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

Query parameters

regionstringOptional

numGpusstringOptional

gpuTypestringOptional

availablebooleanOptional

sortstring · enumOptionalPossible values:

deploymentTypestring · enumOptionalPossible values:

Header parameters

x-api-keystringRequired

The API Key secret should be sent through this header to authenticate the request.

Responses

200

Returns the list of available offers for instances

application/json

403

API key invalid

application/json

404

Not found

application/json

get

GET /gpu-cloud/instances/offers HTTP/1.1
Host: 
x-api-key: text
Accept: */*

[
  {
    "gpuName": "A6000",
    "gpuCount": 8,
    "nvlink": true,
    "deploymentType": "vm",
    "instanceId": "A6000x8",
    "cloudInitAvailable": true,
    "cloud": {
      "_id": "668f9d8df664e3c028ce5de9",
      "name": "AZ_01"
    },
    "configuration": {
      "ramGB": 100,
      "storageGB": 1000,
      "vCpu": 100,
      "vRamGB": 100,
      "os": [
        "ubuntu22.04_cuda12.2_shade_os"
      ],
      "interconnect": "pcie"
    },
    "hourlyPrice": 10,
    "availability": [
      {
        "region": "us-central-2",
        "name": "US, Central",
        "countryCode": "US",
        "available": true
      }
    ]
  }
]

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

Header parameters

x-api-keystringRequired

The API Key secret should be sent through this header to authenticate the request.

Body

namestringRequiredExample: my-machine-name

cloudProviderstringRequiredExample: 668f9d8df664e3c028ce5de9

instanceIdstringRequiredExample: A6000

volumeIdstringOptionalExample: 668f9d8df664e3c028ce5de9

regionstringRequiredExample: us-east-1

sshKeyIdstringOptionalExample: 668f9d8df664e3c028ce5de9

Responses

201

Return the created instance

application/json

403

API key invalid

application/json

404

Not found

application/json

post

POST /gpu-cloud/instances HTTP/1.1
Host: 
x-api-key: text
Content-Type: application/json
Accept: */*
Content-Length: 409

{
  "name": "my-machine-name",
  "cloudProvider": "668f9d8df664e3c028ce5de9",
  "instanceId": "A6000",
  "volumeId": "668f9d8df664e3c028ce5de9",
  "region": "us-east-1",
  "vm": {
    "os": "ubuntu22.04_cuda12.2_shade_os",
    "base64CloudInitScript": "IyEvYmluL2Jhc2gKCiMgRW5kbGVzcyBsb29wCndoaWxlIHRydWUKZG8KICAgICMgRmV0Y2ggYSBjYXQgZmFjdCB3aXRoIG..."
  },
  "dockerContainer": {
    "image": "vllm/vllm-openai:latest"
  },
  "sshKeyId": "668f9d8df664e3c028ce5de9"
}

{
  "_id": "668f9d8df664e3c028ce5de9",
  "name": "my-machine-name",
  "provider": "AZ_01",
  "region": {
    "name": "USA-Central-1",
    "countryCode": "US"
  },
  "volumes": [
    "668f9d8df664e3c028ce5de9"
  ],
  "status": "active",
  "gpuCount": 1,
  "gpuModel": "A100",
  "ram": 100,
  "storage": 100,
  "vramPerGpu": 100,
  "vcpus": 1,
  "interconnect": "VM",
  "nvlink": true,
  "os": "Ubuntu 20.04",
  "ip": "192.168.1.1",
  "sshUser": "sesterce",
  "sshPort": 22,
  "dockerImage": "ubuntu/20.04",
  "dockerCommand": "docker run -it ubuntu/20.04",
  "hourlyPrice": 100,
  "deletedAt": "2021-01-01T00:00:00.000Z",
  "createdAt": "2021-01-01T00:00:00.000Z",
  "updatedAt": "2021-01-01T00:00:00.000Z"
}

Make sure you filled the right OS name, such as ubuntu24.04_cuda12.4_shade_os. You can retrieve the os available with the /gpu-cloud/instances/offers endpoint.

