Alibaba Cloud Model Studio provides services in multiple regions. Each region offers workspace-specific endpoints, DashScope endpoints, and other endpoint types, and supports multiple service deployment scopes to meet access requirements in different scenarios.
Region overview
The region determines the access point and data storage location. Choose a nearby region to reduce latency.
- Service deployment scope: determines the inference execution location. Select a deployment scope with specific geographic boundaries for data compliance requirements, or select the global deployment scope for a larger inference resource pool if no compliance requirements apply.
- Endpoint: affects concurrency limits, timeouts, and other service guarantees. Each region has independent endpoints.
- The application sends a request to the selected region through the endpoint, and the request data is stored in that region.
- The access region forwards the request to an inference node within the service deployment scope for computation. Transmission is encrypted end-to-end.
- The inference result returns to the access region for storage and is then returned to the application. User static data is always stored in the selected region.
Region | Service deployment scope |
|---|---|
US (Virginia) | Global (any available node, including Chinese mainland and overseas) |
United States (inference within the region) |
Endpoints
The US (Virginia) region supports the workspace-specific endpoint (recommended) and the DashScope endpoint. It does not support the trial endpoint. The DashScope endpoint is described as follows:
Endpoint format | Applicable scenario | Authentication method | Rate limit | Request timeout | Protocol support | SLA |
|---|---|---|---|---|---|---|
| DashScope endpoint For existing business compatibility. | Access all workspaces | RPM and TPM vary by model and are aggregated at the Alibaba Cloud account level | 600 seconds | HTTP, SSE, WebSocket | 99.9% |
Access information
The US (Virginia) region has independent endpoints, API keys, and model lists. These cannot be mixed across regions.
Region | Region ID | Workspace-specific endpoint | DashScope endpoint | Trial endpoint | API Key | Model list |
|---|---|---|---|---|---|---|
US (Virginia) |
|
|
| Not supported yet |
Feature support
Region | Real-time inference | Batch inference | Model experience | Model monitoring | Model alerting | Transmission security | Permission management | Model fine-tuning | Application development |
|---|---|---|---|---|---|---|---|---|---|
US (Virginia) | Supported | Not supported | Supported | Supported | Not supported | Supported | Supported | Not supported | Not supported |
Related documents
- Tongyi Qianwen API reference
- Recommended models — Models and context lengths by region
- Model inference pricing — Pricing by region /US (Virginia)/
- Rate limiting— RPM and TPM limits
- Obtain an API key — Create and manage API keys
- Base URL overview — Model service endpoints
- Regions and endpoints - More region information