("string"),
		},
	},
	Name:        pulumi.String("string"),
	Description: pulumi.String("string"),
	ModelUnitId: pulumi.String("string"),
	Moderation: &ark.EndpointModerationArgs{
		Strategy: pulumi.String("string"),
	},
	ProjectName: pulumi.String("string"),
	RateLimit: &ark.EndpointRateLimitArgs{
		Rpm: pulumi.Int(0),
		Tpm: pulumi.Int(0),
	},
	Tags: ark.EndpointTagArray{
		&ark.EndpointTagArgs{
			Key:   pulumi.String("string"),
			Value: pulumi.String("string"),
		},
	},
})

resource "volcenginecc_ark_endpoint" "endpointResource" {
  model_reference = {
    custom_model_id = "string"
    foundation_model = {
      model_version = "string"
      name          = "string"
    }
  }
  name          = "string"
  description   = "string"
  model_unit_id = "string"
  moderation = {
    strategy = "string"
  }
  project_name = "string"
  rate_limit = {
    rpm = 0
    tpm = 0
  }
  tags {
    key   = "string"
    value = "string"
  }
}

var endpointResource = new com.volcengine.volcenginecc.ark.Endpoint("endpointResource", com.volcengine.volcenginecc.ark.EndpointArgs.builder()
    .modelReference(EndpointModelReferenceArgs.builder()
        .customModelId("string")
        .foundationModel(EndpointModelReferenceFoundationModelArgs.builder()
            .modelVersion("string")
            .name("string")
            .build())
        .build())
    .name("string")
    .description("string")
    .modelUnitId("string")
    .moderation(EndpointModerationArgs.builder()
        .strategy("string")
        .build())
    .projectName("string")
    .rateLimit(EndpointRateLimitArgs.builder()
        .rpm(0)
        .tpm(0)
        .build())
    .tags(EndpointTagArgs.builder()
        .key("string")
        .value("string")
        .build())
    .build());

endpoint_resource = volcenginecc.ark.Endpoint("endpointResource",
    model_reference={
        "custom_model_id": "string",
        "foundation_model": {
            "model_version": "string",
            "name": "string",
        },
    },
    name="string",
    description="string",
    model_unit_id="string",
    moderation={
        "strategy": "string",
    },
    project_name="string",
    rate_limit={
        "rpm": 0,
        "tpm": 0,
    },
    tags=[{
        "key": "string",
        "value": "string",
    }])

const endpointResource = new volcenginecc.ark.Endpoint("endpointResource", {
    modelReference: {
        customModelId: "string",
        foundationModel: {
            modelVersion: "string",
            name: "string",
        },
    },
    name: "string",
    description: "string",
    modelUnitId: "string",
    moderation: {
        strategy: "string",
    },
    projectName: "string",
    rateLimit: {
        rpm: 0,
        tpm: 0,
    },
    tags: [{
        key: "string",
        value: "string",
    }],
});

type: volcenginecc:ark:Endpoint
properties:
    description: string
    modelReference:
        customModelId: string
        foundationModel:
            modelVersion: string
            name: string
    modelUnitId: string
    moderation:
        strategy: string
    name: string
    projectName: string
    rateLimit:
        rpm: 0
        tpm: 0
    tags:
        - key: string
          value: string

Endpoint 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 Endpoint resource accepts the following input properties:

ModelReference Volcengine.EndpointModelReference: Endpoint access model
Name string: Endpoint name
Description string: Endpoint description
ModelUnitId string: Model unit. If empty, indicates postpaid; otherwise, prepaid.
Moderation Volcengine.EndpointModeration: Content guardrail scheme
ProjectName string: Project name the resource belongs to; default value is "default"
RateLimit Volcengine.EndpointRateLimit: Endpoint rate limiting
Tags List<Volcengine.EndpointTag>