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

Query parameters

deploymentTypestring · enumOptionalPossible values:

Header parameters

x-api-keystringRequired

The API Key secret should be sent through this header to authenticate the request.

Responses

200

Returns the list of user instances

application/json

403

API key invalid

application/json

404

API key not found

application/json

get

GET /gpu-cloud/instances HTTP/1.1
Host: 
x-api-key: text
Accept: */*

[
  {
    "_id": "668f9d8df664e3c028ce5de9",
    "name": "my-machine-name",
    "provider": "AZ_01",
    "region": {
      "name": "USA-Central-1",
      "countryCode": "US"
    },
    "volumes": [
      "668f9d8df664e3c028ce5de9"
    ],
    "status": "active",
    "gpuCount": 1,
    "gpuModel": "A100",
    "ram": 100,
    "storage": 100,
    "vramPerGpu": 100,
    "vcpus": 1,
    "interconnect": "VM",
    "nvlink": true,
    "os": "Ubuntu 20.04",
    "ip": "192.168.1.1",
    "sshUser": "sesterce",
    "sshPort": 22,
    "dockerImage": "ubuntu/20.04",
    "dockerCommand": "docker run -it ubuntu/20.04",
    "hourlyPrice": 100,
    "deletedAt": "2021-01-01T00:00:00.000Z",
    "createdAt": "2021-01-01T00:00:00.000Z",
    "updatedAt": "2021-01-01T00:00:00.000Z"
  }
]

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

Path parameters

idstringRequired

Header parameters

x-api-keystringRequired

The API Key secret should be sent through this header to authenticate the request.

Responses

200

Return the instance's details

application/json

403

API key invalid

application/json

404

Not found

application/json

get

GET /gpu-cloud/instances/{id} HTTP/1.1
Host: 
x-api-key: text
Accept: */*

{
  "_id": "668f9d8df664e3c028ce5de9",
  "name": "my-machine-name",
  "provider": "AZ_01",
  "status": "active",
  "region": {
    "name": "USA-Central-1",
    "countryCode": "US",
    "id": "us-central-1"
  },
  "volumes": [
    "668f9d8df664e3c028ce5de9"
  ],
  "sshKey": {
    "_id": "668f9d8df664e3c028ce5de9",
    "name": "my-ssh-key",
    "publicKey": "ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDA",
    "createdAt": "2021-01-01T00:00:00.000Z",
    "updatedAt": "2021-01-01T00:00:00.000Z"
  },
  "createdAt": "2021-01-01T00:00:00.000Z",
  "deletedAt": "2021-01-01T00:00:00.000Z",
  "isPending": true,
  "hourlyPrice": 0.15,
  "ip": "127.0.0.1",
  "sshUser": "sesterce",
  "sshPort": 22,
  "portForwards": [
    {
      "internalPort": 80,
      "externalPort": 8080
    }
  ],
  "gpuCount": 1,
  "gpuModel": "A100",
  "ram": 100,
  "storage": 100,
  "vramPerGpu": 100,
  "vcpus": 1,
  "interconnect": "pcie",
  "nvlink": true,
  "os": "ubuntu24.04",
  "dockerImage": "ubuntu/20.04",
  "dockerCommand": "docker run -it ubuntu/20.04"
}

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

Path parameters

idstringRequired

Header parameters

x-api-keystringRequired

The API Key secret should be sent through this header to authenticate the request.

Responses

204

Instance deleted successfully

403

API key invalid

application/json

404

Not found

application/json

delete

DELETE /gpu-cloud/instances/{id} HTTP/1.1
Host: 
x-api-key: text
Accept: */*

No content

PreviousAuthentication NextSSH Keys

Last updated 9 days ago

Was this helpful?