NVIDIA A100 SXM 80GB pricing.
prices as of · 6 providers · 13 configurations
The previous generation's training board. Still the cheapest way to get 80 GB of HBM.
The cheapest A100 80GB SXM today is A100 SXM · Community Cloud at RunPod, $1.39/GPU-hr, read 17 Sept 2026; the cheapest interruptible rate is $0.855/GPU-hr at Verda (DataCrunch).
Cheapest on demand
$1.39
per GPU-hour at RunPod
Median of the spread
$1.71
across 11 configurations
Cheapest interruptible
$0.855
5 of 11 publish one
Per GB of memory
$0.0174/GB-hr
market median $0.0300/GB-hr
What the board is
published by NVIDIA, not by a provider- Memory
- 80 GB
- Memory bandwidth
- 2.04 TB/s
- Architecture
- Ampere
- Launched
- 2021
These are the chip's own figures, kept in this site's registry and the same whoever rents it out. A provider's feed is trusted for its prices, its GPU counts and the memory it states per card, never for what the board is. There is no speed score on this page: bandwidth is a published number, and turning it into a benchmark would be inventing one.
Every provider renting the A100 80GB SXM
Cheapest per GPU-hour first. The rate is for one GPU for one hour, so a node of eight sits beside a single card at a comparable number, with the whole machine's hourly price under it. Where a provider publishes an interruptible rate it is in the same cell.
RunPodA100 SXM · Community Cloud
1x A100 80GB SXM · 80 GB each · 16 vCPU · 125 GB RAM
disk none, billed separately · regions not stated · billed per second · marketplace
Community Cloud: vetted third-party hosts, cheaper and less consistent · storage billed separately · billed per second
$1.39per GPU-hour$1.39/hr all inno spot rate
- RunPod
A100 SXM · Secure Cloud
1x A100 80GB SXM · 80 GB each · 16 vCPU · 125 GB RAM
disk none, billed separately · regions not stated · billed per second
Secure Cloud: RunPod's own datacentres · storage billed separately · billed per second
$1.59per GPU-hour$1.59/hr all inno spot rate
Verda (DataCrunch)8A100.176V · 8x A100 SXM4 80GB
8x A100 80GB SXM · 80 GB each · 176 vCPU · 960 GB RAM
disk none, billed separately · regions not stated · billed per hour
Dedicated Hardware Instance · storage billed separately · 600 GB/s between GPUs
$1.71per GPU-hour$13.67/hr all in$0.855 spot
- Verda (DataCrunch)
1A100.22V · 1x A100 SXM4 80GB
1x A100 80GB SXM · 80 GB each · 22 vCPU · 120 GB RAM
disk none, billed separately · regions not stated · billed per hour
Dedicated Hardware Instance · storage billed separately
$1.71per GPU-hour$1.71/hr all in$0.855 spot
- Verda (DataCrunch)
2A100.44V · 2x A100 SXM4 80GB
2x A100 80GB SXM · 80 GB each · 44 vCPU · 240 GB RAM
disk none, billed separately · regions not stated · billed per hour
Dedicated Hardware Instance · storage billed separately · 100 GB/s between GPUs
$1.71per GPU-hour$3.42/hr all in$0.855 spot
- Verda (DataCrunch)
4A100.88V · 4x A100 SXM4 80GB
4x A100 80GB SXM · 80 GB each · 88 vCPU · 480 GB RAM
disk none, billed separately · regions not stated · billed per hour
Dedicated Hardware Instance · storage billed separately · 300 GB/s between GPUs
$1.71per GPU-hour$6.84/hr all in$0.855 spot
CrusoeNVIDIA A100 SXM
1x A100 80GB SXM · 80 GB each · host size not stated
disk none, billed separately · regions not stated · billed per hour
Priced per GPU-hour · vCPU, RAM and disks billed separately · egress free · no minimum commitment
$2.30per GPU-hour$2.30/hr all inno spot rate
Vultrvbm-48c-1024gb-4-a100-gpu
