Select region and service scope

更新时间:
复制 MD 格式

Before calling Model Studio, select a region and a service deployment scope:

  • Region: Determines the access point and data storage location. Choose a nearby region to reduce latency.

  • Service deployment scope: Determines the inference execution location. If you have data residency requirements, select a scope with specific geographic boundaries. Otherwise, select the Global scope for a larger inference resource pool.

A complete model invocation works as follows:

  1. Your application sends a request to the selected region (such as China (Beijing)) through the Base URL. Request data is stored in that region.

  2. The region forwards the request to an inference node within the service deployment scope (transient data is not persisted; all transmissions are encrypted).

  3. The inference result is returned to the region for storage and then sent back to your application. Your static data always remains in the selected region.

image

Select region and service scope

Choose a region and service deployment scope based on your scenario:

Scenario

Region

Service deployment scope

No data residency restrictions. Maximize the inference resource pool through cross-region scheduling (ensure cross-border compliance independently).

US (Virginia)

Global (any available node, including within and outside China)

No data residency restrictions. Maximize the inference resource pool through cross-region scheduling (ensure cross-border compliance independently).

Germany (Frankfurt)

Global (any available node, including within and outside China)

Data must stay within the Chinese mainland

China (Beijing)

Chinese mainland (inference restricted to China)

Data must not pass through the Chinese mainland (cross-region inference scheduling; ensure cross-border compliance independently)

Singapore

International (global nodes excluding the Chinese mainland)

Data must stay within the US

US (Virginia)

United States (inference restricted to the US)

Data must stay within the EU

Germany (Frankfurt)

EU (inference restricted to the EU)

Regional access information

Each region has its own Base URL, API Key, and model list. These cannot be used across regions.

Important

Model Studio has released new domain names for China (Beijing), Singapore regions: {WorkspaceId}.{region}.maas.aliyuncs.com. {WorkspaceId} is the workspace ID (available from the Workspace Management page of each region), and {region} can be cn-beijing, ap-southeast-1. The new dedicated domains deliver superior performance and higher stability for inference requests. We recommend migrating to the new domains:

  • China (Beijing): We recommend migrating from dashscope.aliyuncs.com to {WorkspaceId}.cn-beijing.maas.aliyuncs.com

  • Singapore: We recommend migrating from dashscope-intl.aliyuncs.com to {WorkspaceId}.ap-southeast-1.maas.aliyuncs.com

China (Beijing)

  • Base URL (OpenAI compatible): https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1. When calling, replace WorkspaceId with your actual workspace ID.

  • Base URL (Anthropic compatible): https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/apps/anthropic

  • Base URL (DashScope): https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1

  • API Key: Key Management (Beijing)

  • Model list: Available Models (Beijing)

Singapore

  • Base URL (OpenAI compatible): https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1. When calling, replace WorkspaceId with your actual workspace ID.

  • Base URL (Anthropic compatible): https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/apps/anthropic

  • Base URL (DashScope): https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1

  • API Key: Key Management (Singapore)

  • Model list: Available Models (Singapore)

US (Virginia)

  • Base URL (OpenAI compatible): https://dashscope-us.aliyuncs.com/compatible-mode/v1

  • Base URL (Anthropic compatible): https://dashscope-us.aliyuncs.com/apps/anthropic

  • Base URL (DashScope): https://dashscope-us.aliyuncs.com/api/v1

  • API Key: Key Management (Virginia)

  • Model list: Available Models (Virginia)

US-only inference: Use model names with the -us suffix, such as qwen-plus-us. Without the suffix, inference defaults to the Global scope.

Germany (Frankfurt)

Frankfurt uses Workspaces to separate deployment scopes. API Keys are isolated between workspaces. Before making API calls, create a workspace:

  1. Go to Workspace Management (Frankfurt) and create a workspace. Select a service deployment scope (Global or EU).

  2. Get the Workspace ID (Frankfurt) and replace {WorkspaceId} in the Base URLs below.

  • Base URL (OpenAI compatible): https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/compatible-mode/v1

  • Base URL (Anthropic compatible): https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/apps/anthropic

  • Base URL (DashScope): https://{WorkspaceId}.eu-central-1.maas.aliyuncs.com/api/v1

  • API Key: Key Management (Frankfurt)

  • Model list: Available Models (Frankfurt)

Feature availability by region

Feature

China (Beijing)

Singapore

US (Virginia)

Germany (Frankfurt)

Real-time inference

Supported

Supported

Supported

Supported

Batch inference

Supported

Supported

Not supported

Not supported

Playground

Supported

Supported

Supported

Supported

Monitoring

Supported

Supported

Supported

Supported

Alerting

Supported

Supported

Not supported

Not supported

Transmission security

Supported

Supported

Supported

Supported

Permissions

Supported

Supported

Supported

Supported

Fine-tuning

Supported

Not supported

Not supported

Not supported

References