SHARON AI API

High‑performance GPU rack in Sharon AI data center

Share this

Introduction

The SHARON AI Client API allows users to interact with the SHARON AI platform, providing functionalities such as retrieving product lists, managing services, and creating virtual machines and containers.

Base URL

All API requests should be made to:

https://billing.sharonai.com/api

 

Authentication

This API requires authentication via an API key, which should be included in the request headers:

x-api-key: {your_api_key}

An API Token can be created by creating an account at SHARON AI Billing.

API Endpoints

1. List Products

Method: POST

Request Body:

{
  "action": "ListProducts"
}


Response Example:

{
  "success": true,
  "products": [
    {
      "id": 44,
      "name": "OD-LIN-H100-SSD-GPU-VM-1",
      "description": "1x NVIDIA H100 NVL GPU | 14 vCores | 90GB of RAM | 1 Public IP Address | 5TB Monthly Data Transfer",
      "pricing": [
        {
          "type": "hourly",
          "price": "$1.9500000000 / H"
        },
        {
          "type": "disk_size",
          "price": "$0.0000000821 / GB/hr"
        }
      ]
    },
    {
      "id": 55,
      "name": "GPU Container",
      "description": "NVIDIA H100 NVL or NVIDIA L40s GPUs",
      "pricing": [
        {
          "type": "l40s_hourly",
          "price": "$0.8500000000 / H"
        },
        {
          "type": "h100_hourly",
          "price": "$1.9500000000 / H"
        }
      ]
    },
    {
      "id": 56,
      "name": "S3 Bucket",
      "description": "",
      "pricing": [
        {
          "type": "disk_hourly",
          "price": "$0.0000109000 / GB/h"
        }
      ]
    }
  ]
}

2. List VM Templates

Method: POST

Request Body:

{
  "action": "ListVmTemplates",
  "productid": 2
}


Response Example:

{
  "success": true,
  "templates": [
    {
      "id": 121,
      "template": "Ubuntu 18.04 LTS"
    },
    {
      "id": 122,
      "template": "Ubuntu 20.04 LTS"
    },
    {
      "id": 123,
      "template": "Ubuntu 22.04 LTS"
    },
    {
      "id": 124,
      "template": "Ubuntu 24.04 LTS"
    },
    {
      "id": 186,
      "template": "Ubuntu 24.10"
    }
  ]
}

3. List VM Applications

Method: POST

Request Body:

{
  "action": "ListVmApplications",
  "productid": 2
}


Response Example:

{
  "success": true,
  "applications": [
    {
      "id": 176,
      "template": "No Pre Installed Application"
    },
    {
      "id": 178,
      "template": "DeepSeek-R1"
    },
    {
      "id": 182,
      "template": "JupyterHub PyTorch"
    },
    {
      "id": 183,
      "template": "Docker, Portainer, NVIDIA Container Toolkit"
    },
    {
      "id": 188,
      "template": "Ollama Integrations"
    }
  ]
}

4. Get Service Details

Method: POST

Request Body:

{
  "action": "GetService",
  "serviceid": 133
}


Response Example:

{
  "success": true,
  "service": {
    "id": 133,
    "domain": "SAIVM133",
    "name": "OD-LIN-SSD-CPU-VM-4",
    "domainstatus": "Active",
    "dedicatedip": "192.168.1.1",
    "username": "ubuntu",
    "password": "XXXXXXXXXXXX"
  }
}

5. List Services

Method: POST

Request Body:

{
  "action": "ListServices"
}


Response Example:

{
  "success": true,
  "services": [
    {
      "id": 90,
      "name": "",
      "product": "S3 Bucket",
      "status": "Active"
    },
    {
      "id": 133,
      "name": "SAIVM133",
      "product": "OD-LIN-SSD-CPU-VM-4",
      "status": "Active"
    }
  ]
}

6. Create Container

Method: POST

Request Body:

{
  "action": "CreateContainer",
  "productid": 55,
  "image": "nginx:latest",
  "gputype": "L40s",
  "gpucount": 1,
  "ports": [
    80,
    443
  ],
  "environment": [
    "APP_NAME=app1",
    "APP_PORT=80"
  ]
}


Response Example:

{
  "success": true,
  "message": "Successfully created service"
}

7. Create Virtual Machine

Method: POST

Request Body:

{
  "action": "CreateVM",
  "productid": 7,
  "templateid": 122,
  "applicationid": 176,
  "disksize": 32,
  "sshkey": "ssh-rsa AAAAB3..."
}

NB: applicationid and sshkey are optional.


Response Example:

{
  "success": true,
  "message": "Successfully created ServiceID 130"
}

8. Delete Service

NB: executing this endpoint against an active service will immediately terminate the instance, causing all data held within this service to be lost.

Method: POST

Request Body:

{
  "action": "DeleteService",
  "serviceid": 131
}


Response Example:

{
  "success": true
}

 

9. Start Service

Method: POST

Request Body:

{
    "action": "StartService",
    "serviceid": 133
}


Response Example:

{
  "success": true
}

10. Stop Service

Method: POST

Request Body:

{
    "action": "StopService",
    "serviceid": 133
}


Response Example:

{
  "success": true
}

NB: Stopped services will still incur charges. if you wish to stop billing for an instance, request a cancelation or delete the service via the API.


Related Articles

News & Updates

Want to learn more?

×
By clicking the "submit" button, you agree to and accept our Terms & Conditions and Privacy Policy .
×
By clicking the "submit" button, you agree to and accept our Terms & Conditions and Privacy Policy .
×
By clicking the "submit" button, you agree to and accept our Terms & Conditions and Privacy Policy .
×
By clicking the "submit" button, you agree to and accept our Terms & Conditions and Privacy Policy .
Calculator Icon

Pricing Calculator

GPU Cost in Seconds

Loading...
-
/ hourly cost

Estimate GPU Cloud Costs Instantly

Calculate your GPU cloud computing costs with our interactive pricing tool.

Billing Type

Product Type

GPU Type

Hardware Configuration

Contract Options

No contract discount applied
best value

GPU Plan Estimate

Hourly Cost
Loading...
-
Total cost per month
Loading...
-
Total cost
Loading...
-

Prices shown include all applicable discounts

Total cost per month
Loading...
-
Total cost
Loading...
-