> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nemo-platform/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo-platform/_mcp/server. # Get VirtualModel GET https://host.com/apis/inference-gateway/v2/workspaces/{workspace}/virtual-models/{name} Get a VirtualModel by workspace and name. Reference: https://docs.nvidia.com/nemo-platform/nemo-platform/documentation/reference/api-reference/virtual-models/get-virtual-model ## OpenAPI Specification ```yaml openapi: 3.1.0 info: title: Nemo Platform API version: 1.0.0 paths: /apis/inference-gateway/v2/workspaces/{workspace}/virtual-models/{name}: get: operationId: get-virtual-model summary: Get VirtualModel description: Get a VirtualModel by workspace and name. tags: - subpackage_virtualModels parameters: - name: workspace in: path required: true schema: type: string - name: name in: path required: true schema: type: string responses: '200': description: VirtualModel details content: application/json: schema: $ref: '#/components/schemas/VirtualModel' '404': description: VirtualModel not found. content: application/json: schema: description: Any type '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' servers: - url: https://host.com description: Default components: schemas: BackendFormat: type: string enum: - OPENAI_CHAT - ANTHROPIC_MESSAGES description: >- Inference backend API wire formats understood by IGW and middleware plugins. title: BackendFormat VirtualModelInferenceConfig: type: object properties: model: type: string backend_format: oneOf: - $ref: '#/components/schemas/BackendFormat' - type: 'null' description: Optional backend format override for this VirtualModel entry. required: - model description: >- Inference configuration for one model entity referenced by a VirtualModel. title: VirtualModelInferenceConfig MiddlewareCall: type: object properties: name: type: string config_type: type: string config: type: object additionalProperties: description: Any type config_id: type: string required: - name - config_type description: >- One entry in a VirtualModel middleware pipeline. Declares which plugin to invoke and how to resolve its configuration. Exactly one of ``config`` (inline dict) or ``config_id`` (entity reference) should be provided. ``config_type`` is always required regardless of which is used — it is the discriminator that tells IGW (and the plugin) which config schema applies. Attributes: name: The entry-point key of the plugin to invoke (e.g. ``"nemo-switchyard"``). Must match the plugin's ``nemo.inference_middleware`` entry-point key. config_type: Always required. Maps to the ``entity_type`` of the plugin's config ``NemoEntity`` subclass (e.g. ``"routellm_config"``). Used by IGW to call :meth:`~NemoInferenceMiddleware.validate_middleware_config` with the right discriminator, and by the plugin to dispatch to the correct schema when it supports multiple config types. config: Inline config dict. Mutually exclusive with ``config_id``. config_id: ``"workspace/name"`` reference to a stored config entity. Mutually exclusive with ``config``. IGW resolves this by calling :meth:`~NemoInferenceMiddleware.get_middleware_config` on the plugin. title: MiddlewareCall VirtualModel: type: object properties: name: type: string default: '' description: Entity name within the workspace workspace: type: string description: Workspace identifier project: type: string description: The name of the project associated with this entity. default_model_entity: type: string autoprovisioned: type: boolean default: false description: >- Marks this VirtualModel as controller-managed. The Models controller will delete it once no ModelProvider serves the matching entity. Setting this manually opts the VirtualModel into that cleanup behavior. models: type: array items: $ref: '#/components/schemas/VirtualModelInferenceConfig' request_middleware: type: array items: $ref: '#/components/schemas/MiddlewareCall' default: [] response_middleware: type: array items: $ref: '#/components/schemas/MiddlewareCall' default: [] post_response_middleware: type: array items: $ref: '#/components/schemas/MiddlewareCall' default: [] override_proxy: type: string id: type: string created_at: type: string format: date-time created_by: type: - string - 'null' updated_at: type: string format: date-time updated_by: type: - string - 'null' entity_id: type: string description: Alias for id for backwards compatibility. parent: type: string description: Parent entity ID for nested entities. required: - workspace - id - created_at - created_by - updated_at - updated_by - entity_id - parent description: >- Logical inference route. Maps a user-facing model name to an optional default model entity and defines ordered middleware