A100
NVIDIA A100, Ampere, 40/80 GB
- Index
- USD 1.98EUR 1.77CHF 1.63
- per GPU-hour, As of Oct 25, 2026
- 7D %
- unchanged ±0.00 %
- ±0.00±0.00±0.00
- Providers
- 22
- 329 offers
- Range
- 1.090.970.90 – 8.197.326.75
- per GPU-hour
The price engine is not reachable right now. Shown: the last data received, as of Oct 25, 2026, 21:05 UTC.
Daily index of A100 per GPU-hour
Show as table
| Date | Index (USD) |
|---|---|
| Oct 10, 2026 | 3.08 |
| Oct 11, 2026 | 3.08 |
| Oct 12, 2026 | 3.08 |
| Oct 13, 2026 | 3.08 |
| Oct 14, 2026 | 1.98 |
| Oct 15, 2026 | 1.98 |
| Oct 16, 2026 | 1.98 |
| Oct 17, 2026 | 1.98 |
| Oct 18, 2026 | 1.98 |
| Oct 19, 2026 | 1.98 |
| Oct 20, 2026 | 1.98 |
| Oct 21, 2026 | 1.98 |
| Oct 22, 2026 | 1.98 |
| Oct 23, 2026 | 1.98 |
| Oct 24, 2026 | 1.98 |
| Oct 25, 2026 | 1.98 |
Factsheet
- Index
- USD 1.98EUR 1.77CHF 1.63 per GPU-hour, As of Oct 25, 2026
- Cheapest current offer
- USD 1.09EUR 0.97CHF 0.90 Civo, United Kingdom
- Providers
- 22 (329 offers, 7 in index)
- Countries
- 23
- Price per pricing model: On-demand
- USD 1.98EUR 1.77CHF 1.63 Index, cheapest 1.090.970.90
- Price per pricing model: Spot
- USD 0.68EUR 0.61CHF 0.56 cheapest
- Price per pricing model: Reserved
- USD 0.56EUR 0.50CHF 0.46 cheapest
- High since start
- USD 3.08EUR 2.75CHF 2.54 Oct 10, 2026
- Low since start
- USD 1.98EUR 1.77CHF 1.63 Oct 14, 2026
- Range
- 1.090.970.90 – 8.197.326.75
- 1D
- unchanged ±0.00 %
- 30 days
- from Nov 9, 2026
- Year to date
- no data yet
- Pricing models
- On-demand, Spot, Reserved
- Use cases (manufacturer)
- Training large models, Inference, HPC and simulation Manufacturer page
- Data since
- Oct 10, 2026
- As of
- Oct 25, 2026
Price distribution
Cheapest comparable on-demand price of each provider, from lowest to highest. The line marks the index.
Cheapest offers
All offers (329)| Provider | Configuration | Location | Price per GPU-hour |
|---|---|---|---|
| Civo | A100 40GB | United Kingdom | 1.090.970.90 |
| Verda (formerly DataCrunch) | A100 SXM 40GB | Finland | 1.561.391.29 |
| Leafcloud | A100 SXM 80GB x2 | Netherlands | 1.791.601.48 |
| E2E Networks | A100 40GB | India | 1.981.771.63 |
| Lambda | A100 SXM 40GB x8 | location not stated | 1.991.781.64 |
| Amazon Web Services (AWS) | A100 40GB x8 | United States | 2.742.452.26 |
| OVHcloud | A100 80GB x4 | location not stated | 3.082.752.54 |
| Microsoft Azure | A100 40GB x8 | United States | 3.403.042.80 |
About this GPU
NVIDIA positions the A100 for AI training, inference, data analytics and high-performance computing. Multi-Instance GPU (MIG) splits one card into up to seven isolated instances.
A100 is a data center GPU by NVIDIA based on the Ampere architecture, introduced in 2020. Offered variants: A100 40GB, A100 PCIe 40GB, A100 SXM 40GB, A100 80GB, A100 PCIe 80GB, A100 SXM 80GB. Specifications are manufacturer figures.
