Inference Logoinference.sh
gpus/h100

nvidia h100

Hopper · 80gb vram · 267.6 fp16 tflops

from

$1.66/hr

~$1195/mo · latitude

specifications

fp16 tflops

267.6

fp32 tflops

66.91

vram

80gb

bandwidth

3350 gb/s

tensor cores

528

tdp

700w

process

4nm

architecture

Hopper

1x gpu pricing

provider$/hr
latitude
$1.66
hyperstack
$1.90
latitude
$1.99
voltagepark
$1.99
verda
$2.36
imwt
$2.48
massedcompute
$2.98
nebius
$3.06
scaleway
$3.30
digitalocean
$3.34
lambdalabs
$4.29
lambdalabs
$4.36
paperspace
$5.99

multi-gpu pricing

providergpus$/hr
hyperstack
2x$3.80
voltagepark
2x$3.98
imwt
2x$4.96
massedcompute
2x$5.96
scaleway
2x$6.60
hyperstack
4x$7.60
voltagepark
4x$7.96
lambdalabs
2x$8.38
latitude
4x$8.97
imwt
4x$9.92
massedcompute
4x$11.92
latitude
8x$14.34
hyperstack
8x$15.20
hyperstack
8x$15.60
horizon
8x$15.60
voltagepark
8x$15.92
voltagepark
8x$15.92
lambdalabs
4x$16.36
denvr
8x$18.80
hyperstack
8x$19.20
imwt
8x$19.84
massedcompute
8x$22.00
massedcompute
8x$23.92
digitalocean
8x$23.92
nebius
8x$23.99
lambdalabs
8x$31.92

rent nvidia h100 now

from $1.66/hr. spin up in minutes.

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.