ModelReference EndpointModelReferenceArgs: Endpoint access model
Name string: Endpoint name
Description string: Endpoint description
ModelUnitId string: Model unit. If empty, indicates postpaid; otherwise, prepaid.
Moderation EndpointModerationArgs: Content guardrail scheme
ProjectName string: Project name the resource belongs to; default value is "default"
RateLimit EndpointRateLimitArgs: Endpoint rate limiting
Tags []EndpointTagArgs

model_reference object: Endpoint access model
name string: Endpoint name
description string: Endpoint description
model_unit_id string: Model unit. If empty, indicates postpaid; otherwise, prepaid.
moderation object: Content guardrail scheme
project_name string: Project name the resource belongs to; default value is "default"
rate_limit object: Endpoint rate limiting
tags list(object)

modelReference EndpointModelReference: Endpoint access model
name String: Endpoint name
description String: Endpoint description
modelUnitId String: Model unit. If empty, indicates postpaid; otherwise, prepaid.
moderation EndpointModeration: Content guardrail scheme
projectName String: Project name the resource belongs to; default value is "default"
rateLimit EndpointRateLimit: Endpoint rate limiting
tags List<EndpointTag>

modelReference EndpointModelReference: Endpoint access model
name string: Endpoint name
description string: Endpoint description
modelUnitId string: Model unit. If empty, indicates postpaid; otherwise, prepaid.
moderation EndpointModeration: Content guardrail scheme
projectName string: Project name the resource belongs to; default value is "default"
rateLimit EndpointRateLimit: Endpoint rate limiting
tags EndpointTag[]

model_reference EndpointModelReferenceArgs: Endpoint access model
name str: Endpoint name
description str: Endpoint description
model_unit_id str: Model unit. If empty, indicates postpaid; otherwise, prepaid.
moderation EndpointModerationArgs: Content guardrail scheme
project_name str: Project name the resource belongs to; default value is "default"
rate_limit EndpointRateLimitArgs: Endpoint rate limiting
tags Sequence[EndpointTagArgs]

modelReference Property Map: Endpoint access model
name String: Endpoint name
description String: Endpoint description
modelUnitId String: Model unit. If empty, indicates postpaid; otherwise, prepaid.
moderation Property Map: Content guardrail scheme
projectName String: Project name the resource belongs to; default value is "default"
rateLimit Property Map: Endpoint rate limiting
tags List<Property Map>

Outputs

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

BatchOnly bool: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
Certificate Volcengine.EndpointCertificate: Certificate information
CreateTime string: Endpoint creation time, RFC3339 format
EndpointId string: Inference access point ID.
EndpointModelType string: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
Id string: The provider-assigned unique ID for this managed resource.
RollingId string: Endpoint switch ID
ScaleTierId string: If a TPM protection package exists, this is the TPM protection package ID.
Status string: Endpoint status
StatusReason string: Additional status information
SupportRolling bool: Whether endpoint supports switching model versions
SupportScaleTier bool: Whether TPM protection package is supported
UpdateTime string: Endpoint update time, RFC3339 format

BatchOnly bool: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
Certificate EndpointCertificate: Certificate information
CreateTime string: Endpoint creation time, RFC3339 format
EndpointId string: Inference access point ID.
EndpointModelType string: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
Id string: The provider-assigned unique ID for this managed resource.
RollingId string: Endpoint switch ID
ScaleTierId string: If a TPM protection package exists, this is the TPM protection package ID.
Status string: Endpoint status
StatusReason string: Additional status information
SupportRolling bool: Whether endpoint supports switching model versions
SupportScaleTier bool: Whether TPM protection package is supported
UpdateTime string: Endpoint update time, RFC3339 format

batch_only bool: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
certificate object: Certificate information
create_time string: Endpoint creation time, RFC3339 format
endpoint_id string: Inference access point ID.
endpoint_model_type string: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
id string: The provider-assigned unique ID for this managed resource.
rolling_id string: Endpoint switch ID
scale_tier_id string: If a TPM protection package exists, this is the TPM protection package ID.
status string: Endpoint status
status_reason string: Additional status information
support_rolling bool: Whether endpoint supports switching model versions
support_scale_tier bool: Whether TPM protection package is supported
update_time string: Endpoint update time, RFC3339 format

