Skip to content
aipowered

Find your next machine.

Try “5090”, “Jetson”, or “DGX”.

NVIDIA A100 (80GB HBM2e)

80GB HBM2e
Memory
2,039GB/s
Memory bandwidth
Q4 2020
Released

Price history

On-demandReservedSpot
USD / GPU / HR
On-demand · latest$1.862026-10-05

What it costs to rent an NVIDIA A100

The NVIDIA A100 is an Ampere-architecture fine-tuning NVIDIA GPU with 80GB of HBM2e memory and 2,039 GB/s of memory bandwidth, released Q4 2020. It is built for large-model training and high-throughput inference.

Renting one currently costs between $0.52 and $6.78 per GPU-hour across the 27 cloud providers we track, with a median of $1.90. The cheapest live rate is $0.52/hr from Google Cloud (Spot), and hosting one pays about $1.13/hr on Akash while it is running. All rates below are normalised to a single GPU per hour so providers with multi-GPU nodes compare like-for-like.

Where to rent the A100

How we rank

The median is one provider, one vote: each provider contributes the median of its own on-demand listings, then the headline is the median across providers — so no single marketplace or hyperscaler sets the price alone. Below two providers we show the range instead.

Default order is relevance, weighed the way a buyer would: price per GPU first, lightly blended with total node cost; on-demand preferred over spot and reserved when prices are close; established clouds edged above marketplaces; in-stock, recently-checked offers above stale ones; and no single provider is allowed to crowd the top. Click a column to sort by the raw numbers. No paid placements — ranking is never sold.

Scroll horizontally to compare all columns →

ProviderTierConfigTotal VRAMBillingAvailabilityGo to provider
Google CloudBestHyperscaler1× A10080GBSpot$0.52$0.52Rent
Vast.aiGPU cloud6× A100 PCIE480GBOn-demand$0.53$3.20Rent
Clore.aiGPU cloud8× A100 PCIE640GBOn-demand$0.56$4.50Rent
Vast.aiGPU cloud8× A100 PCIE640GBOn-demand$0.53$4.27Rent
NosanaGPU cloud1× A10080GBCommunity$0.61$0.61Rent
AzureHyperscaler1× A10080GBSpot$0.68$0.68Rent
Vast.aiGPU cloud1× A100 PCIE80GBOn-demand$0.68$0.68Rent
AzureHyperscaler2× A100160GBSpot$0.68$1.36Rent

Earn by hosting the A100

How this is worked out

“Renters pay” is the median live rate for this GPU on that marketplace — the median, not the floor, because the cheapest listing is one host undercutting everyone. “You earn” is that figure less the platform’s cut.

“Per day” is a ceiling: 24 hours, every hour rented, which no host achieves — scale it by the utilisation you expect. A card sitting idle earns nothing.Fees marked as published come from the platform’s terms; the rest are our estimates, labelled on each row.

Go to platform
AkashBest yield$1.13/hrHost
RunPod$1.11/hrHost
Nosana$0.72/hrHost
Clore.ai$0.51/hrHost
Vast.ai$0.43/hrHost

Technical specifications

Throughput
FP649.7 TFLOPS
FP3220 TFLOPS
TF32156 TFLOPS
FP16/BF16312 TFLOPS
Silicon & memory
Memory
80 GB
Memory bandwidth
1,560 GB/s
TDP
400 W
INT8
624 TOPS
Process
7 nm
Die size
826 mm²
Transistors
54.2 B
Foundry
TSMC
Released
1 Mar 2020
TrainingInference
Datasheet
ArchitectureAmpere
Memory80 GB HBM2e
Bandwidth2.0 TB/s
Tensor compute312 TFLOPS FP16 (sparse)
MIGup to 7 instances
Power300 W PCIe, 400 W SXM
Class
Fine-tuning
Cloud providers
27 tracked
Price range
$0.52 – $6.78 / GPU / hr

SNAPSHOT 2026-10-12T05:40:41.151564+00:00 · BACK TO THE FULL INDEX