Update Inference Instance

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

instance_id · string · required

Inference Instance ID

Body

application/json

containers · ContainerInSerializer · object[] · required

List of containers for the inference instance.

Minimum length: 1

Show child attributes

Examples:

[
  {
    "region_id": 7,
    "scale": {
      "cooldown_period": 60,
      "max": 3,
      "min": 1,
      "triggers": {
        "cpu": { "threshold": 80 },
        "memory": { "threshold": 70 }
      }
    }
  }
]

flavor_id · string<uuid> · required

Flavor ID for the inference instance.

Examples:

"3fa85f64-5717-4562-b3fc-2c963f66afa6"

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"

listening_port · integer · required

Listening port for the inference instance.

Required range: 1 <= x <= 65535

Examples:

8080

name · string · required

Inference instance name.

Required string length: 4 - 30

Examples:

"my-instance"

api_key_ids · string<uuid>[]

List of API keys IDs to attach to the inference instance

Examples:

["3fa85f64-5717-4562-b3fc-2c963f66afa6"]

auth_enabled · boolean · default: false

Set to true to enable API key authentication for the inference instance. Manage API keys through the '/v1/inference_instances/keys' endpoint.

Examples:

false

command · string[] | null

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

Examples:

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

description · string | null

Inference instance description.

Examples:

"My first instance"

envs · object

Environment variables for the inference instance.

Show child attributes

Examples:

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

image_registry_id · string<uuid> | null

Image registry ID for authentication in private registries. Leave this parameter empty if no authentication is required for the repository.

Examples:

"3fa85f64-5717-4562-b3fc-2c963f66afa6"

probes · object | null

Probes configured for all containers of the inference instance. If probes are not provided, and the image_name is from a the Model Catalog registry, the default probes will be used.

Show child attributes

project_id · integer | null

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

Examples:

1

timeout · integer | null · default: 120

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. The default value when the parameter is not set is 120.

Required range: x >= 0

Examples:

120

Response

200

application/json

Inference instance

containers · ContainerOutSerializer · object[] · required

List of containers for the inference instance

Show child attributes

Examples:

[
  {
    "deploy_status": { "ready": 1, "total": 3 },
    "region_id": 7,
    "scale": {
      "cooldown_period": 60,
      "max": 3,
      "min": 1,
      "triggers": {
        "cpu": { "threshold": 80 },
        "memory": { "threshold": 70 }
      }
    }
  }
]

flavor_id · string<uuid> · required

Flavor ID for the inference instance

Examples:

"3fa85f64-5717-4562-b3fc-2c963f66afa6"

id · string<uuid> · required

Inference instance ID.

Examples:

"3fa85f64-5717-4562-b3fc-2c963f66afa6"

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"

listening_port · integer · required

Listening port for the inference instance.

Examples:

8080

name · string · required

Inference instance name.

Examples:

"my-instance"

status · enum<string> · required

Inference instance status

Available options:

ACTIVE,

DELETED,

DELETING,

DEPLOYING,

DISABLED,

ERROR,

FAILED,

NEW,

PARTIALLYDEPLOYED,

PENDING

address · string<uri> | null

Address of the inference instance

Minimum length: 1

Examples:

"https://example.com"

api_key_ids · string<uuid>[]

List of API keys IDs attached to the inference instance

Examples:

["3fa85f64-5717-4562-b3fc-2c963f66afa6"]

auth_enabled · boolean · default: false

Set to true if instance uses API key authentication. Manage API keys through the '/v1/inference_instances/keys' endpoint.

Examples:

false

command · string[] | null

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

Examples:

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

created_at · string<date-time> | null

Inference instance creation date in ISO 8601 format.

Examples:

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

description · string | null

Inference instance description.

Examples:

"My first instance"

envs · object | null

Environment variables for the inference instance

Show child attributes

Examples:

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

image_registry_id · string<uuid> | null

Image registry ID for authentication in private registries. This parameter is empty if no authentication is required for the repository.

Examples:

"3fa85f64-5717-4562-b3fc-2c963f66afa6"

probes · object | null

Probes configured for all containers of the inference instance.

Show child attributes

timeout · integer | null · default: 120

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