batchOnly Boolean: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
certificate EndpointCertificate: Certificate information
createTime String: Endpoint creation time, RFC3339 format
endpointId String: Inference access point ID.
endpointModelType String: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
id String: The provider-assigned unique ID for this managed resource.
rollingId String: Endpoint switch ID
scaleTierId String: If a TPM protection package exists, this is the TPM protection package ID.
status String: Endpoint status
statusReason String: Additional status information
supportRolling Boolean: Whether endpoint supports switching model versions
supportScaleTier Boolean: Whether TPM protection package is supported
updateTime String: Endpoint update time, RFC3339 format

batchOnly boolean: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
certificate EndpointCertificate: Certificate information
createTime string: Endpoint creation time, RFC3339 format
endpointId string: Inference access point ID.
endpointModelType string: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
id string: The provider-assigned unique ID for this managed resource.
rollingId string: Endpoint switch ID
scaleTierId string: If a TPM protection package exists, this is the TPM protection package ID.
status string: Endpoint status
statusReason string: Additional status information
supportRolling boolean: Whether endpoint supports switching model versions
supportScaleTier boolean: Whether TPM protection package is supported
updateTime string: Endpoint update time, RFC3339 format

batch_only bool: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
certificate EndpointCertificate: Certificate information
create_time str: Endpoint creation time, RFC3339 format
endpoint_id str: Inference access point ID.
endpoint_model_type str: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
id str: The provider-assigned unique ID for this managed resource.
rolling_id str: Endpoint switch ID
scale_tier_id str: If a TPM protection package exists, this is the TPM protection package ID.
status str: Endpoint status
status_reason str: Additional status information
support_rolling bool: Whether endpoint supports switching model versions
support_scale_tier bool: Whether TPM protection package is supported
update_time str: Endpoint update time, RFC3339 format

batchOnly Boolean: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
certificate Property Map: Certificate information
createTime String: Endpoint creation time, RFC3339 format
endpointId String: Inference access point ID.
endpointModelType String: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
id String: The provider-assigned unique ID for this managed resource.
rollingId String: Endpoint switch ID
scaleTierId String: If a TPM protection package exists, this is the TPM protection package ID.
status String: Endpoint status
statusReason String: Additional status information
supportRolling Boolean: Whether endpoint supports switching model versions
supportScaleTier Boolean: Whether TPM protection package is supported
updateTime String: Endpoint update time, RFC3339 format

Look up Existing Endpoint Resource

Get an existing Endpoint 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?: EndpointState, opts?: CustomResourceOptions): Endpoint

@staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        batch_only: Optional[bool] = None,
        certificate: Optional[EndpointCertificateArgs] = None,
        create_time: Optional[str] = None,
        description: Optional[str] = None,
        endpoint_id: Optional[str] = None,
        endpoint_model_type: Optional[str] = None,
        model_reference: Optional[EndpointModelReferenceArgs] = None,
        model_unit_id: Optional[str] = None,
        moderation: Optional[EndpointModerationArgs] = None,
        name: Optional[str] = None,
        project_name: Optional[str] = None,
        rate_limit: Optional[EndpointRateLimitArgs] = None,
        rolling_id: Optional[str] = None,
        scale_tier_id: Optional[str] = None,
        status: Optional[str] = None,
        status_reason: Optional[str] = None,
        support_rolling: Optional[bool] = None,
        support_scale_tier: Optional[bool] = None,
        tags: Optional[Sequence[EndpointTagArgs]] = None,
        update_time: Optional[str] = None) -> Endpoint

func GetEndpoint(ctx *Context, name string, id IDInput, state *EndpointState, opts ...ResourceOption) (*Endpoint, error)

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

public static Endpoint get(String name, Output<String> id, EndpointState state, CustomResourceOptions options)

resources:  _:    type: volcenginecc:ark:Endpoint    get:      id: ${id}

import {
  to = volcenginecc_ark_endpoint.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:

