Skip to main content
GET
/
api
/
v1
/
availability
/
gpus
Get Gpu Availability
curl --request GET \
  --url https://api.primeintellect.ai/api/v1/availability/gpus \
  --header 'Authorization: Bearer <token>'
{
  "items": [
    {
      "cloudId": "<string>",
      "gpuType": "CPU_NODE",
      "socket": "PCIe",
      "provider": "runpod",
      "gpuCount": 123,
      "gpuMemory": 123,
      "security": "secure_cloud",
      "prices": {
        "currency": "USD",
        "onDemand": 1.15,
        "communityPrice": null,
        "isVariable": false
      },
      "images": [
        "ubuntu_22_cuda_12"
      ],
      "region": "africa",
      "dataCenter": "<string>",
      "country": "<string>",
      "disk": {},
      "sharedDisk": {},
      "vcpu": {},
      "memory": {},
      "internetSpeed": 123,
      "interconnect": 123,
      "interconnectType": "<string>",
      "provisioningTime": 123,
      "stockStatus": "Available",
      "isSpot": true,
      "prepaidTime": 123
    }
  ],
  "totalCount": 123
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

​
page
integer
default:1

Page number (1-indexed) Page number (1-indexed)

Required range: x >= 1
​
page_size
integer
default:100

Number of results per page Number of results per page

Required range: 1 <= x <= 100
​
regions
enum<string>[] | null

List of regions to filter List of regions to filter

Available options:
africa,
asia_south,
asia_northeast,
australia,
canada,
eu_east,
eu_north,
eu_west,
middle_east,
south_america,
united_states
​
gpu_count
integer | null

Desired number of GPUs Desired number of GPUs

​
gpu_type
enum<string> | null

GPU model GPU model

Available options:
CPU_NODE,
A10_24GB,
A100_80GB,
A100_40GB,
A30_24GB,
A40_48GB,
B200_180GB,
B300_262GB,
RTX3070_8GB,
RTX3070_8GB,
RTX3080_10GB,
RTX3080Ti_12GB,
RTX3090_24GB,
RTX3090Ti_24GB,
RTX4070Ti_12GB,
RTX4080_16GB,
RTX4080Ti_16GB,
RTX4090_24GB,
RTX5090_32GB,
H100_80GB,
H200_96GB,
GH200_96GB,
H200_141GB,
GH200_480GB,
GH200_624GB,
L4_24GB,
L40_48GB,
L40S_48GB,
RTX4000_8GB,
RTX5000_16GB,
RTX6000_24GB,
RTX8000_48GB,
RTX2000Ada_16GB,
RTX4000Ada_20GB,
RTX5000Ada_32GB,
RTX6000Ada_48GB,
A2000_6GB,
A4000_16GB,
A4500_20GB,
A5000_24GB,
A6000_48GB,
V100_16GB,
V100_32GB,
P100_16GB,
T4_16GB,
P4_8GB,
P40_24GB,
RTX_PRO_6000B_96GB
​
socket
enum<string> | null

Socket for selected gpu model Socket for selected gpu model

Available options:
PCIe,
SXM2,
SXM3,
SXM4,
SXM5,
SXM6
​
security
enum<string> | null

Security type Security type

Available options:
secure_cloud,
community_cloud
​
data_center_id
string | null

Filter by data center ID Filter by data center ID

​
cloud_id
string | null

Filter by cloud ID Filter by cloud ID

​
disks
string[] | null

List of disk IDs to filter instances by location List of disk IDs to filter instances by location

Response

Successful Response

​
items
GpuAvailability · object[]
required

List of available GPU configurations

​
totalCount
integer
required

Total number of matching GPU configurations