> 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 Latest ModelDeploymentConfig Version

GET https://host.com/apis/models/v2/workspaces/{workspace}/deployment-configs/{name}

Get the latest version of a ModelDeploymentConfig.

Reference: https://docs.nvidia.com/nemo-platform/nemo-platform/documentation/reference/api-reference/model-deployment-configs/get-latest-deployment-config-apis-models-v-2-workspaces-workspace-deployment-configs-name-get

## OpenAPI Specification

```yaml
openapi: 3.1.0
info:
  title: Nemo Platform API
  version: 1.0.0
paths:
  /apis/models/v2/workspaces/{workspace}/deployment-configs/{name}:
    get:
      operationId: >-
        get-latest-deployment-config-apis-models-v-2-workspaces-workspace-deployment-configs-name-get
      summary: Get Latest ModelDeploymentConfig Version
      description: Get the latest version of a ModelDeploymentConfig.
      tags:
        - subpackage_modelDeploymentConfigs
      parameters:
        - name: workspace
          in: path
          required: true
          schema:
            type: string
        - name: name
          in: path
          required: true
          schema:
            type: string
      responses:
        '200':
          description: Return the latest version of a model deployment configuration
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ModelDeploymentConfig'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
servers:
  - url: https://host.com
    description: Default
components:
  schemas:
    Engine:
      type: string
      enum:
        - nim
        - vllm
        - generic
      description: >-
        Inference engine selecting the compiler path for a deployment.


        The engine determines what command, image, and env a deployment compiles
        to.

        The fields a compiler consumes are not engine-specific; engines take the
        same

        inputs (model_spec + executor_config) and differ in what they do with
        them.
      title: Engine
    ModelType:
      type: string
      enum:
        - llm
        - embed
        - other
      description: Model type enum for NIM deployments.
      title: ModelType
    ToolCallConfig:
      type: object
      properties:
        tool_call_parser:
          type: string
          description: >-
            Name of the tool call parser to use (e.g., 'openai', 'hermes',
            'pythonic', 'llama3_json', 'mistral').
        tool_call_plugin:
          type: string
          description: >-
            Reference to a fileset containing the custom tool call plugin Python
            file. Expected format: '{workspace}/{fileset_name}'. The fileset is
            mounted separately from the model checkpoint at deployment time.
        auto_tool_choice:
          type: boolean
          description: >-
            Whether to enable automatic tool choice. When enabled, the model can
            decide to call tools without explicit user instruction.
      description: Configuration for tool calling support in NIM deployments.
      title: ToolCallConfig
    ModelDeploymentConfigModelSpec:
      type: object
      properties:
        model_type:
          $ref: '#/components/schemas/ModelType'
          description: Type of model being deployed
        model_namespace:
          type: string
          description: >-
            Model repository namespace - organization/user namespace as it
            exists in repo_id.
        model_name:
          type: string
          description: Model name - model repository name for model weights.
        model_revision:
          type: string
          description: >-
            Model revision (branch, tag, or commit). If not specified, parsed
            from model_name @revision suffix or defaults to 'main'
        chat_template:
          type: string
          description: >-
            Jinja2 chat template string for the model. Overrides the
            chat_template from ModelEntity.spec if both are set. Used by the
            engine to format chat completions.
        tool_call_config:
          $ref: '#/components/schemas/ToolCallConfig'
          description: >-
            Tool calling configuration for the deployment. Overrides
            tool_call_config from ModelEntity.spec if both are set. Controls how
            the model handles function/tool calling.
        lora_enabled:
          type: boolean
          default: false
          description: Whether to enable LoRA support
      description: >-
        What model to serve and how -- independent of the executor it runs on.


        Executor-invariant facts about the model. The compiler resolves the
        weight

        source per engine; serving fields override the model entity spec when
        set.