pipelines for the request, response, and post-response phases. When a caller sets ``model: "workspace/my-virtual-model"`` in an inference request, IGW resolves the ``VirtualModel`` instead of a ``ModelEntity`` directly. If ``default_model_entity`` is set, IGW writes it into ``request["model"]`` before the request middleware pipeline runs. Middleware may mutate ``request["model"]`` freely. After the pipeline completes, IGW reads ``request["model"]``, resolves it to a ``ModelProvider`` via the ``ModelCache``, and proxies. The ``ModelProviderReconciler`` auto-creates a passthrough ``VirtualModel`` for each discovered model (same workspace and name as the ``ModelEntity``, empty middleware lists, ``default_model_entity`` pointing to that entity). All existing inference requests continue to work without changes. title: VirtualModel ValidationErrorLocItems: oneOf: - type: string - type: integer title: ValidationErrorLocItems ValidationError: type: object properties: loc: type: array items: $ref: '#/components/schemas/ValidationErrorLocItems' msg: type: string type: type: string input: description: Any type ctx: type: object additionalProperties: description: Any type required: - loc - msg - type title: ValidationError HTTPValidationError: type: object properties: detail: type: array items: $ref: '#/components/schemas/ValidationError' title: HTTPValidationError ``` ## Examples **Request** ```json {} ``` **Response** ```json { "workspace": "nemo-enterprise", "id": "a3f47b9e-8c2d-4f1a-9b7e-2d3f5c6a7e8b", "created_at": "2024-01-15T09:30:00Z", "created_by": "admin@nemo-enterprise.com", "updated_at": "2024-04-10T14:45:00Z", "updated_by": "devops@nemo-enterprise.com", "entity_id": "a3f47b9e-8c2d-4f1a-9b7e-2d3f5c6a7e8b", "parent": "nemo-enterprise/root-virtual-model", "name": "customer-support-bot", "project": "customer-engagement", "default_model_entity": "nemo-enterprise/gpt-4-chat", "autoprovisioned": false, "models": [ { "model": "nemo-enterprise/gpt-4-chat", "backend_format": "OPENAI_CHAT" } ], "request_middleware": [ { "name": "nemo-authenticator", "config_type": "auth_config", "config": { "token_header": "Authorization", "token_prefix": "Bearer" }, "config_id": "" } ], "response_middleware": [ { "name": "nemo-logger", "config_type": "logging_config", "config": { "log_level": "INFO", "log_format": "json" }, "config_id": "" } ], "post_response_middleware": [ { "name": "nemo-metrics", "config_type": "metrics_config", "config": { "enabled": true, "metrics_endpoint": "/metrics" }, "config_id": "" } ], "override_proxy": "https://proxy.nemo-enterprise.com" } ``` **SDK Code** ```python import requests url = "https://host.com/apis/inference-gateway/v2/workspaces/workspace/virtual-models/name" payload = {} headers = {"Content-Type": "application/json"} response = requests.get(url, json=payload, headers=headers) print(response.json()) ``` ```javascript const url = 'https://host.com/apis/inference-gateway/v2/workspaces/workspace/virtual-models/name'; const options = {method: 'GET', headers: {'Content-Type': 'application/json'}, body: '{}'}; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://host.com/apis/inference-gateway/v2/workspaces/workspace/virtual-models/name" payload := strings.NewReader("{}") req, _ := http.NewRequest("GET", url, payload) req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```ruby require 'uri' require 'net/http' url = URI("https://host.com/apis/inference-gateway/v2/workspaces/workspace/virtual-models/name") http = Net::HTTP.new(url.host, url.port) http.use_ssl = true request = Net::HTTP::Get.new(url) request["Content-Type"] = 'application/json' request.body = "{}" response = http.request(request) puts response.read_body ``` ```java import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.get("https://host.com/apis/inference-gateway/v2/workspaces/workspace/virtual-models/name") .header("Content-Type", "application/json") .body("{}") .asString(); ``` ```php request('GET', 'https://host.com/apis/inference-gateway/v2/workspaces/workspace/virtual-models/name', [ 'body' => '{}', 'headers' => [ 'Content-Type' => 'application/json', ], ]); echo $response->getBody(); ``` ```csharp using RestSharp; var client = new RestClient("https://host.com/apis/inference-gateway/v2/workspaces/workspace/virtual-models/name"); var request = new RestRequest(Method.GET); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift import Foundation let headers = ["Content-Type": "application/json"] let parameters = [] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://host.com/apis/inference-gateway/v2/workspaces/workspace/virtual-models/name")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "GET" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ```