Get Gpu Availability

Authorizations

Authorization

string

headerrequired

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

Query Parameters

regions

enum<string>[] | null

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

gpu_type

enum<string> | null

GPU model

Available options:

CPU_NODE,

A10_24GB,

A100_80GB,

A100_40GB,

A30_24GB,

A40_48GB,

RTX3070_8GB,

RTX3080_10GB,

RTX3080Ti_12GB,

RTX3090_24GB,

RTX3090Ti_24GB,

RTX4070Ti_12GB,

RTX4080_16GB,

RTX4080Ti_16GB,

RTX4090_24GB,

H100_80GB,

H200_96GB,

H200_141GB,

GH200_480GB,

GH200_624GB,

L4_24GB,

L40_48GB,

L40S_48GB,

RTX4000_8GB,

RTX5000_16GB,

RTX6000_24GB,

RTX8000_48GB,

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

socket

enum<string> | null

Socket for selected gpu model

Available options:

PCIe,

SXM2,

SXM3,

SXM4,

SXM5

security

enum<string> | null

Security type

Available options:

secure_cloud,

community_cloud

Response

200 - application/json

{GPUType}

object[]

{GPUType}.cloudId

string

required

Cloud ID, used for provisioning

{GPUType}.gpuType

enum<string>

required

GPU model

Available options:

CPU_NODE,

A10_24GB,

A100_80GB,

A100_40GB,

A30_24GB,

A40_48GB,

RTX3070_8GB,

RTX3080_10GB,

RTX3080Ti_12GB,

RTX3090_24GB,

RTX3090Ti_24GB,

RTX4070Ti_12GB,

RTX4080_16GB,

RTX4080Ti_16GB,

RTX4090_24GB,

H100_80GB,

H200_96GB,

H200_141GB,

GH200_480GB,

GH200_624GB,

L4_24GB,

L40_48GB,

L40S_48GB,

RTX4000_8GB,

RTX5000_16GB,

RTX6000_24GB,

RTX8000_48GB,

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

{GPUType}.socket

enum<string>

required

GPU socket

Available options:

PCIe,

SXM2,

SXM3,

SXM4,

SXM5

{GPUType}.provider

enum<string>

required

Provider's ID

Available options:

runpod,

fluidstack,

lambdalabs,

hyperstack,

oblivus,

cudocompute,

scaleway,

tensordock,

datacrunch,

latitude,

crusoecloud,

massedcompute,

akash,

primeintellect,

primecompute,

dc_impala,

dc_kudu,

dc_roan

{GPUType}.dataCenter

string | null

Location of the data center housing the GPU.

{GPUType}.country

string | null

Country where the data center is located.

{GPUType}.gpuCount

integer

required

Total number of GPUs available in this configuration.

{GPUType}.gpuMemory

integer

required

Amount of memory available per GPU in GB.

{GPUType}.disk

object

Disk capacity in GB.

{GPUType}.vcpu

object

Number of virtual CPUs allocated.

{GPUType}.memory

object

RAM size available in GB.

{GPUType}.internetSpeed

integer | null

Internet speed available in Mbps.

{GPUType}.interconnect

integer | null

Interconnect speed between GPUs or nodes in Gbps.

{GPUType}.interconnectType

string | null

Type of interconnect technology (e.g. Infiniband).

{GPUType}.provisioningTime

integer | null

Estimated time in minutes required for GPU provisioning.

{GPUType}.stockStatus

enum<string>

default: Available

Current stock availability status of GPUs.

Available options:

Available,

Low,

Medium,

High,

Unavailable

{GPUType}.security

enum<string>

required

GPU is either from community cloud or secure cloud

Available options:

secure_cloud,

community_cloud

{GPUType}.prices

object

required

Hourly pricing details.

{GPUType}.images

enum<string>[]

required

List of available images for this GPU.

Available options:

ubuntu_22_cuda_12,

cuda_12_1_pytorch_2_2,

cuda_11_8_pytorch_2_1,

cuda_12_1_pytorch_2_3,

cuda_12_1_pytorch_2_4,

cuda_12_4_pytorch_2_4,

stable_diffusion,

axolotl,

bittensor,

hivemind,

petals_llama,

vllm_llama_8b,

vllm_llama_70b,

vllm_llama_405b,

custom_template,

flux

{GPUType}.isSpot

boolean | null

Indicates if the GPU can be provisioned on a spot pricing model.

{GPUType}.prepaidTime

number | null

If set, you will be pre-charged for the total number of hours specified in this field at the time of ordering, regardless of actual usage. After the prepaid time expires, the standard hourly rate will apply.

API Documentation

Availability

Pods

Authorizations

Query Parameters

Response