Launch GPU instance

Launches a new GPU compute instance with automatic SSH key generation. Supports mounting Case.dev Vaults as filesystems and configurable auto-shutdown. Instance boots in ~2-5 minutes. Perfect for batch OCR processing, AI model training, and intensive document analysis workloads.

POST /compute/v1/instances

Launch GPU instance

cURL

curl --request POST \
  --url https://api.case.dev/compute/v1/instances \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "ocr-batch-job",
  "instanceType": "gpu_1x_a10",
  "region": "us-west-1",
  "autoShutdownMinutes": 120,
  "vaultIds": [
    "vault_abc123"
  ]
}
'

201

{
  "id": "<string>",
  "name": "<string>",
  "status": "<string>",
  "instanceType": "<string>",
  "region": "<string>",
  "pricePerHour": "<string>",
  "gpu": "<string>",
  "specs": {},
  "autoShutdownMinutes": 123,
  "vaults": "<array>",
  "createdAt": "<string>",
  "message": "<string>"
}

Authorizations

Authorization · string · header · required

API key starting with sk_case_

Body

application/json

name · string · required

Instance name

instanceType · string · required

GPU type (e.g., 'gpu_1x_h100_sxm5')

region · string · required

Region (e.g., 'us-west-1')

autoShutdownMinutes · integer | null

Auto-shutdown timer (null = never)

vaultIds · string[]

Vault IDs to mount

Response

201

application/json

Instance launching

id · string

name · string

status · string

instanceType · string

region · string

pricePerHour · string

gpu · string

specs · object

autoShutdownMinutes · integer | null

vaults · array

createdAt · string

message · string