BatchOnly bool: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
Certificate Volcengine.EndpointCertificate: Certificate information
CreateTime string: Endpoint creation time, RFC3339 format
Description string: Endpoint description
EndpointId string: Inference access point ID.
EndpointModelType string: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
ModelReference Volcengine.EndpointModelReference: Endpoint access model
ModelUnitId string: Model unit. If empty, indicates postpaid; otherwise, prepaid.
Moderation Volcengine.EndpointModeration: Content guardrail scheme
Name string: Endpoint name
ProjectName string: Project name the resource belongs to; default value is "default"
RateLimit Volcengine.EndpointRateLimit: Endpoint rate limiting
RollingId string: Endpoint switch ID
ScaleTierId string: If a TPM protection package exists, this is the TPM protection package ID.
Status string: Endpoint status
StatusReason string: Additional status information
SupportRolling bool: Whether endpoint supports switching model versions
SupportScaleTier bool: Whether TPM protection package is supported
Tags List<Volcengine.EndpointTag>
UpdateTime string: Endpoint update time, RFC3339 format

BatchOnly bool: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
Certificate EndpointCertificateArgs: Certificate information
CreateTime string: Endpoint creation time, RFC3339 format
Description string: Endpoint description
EndpointId string: Inference access point ID.
EndpointModelType string: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
ModelReference EndpointModelReferenceArgs: Endpoint access model
ModelUnitId string: Model unit. If empty, indicates postpaid; otherwise, prepaid.
Moderation EndpointModerationArgs: Content guardrail scheme
Name string: Endpoint name
ProjectName string: Project name the resource belongs to; default value is "default"
RateLimit EndpointRateLimitArgs: Endpoint rate limiting
RollingId string: Endpoint switch ID
ScaleTierId string: If a TPM protection package exists, this is the TPM protection package ID.
Status string: Endpoint status
StatusReason string: Additional status information
SupportRolling bool: Whether endpoint supports switching model versions
SupportScaleTier bool: Whether TPM protection package is supported
Tags []EndpointTagArgs
UpdateTime string: Endpoint update time, RFC3339 format

batch_only bool: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
certificate object: Certificate information
create_time string: Endpoint creation time, RFC3339 format
description string: Endpoint description
endpoint_id string: Inference access point ID.
endpoint_model_type string: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
model_reference object: Endpoint access model
model_unit_id string: Model unit. If empty, indicates postpaid; otherwise, prepaid.
moderation object: Content guardrail scheme
name string: Endpoint name
project_name string: Project name the resource belongs to; default value is "default"
rate_limit object: Endpoint rate limiting
rolling_id string: Endpoint switch ID
scale_tier_id string: If a TPM protection package exists, this is the TPM protection package ID.
status string: Endpoint status
status_reason string: Additional status information
support_rolling bool: Whether endpoint supports switching model versions
support_scale_tier bool: Whether TPM protection package is supported
tags list(object)
update_time string: Endpoint update time, RFC3339 format

batchOnly Boolean: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
certificate EndpointCertificate: Certificate information
createTime String: Endpoint creation time, RFC3339 format
description String: Endpoint description
endpointId String: Inference access point ID.
endpointModelType String: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
modelReference EndpointModelReference: Endpoint access model
modelUnitId String: Model unit. If empty, indicates postpaid; otherwise, prepaid.
moderation EndpointModeration: Content guardrail scheme
name String: Endpoint name
projectName String: Project name the resource belongs to; default value is "default"
rateLimit EndpointRateLimit: Endpoint rate limiting
rollingId String: Endpoint switch ID
scaleTierId String: If a TPM protection package exists, this is the TPM protection package ID.
status String: Endpoint status
statusReason String: Additional status information
supportRolling Boolean: Whether endpoint supports switching model versions
supportScaleTier Boolean: Whether TPM protection package is supported
tags List<EndpointTag>
updateTime String: Endpoint update time, RFC3339 format

batchOnly boolean: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
certificate EndpointCertificate: Certificate information
createTime string: Endpoint creation time, RFC3339 format
description string: Endpoint description
endpointId string: Inference access point ID.
endpointModelType string: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
modelReference EndpointModelReference: Endpoint access model
modelUnitId string: Model unit. If empty, indicates postpaid; otherwise, prepaid.
moderation EndpointModeration: Content guardrail scheme
name string: Endpoint name
projectName string: Project name the resource belongs to; default value is "default"
rateLimit EndpointRateLimit: Endpoint rate limiting
rollingId string: Endpoint switch ID
scaleTierId string: If a TPM protection package exists, this is the TPM protection package ID.
status string: Endpoint status
statusReason string: Additional status information
supportRolling boolean: Whether endpoint supports switching model versions
supportScaleTier boolean: Whether TPM protection package is supported
tags EndpointTag[]
updateTime string: Endpoint update time, RFC3339 format

