import * as pulumi from "@pulumi/pulumi"; import * as inputs from "../types/input"; import * as outputs from "../types/output"; /** * 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 * * ## Import * * ```sh * $ pulumi import volcenginecc:ark/endpoint:Endpoint example "endpoint_id" * ``` */ export declare class Endpoint extends pulumi.CustomResource { /** * Get an existing Endpoint resource's state with the given name, ID, and optional extra * properties used to qualify the lookup. * * @param name The _unique_ name of the resulting resource. * @param id The _unique_ provider ID of the resource to lookup. * @param state Any extra arguments used during the lookup. * @param opts Optional settings to control the behavior of the CustomResource. */ static get(name: string, id: pulumi.Input, state?: EndpointState, opts?: pulumi.CustomResourceOptions): Endpoint; /** * Returns true if the given object is an instance of Endpoint. This is designed to work even * when multiple copies of the Pulumi SDK have been loaded into the same process. */ static isInstance(obj: any): obj is Endpoint; /** * Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed */ readonly batchOnly: pulumi.Output; /** * Certificate information */ readonly certificate: pulumi.Output; /** * Endpoint creation time, RFC3339 format */ readonly createTime: pulumi.Output; /** * Endpoint description */ readonly description: pulumi.Output; /** * Inference access point ID. */ readonly endpointId: pulumi.Output; /** * Access point model type. Options: FoundationModel for base model; CustomModel for custom model. */ readonly endpointModelType: pulumi.Output; /** * Endpoint access model */ readonly modelReference: pulumi.Output; /** * Model unit. If empty, indicates postpaid; otherwise, prepaid. */ readonly modelUnitId: pulumi.Output; /** * Content guardrail scheme */ readonly moderation: pulumi.Output; /** * Endpoint name */ readonly name: pulumi.Output; /** * Project name the resource belongs to; default value is "default" */ readonly projectName: pulumi.Output; /** * Endpoint rate limiting */ readonly rateLimit: pulumi.Output; /** * Endpoint switch ID */ readonly rollingId: pulumi.Output; /** * If a TPM protection package exists, this is the TPM protection package ID. */ readonly scaleTierId: pulumi.Output; /** * Endpoint status */ readonly status: pulumi.Output; /** * Additional status information */ readonly statusReason: pulumi.Output; /** * Whether endpoint supports switching model versions */ readonly supportRolling: pulumi.Output; /** * Whether TPM protection package is supported */ readonly supportScaleTier: pulumi.Output; readonly tags: pulumi.Output; /** * Endpoint update time, RFC3339 format */ readonly updateTime: pulumi.Output; /** * Create a Endpoint resource with the given unique name, arguments, and options. * * @param name The _unique_ name of the resource. * @param args The arguments to use to populate this resource's properties. * @param opts A bag of options that control this resource's behavior. */ constructor(name: string, args: EndpointArgs, opts?: pulumi.CustomResourceOptions); } /** * Input properties used for looking up and filtering Endpoint resources. */ export interface EndpointState { /** * Whether only BatchChat is supported. If true, only batch inference interfaces can be accessed; otherwise, only online inference interfaces can be accessed */ batchOnly?: pulumi.Input; /** * Certificate information */ certificate?: pulumi.Input; /** * Endpoint creation time, RFC3339 format */ createTime?: pulumi.Input; /** * Endpoint description */ description?: pulumi.Input; /** * Inference access point ID. */ endpointId?: pulumi.Input; /** * Access point model type. Options: FoundationModel for base model; CustomModel for custom model. */ endpointModelType?: pulumi.Input; /** * Endpoint access model */ modelReference?: pulumi.Input; /** * Model unit. If empty, indicates postpaid; otherwise, prepaid. */ modelUnitId?: pulumi.Input; /** * Content guardrail scheme */ moderation?: pulumi.Input; /** * Endpoint name */ name?: pulumi.Input; /** * Project name the resource belongs to; default value is "default" */ projectName?: pulumi.Input; /** * Endpoint rate limiting */ rateLimit?: pulumi.Input; /** * Endpoint switch ID */ rollingId?: pulumi.Input; /** * If a TPM protection package exists, this is the TPM protection package ID. */ scaleTierId?: pulumi.Input; /** * Endpoint status */ status?: pulumi.Input; /** * Additional status information */ statusReason?: pulumi.Input; /** * Whether endpoint supports switching model versions */ supportRolling?: pulumi.Input; /** * Whether TPM protection package is supported */ supportScaleTier?: pulumi.Input; tags?: pulumi.Input[]>; /** * Endpoint update time, RFC3339 format */ updateTime?: pulumi.Input; } /** * The set of arguments for constructing a Endpoint resource. */ export interface EndpointArgs { /** * Endpoint description */ description?: pulumi.Input; /** * Endpoint access model */ modelReference: pulumi.Input; /** * Model unit. If empty, indicates postpaid; otherwise, prepaid. */ modelUnitId?: pulumi.Input; /** * Content guardrail scheme */ moderation?: pulumi.Input; /** * Endpoint name */ name: pulumi.Input; /** * Project name the resource belongs to; default value is "default" */ projectName?: pulumi.Input; /** * Endpoint rate limiting */ rateLimit?: pulumi.Input; tags?: pulumi.Input[]>; }