Create a Container

Overview

The "Create a Container" API endpoint allows you to deploy a new container with the specified configurations. Use this endpoint to initiate a container deployment with parameters like model ID, GPU count, GPU type etc.

This endpoint handles container creation and returns a unique container ID in the response, which can be used for subsequent operations like status monitoring or deletion.

---

Example

• Method: POST

Endpoint

 https://api.gpulab.ai/container/deploy 

Headers

Header	Description	Type
api-key	Your API Key for request authorization.	string

Request Body Attributes

Parameter	Description	Type
model_id	ID of the model to deploy.	int
gpu_count	Number of GPUs to allocate for the container.	int
gpu_type	Type of GPU to deploy (e.g., NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce GT 710, NVIDIA GeForce RTX 4090, etc.).	str
volume_container_identifier	Optional. Identifier for the volume container, if applicable.	Optional[str]
environment_variables	Optional. Dictionary of environment variables to pass to the container.	Optional[Dict[str, str]]
server_name	Optional. Custom name for the server. If not provided, a default name will be generated.	Optional[str]

Request

Body (JSON)

{
    "model_id": 2,
    "gpu_count": 2,
    "gpu_type": "NVIDIA GeForce RTX 3090 Ti",
    "volume_container_identifier": "12345",
    "server_name": "737d0da16915489",
    "environment_variables": {
        "DEBUG": "true",
        "API_KEY": "your-api-key",
        "SERVER_URL": "https://example.com"
    }
}

Response (Success)

{
    "status": "success",
    "message": "Container Deploy Process Started in the background",
    "container_id": null
}

Note: The actual container ID will be provided in a subsequent response once the deployment completes successfully.

Response (Error)

{
    "status": "error",
    "message": "Error message details"
}