NVIDIA L40S 48GB rental pricing

The cheapest NVIDIA L40S 48GB in stock right now is $0.54 per GPU-hour community from Vast.ai for the 1× L40S 48GB configuration. The median on-demand rate across 23 providers is $1.50 per GPU-hour.

Running one NVIDIA L40S 48GB around the clock for a month (730 hours) costs about $391 at the cheapest in-stock rate of $0.54 per hour. At the median on-demand rate it is about $1,092 a month. Reserved terms usually come in below that; ask the provider for a quote.

Vast.ai has the cheapest NVIDIA L40S 48GB in stock right now at $0.54 per GPU-hour community for the 1× L40S 48GB configuration. That is a community rate; see the provider table for the cheapest on-demand listing. Rates change often, so check the provider table for today's figure before you commit.

We have 5 weeks of price history for the NVIDIA L40S 48GB, not yet enough like-for-like weeks to call a trend: the set of providers we track is still growing, and a median over more sellers is not a price move. The chart above fills in as our daily checks accumulate.

On-demand is pay-as-you-go with no commitment. Spot is spare capacity sold at a discount that the provider can reclaim at short notice. Reserved is a committed term, usually months, in exchange for a lower rate. Community is capacity from individual hosts on a marketplace, cheaper and less uniform. This week's median rates for the NVIDIA L40S 48GB are on-demand $1.50 (23 providers), spot $0.87 (2 providers), reserved $2.20 (2 providers), community $0.79 (3 providers), per GPU-hour.

We track 24 providers with 41 live prices for the NVIDIA L40S 48GB. Sold-out listings stay in the table so you can see who normally carries it, but never set the cheapest figure.

With 8-bit weights and a single sequence of context, one NVIDIA L40S 48GB holds gpt-oss-20b (20.9B), Gemma 3 27B (27.4B), Qwen3-32B (32.8B). See the model fit table for the full ladder.

At its cheapest in-stock on-demand rate the NVIDIA L40S 48GB delivers dense FP8 compute at $1.04 per PFLOP-hour, which ranks 9 of 30 priced GPUs we cover on that basis. Lower is better: it is the rental price divided by peak FP8 throughput.

Prices are read daily from each provider's public price list or API and recorded whenever they change. Listings are shown per GPU-hour on-demand unless marked otherwise, and the chart covers the last 30 days. The newest listing was checked 5h ago.