Source: manufacturer: www.nvidia.com
News
Independent reports
- The High-Value Fleet: Why Everyday AI Cargo Flies on Gaudi 2 and A100-40Denvr Dataworks, Sep 10, 2026
- NVIDIA GPUs: Comparing A100 vs H100 for Optimizing AI WorkloadsVoltage Park (with Lightning AI), Sep 12, 2025
- Deploying Google Gemma-3 on Denvr AI Compute: Tuning Parameters for A100 40GB and 80GB CardsDenvr Dataworks, Mar 13, 2025
- Deploying LLaMA 3.3 with Hugging Face TGI: Performance Analysis on A100 and H100 80GB GPUsDenvr Dataworks, Dec 8, 2024
Provider blogs
- NVIDIA's full GPU range compared: A100 vs. L40S vs. H100 vs. H200 vs. B200 vs. B300 vs. Vera RubinProvider blogCivo, Aug 8, 2026
Reports that mention this GPU, from the Intelaris news feed. Links go to the source.
Daily index of A100 per GPU-hour
Show as table
| Date | Index (USD) |
|---|---|
| Oct 10, 2026 | 3.08 |
| Oct 11, 2026 | 3.08 |
| Oct 12, 2026 | 3.08 |
| Oct 13, 2026 | 3.08 |
| Oct 14, 2026 | 1.98 |
| Oct 15, 2026 | 1.98 |
| Oct 16, 2026 | 1.98 |
| Oct 17, 2026 | 1.98 |
| Oct 18, 2026 | 1.98 |
| Oct 19, 2026 | 1.98 |
| Oct 20, 2026 | 1.98 |
| Oct 21, 2026 | 1.98 |
| Oct 22, 2026 | 1.98 |
| Oct 23, 2026 | 1.98 |
| Oct 24, 2026 | 1.98 |
| Oct 25, 2026 | 1.98 |
Specifications
Manufacturer figures as delivered by the price engine. Tensor values as stated: dense or with sparsity.
| Model | Memory | Type | Bandwidth | FP8 | FP16 | FP32 | Tensor values | Max. power | Interconnect | Source |
|---|---|---|---|---|---|---|---|---|---|---|
| A100 40GB (form factor not stated) | 40 GB | HBM2 | 1.56 TB/s | – | 312 | 19.5 | dense | – | – | www.nvidia.comretrieved Oct 18, 2026 |
| A100 PCIe 40GB | 40 GB | HBM2 | 1.56 TB/s | – | 312 | 19.5 | dense | 250 W | PCIe Gen4; NVLink 3 (bridge, 2 GPUs) | www.nvidia.comretrieved Oct 18, 2026 |
| A100 SXM 40GB | 40 GB | HBM2 | 1.56 TB/s | – | 312 | 19.5 | dense | 400 W | NVLink 3 | www.nvidia.comretrieved Oct 18, 2026 |
| A100 80GB (form factor not stated) | 80 GB | HBM2e | – | – | 312 | 19.5 | dense | – | – | www.nvidia.comretrieved Oct 18, 2026 |
| A100 PCIe 80GB | 80 GB | HBM2e | 1.94 TB/s | – | 312 | 19.5 | dense | 300 W | PCIe Gen4; NVLink 3 (bridge, 2 GPUs) | www.nvidia.comretrieved Oct 18, 2026 |
| A100 SXM 80GB | 80 GB | HBM2e | 2.04 TB/s | – | 312 | 19.5 | dense | 400 W | NVLink 3 | www.nvidia.comretrieved Oct 18, 2026 |
FP8, FP16, FP32: TFLOPS.
How these figures are calculated
The index is the typical price of a GPU: the median of the cheapest on-demand price per GPU-hour of each direct provider (hyperscalers excluded), taken from the provider's latest live fetch within the last 3 days, with outliers removed; it is shown only when at least 3 providers have a price.
The cheapest current offer is the single lowest comparable on-demand price of any provider and source, including hyperscalers and published prices up to 14 days old.
Changes over 1, 7 and 30 days and the price chart use the same daily index, and a change compares only providers with a price on both days, so a provider joining or leaving does not move the number.
- index
- median across direct providers (hyperscalers excluded) of each provider's cheapest comparable on-demand price per GPU-hour from its latest live retrieval within the last 3 days (official API, public price page or partner feed), outliers (below 1/3 or above 3x the median) excluded; published only with at least 3 providers
- cheapestCurrentOffer
- lowest current comparable on-demand price per GPU-hour of all providers and sources (live, published within 14 days, hyperscalers included), outliers excluded
- providers
- All providers with a current offer for this GPU (GPU-only partial prices and offers without a stated pricing model excluded), any source and pricing model, hyperscalers included; usually more than indexProviders.
- change
- Change of the index against the last value on or before 1, 7 or 30 days ago, over the providers with prices on both days.
- high52w
- Highest and lowest daily index of the last 52 weeks; until 52 weeks of data exist, counted from dataSince.