GET
/
cloud
/
v2
/
inference
/
flavors
List inference instance flavors
curl --request GET \
  --url https://api.gcore.com/cloud/v2/inference/flavors \
  --header 'Authorization: <api-key>'
{
  "cpu": 1000,
  "description": "My first flavor",
  "gpu_count": 1,
  "gpu_memory": 1024,
  "gpu_model": "L40s",
  "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "name": "flavor1",
  "ram": 2048
}

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

Query Parameters

​
limit
integer

Limit the number of returned events. Defaults to 100. Limited by max limit value of 1000

​
offset
integer

Offset value is used to exclude the first set of records from the result

Response

List of the inference instance flavors

​
cpu
integer
required

Number of CPU millicores.

Examples:

1000

​
description
string
required

Description of the flavor.

Examples:

"My first flavor"

​
id
string<uuid>
required

Flavor ID.

Examples:

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

​
name
string
required

Name of the flavor.

Examples:

"flavor1"

​
ram
integer
required

Amount of RAM in MiB.

Examples:

2048

​
gpu_count
integer
default:0

Number of GPUs.

Examples:

1

​
gpu_memory
integer
default:0

GPU memory in MiB.

Examples:

1024

​
gpu_model
string
default:""

Model of the GPU.

Examples:

"L40s"