      title: ModelDeploymentConfigModelSpec
    K8sNIMOperatorConfig:
      type: object
      properties:
        resources:
          type: object
          additionalProperties:
            description: Any type
          description: >-
            Kubernetes resource requirements including requests and limits.
            Example: {'requests': {'cpu': '2', 'memory': '8Gi'}, 'limits':
            {'memory': '16Gi'}}
        tolerations:
          type: array
          items:
            type: object
            additionalProperties:
              description: Any type
          description: >-
            Kubernetes tolerations for pod scheduling. Example: [{'key':
            'nvidia.com/gpu', 'operator': 'Exists', 'effect': 'NoSchedule'}]
        node_selector:
          type: object
          additionalProperties:
            type: string
          description: >-
            Kubernetes node selector for pod placement. Example: {'node-type':
            'gpu-node', 'zone': 'us-west1-a'}
        startup_probe_grace_seconds:
          type: integer
          description: >-
            Grace period in seconds for NIM startup. Determines how long
            Kubernetes will wait for the NIM to become ready before restarting
            it. Example: 600 (10 minutes). Must be a positive integer.
      description: >-
        Kubernetes configuration for NIM deployment via k8s-nim-operator.


        These fields provide typed access to commonly-used NIMService Spec
        fields

        and are applied before override_config in the compilation precedence.
      title: K8sNIMOperatorConfig
    ContainerExecutorConfig:
      type: object
      properties:
        gpu:
          type: integer
          description: Number of GPUs required for the deployment. 0 = CPU-only.
        disk_size:
          type: string
          default: 50Gi
          description: Disk size for the deployment
        image_name:
          type: string
          description: >-
            Container image name. If not specified, defaults to the engine's
            configured image (e.g. default_vllm_image /
            default_nimservice_image). Required for engine='generic'.
        image_tag:
          type: string
          description: >-
            Container image tag. If not specified, defaults to the engine's
            configured image tag.
        health_check_path:
          type: string
          description: >-
            HTTP path used for the container readiness probe. If not specified,
            defaults to the engine's standard health endpoint (e.g.
            '/v1/health/ready' for NIM, '/health' for vLLM). Set this for
            engine='generic' containers that expose a non-standard health
            endpoint.
        additional_envs:
          type: object
          additionalProperties:
            type: string
          description: Additional environment variables for the deployment
        additional_args:
          type: array
          items:
            type: string
          description: >-
            Raw container/`serve` args appended verbatim to the container's arg
            vector.
        k8s_nim_operator_config:
          $ref: '#/components/schemas/K8sNIMOperatorConfig'
          description: >-
            Typed Kubernetes configuration for common NIMService Spec fields
            (NIM engine on k8s). Applied after defaults but before
            override_config. Ignored by non-NIM engines.
        override_config:
          type: object
          additionalProperties:
            description: Any type
          description: >-
            Raw NIMService spec configuration that takes precedence over
            generated config (NIM engine on k8s). Allows advanced configuration
            options directly. Ignored by non-NIM engines.
      required:
        - gpu
      description: |-
        Compute + container settings shared by the docker and k8s executors.

        Both the docker and k8s executors run containers and share this shape.
        A future non-container executor (e.g. subprocess) would warrant turning
        ``executor_config`` into a discriminated union.
      title: ContainerExecutorConfig
    ModelDeploymentConfig:
      type: object
      properties:
        id:
          type: string
          description: Unique identifier for the deployment config
        name:
          type: string
          description: >-
            Name of the entity. Name/workspace combo must be unique across all
            entities. Allowed characters: letters (a-z, A-Z), digits (0-9),
            underscores, hyphens, and dots.
        workspace:
          type: string
          description: >-
            The workspace of the entity. Allowed characters: letters (a-z, A-Z),
