GPU Cloud instances

The following endpoints allow to create and manage GPU Cloud instances from the API.

Get the list of available offers

Use this endpoint when you want to explore the different GPU instance options available for your project. This is particularly useful when planning new deployments and needing to compare offers to find the best fit in terms of cost and performance.

Double-check all inputs in the request body to ensure successful creation.

GET/gpu-cloud/instances/offers

Query parameters

Header parameters

Response

200403404

Returns the list of available offers for instances

Body

application/json

id*string

Example: "A6000x8"

cloudProvider*CloudProviderResponse (object)

configuration*ConfigurationInstanceResponse (object)

hourlyPrice*number

Example: 100

availability*array of AvailabilityResponse (object)

bootTimeBootTimeResponse (object)

Request

JavaScriptCurlPython

const response = await fetch('/gpu-cloud/instances/offers', {
    method: 'GET',
    headers: {
      "x-api-key": "text"
    },
});
const data = await response.json();

Response

200403404

[
  {
    "id": "A6000x8",
    "cloudProvider": {
      "_id": "668f9d8df664e3c028ce5de9",
      "displayName": "SESTERCE_IMW"
    },
    "configuration": {
      "memoryInGb": 100,
      "storageInGb": 1000,
      "vcpus": 100,
      "numGpus": 10,
      "gpuType": "A6000",
      "interconnect": "pcie",
      "vramPerGpuInGb": 100,
      "osOptions": "ubuntu22.04_cuda12.2_shade_os"
    },
    "hourlyPrice": 100,
    "availability": [
      {
        "region": "us-central-2",
        "displayName": "US, Central",
        "available": true
      }
    ],
    "bootTime": {
      "minBootInSec": 300,
      "maxBootInSec": 600
    }
  }
]

Create a GPU Cloud instance

Use this endpoint when you're ready to launch a new GPU instance for a specific project or task. This is the crucial step to deploy new computing resources.

You can use query parameters to fine-tune search results and find the best offer for your specific needs

POST/gpu-cloud/instances

Header parameters

Body

application/json

name*string

cloudProvider*string

Example: "cloudProviderId"

instanceOffer*string

Example: "instanceOfferId"

region*string

Example: "regionId"

vmVirtualMachineDto (object)

dockerContainerDockerContainerDto (object)

sshKeystring

Response

201403404

Return the created instance

Body

application/json

_id*string

Example: "668f9d8df664e3c028ce5de9"

user*string

Example: "668f9d8df664e3c028ce5de9"

name*string

Example: "my-machine-name"

region*string

Example: "us-central-2"

volumes*array of array

isPending*boolean

Example: true

createdAt*string

Example: "2023-08-08T12:34:56.789Z"

updatedAt*string

Example: "2023-08-08T12:34:56.789Z"

Request

JavaScriptCurlPython

const response = await fetch('/gpu-cloud/instances', {
    method: 'POST',
    headers: {
      "x-api-key": "text",
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "name": "my-machine-name",
      "cloudProvider": "670fe43738c181c96d19091e",
      "instanceOffer": "670fe43738c181c96d19091e",
      "region": "MON1",
      "vm": {
        "os": "ubuntu22.04_cuda12.2_shade_os",
        "base64StartupScript": "IyEvYmluL2Jhc2gKCiMgRW5kbGVzcyBsb29wCndoaWxlIHRydWUKZG8KICAgICMgRmV0Y2ggYSBjYXQgZmFjdCB3aXRoIG...",
        "volumes": [
          "670fe43738c181c96d19091e",
          "670fe43738c181c96d19091f"
        ]
      },
      "sshKey": "670fe43738c181c96d19091e"
    }),
});
const data = await response.json();

Response

201403404

{
  "_id": "668f9d8df664e3c028ce5de9",
  "user": "668f9d8df664e3c028ce5de9",
  "name": "my-machine-name",
  "region": "us-central-2",
  "volumes": [
    "668f9d8df664e3c028ce5de9"
  ],
  "isPending": true,
  "createdAt": "2023-08-08T12:34:56.789Z",
  "updatedAt": "2023-08-08T12:34:56.789Z"
}

Get the list of instances created

This endpoint is essential for users who want an overview of all the instances they have created. It is ideal for managing and monitoring current resources.

Ensure your API key is active and correctly entered to view your instances.

