Get inference deployment

Authorizations

Authorization · string · header · required

API key for authentication. Make sure to include the word apikey, followed by a single space and then your token. Example: apikey 1234$abcdef

Path Parameters

project_id · integer · required

Project ID

Examples:

1

deployment_name · string · required

Inference instance name.

Required string length: 4 - 30

Examples:

"my-instance"

Response

200 - application/json

OK

address · string<uri> | null · required

Address of the inference instance

Minimum length: 1

Examples:

"https://example.com"

auth_enabled · boolean · required

true if instance uses API key authentication. "Authorization": "Bearer ****\*" or "X-Api-Key": "****\*" header is required for the requests to the instance if enabled.

Examples:

false

command · string | null · required

Command to be executed when running a container from an image.

Examples:

["nginx", "-g", "daemon off;"]

containers · ContainerOutSerializerV3 · object[] · required

List of containers for the inference instance

Show child attributes

Examples:

[
  {
    "deploy_status": { "ready": 1, "total": 3 },
    "region_id": 1,
    "scale": {
      "cooldown_period": 60,
      "max": 3,
      "min": 1,
      "triggers": {
        "cpu": { "threshold": 80 },
        "memory": { "threshold": 70 }
      }
    }
  }
]

created_at · string | null · required

Inference instance creation date in ISO 8601 format.

Examples:

"2023-08-22T11:21:00Z"

credentials_name · string · required

Registry credentials name

Examples:

"dockerhub"

description · string · required

Inference instance description.

Examples:

"My first instance"

envs · object | null · required

Environment variables for the inference instance

Show child attributes

Examples:

{ "DEBUG_MODE": "False", "KEY": "12345" }

flavor_name · string · required

Flavor name for the inference instance

Examples:

"inference-16vcpu-232gib-1xh100-80gb"

image · string · required

Docker image for the inference instance. This field should contain the image name and tag in the format 'name:tag', e.g., 'nginx:latest'. It defaults to Docker Hub as the image registry, but any accessible Docker image URL can be specified.

Examples:

"nginx:latest"

ingress_opts · object | null · required

Ingress options for the inference instance

Show child attributes

Examples:

{ "disable_response_buffering": true }

listening_port · integer · required

Listening port for the inference instance.

Examples:

8080

logging · object | null · required

Logging configuration for the inference instance

Show child attributes

Examples:

{
  "destination_region_id": 1,
  "enabled": true,
  "retention_policy": { "period": 45 },
  "topic_name": "my-log-name"
}

name · string · required

Inference instance name.

Examples:

"my-instance"

probes · object | null · required

Probes configured for all containers of the inference instance.

Show child attributes

project_id · integer · required

Project ID. If not provided, your default project ID will be used.

Examples:

1

status · enum<string> · required

Inference instance status. Value can be one of the following:

• DEPLOYING - The instance is being deployed. Containers are not yet created.
• PARTIALLYDEPLOYED - All containers have been created, but some may not be ready yet. Instances stuck in this state typically indicate either image being pulled, or a failure of some kind. In the latter case, the error_message field of the respective container object in the containers collection explains the failure reason.
• ACTIVE - The instance is running and ready to accept requests.
• DISABLED - The instance is disabled and not accepting any requests.
• PENDING - The instance is running but scaled to zero. It will be automatically scaled up when a request is made.
• DELETING - The instance is being deleted.

Available options:

ACTIVE,

DELETING,

DEPLOYING,

DISABLED,

PARTIALLYDEPLOYED,

PENDING

timeout · integer | null · required

Specifies the duration in seconds without any requests after which the containers will be downscaled to their minimum scale value as defined by scale.min. If set, this helps in optimizing resource usage by reducing the number of container instances during periods of inactivity.

Required range: x >= 0

Examples:

120