            digits (0-9), underscores, hyphens, and dots.
        project:
          type: string
          description: The URN of the project associated with this entity.
        created_at:
          type: string
          format: date-time
          description: The timestamp of model entity creation
        updated_at:
          type: string
          format: date-time
          description: The timestamp of the last model entity update
        entity_version:
          type: integer
          description: Version of this deployment config. Automatically managed.
        description:
          type: string
          description: Optional description of the deployment configuration
        engine:
          $ref: '#/components/schemas/Engine'
          description: Inference engine selecting the compiler path (nim/vllm/generic)
        model_spec:
          $ref: '#/components/schemas/ModelDeploymentConfigModelSpec'
          description: >-
            What model to serve and how -- independent of the executor it runs
            on
        executor_config:
          $ref: '#/components/schemas/ContainerExecutorConfig'
          description: Compute + container settings for the executor the deployment runs on
        model_entity_id:
          type: string
          description: Optional reference to the base model entity ID for this deployment
      required:
        - name
        - workspace
        - created_at
        - updated_at
        - entity_version
        - engine
        - model_spec
        - executor_config
      description: >-
        ModelDeploymentConfig stores the configuration details for deploying a
        model.

        These objects are immutable with automatic versioning.


        The unique identifier is the combination of
        workspace/name/entity_version.
      title: ModelDeploymentConfig
    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
{
  "name": "llama-3.1-8b",
  "workspace": "research_team_alpha",
  "created_at": "2024-01-15T09:30:00Z",
  "updated_at": "2024-04-20T16:45:00Z",
  "entity_version": 3,
  "engine": "nim",
  "model_spec": {
    "model_type": "llm",
    "model_namespace": "meta",
    "model_name": "llama-3.1-8b",
    "model_revision": "v3.1.0",
    "chat_template": "{% raw %}{{ user_message }}{% endraw %}",
    "tool_call_config": {
      "tool_call_parser": "openai",
      "tool_call_plugin": "research_team_alpha/custom_tool_plugin",
      "auto_tool_choice": true
    },
    "lora_enabled": false
  },
  "executor_config": {
    "gpu": 2,
    "disk_size": "100Gi",
    "image_name": "nemo/nimservice-llama",
    "image_tag": "v3.1.0",
    "health_check_path": "/v1/health/ready",
    "additional_envs": {
      "NIM_LOG_LEVEL": "info",
      "MAX_BATCH_SIZE": "16"
    },
    "additional_args": [
      "--enable-logging"
    ],
    "k8s_nim_operator_config": {
      "resources": {
        "requests": {
          "cpu": "4",
          "memory": "16Gi"
        },
        "limits": {
          "cpu": "8",
          "memory": "32Gi"
        }
      },
      "tolerations": [
        {
          "key": "nvidia.com/gpu",
          "operator": "Exists",
          "effect": "NoSchedule"
        }
      ],
      "node_selector": {
        "node-type": "gpu-node",
        "zone": "us-west1-a"
      },
      "startup_probe_grace_seconds": 600
    },
    "override_config": {}
  },
  "id": "d4f7a9b2-3c1e-4f8a-9b7d-2e5f6a7c8d9e",
  "project": "urn:nemo:projects:language-models/v1",
  "description": "Deployment config for LLaMA 3.1 8B model optimized for chat applications.",
  "model_entity_id": "meta/llama-3.1-8b"
}
```

**SDK Code**

```python
import requests

url = "https://host.com/apis/models/v2/workspaces/workspace/deployment-configs/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/models/v2/workspaces/workspace/deployment-configs/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/models/v2/workspaces/workspace/deployment-configs/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/models/v2/workspaces/workspace/deployment-configs/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<String> response = Unirest.get("https://host.com/apis/models/v2/workspaces/workspace/deployment-configs/name")
  .header("Content-Type", "application/json")
  .body("{}")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('GET', 'https://host.com/apis/models/v2/workspaces/workspace/deployment-configs/name', [
  'body' => '{}',
  'headers' => [
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://host.com/apis/models/v2/workspaces/workspace/deployment-configs/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/models/v2/workspaces/workspace/deployment-configs/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()
```