Two Nvidia data center GPUs, one Hopper and one Ada Lovelace: 80 GB HBM2e against 48 GB GDDR6, 2.3x the memory bandwidth on the H800, and NVLink 400 GB/s on the H800 where the L40S is PCIe only.
At a glance
Updated 6 minutes ago- Memory
- 80 GB
- HBM2e
- Memory bandwidth
- 2.00 TB/s
- From
- --
- Memory
- 48 GB
- GDDR6
- Memory bandwidth
- 864 GB/s
- From
- $0.55 /GPU/hr
- 34 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | H800 | L40S | Difference |
|---|---|---|---|
| On-demand | -- | $0.55 | |
| Spot | No spot listings | $0.74 | |
| Reserved | No reserved listings | $0.60 | |
| Median | -- | $1.60 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
H800 vs L40S price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | H800 | L40S | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 80 GB HBM2e | 48 GB GDDR6 | 1.7x more on H800 |
| Bandwidth | 2,000 GB/s | 864 GB/s | 2.3x higher on H800 |
| Bus width | 5,120-bit | 384-bit | 13x wider on H800 |
| Compute · dense | |||
| FP8 | 1,513 TFLOPS | 733 TFLOPS | 2.1x higher on H800 |
| FP16 / BF16 | 756.5 TFLOPS | 362.1 TFLOPS | 2.1x higher on H800 |
| INT8 | 1,513 TOPS | 733 TOPS | 2.1x higher on H800 |
| FP32 | 51 TFLOPS | 91.6 TFLOPS | 1.8x higher on L40S |
| Platform | |||
| Interconnect | NVLink 400 GB/s | PCIe only | NVLink on H800 only |
| Board power | 350 W | 350 W | Identical |
| Released | Q1 2023 | Q3 2023 | |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: L40S datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | H800 /GPU/hr | L40S /GPU/hr |
|---|---|---|
Novita
|
-- | On-Demand $0.55 |
GPU.ai
|
-- | On-Demand $0.80 |
Packet·ai
|
-- | On-Demand $0.92 |
Sesterce
|
-- | On-Demand $0.97 |
Massed Compute
|
-- | On-Demand $0.97 |
Runcrate
|
-- | On-Demand $0.97 |
UpCloud
|
-- | On-Demand $1.19 |
Koyeb
|
-- | On-Demand $1.20 |
0 providers list the H800 and 34 the L40S. Every listing is on the H800 page and the L40S page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia H800 was last updated on Sept. 7, 2026, and for Nvidia L40S on Sept. 7, 2026.