Cheapest Inference
The lowest verified on-demand price for every GPU we track
Prices are collected automatically from providers' public pages and can be outdated or wrong. Confirm with the provider before you buy.
Floor prices · on-demand
The cheapest verified rate for each GPU. Tap one to see every offer on the leaderboard.
RTX A4000
$0.10/hr
TensorDock
RTX 3080 Ti
$0.20/hr
SaladCloud
RTX 3090
$0.20/hr
SaladCloud
T4
$0.20/hr
Theta EdgeCloud
RTX 3090 Ti
$0.22/hr
SaladCloud
RTX 4080
$0.27/hr
SaladCloud
RTX A5000
$0.27/hr
Runpod
RTX 5080
$0.32/hr
SaladCloud
RTX A6000
$0.35/hr
Thunder Compute
A30
$0.35/hr
Massed Compute
V100 32GB
$0.42/hr
TensorDock · SXM
L4
$0.44/hr
Jarvis Labs
RTX 4090
$0.44/hr
SaladCloud
A40
$0.59/hr
Runpod
RTX 5090
$0.60/hr
SaladCloud
L40S
$0.69/hr
CloudRift
RTX 4000 Ada
$0.76/hr
DigitalOcean (Paperspace)
RTX 6000 Ada
$0.79/hr
Massed Compute
L40
$0.79/hr
Thunder Compute
A100 40GB
$0.89/hr
Jarvis Labs
RTX PRO 4500
$0.92/hr
Massed Compute
V100 16GB
$0.99/hr
Theta EdgeCloud
A10
$1.29/hr
Lambda (Lambda Labs)
A100 80GB
$1.35/hr
Hyperstack · SXM
H100
$1.68/hr
Latitude
RTX PRO 6000
$1.80/hr
Nebius
H200
$2.30/hr
Crusoe · SXM
MI300X
$2.59/hr
DigitalOcean (Paperspace)
H100
$2.92/hr
Massed Compute · NVLink
MI325X
$3.80/hr
DigitalOcean (Paperspace)
MI350X
$4.00/hr
CloudRift
B200
$5.43/hr
Massed Compute · SXM
B200
$5.50/hr
Koyeb
MI355X
$5.99/hr
Daytona
B300
$6.25/hr
Daytona
GH200
$6.50/hr
CoreWeave
GB200
$10.50/hr
CoreWeave
GB300
$13.44/hr
Verda (formerly DataCrunch) · SXM