L40S

Every provider's rate, side by side.

L40S is available through the OneInfer GPU marketplace with live provider pricing, regions, VRAM, and deployment options from the API.

16 providers list it in 19 regions, from $0.54 per GPU-hour with vastai. It has 48 GB of GPU memory. Pick a provider and region, deploy it from the OneInfer Console with your own Docker image, connect over SSH, and pay from one pay-as-you-go wallet while it runs.

Deploy the L40S in 4 steps

Step 1 of 4

16 providers list the L40S, from $0.54 per GPU-hour. The table below sorts them by price.

Cloud GPU
VRAM
48GB
CUDA cores
18,176
TDP
350W
Bandwidth
N/A
Process node
5nm
Launch date
N/A

Where you can run it

The L40S is available now in 19 of the 96 regions OneInfer has GPUs in. Pick a region to see who offers it there, or see every GPU by region.

Available nowNot available

Americas

Europe

Asia-Pacific

Prices are per GPU-hour, the lowest in each region. Grey regions have other GPUs, not the L40S.

Available from 16 providers

Sorted by price. Select the price heading to re-sort.

L40S providers, regions, configurations and hourly prices
ProviderRegionsConfigAvailabilityDeploy
vastaivastai
EU-FI-01, EU-RO-01, EU-SL-01, AS-KR-01, EU-ES-01, AS-TW-01, US-TX-011x 48GB$0.54Available
vastaivastai
CA-QC-011x 48GB$0.76Available
vastaivastai
EU-RO-01, AS-TW-014x 48GB$0.80$3.20/hr for 4 GPUsAvailable
vastaivastai
EU-RO-01, EU-SL-01, AS-KR-01, AS-TW-012x 48GB$0.80$1.60/hr for 2 GPUsAvailable
runpodrunpod
US-TX-03, US-MO-011x 48GB$1.09Available
nebius_ainebius_ai
EU-FI-011x 48GB$1.35Available
vultrvultr
US-GA-011x 48GB$1.67Available
aws
AS-KR-01, DE-HE-01, IN-MH-01, IN-TS-01, JP-OSQ-01, JP-TYO-01, SE-AB-01, US-OH-01, US-OR-01, US-VA-011x 48GB$1.86Available
aws
AS-KR-01, DE-HE-01, IN-MH-01, IN-TS-01, JP-OSQ-01, JP-TYO-01, SE-AB-01, US-OH-01, US-OR-01, US-VA-011x 48GB$2.24Available
aws
AS-KR-01, DE-HE-01, IN-MH-01, IN-TS-01, JP-OSQ-01, JP-TYO-01, SE-AB-01, US-OH-01, US-OR-01, US-VA-014x 48GB$2.62$10.49/hr for 4 GPUsAvailable
aws
AS-KR-01, DE-HE-01, IN-MH-01, IN-TS-01, JP-OSQ-01, JP-TYO-01, SE-AB-01, US-OH-01, US-OR-01, US-VA-011x 48GB$3.00Available
vultrvultr
US-GA-011x 48GB$3.34Available
aws
AS-KR-01, DE-HE-01, IN-MH-01, IN-TS-01, JP-OSQ-01, JP-TYO-01, SE-AB-01, US-OH-01, US-OR-01, US-VA-014x 48GB$3.77$15.07/hr for 4 GPUsAvailable
aws
AS-KR-01, DE-HE-01, IN-MH-01, IN-TS-01, JP-OSQ-01, JP-TYO-01, SE-AB-01, US-OH-01, US-OR-01, US-VA-018x 48GB$3.77$30.13/hr for 8 GPUsAvailable
aws
AS-KR-01, DE-HE-01, IN-MH-01, IN-TS-01, JP-OSQ-01, JP-TYO-01, SE-AB-01, US-OH-01, US-OR-01, US-VA-011x 48GB$4.53Available
aws
AS-KR-01, DE-HE-01, IN-MH-01, IN-TS-01, JP-OSQ-01, JP-TYO-01, SE-AB-01, US-OH-01, US-OR-01, US-VA-011x 48GB$7.58Available

Full specifications

Data from GPU specs and provider APIs

AI TOPS
733
FP8 TFLOPS
1,466
FP16 TFLOPS
362
BF16 TFLOPS
362
FP32 TFLOPS
91.61
INT8 TOPS
1,466
Sparse multiplier
2

Benchmarks

L40S vs comparable GPUs on the platform

Inference throughput

7B model, tokens per second

B200 SXM15,000
H200 SXM8,500
H100620
A100500
GeForce RTX 5090180

Training performance

Overall training multiplier

B200 SXM30x
H200 SXM18x
H10015x
A1003.4x
L40S2.8x

GeekBench OpenCL

Compute benchmark score

GeForce RTX 5090367,740
H200 SXM343,598
L40S337,706
H100336,474
B200 SXM333,768

Ready to deploy L40S?

Deploy from your choice of 16 providers.