L40S vs RTX5090
The L40S delivers 1.7× the FP16 compute of the RTX5090 while costing 1.9× more on average, making the RTX5090 10% more cost-efficient per TFLOP.
Spec Comparison
Spec
L40S
RTX5090
Architecture
Ada Lovelace
Blackwell
VRAM
48 GB
32 GB
FP16 TFLOPS
362
210
Memory Bandwidth
864 GB/s
1,792 GB/s
MSRP
$14,000
$1,999
Used/Market Price
$9,000
N/A
Live Pricing
Cost Efficiency
Metric
L40S
RTX5090
$/TFLOP/hr
$0.0083
$0.0076
$/GB-VRAM/hr
$0.0626
$0.0497
Lower $/TFLOP and $/GB-VRAM is better. Based on median hourly pricing.
Provider Availability
L40S Cloud Pricing
180 instances| Provider | GPUs | VRAM | Region | Type | Price/hr | |
|---|---|---|---|---|---|---|
| CHEAPESTVerda | 1x | 48 GB | EU-Central | Spot | $0.320 | Rent |
| AWS | 1x | 44.7 GB | US-East | Spot | $0.446 | Rent |
| Crusoe | 1x | 48 GB | US-West | Spot | $0.500 | Rent |
| AWS | 1x | 44.7 GB | US-East | Spot | $0.532 | Rent |
| AWS | 1x | 44.7 GB | Asia-Pacific | Spot | $0.560 | Rent |
| AWS | 1x | 44.7 GB | US-East | Spot | $0.587 | Rent |
| Verda | 2x | 96 GB | EU-Central | Spot | $0.640 | Rent |
| AWS | 1x | 44.7 GB | Asia-Pacific | Spot | $0.669 | Rent |
| AWS | 1x | 44.7 GB | eu-north-1 | Spot | $0.723 | Rent |
| AWS | 1x | 44.7 GB | eu-north-1 | Spot | $0.723 | Rent |
RTX5090 Cloud Pricing
108 instances| Provider | GPUs | VRAM | Region | Type | Price/hr | |
|---|---|---|---|---|---|---|
| CHEAPESTVast.ai | 1x | 32 GB | US-East | Spot | $0.0940 | Rent |
| Vast.ai | 1x | 32 GB | Asia-Pacific | Spot | $0.100 | Rent |
| Vast.ai | 1x | 32 GB | EU-Central | Spot | $0.120 | Rent |
| Vast.ai | 2x | 64 GB | Asia-Pacific | Spot | $0.267 | Rent |
| Vast.ai | 1x | 32 GB | US-Central | Spot | $0.268 | Rent |
| Vast.ai | 1x | 32 GB | US-Central | On-Demand | $0.280 | Rent |
| Vast.ai | 1x | 32 GB | US-West | Spot | $0.293 | Rent |
| Vast.ai | 1x | 32 GB | EU-Central | On-Demand | $0.330 | Rent |
| Vast.ai | 1x | 32 GB | Asia-Pacific | On-Demand | $0.368 | Rent |
| Vast.ai | 2x | 64 GB | vn-vietnam | Spot | $0.373 | Rent |