NeMo Studio Virtual Models | NVIDIA NeMo Platform

Use 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 details panel.

Action	Where	Result
View details	Select a row or row actions > View	Opens the virtual model details panel.
Search	Name search bar	Filters the list to virtual models whose names match the query.
Filter by base model	Default Model filter	Shows only virtual models backed by the selected base model.
Filter by date	Created At filter	Narrows results to a specific creation date range.
Delete a virtual model	Row actions > Delete	Removes the virtual model. Requires typing the model name to confirm.

The table shows each virtual model’s name, default model, middleware call count, 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 a details panel with the full configuration of a single virtual model.

Summary

Field	Description
Created	When the virtual model was first created.
Default model	The backend model entity IGW routes requests to, if configured. When omitted, a request middleware plugin handles backend routing.
Autoprovisioned	Whether the route is controller-managed. The Models controller deletes controller-managed virtual models once no ModelProvider serves the matching entity; setting this field manually opts the virtual model into that cleanup behavior. Controller-managed models are hidden from the list.
Override proxy	An optional plugin-provided proxy identifier (format: `plugin-name.proxy-name`) that overrides the default IGW proxy, if set.
Models	Backend model entries associated with this virtual model, displayed as `model (backend_format)`.

Middleware

The details panel shows three ordered middleware pipelines applied to every request through this virtual model.

Pipeline	When it runs
Request middleware	Before the request reaches the backend model.
Response middleware	After the model responds, before the response is returned to the caller.
Post-response middleware	After the response is returned to the caller.

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.