4x A100 80GB SXM · 80 GB each · 48 vCPU · 1024 GB RAM
disk 450 GB · regions not stated · billed per hour
Bare metal · $7000/mo if kept a whole month
$2.40per GPU-hour$9.59/hr all inno spot rate
CoreWeaveNVIDIA A100
8x A100 80GB SXM · 80 GB each · 128 vCPU · 2048 GB RAM · NVLink
disk 7.7 TB · 2 regions · billed per hour
$21.6 an hour for the whole node · egress and VPC free · IPv4 and storage billed separately · spot shown is the cheaper of the two regions
$2.70per GPU-hour$21.60/hr all in$1.19 spot
Lambda8x NVIDIA A100 SXM
8x A100 80GB SXM · 80 GB each · 240 vCPU · 1800 GB RAM · NVLink
disk 19.5 TB · regions not stated · billed per minute
Priced per GPU-hour, billed by the minute · storage included in the instance
$2.79per GPU-hour$22.32/hr all inno spot rate
- Vultr
vbm-112c-2048gb-8-a100-gpu
8x A100 80GB SXM · 80 GB each · 112 vCPU · 2048 GB RAM · NVLink
disk 960 GB · 1 region · billed per hour
Bare metal · $15052.8/mo if kept a whole month
$2.80per GPU-hour$22.40/hr all inno spot rate
Billed as a function
2 rates · never rankedThese rates buy a container that runs when it is called, not a machine you hold. CPU and memory are billed on top, a chosen region or a guarantee against preemption costs more, and the figure is a floor rather than a price. They are listed for what they are and ranked nowhere on this site.
ModalNvidia A100, 80 GB
1x A100 80GB SXM · 80 GB each · host size not stated
disk none, billed separately · regions not stated · billed per second · serverless
$0.000694 a GPU-second, the preemptible region-agnostic rate · a chosen region costs 1.15x to 1.75x and non-preemptible 3x · CPU, memory and volumes billed on top · memory is the board's published spec
$2.50per GPU-hour$2.50/hr all inno spot rate
BasetenA100 80 GiB
1x A100 80GB SXM · 80 GB each · host size not stated
disk not stated · regions not stated · billed per minute · serverless
$0.06667 a GPU-minute on a dedicated deployment · CPU instances priced separately · Baseten publishes no regions, storage or egress rate beside this
$4.00per GPU-hour$4/hr all inno spot rate
Frequently asked
- Who rents the A100 80GB SXM cheapest?
- RunPod, at $1.39/GPU-hr on A100 SXM · Community Cloud, read on 17 Sept 2026. That is the on-demand rate for one GPU for one hour; the whole machine bills $1.39/hr.
- What is the NVIDIA A100 SXM 80GB?
- The previous generation's training board. Still the cheapest way to get 80 GB of HBM. It is a Ampere board from 2021 with 80 GB of memory at 2.04 TB/s, in the SXM package. Those figures come from the vendor, not from any provider's price page.
- Can I rent a A100 80GB SXM on spot?
- Yes. 5 of the 11 configurations here publish an interruptible rate, the cheapest being $0.855/GPU-hr at Verda (DataCrunch), 50% under its own on-demand rate. The machine can be taken back mid-run, so it suits work that checkpoints.
- Why do A100 80GB SXM prices differ so much?
- The spread here runs from $1.39/GPU-hr to $2.80/GPU-hr for the same silicon, because what else comes with it differs: the vCPU and RAM around the GPU, whether a disk is included, how many regions it runs in, and whether the machine belongs to the provider or to a third party on a marketplace. Each row says which.
- How current are these prices?
- They are read every morning from each provider's own public page or API, and this page recomputes with them. Last refresh: 17 Sept 2026. Reserved and committed rates are not indexed. Prices exclude tax.