Region and endpoints

​

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.

A complete model invocation flow works as follows:

1. The application sends a request to the selected region through the endpoint, and the request data is stored in that region.
2. The access region forwards the request to an inference node within the service deployment scope for computation. Transmission is encrypted end-to-end.
3. 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.

The current region is Germany (Frankfurt). The service deployment scopes supported by this region are as follows:

Region	Service deployment scope
Germany (Frankfurt)	Global (any available node, including Chinese mainland and overseas)
	EU (inference within the region)

​

Endpoints

The Germany (Frankfurt) region supports only workspace-specific endpoints. It does not support the DashScope endpoint or the trial endpoint. The workspace-specific endpoint is described as follows:

Endpoint format	Applicable scenario	Authentication method	Rate limit	Request timeout	Protocol support	SLA
{WorkspaceId}.eu-central-1.maas.aliyuncs.com	Workspace-specific endpoint Recommended for production environments. Provides higher concurrency capacity and network isolation, ensuring stable, low-latency access in high-traffic scenarios.	Access only the current workspace	RPM and TPM vary by model and are aggregated at the Alibaba Cloud account level	3600 seconds	HTTP, SSE, WebSocket, WebRTC, AOQ (AI over QUIC)	99.9%

​

Access information

The Germany (Frankfurt) 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
Germany (Frankfurt)	eu-central-1	{WorkspaceId}.eu-central-1.maas.aliyuncs.com	Not supported	Not supported yet	API key management	Available models

• The Germany (Frankfurt) region distinguishes service deployment scopes by workspace. Before you start calling APIs, go to the Workspace Management page to create a workspace and select a service deployment scope: Germany (Frankfurt) (Global/EU).

​

Obtain a workspace-specific endpoint

The Germany (Frankfurt) region supports only workspace-specific endpoints. On the Workspace Management page, copy the content in the API Host column and use it as the domain name in the request address. llm-xxx is the workspace ID. The request addresses for APIs in the Germany (Frankfurt) region are as follows:

• OpenAI-compatible API: https://llm-xxx.eu-central-1.maas.aliyuncs.com/compatible-mode/v1
• DashScope API: https://llm-xxx.eu-central-1.maas.aliyuncs.com/api/v1
• Anthropic-compatible API: https://llm-xxx.eu-central-1.maas.aliyuncs.com/apps/anthropic

​

Feature support

Region	Real-time inference	Batch inference	Model experience	Model monitoring	Model alerting	Transmission security	Permission management	Model fine-tuning	Application development
Germany (Frankfurt)	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 /Germany (Frankfurt)/
• 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