batch_only bool: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
certificate EndpointCertificateArgs: Certificate information
create_time str: Endpoint creation time, RFC3339 format
description str: Endpoint description
endpoint_id str: Inference access point ID.
endpoint_model_type str: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
model_reference EndpointModelReferenceArgs: Endpoint access model
model_unit_id str: Model unit. If empty, indicates postpaid; otherwise, prepaid.
moderation EndpointModerationArgs: Content guardrail scheme
name str: Endpoint name
project_name str: Project name the resource belongs to; default value is "default"
rate_limit EndpointRateLimitArgs: Endpoint rate limiting
rolling_id str: Endpoint switch ID
scale_tier_id str: If a TPM protection package exists, this is the TPM protection package ID.
status str: Endpoint status
status_reason str: Additional status information
support_rolling bool: Whether endpoint supports switching model versions
support_scale_tier bool: Whether TPM protection package is supported
tags Sequence[EndpointTagArgs]
update_time str: Endpoint update time, RFC3339 format

batchOnly Boolean: Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed
certificate Property Map: Certificate information
createTime String: Endpoint creation time, RFC3339 format
description String: Endpoint description
endpointId String: Inference access point ID.
endpointModelType String: Access point model type. Options: FoundationModel for base model; CustomModel for custom model.
modelReference Property Map: Endpoint access model
modelUnitId String: Model unit. If empty, indicates postpaid; otherwise, prepaid.
moderation Property Map: Content guardrail scheme
name String: Endpoint name
projectName String: Project name the resource belongs to; default value is "default"
rateLimit Property Map: Endpoint rate limiting
rollingId String: Endpoint switch ID
scaleTierId String: If a TPM protection package exists, this is the TPM protection package ID.
status String: Endpoint status
statusReason String: Additional status information
supportRolling Boolean: Whether endpoint supports switching model versions
supportScaleTier Boolean: Whether TPM protection package is supported
tags List<Property Map>
updateTime String: Endpoint update time, RFC3339 format

Supporting Types

EndpointCertificate, EndpointCertificateArgs

NotAfter int: X509 private certificate expiration time, represented as a timestamp in seconds
NotBefore int: X509 private certificate activation time, represented as a timestamp in seconds
PcaHost string: Certificate subject
PcaInstanceCertificate string: PEM format leaf certificate
PcaName string: Certificate name
PcaRootCaCertificate string: PEM format root certificate
PcaSubCaCertificate string: Intermediate certificate and root certificate in PEM format

NotAfter int: X509 private certificate expiration time, represented as a timestamp in seconds
NotBefore int: X509 private certificate activation time, represented as a timestamp in seconds
PcaHost string: Certificate subject
PcaInstanceCertificate string: PEM format leaf certificate
PcaName string: Certificate name
PcaRootCaCertificate string: PEM format root certificate
PcaSubCaCertificate string: Intermediate certificate and root certificate in PEM format

not_after number: X509 private certificate expiration time, represented as a timestamp in seconds
not_before number: X509 private certificate activation time, represented as a timestamp in seconds
pca_host string: Certificate subject
pca_instance_certificate string: PEM format leaf certificate
pca_name string: Certificate name
pca_root_ca_certificate string: PEM format root certificate
pca_sub_ca_certificate string: Intermediate certificate and root certificate in PEM format

notAfter Integer: X509 private certificate expiration time, represented as a timestamp in seconds
notBefore Integer: X509 private certificate activation time, represented as a timestamp in seconds
pcaHost String: Certificate subject
pcaInstanceCertificate String: PEM format leaf certificate
pcaName String: Certificate name
pcaRootCaCertificate String: PEM format root certificate
pcaSubCaCertificate String: Intermediate certificate and root certificate in PEM format

