Create Instance

POSThttps://api.oneinfer.ai/v1/developer/:developerId/create-instance

Provision a new GPU instance on a specific provider with custom resources and a docker image.

Request body

provider_namestringrequired
Name of the provider (e.g., 'novita', 'verda', 'runpod').
instance_namestringrequired
User-defined name for the instance.
gpu_idstringrequired
Identifier for the requested GPU type.
gpu_numnumberrequired
Quantity of GPUs to provision.
disk_sizenumberrequired
Size of the root disk in GB.
image_urlstringrequired
Docker image URL to deploy.
regionstringrequired
Region identifier (e.g., 'us-east', 'eu-west').

Example request body

JSON
{
  "provider_name": "novita",
  "instance_name": "my-gpu-instance",
  "gpu_id": "nvidia_a100_80gb",
  "gpu_num": 1,
  "disk_size": 100,
  "image_url": "pytorch/pytorch:latest",
  "region": "us-west-1"
}

Error status codes

CodeStatusDescription
200OKInstance provisioned successfully.
400Bad RequestInvalid request body or unsupported provider.
401UnauthorizedMissing or invalid Authorization header / Bearer token.
403ForbiddenInsufficient credit balance or provider validation failed.
422Unprocessable EntityRequest body failed schema validation.
500Internal Server ErrorUnexpected error during instance provisioning.

Response

202 - application/json