> ## Documentation Index > Fetch the complete documentation index at: https://gcore.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Create inference application deployment > Creates a new application deployment based on a selected catalog application. Specify the desired deployment name, target regions, and configuration for each component. The platform will provision the necessary resources and initialize the application accordingly. ## OpenAPI ````yaml /api-reference/services_documented/cloud_api.yaml post /cloud/v3/inference/applications/{project_id}/deployments openapi: 3.1.0 info: title: Gcore OpenAPI – Cloud API description: >- This OpenAPI is an aggregated OpenAPI specification that unifies all Gcore products into a single file. It covers Cloud, CDN, DNS, WAAP, DDoS Protection, Object Storage, Streaming, and FastEdge services. version: '2026-05-11T15:10:30.328297+00:00' servers: - url: https://api.gcore.com security: - APIKey: [] tags: - name: Bare Metal x-displayName: Bare Metal - name: Container as a Service x-displayName: Container as a Service - name: Cost Reports x-displayName: Cost Reports - name: DDoS Protection x-displayName: DDoS Protection - name: Everywhere Inference x-displayName: Everywhere Inference - name: Everywhere Inference Apps x-displayName: Everywhere Inference Apps - name: File Shares x-displayName: File Shares - name: Floating IPs x-displayName: Floating IPs - name: Function as a Service x-displayName: Function as a Service - name: GPU Bare Metal x-displayName: GPU Bare Metal - name: GPU Virtual x-displayName: GPU Virtual - name: IP Ranges x-displayName: IP Ranges - name: Images x-displayName: Images - name: Instances x-displayName: Instances - name: Load Balancers x-displayName: Load Balancers - name: Logging x-displayName: Logging - name: Managed Kubernetes x-displayName: Managed Kubernetes - name: Managed PostgreSQL x-displayName: Managed PostgreSQL - name: Networks x-displayName: Networks - name: Placement Groups x-displayName: Placement Groups - name: Projects x-displayName: Projects - name: Quotas x-displayName: Quotas - name: Regions x-displayName: Regions - name: Registry x-displayName: Registry - name: Reservations x-displayName: Reservations - name: Reserved IPs x-displayName: Reserved IPs - name: Routers x-displayName: Routers - name: SSH Keys x-displayName: SSH Keys - name: Secrets x-displayName: Secrets - name: Security Groups x-displayName: Security Groups - name: Snapshot Schedules x-displayName: Snapshot Schedules - name: Snapshots x-displayName: Snapshots - name: Tasks x-displayName: Tasks - name: User Actions x-displayName: User Actions - name: User Role Assignments x-displayName: User Role Assignments - name: Volumes x-displayName: Volumes paths: /cloud/v3/inference/applications/{project_id}/deployments: post: tags: - Everywhere Inference Apps summary: Create inference application deployment description: >- Creates a new application deployment based on a selected catalog application. Specify the desired deployment name, target regions, and configuration for each component. The platform will provision the necessary resources and initialize the application accordingly. operationId: InferenceApplicationDeploymentsCollection.post parameters: - in: path name: project_id required: true description: Project ID schema: description: Project ID example: 1 examples: - 1 title: Project Id type: integer requestBody: content: application/json: schema: $ref: '#/components/schemas/AppDeploymentCreateRequest' responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/TaskIDsSerializer' x-codeSamples: - lang: Python source: >- import os from gcore import Gcore client = Gcore( api_key=os.environ.get("GCORE_API_KEY"), # This is the default and can be omitted ) task_id_list = client.cloud.inference.applications.deployments.create( project_id=1, application_name="demo-app", components_configuration={ "model": { "exposed": True, "flavor": "inference-16vcpu-232gib-1xh100-80gb", "scale": { "max": 1, "min": 1, }, } }, name="name", regions=[1, 2], ) print(task_id_list.tasks) - lang: Go source: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\n\t\"github.com/G-Core/gcore-go\"\n\t\"github.com/G-Core/gcore-go/cloud\"\n\t\"github.com/G-Core/gcore-go/option\"\n)\n\nfunc main() {\n\tclient := gcore.