notAfter number: X509 private certificate expiration time, represented as a timestamp in seconds
notBefore number: X509 private certificate activation time, represented as a timestamp in seconds
pcaHost string: Certificate subject
pcaInstanceCertificate string: PEM format leaf certificate
pcaName string: Certificate name
pcaRootCaCertificate string: PEM format root certificate
pcaSubCaCertificate string: Intermediate certificate and root certificate in PEM format

not_after int: X509 private certificate expiration time, represented as a timestamp in seconds
not_before int: X509 private certificate activation time, represented as a timestamp in seconds
pca_host str: Certificate subject
pca_instance_certificate str: PEM format leaf certificate
pca_name str: Certificate name
pca_root_ca_certificate str: PEM format root certificate
pca_sub_ca_certificate str: Intermediate certificate and root certificate in PEM format

notAfter Number: X509 private certificate expiration time, represented as a timestamp in seconds
notBefore Number: X509 private certificate activation time, represented as a timestamp in seconds
pcaHost String: Certificate subject
pcaInstanceCertificate String: PEM format leaf certificate
pcaName String: Certificate name
pcaRootCaCertificate String: PEM format root certificate
pcaSubCaCertificate String: Intermediate certificate and root certificate in PEM format

EndpointModelReference, EndpointModelReferenceArgs

CustomModelId string: Custom model ID
FoundationModel Volcengine.EndpointModelReferenceFoundationModel: Base model

CustomModelId string: Custom model ID
FoundationModel EndpointModelReferenceFoundationModel: Base model

custom_model_id string: Custom model ID
foundation_model object: Base model

customModelId String: Custom model ID
foundationModel EndpointModelReferenceFoundationModel: Base model

customModelId string: Custom model ID
foundationModel EndpointModelReferenceFoundationModel: Base model

custom_model_id str: Custom model ID
foundation_model EndpointModelReferenceFoundationModel: Base model

customModelId String: Custom model ID
foundationModel Property Map: Base model

EndpointModelReferenceFoundationModel, EndpointModelReferenceFoundationModelArgs

ModelVersion string: Base model version
Name string: Base model name. Note: Model names are lowercase. The model name format for doubao 1.5 generation models is "doubao-1-5-**".

ModelVersion string: Base model version
Name string: Base model name. Note: Model names are lowercase. The model name format for doubao 1.5 generation models is "doubao-1-5-**".

model_version string: Base model version
name string: Base model name. Note: Model names are lowercase. The model name format for doubao 1.5 generation models is "doubao-1-5-**".

modelVersion String: Base model version
name String: Base model name. Note: Model names are lowercase. The model name format for doubao 1.5 generation models is "doubao-1-5-**".

modelVersion string: Base model version
name string: Base model name. Note: Model names are lowercase. The model name format for doubao 1.5 generation models is "doubao-1-5-**".

model_version str: Base model version
name str: Base model name. Note: Model names are lowercase. The model name format for doubao 1.5 generation models is "doubao-1-5-**".

modelVersion String: Base model version
name String: Base model name. Note: Model names are lowercase. The model name format for doubao 1.5 generation models is "doubao-1-5-**".

EndpointModeration, EndpointModerationArgs

Strategy string: Content safety guardrail scheme. Values: Default: default scheme. Lower latency, broadly covers general content safety requirements; Basic: basic scheme (public beta). Supports providing triggered risk categories in interface responses, currently only includes two risk types: severe violations and aggressive behavior. Note: If using streaming interface calls, this scheme is not recommended, as it will increase the length of each output fragment and raise latency

