gpu catalog: a30

Rent A30●

A data center inference card with real HBM2 bandwidth at low power, an efficient host for mid-size model serving.

Live platform rates

● 25 GPU types online
GPUVRAMRegionsAvailabilityPrice / GPU
A3024G—out of stock—

A30 is out of stock right now — these are live:

A data center inference card with real HBM2 bandwidth at low power, an efficient host for mid-size model serving.

VRAM24 GB HBM2
Memory bandwidth0.9 TB/s
FP16 tensor165 TFLOPS
ArchitectureAmpere
InterconnectPCIe 4.0
Board power165 W
Released2021
RTX PRO 600096G4 regionshigh availability$2.03/hrlaunch
RTX A600048G2 regionshigh availability$0.54/hrlaunch
RTX 5090community32G6 regionshigh availability$0.52/hrlaunch
RTX 6000 ADA48G1 regionhigh availability$0.78/hrlaunch
L4048G2 regionshigh availability$0.94/hrlaunch
RTX 4090community24G7 regionshigh availability$0.46/hrlaunch
A10080G5 regionshigh availability$1.48/hrlaunch
RTX 3090community24G6 regionshigh availability$0.18/hrlaunch
H100 SXM80G5 regionshigh availability$5.27/hrlaunch
H200 SXMcommunity141G5 regionsavailable$4.31/hrlaunch
L40S48G2 regionsavailable$0.96/hrlaunch
H200 SXM141G4 regionsavailable$6.35/hrlaunch
RTX 5080community16G6 regionsavailable$0.24/hrlaunch
A1616G6 regionsavailable$0.56/hrlaunch
RTX A4000community16G5 regionsavailable$0.10/hrlaunch
RTX 3080community10G4 regionsavailable$0.14/hrlaunch
H200 NVLcommunity141G5 regionsavailable$4.33/hrlaunch
RTX 4080community16G5 regionsrunning low$0.27/hrlaunch
A4048G3 regionsrunning low$0.71/hrlaunch
B200community192G3 regionsrunning low$9.64/hrlaunch
B200192G2 regionsrunning low$9.59/hrlaunch
L40Scommunity48G2 regionsrunning low$0.96/hrlaunch
A40community48G1 regionrunning low$0.72/hrlaunch
H100 NVLcommunity94G2 regionsrunning low$3.11/hrlaunch
RTX A500024G1 regionrunning low$0.32/hrlaunch
L4community24G2 regionsrunning low$0.54/hrlaunch
A100community80G1 regionrunning low$1.14/hrlaunch
RTX 509032G1 regionrunning low$1.67/hrlaunch
H100 NVL94G1 regionrunning low$3.83/hrlaunch
B300288G1 regionrunning low$10.79/hrlaunch
H200 NVL141G1 regionrunning low$3.95/hrlaunch
RTX A6000community48G1 regionrunning low$0.55/hrlaunch
H100 SXMcommunity80G2 regionsrunning low$5.60/hrlaunch
RTX A400016G1 regionrunning low$0.14/hrlaunch
V100community16G1 regionrunning low$0.14/hrlaunch
RTX A5000community24G1 regionrunning low$0.27/hrlaunch
H100 PCIE80G1 regionrunning low$2.98/hrlaunch

lowest live on-demand rate per GPU, refreshed continuously · per-second billing

A30 price history

last 90 days

Our floor price for the A30, sampled continuously across every provider in the fleet and rolled up to one point per day. A dot on the zero line is a day we checked and found nothing launchable; a shaded break is a day we did not sample. Those are different facts, so this chart never draws one as the other.

  • Price ($/GPU-hr)
  • Sold out — 0 available
  • No data collected for this window

Daily trend, updated hourly · Full 15-minute history available via API

Compare and explore

faq

A30 rental questions●

How much does it cost to rent an A30 in the cloud?

A30 capacity is temporarily out of stock on GPU.ai. When available, it's billed per second at the live rate shown here. Check this page again. Stock and prices refresh continuously.

How much VRAM does the A30 have?

The NVIDIA A30 has 24 GB of HBM2 memory with up to 933 GB/s of bandwidth. GPU.ai reports the minimum VRAM actually delivered across our fleet, so the figure you see at launch is the figure you get.

How does GPU.ai's A30 pricing compare to AWS, Azure, and CoreWeave?

GPU.ai aggregates a dozen-plus GPU clouds and routes each launch to the cheapest one with stock, so the same silicon is typically far cheaper than hyperscaler list rates. The comparison table on this page shows the current public on-demand list prices side by side.

How does billing work?

Billing is per second, starting when your instance is SSH-ready and stopping the moment you terminate. There are no minimum commitments, no reservation fees, and no egress surprises: you pay the listed hourly rate pro-rated to the second.