A40 vs B200: cloud rental cost compared

You can rent both by the hour, no purchase required. A40 from $0.075/GPU/hr across 2 providers; B200 from $6.79/GPU/hr across 2 providers. The A40 is 99% cheaper at the entry rate.

A40
Good for training and inference on models that don't need FP8 kernels
$0.075/hr
Lowest / GPU
$0.440/hr
Median / GPU
48 GB
VRAM
Ampere
Architecture
B200
Good for training and serving frontier-scale LLMs
$6.79/hr
Lowest / GPU
$6.79/hr
Median / GPU
180 GB
VRAM
Blackwell
Architecture

Specs side by side

Spec
A40
B200
VRAM
48 GB
180 GB
Architecture
Ampere
Blackwell
Compute capability
8.6
10.0
Precisions in hardware
FP32, FP16, BF16, INT4
FP32, FP16, BF16, FP8, INT4
Interconnect
PCIe
PCIe
Lowest $/GPU/hr
$0.075
$6.79
Median $/GPU/hr
$0.440
$6.79
Providers
2
2
Regions
2
2

Price by provider

Provider
A40 $/GPU/hr
B200 $/GPU/hr
RunPod
$0.440
$6.79
Vultr
$0.075
Vast.ai
$10.12

A40 vs B200: common questions

Is the A40 or the B200 cheaper to rent?

On Aquanode's live marketplace the A40 starts at $0.075/GPU/hr (median $0.440/GPU/hr across 2 providers) and the B200 starts at $6.79/GPU/hr (median $6.79/GPU/hr across 2 providers). The A40 is the cheaper of the two at the entry rate, by 99%.

What is the difference between the A40 and the B200?

The A40 has 48 GB of VRAM against the B200's 180 GB; the A40 is an Ampere part and the B200 is Blackwell (compute capability 8.6 vs 10.0); only the B200 supports FP8 compute. On price, the A40 lists from $0.075/GPU/hr and the B200 from $6.79/GPU/hr.

Which cloud providers offer the A40 and the B200?

2 providers list the A40 (Vultr and RunPod) and 2 list the B200 (RunPod and Vast.ai), across 2 and 2 regions respectively. Both are available from RunPod.

How much does 1,000 GPU-hours cost on the A40 vs the B200?

At the lowest rates listed today, 1,000 GPU-hours costs $75 on the A40 and $6,790 on the B200 — a difference of $6,715 for the same runtime. Rates are per GPU per hour and update hourly.

How this comparison is calculated

Every price is normalized to a per-GPU hourly rate using the same pipeline as every other pricing surface on Aquanode, and only the cheapest qualifying offer per provider is shown. A dash means that provider does not currently list that GPU.

Architecture, compute capability and supported precisions come from each vendor's published datasheet for that generation — not from the marketplace feed. This page regenerates at most once per hour.

Ready when you are

Stop paying for
idle GPUs.

Sign up in 60 seconds. Pay only for the GPU minutes you actually use.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.