Get inference flavor

GET /cloud/v3/inference/flavors/{flavor_name}

Python

Python

import os
from gcore import Gcore

client = Gcore(
    api_key=os.environ.get("GCORE_API_KEY"),  # This is the default and can be omitted
)
inference_flavor = client.cloud.inference.flavors.get(
    "inference-16vcpu-232gib-1xh100-80gb",
)
print(inference_flavor.cpu)

200

{
  "cpu": 2,
  "description": "1xL40S / 16 vCPU / 232GiB RAM",
  "gpu": 1,
  "gpu_compute_capability": "8.6",
  "gpu_memory": 80,
  "gpu_model": "H100",
  "is_gpu_shared": false,
  "memory": 4,
  "name": "inference-16vcpu-232gib-1xh100-80gb"
}

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

flavor_name · string · required

Inference flavor name.

Example:

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

Response

200 - application/json

OK

cpu · number · required

Inference flavor cpu count.

Example:

2

description · string · required

Inference flavor description.

Example:

"1xL40S / 16 vCPU / 232GiB RAM"

gpu · integer · required

Inference flavor gpu count.

Example:

1

gpu_compute_capability · string · required

Inference flavor gpu compute capability.

Example:

"8.6"

gpu_memory · number · required

Inference flavor gpu memory in Gi.

Example:

80

gpu_model · string · required

Inference flavor gpu model.

Example:

"H100"

is_gpu_shared · boolean · required

Inference flavor is gpu shared.

Example:

false

memory · number · required

Inference flavor memory in Gi.

Example:

4

name · string · required

Inference flavor name.

Example:

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