NVIDIA A100 40GB cloud prices
A100 40GB on-demand cloud prices run from $1.66 to $2.74 per GPU-hour across 2 providers gpu.gl tracks (median $2.20). The lowest is DataCrunch.
Lowest price by provider
| Configuration | Where | Fetched | Source | |||
|---|---|---|---|---|---|---|
| DataCrunch | On-demand | $1.66 | 1A100.40S.22V · 1, 8 GPUs | Not stated per region | DataCrunch ↗ | |
| AWS | On-demand | $2.74 | p4d.24xlarge · 8 GPUs | 6 regions | AWS ↗ | |
| DataCrunch | Spot / interruptible | $0.829 | 1A100.40S.22V · 1, 8 GPUs | Not stated per region | DataCrunch ↗ | |
| AWS | Reserved 1 yr | $1.74 | p4d.24xlarge · 8 GPUs | 6 regions | AWS ↗ | |
| AWS | Reserved 3 yr | $1.17 | p4d.24xlarge · 8 GPUs | 6 regions | AWS ↗ |
Price history
History starts 2026-11-08. gpu.gl stores one snapshot a day from launch and never back-fills, so a chart appears here once there are two daily snapshots with on-demand prices for this GPU (1 so far).
A100 40GB specifications
The A100 40GB has 40 GB of HBM2 and 1.555 TB/s of memory bandwidth. That is about 201 dense FP16 TFLOPS per TB/s of bandwidth; workloads that stream large weights, like LLM inference at small batch sizes, tend to be limited by the bandwidth figure, while large-batch training leans on the compute figure.
| Architecture | Ampere |
|---|---|
| Memory | 40 GB HBM2 |
| Memory bandwidth | 1.555 TB/s |
| FP16 / BF16 tensor (dense) | 312 TFLOPS |
| FP8 tensor (dense) | Not supported |
| Max power | 400 W |
| Form factor | SXM4 |
Source: NVIDIA spec sheet. Tensor figures are dense (without sparsity). Figures for the SXM version; the PCIe version is limited to 250 W.
Every configuration
Each instance size or listing, at its cheapest region.
| Provider | Price type | $/GPU-hr | Instance | GPUs | Instance price | Cheapest region | Fetched | Source |
|---|---|---|---|---|---|---|---|---|
| DataCrunch | On-demand | $1.66 | 1A100.40S.22V | 1 | $1.66/hr | Not stated per region | DataCrunch ↗ | |
| DataCrunch | On-demand | $1.66 | 8A100.40S.176V | 8 | $13.26/hr | Not stated per region | DataCrunch ↗ | |
| AWS | On-demand | $2.74 | p4d.24xlarge | 8 | $21.96/hr | US West (Oregon) +5 more | AWS ↗ | |
| DataCrunch | Spot / interruptible | $0.829 | 1A100.40S.22V | 1 | $0.8285/hr | Not stated per region | DataCrunch ↗ | |
| DataCrunch | Spot / interruptible | $0.829 | 8A100.40S.176V | 8 | $6.63/hr | Not stated per region | DataCrunch ↗ | |
| AWS | Reserved 1 yr | $1.74 | p4d.24xlarge | 8 | $13.92/hr | US West (Oregon) +5 more | AWS ↗ | |
| AWS | Reserved 3 yr | $1.17 | p4d.24xlarge | 8 | $9.37/hr | US West (Oregon) +5 more | AWS ↗ |