Strategy string: Content safety guardrail scheme. Values: Default: default scheme. Lower latency, broadly covers general content safety requirements; Basic: basic scheme (public beta). Supports providing triggered risk categories in interface responses, currently only includes two risk types: severe violations and aggressive behavior. Note: If using streaming interface calls, this scheme is not recommended, as it will increase the length of each output fragment and raise latency

strategy string: Content safety guardrail scheme. Values: Default: default scheme. Lower latency, broadly covers general content safety requirements; Basic: basic scheme (public beta). Supports providing triggered risk categories in interface responses, currently only includes two risk types: severe violations and aggressive behavior. Note: If using streaming interface calls, this scheme is not recommended, as it will increase the length of each output fragment and raise latency

strategy String: Content safety guardrail scheme. Values: Default: default scheme. Lower latency, broadly covers general content safety requirements; Basic: basic scheme (public beta). Supports providing triggered risk categories in interface responses, currently only includes two risk types: severe violations and aggressive behavior. Note: If using streaming interface calls, this scheme is not recommended, as it will increase the length of each output fragment and raise latency

strategy string: Content safety guardrail scheme. Values: Default: default scheme. Lower latency, broadly covers general content safety requirements; Basic: basic scheme (public beta). Supports providing triggered risk categories in interface responses, currently only includes two risk types: severe violations and aggressive behavior. Note: If using streaming interface calls, this scheme is not recommended, as it will increase the length of each output fragment and raise latency

strategy str: Content safety guardrail scheme. Values: Default: default scheme. Lower latency, broadly covers general content safety requirements; Basic: basic scheme (public beta). Supports providing triggered risk categories in interface responses, currently only includes two risk types: severe violations and aggressive behavior. Note: If using streaming interface calls, this scheme is not recommended, as it will increase the length of each output fragment and raise latency

strategy String: Content safety guardrail scheme. Values: Default: default scheme. Lower latency, broadly covers general content safety requirements; Basic: basic scheme (public beta). Supports providing triggered risk categories in interface responses, currently only includes two risk types: severe violations and aggressive behavior. Note: If using streaming interface calls, this scheme is not recommended, as it will increase the length of each output fragment and raise latency

EndpointRateLimit, EndpointRateLimitArgs

Rpm int: Requests Per Minute, number of requests per minute
Tpm int: Tokens Per Minute, number of tokens requested per minute

Rpm int: Requests Per Minute, number of requests per minute
Tpm int: Tokens Per Minute, number of tokens requested per minute

rpm number: Requests Per Minute, number of requests per minute
tpm number: Tokens Per Minute, number of tokens requested per minute

rpm Integer: Requests Per Minute, number of requests per minute
tpm Integer: Tokens Per Minute, number of tokens requested per minute

rpm number: Requests Per Minute, number of requests per minute
tpm number: Tokens Per Minute, number of tokens requested per minute

rpm int: Requests Per Minute, number of requests per minute
tpm int: Tokens Per Minute, number of tokens requested per minute

rpm Number: Requests Per Minute, number of requests per minute
tpm Number: Tokens Per Minute, number of tokens requested per minute

EndpointTag, EndpointTagArgs

Key string: Tag key
Value string: Tag value

Key string: Tag key
Value string: Tag value

key string: Tag key
value string: Tag value

key String: Tag key
value String: Tag value

key string: Tag key
value string: Tag value

key str: Tag key
value str: Tag value

key String: Tag key
value String: Tag value

Import

$ pulumi import volcenginecc:ark/endpoint:Endpoint example "endpoint_id"

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

Package Details

Repository: volcenginecc volcengine/pulumi-volcenginecc
License: MPL-2.0
Notes: This Pulumi package is based on the volcenginecc Terraform Provider.

Viewing docs for volcenginecc v0.0.35
published on Thursday, May 14, 2026 by Volcengine

Schema (JSON)

volcengine/pulumi-volcenginecc

volcenginecc.ark.Endpoint

On this page

On this page

Example Usage

Create Endpoint Resource

Constructor syntax

Parameters

Constructor example

Endpoint Resource Properties

Inputs

Outputs

Look up Existing Endpoint Resource

Supporting Types

EndpointCertificate, EndpointCertificateArgs

EndpointModelReference, EndpointModelReferenceArgs

EndpointModelReferenceFoundationModel, EndpointModelReferenceFoundationModelArgs

EndpointModeration, EndpointModerationArgs

EndpointRateLimit, EndpointRateLimitArgs

EndpointTag, EndpointTagArgs

Import

Package Details

On this page

On this page