Guide4 sections2 min read
The short answer
An NVIDIA L40S is rented per GPU-hour. The table below shows the best live offer for the L40S on EverXCloud, next to the L40 and the RTX 6000 Ada, which also have 48 GB, excluding tax.
What you get with an L40S
The L40S is an Ada Lovelace data center GPU with 48 GB of GDDR6 and 864 GB/s of bandwidth, rated at 362 TFLOPS in BF16 and 733 TFLOPS in FP8, at up to 350 W over PCIe 4.0.
It is a common choice for inference, image and video generation and rendering, where 48 GB on one card matters more than the HBM bandwidth of an H100 or A100.
What moves the hourly rate
On an exchange, the rate moves with supply and demand: more offers lower the best price, more demand raises it. Region, GPU count per machine, storage and network included in the configuration also change the price of an offer.
Compare the same variant, memory size and form factor, in the same region. A headline hourly rate rarely describes the full session cost, so add preparation time, storage and any separately billed resources.
Pay the price you choose
If the best offer is above your budget, place a bid at the price you are willing to pay per GPU-hour. The bid is matched when an offer meets it.
During pre-launch, prices shown on EverXCloud are indicative and become rentable on launch day. The table above is read from the live exchange each time the page is generated.
Live prices on EverXCloud
| GPU | Memory | From, per GPU-hour |
|---|---|---|
| NVIDIA L40S 48GB | 48 GB | $0.79 |
| NVIDIA L40 48GB | 48 GB | $0.69 |
| NVIDIA RTX 6000 Ada 48GB | 48 GB | $0.74 |
Best live offer on the exchange, excluding tax. Prices are indicative during pre-launch.
Frequently asked questions
- How much does it cost to rent an L40S?
- The current rate is the best live offer on the EverXCloud exchange, shown on this page and on the L40S page, per GPU-hour and excluding tax.
- L40S or A100 for inference?
- The A100 80GB has more memory and far higher bandwidth; the L40S has 48 GB and supports FP8. For models that fit in 48 GB, compare both on your own prompts and batch sizes.
- Are the prices shown final?
- No. During pre-launch, EverXCloud prices are indicative. They are shown per GPU-hour, excluding tax, and become rentable on launch day.