Alibaba Cloud Model Studio is available in multiple regions. Each region offers various types of access domains, including workspace-dedicated and DashScope domains, and supports multiple service deployment scopes to meet different access requirements.
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.
- Your application sends a request to the selected region through the access domain. Request data is stored in that region.
- The region forwards the request to inference nodes within the service deployment scope for computation (all transmissions are encrypted).
- 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.
Select a region and service deployment scope
Different regions support different service deployment scopes, and Model Studio schedules inference within the selected scope. For example, US (Virginia) supports Global and US, and Germany (Frankfurt) supports Global and EU. For a complete list of regions and their supported service deployment scopes, go to the console.
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:
| Comparison | Workspace-dedicated domain (recommended) | DashScope domain (existing domain) | Trial domain |
|---|---|---|---|
| Domain format | {WorkspaceId}.{region}.maas.aliyuncs.com | dashscope-intl.aliyuncs.comUsing Singapore region as an example | trial.{region}.maas.aliyuncs.com |
| Use case | Recommended for production environments. Offers higher concurrency capacity and network isolation, ensuring stable and low-latency access under heavy traffic. | For existing integrations. We recommend migrating to the workspace-dedicated domain. | Quick trial and feature validation. Not recommended for production environments. |
| Authentication scope | Access to the current workspace only | Access to all workspaces | Access to all workspaces |
| Rate limits | RPM and TPM vary by model and are aggregated at the Alibaba Cloud account level | RPM and TPM vary by model and are aggregated at the Alibaba Cloud account level | RPM is 1000 (at the Alibaba Cloud account level); TPM varies by model |
| Request timeout | 3600 seconds | 600 seconds | 600 seconds |
| Protocol support | HTTP, SSE, WebSocket, WebRTC, AOQ (AI over QUIC) | HTTP, SSE, WebSocket | HTTP, SSE |
| SLA | 99.9% | 99.9% | Not provided |
Regional access information
Each region has its own access domain, API Key, and model list. These cannot be used across regions.
Region | Region ID | Workspace-dedicated domain | DashScope domain | Trial domain | API Key | Model list |
|---|---|---|---|---|---|---|
China (Beijing) |
|
|
|
| ||
Singapore |
|
|
|
| ||
Germany (Frankfurt) |
|
| Not supported | Not yet supported | ||
Japan (Tokyo) |
|
| Not supported | Not yet supported | ||
China (Hong Kong) |
|
|
|
| ||
US (Virginia) |
|
| Not supported | Not yet supported |
- Germany (Frankfurt), Japan (Tokyo), and China (Hong Kong) 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), China (Hong Kong) (Global/Hong Kong).
- US (Virginia) region: Use model names with the
-ussuffix (such asqwen-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:
- Obtain the workspace-dedicated domain: On the Workspace Management page, copy the content in the API Host column.
-
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, wherellm-xxxis the workspace ID:- OpenAI compatible: Replace
https://dashscope.aliyuncs.com/compatible-mode/v1withhttps://llm-xxx.cn-beijing.maas.aliyuncs.com/compatible-mode/v1 - DashScope: Replace
https://dashscope.aliyuncs.com/api/v1withhttps://llm-xxx.cn-beijing.maas.aliyuncs.com/api/v1 - Anthropic compatible: Replace
https://dashscope.aliyuncs.com/apps/anthropicwithhttps://llm-xxx.cn-beijing.maas.aliyuncs.com/apps/anthropic
- OpenAI compatible: Replace
Feature availability by region
Feature | Singapore | US (Virginia) | China (Beijing) | China (Hong Kong) | Germany (Frankfurt) | Japan (Tokyo) |
|---|---|---|---|---|---|---|
Real-time inference | Supported | Supported | Supported | Supported | Supported | Supported |
Batch inference | Supported | Not supported | Supported | Not supported | Not supported | Not supported |
Playground | Supported | Supported | Supported | Supported | Supported | Supported |
Monitoring (standard) | Supported | Supported | Supported | Supported | Supported | Supported |
Monitoring (advanced) | Supported | Supported | Supported | Not supported | Not supported | Not supported |
Alerting | Supported | Not supported | Supported | Not supported | Not supported | Not supported |
Transmission security | Supported | Supported | Supported | Supported | Supported | Supported |
Permissions | Supported | Supported | Supported | Supported | Supported | Supported |
Fine-tuning | Supported | Not supported | Supported | Not supported | Not supported | Not supported |
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