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\ttaskIDList, err := client.Cloud.Inference.Applications.Deployments.New(context.TODO(), cloud.InferenceApplicationDeploymentNewParams{\n\t\tProjectID: gcore.Int(1),\n\t\tApplicationName: \"demo-app\",\n\t\tComponentsConfiguration: map[string]cloud.InferenceApplicationDeploymentNewParamsComponentsConfiguration{\n\t\t\t\"model\": {\n\t\t\t\tExposed: true,\n\t\t\t\tFlavor: \"inference-16vcpu-232gib-1xh100-80gb\",\n\t\t\t\tScale: cloud.InferenceApplicationDeploymentNewParamsComponentsConfigurationScale{\n\t\t\t\t\tMax: 1,\n\t\t\t\t\tMin: 1,\n\t\t\t\t},\n\t\t\t},\n\t\t},\n\t\tName: \"name\",\n\t\tRegions: []int64{1, 2},\n\t})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", taskIDList.Tasks)\n}\n" components: schemas: AppDeploymentCreateRequest: properties: api_keys: description: List of API keys for the application example: - key1 - key2 examples: - - key1 - key2 items: type: string title: Api Keys type: array application_name: description: Identifier of the application from the catalog example: demo-app examples: - demo-app title: Application Name type: string components_configuration: additionalProperties: $ref: '#/components/schemas/CreateComponentConfiguration' description: >- Mapping of component names to their configuration (e.g., `"model": {...}`) example: model: exposed: true flavor: inference-16vcpu-232gib-1xh100-80gb scale: max: 1 min: 1 examples: - model: exposed: true flavor: inference-16vcpu-232gib-1xh100-80gb scale: max: 1 min: 1 title: Components Configuration type: object name: description: Desired name for the new deployment example: my-app-deployment examples: - my-app-deployment maxLength: 15 title: Name type: string regions: description: Geographical regions where the deployment should be created example: - 1 - 2 examples: - - 1 - 2 items: type: integer title: Regions type: array required: - application_name - name - regions - components_configuration title: AppDeploymentCreateRequest type: object TaskIDsSerializer: properties: tasks: description: >- List of task IDs representing asynchronous operations. Use these IDs to monitor operation progress: - `GET /v1/tasks/{task_id}` - Check individual task status and details Poll task status until completion (`FINISHED`/`ERROR`) before proceeding with dependent operations. example: - d478ae29-dedc-4869-82f0-96104425f565 examples: - - d478ae29-dedc-4869-82f0-96104425f565 items: type: string title: Tasks type: array required: - tasks title: TaskIDsSerializer type: object CreateComponentConfiguration: properties: exposed: description: >- Whether the component should be exposed via a public endpoint (e.g., for external inference/API access). title: Exposed type: boolean flavor: description: >- Specifies the compute configuration (e.g., CPU/GPU size) to be used for the component. title: Flavor type: string parameter_overrides: additionalProperties: $ref: '#/components/schemas/ParameterOverride' description: Map of parameter overrides for customization title: Parameter Overrides type: object scale: $ref: '#/components/schemas/Scale' description: Scaling parameters of the component required: - flavor - exposed - scale title: CreateComponentConfiguration type: object ParameterOverride: properties: value: description: New value assigned to the overridden parameter title: Value type: string required: - value title: ParameterOverride type: object Scale: properties: max: description: Maximum number of replicas the container can be scaled up to title: Max type: integer min: description: Minimum number of replicas the component can be scaled down to title: Min type: integer required: - min - max title: Scale type: object securitySchemes: APIKey: description: >- API key for authentication. Make sure to include the word `apikey`, followed by a single space and then your token. Example: `apikey 1234$abcdef` type: apiKey in: header name: Authorization ````