NeMo Studio Virtual Models
The Virtual Models Studio UI is a preview feature and is disabled by default. An administrator must set studio.feature_flags.guardrails_enabled: true in the platform configuration and restart Studio before Models > Virtual Models appears. This flag also enables Governance > Guardrails.
Use Models > Virtual Models in the NeMo Studio workspace sidebar to inspect inference routes and their middleware pipelines for the selected workspace.
Virtual Model List
The Virtual Models table shows all user-created virtual models in the current workspace. Controller-managed passthrough routes are hidden. Select a row or choose View from the row actions menu to open the virtual model detail page.
The table shows each virtual model’s name, default model, middleware call count (or None), and creation time.
Virtual models are created and updated through the nemo inference virtual-models CLI or the Inference Gateway API. NeMo Studio reflects the current workspace state.
Virtual Model Details
Selecting a row opens the detail page for a single virtual model. The page has two tabs: Details shows the virtual model’s full configuration, and Chat lets you send messages through the virtual model.
Summary
The Details tab lists the following fields.
Middleware
The Details tab shows three ordered middleware pipelines applied to every request through this virtual model.
Each middleware entry shows its plugin name, config type, config reference, and inline config payload if one is set. A guardrails middleware entry, for example, shows the plugin nemo-guardrails, the config type guardrail_config, and a config ID pointing to a workspace guardrail configuration.
Chat
The Chat tab opens a chat session that sends requests through the virtual model, so its middleware pipelines (for example, guardrails) apply to every message. Use the Inference parameters control above the chat to adjust settings such as temperature and max tokens.