GET/gpu-cloud/instances

Header parameters

Response

200403404

Returns the list of user instances

Body

application/json

_id*string

Example: "668f9d8df664e3c028ce5de9"

user*string

Example: "668f9d8df664e3c028ce5de9"

name*string

Example: "my-machine-name"

region*string

Example: "us-central-2"

volumes*array of array

isPending*boolean

Example: true

createdAt*string

Example: "2023-08-08T12:34:56.789Z"

updatedAt*string

Example: "2023-08-08T12:34:56.789Z"

Request

JavaScriptCurlPython

const response = await fetch('/gpu-cloud/instances', {
    method: 'GET',
    headers: {
      "x-api-key": "text"
    },
});
const data = await response.json();

Response

200403404

[
  {
    "_id": "668f9d8df664e3c028ce5de9",
    "user": "668f9d8df664e3c028ce5de9",
    "name": "my-machine-name",
    "region": "us-central-2",
    "volumes": [
      "668f9d8df664e3c028ce5de9"
    ],
    "isPending": true,
    "createdAt": "2023-08-08T12:34:56.789Z",
    "updatedAt": "2023-08-08T12:34:56.789Z"
  }
]

Get details about a GPU Cloud instance created

This endpoint is useful when you need to check the details and status of a specific instance, for example, for troubleshooting or configuration verification.

Use the instance ID from your list to quickly retrieve detailed information.

GET/gpu-cloud/instances/{id}

Path parameters

id*string

Header parameters

Response

200403404

Return the instance's details

Body

application/json

_id*string

Example: "668f9d8df664e3c028ce5de9"

user*string

Example: "668f9d8df664e3c028ce5de9"

name*string

Example: "my-machine-name"

region*string

Example: "us-central-2"

volumes*array of array

configuration*ConfigurationInstanceDetailsResponse (object)

ip*string

Example: "127.0.0.1"

sshKey*SSHKeyResponse (object)

sshUser*string

Example: "sesterce"

sshPort*number

Example: 22

status*enum

pendingactivedeleted

costEstimate*string

Example: "0"

hourlyPrice*number

Example: 10

createdAt*string

Example: "2024-11-15T12:40:44.023Z"

updatedAt*string

Example: "2024-11-15T12:40:44.051Z"

Request

JavaScriptCurlPython

const response = await fetch('/gpu-cloud/instances/{id}', {
    method: 'GET',
    headers: {
      "x-api-key": "text"
    },
});
const data = await response.json();

Response

200403404

{
  "_id": "668f9d8df664e3c028ce5de9",
  "user": "668f9d8df664e3c028ce5de9",
  "name": "my-machine-name",
  "region": "us-central-2",
  "volumes": [
    "668f9d8df664e3c028ce5de9"
  ],
  "configuration": {
    "memoryInGb": 10,
    "storageInGb": 10,
    "vcpus": 10,
    "numGpus": 10,
    "gpuType": "A6000",
    "interconnect": "pcie",
    "nvlink": false,
    "os": "ubuntu22.04_cuda12.2_shade_os",
    "vramPerGpuInGb": 10
  },
  "ip": "127.0.0.1",
  "sshKey": {
    "_id": "668f9d8df664e3c028ce5de9",
    "user": "668f9d8df664e3c028ce5de9",
    "name": "ssh-key-name",
    "publicKey": "ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABgQDHRbO3HkzPmp65PR...fAn7Jlb8b61BFh6k= cloud@sesterce",
    "isDefault": false,
    "createdAt": "2024-10-16T16:05:11.439Z",
    "updatedAt": "2024-11-15T12:46:12.327Z"
  },
  "sshUser": "sesterce",
  "sshPort": 22,
  "status": "pending",
  "costEstimate": "0",
  "hourlyPrice": 10,
  "createdAt": "2024-11-15T12:40:44.023Z",
  "updatedAt": "2024-11-15T12:40:44.051Z"
}

Delete a GPU Cloud instance

If needed, ensure data backup before deleting instances to prevent data loss. Discover how to create persistent storage through the following endpoint.

Use this endpoint when you want to free up resources by deleting an instance that is no longer needed, optimizing your resource usage and costs.

DELETE/gpu-cloud/instances/{id}

Path parameters

id*string

Header parameters

Response

204403404

Instance deleted successfully

Request

JavaScriptCurlPython

const response = await fetch('/gpu-cloud/instances/{id}', {
    method: 'DELETE',
    headers: {
      "x-api-key": "text"
    },
});
const data = await response.json();

Response

403404

{
  "statusCode": 403,
  "timestamp": "2023-08-08T12:34:56.789Z",
  "path": "/gpu-cloud/instances/:id",
  "message": "API key invalid"
}