The NVIDIA L40 is an enterprise-class GPU built on the Ada Lovelace architecture, featuring 48 GB of memory with 864 GB/s of memory bandwidth and a 300 W TDP. It delivers 90.5 TFLOPS of FP32 performance and 181 TFLOPS of FP16 tensor performance. Currently available from 6 providers starting at $0.34/GPU/hour, with a market median of $0.99/GPU/hour across 21 configurations.
Cheapest
$0.340/hr
Vast.ai
Median
$0.990/hr
across 21 offerings
Most expensive
$1.390/hr
Thunder Compute
90-day trend
-1.0%
median rate
Hardware specifications
Same across all providers
Memory
48 GB
FP16 performance
181 TFLOPS
peak
TDP
300 W
Memory bandwidth
864 GB/s
Architecture
Ada Lovelace
FP32 performance
90.5 TFLOPS
Brand
NVIDIA
Series
L40
Market price history
Median price across all providers
6 offerings from 6 providers
Sorted by price ascending. Compare configurations side-by-side.
| Provider | Count | vCPU | RAM | Region | Per GPU hour | Total/hr | Action |
|---|---|---|---|---|---|---|---|
| ×1 | 48 | 188 GB |    | From$0.340 -18.2% 30d | From$0.34 | Launch | |
 Thunder ComputeReferral link | ×1 | 4 | 32 GB | -- | From$0.790 +11.2% 30d | From$0.79 | Launch |
 RunpodReferral link | ×1 | 32 | 250 GB |  | $0.820 0.0% 30d | $0.82 | Launch |
| ×1 | 26 | 192 GB |  | $0.970 0.0% 30d | From$0.97 | Launch | |
| ×1 | 28 | 58 GB | | $1.000 0.0% 30d | From$1.00 | Launch | |
 Sesterce CloudReferral link | ×1 | 28 | 58 GB | | From$1.100 0.0% 30d | From$1.10 | Launch |
Similar GPUs
Want more from this page?
See incorrect data?
Frequently asked questions
How much does the L40 cost per hour?
The L40 starts at $0.34 per GPU-hour, with a median of $0.99 across 21 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.
Which cloud providers offer the L40?
6 providers currently list the L40: Thunder Compute, Runpod, Sesterce Cloud, Runcrate, Vast.ai, Hyperstack. Compare their hourly pricing, regions and machine specs in the table above.
How much VRAM does the L40 have?
The L40 comes with 48 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.
Where is the L40 cheapest?
The lowest on-demand price we currently track for the L40 is $0.34 per GPU-hour at Vast.ai. Because providers update pricing and availability frequently, check the live table above before you launch.