Regions and Access Domains

Region overview

Regions determine 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 compliance requirements, select a scope with specific geographic boundaries. Otherwise, select the Global scope for a larger inference resource pool.

• Access domain: Affects concurrency limits, timeouts, and other service guarantees. Each region has its own dedicated access domain.

A complete model invocation flow is as follows:

1. Your application sends a request to the selected region through the access domain. Request data is stored in that region.

2. The region forwards the request to inference nodes within the service deployment scope for computation (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.

Access Domain

Model Studio provides three types of access domains for model inference APIs: workspace-dedicated, DashScope, and trial, covering scenarios from trial exploration to enterprise-grade production. We recommend using the workspace-dedicated domain. The key differences are as follows:

Regional access information

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

• Germany (Frankfurt), Japan (Tokyo) regions use Workspaces to separate service deployment scopes. Before making API calls, go to the Workspace Management page to create a workspace and select a service deployment scope: Germany (Frankfurt) (Global/EU), Japan (Tokyo) (Global/Japan).

• US (Virginia) region: Use model names with the -us suffix (such as qwen-plus-us) to restrict inference to the US. Without the suffix, inference defaults to the Global scope.

• China (Beijing) and Singapore regions each support only one service deployment scope (Chinese mainland and International, respectively), so no selection is needed.

Migrate to workspace-dedicated domain

Migrating from a DashScope domain or trial domain to a workspace-dedicated domain requires only two steps, with no changes to your business logic code:

1. Obtain the workspace-dedicated domain: On the Workspace Management page, copy the content in the API Host column.

2. Replace the domain in the request URL: Replace the original domain in your code with the copied API Host (e.g., llm-xxx.cn-beijing.maas.aliyuncs.com). Using China (Beijing) region as an example, where llm-xxx is the workspace ID:

   • OpenAI compatible: Replace https://dashscope.aliyuncs.com/compatible-mode/v1 with https://llm-xxx.cn-beijing.maas.aliyuncs.com/compatible-mode/v1

   • DashScope: Replace https://dashscope.aliyuncs.com/api/v1 with https://llm-xxx.cn-beijing.maas.aliyuncs.com/api/v1

   • Anthropic compatible: Replace https://dashscope.aliyuncs.com/apps/anthropic with https://llm-xxx.cn-beijing.maas.aliyuncs.com/apps/anthropic

Feature availability by region

FAQ

Do I need to use an overseas region to call the Model Studio API (for example, to call deepseek models)?

No. You can call all models, including deepseek, from a Chinese mainland region such as China (Beijing). Overseas regions are optional.

Configure models such as deepseek with a Model Studio API key. Model Studio API keys support both the pay-as-you-go billing method and the token plan billing method, and both support deepseek models.

To configure a model, create an API key in the Model Studio console, and use the OpenAI-compatible base URL together with the API key to call the model.

References

• Qwen API Reference

• Recommended models — Models and context lengths by region

• Model inference pricing — Pricing by region

• Rate limiting— RPM and TPM limits

• Obtain an API key — Create and manage keys

• Base URL overview — Model API access URLs

• Realtime API Reference