[Feature Request] API Support for Workspace Model Authorization and Rate Limiting Configuration

[zhou3yang]

Is your feature request related to a problem? Please describe.

Currently, managing model access and usage quotas across different workspaces in Alibaba Cloud Model Studio (Bailian) often requires manual configuration via the console. For enterprise users managing multiple teams or environments (Dev/Staging/Prod) programmatically, the lack of dedicated APIs for workspace-level model assignment and rate limiting creates operational bottlenecks. We cannot easily automate the provisioning of new workspaces with specific model permissions and throttling policies.

Describe the solution you'd like

I propose adding new API endpoints to the Model Studio SDK/CLI to support programmatic workspace management. Specifically:

• Model Assignment API: Ability to activate/deactivate specific models for a specific Workspace ID.
• Rate Limiting/Quota API: Ability to set RPM (Requests Per Minute) or TPM (Tokens Per Minute) limits for a specific model within a workspace.
• Query APIs: Endpoints to retrieve current assignment and quota configurations.

Additional context

Currently, we have to rely on manual operations in the web console or contact support for bulk changes, which is not scalable for automated DevOps workflows. Enabling these APIs would significantly improve automation capabilities for enterprise users.