L40S vs RTX 5090: cloud rental cost compared
You can rent both by the hour, no purchase required. L40S from $0.668/GPU/hr across 4 providers; RTX 5090 from $0.567/GPU/hr across 4 providers. The RTX 5090 is 15% cheaper at the entry rate.
Specs side by side
Price by provider
L40S vs RTX 5090: common questions
Is the L40S or the RTX 5090 cheaper to rent?
On Aquanode's live marketplace the L40S starts at $0.668/GPU/hr (median $1.09/GPU/hr across 4 providers) and the RTX 5090 starts at $0.567/GPU/hr (median $0.990/GPU/hr across 4 providers). The RTX 5090 is the cheaper of the two at the entry rate, by 15%.
What is the difference between the L40S and the RTX 5090?
The L40S has 48 GB of VRAM against the RTX 5090's 32 GB; the L40S is an Ada Lovelace part and the RTX 5090 is Blackwell (compute capability 8.9 vs 12.0); both run BF16, FP8, INT4 workloads in hardware. On price, the L40S lists from $0.668/GPU/hr and the RTX 5090 from $0.567/GPU/hr.
Which cloud providers offer the L40S and the RTX 5090?
4 providers list the L40S (Vast.ai, RunPod, Massed Compute and Nebius) and 4 list the RTX 5090 (Vast.ai, Akash, RunPod and SimplePod), across 4 and 4 regions respectively. Both are available from Vast.ai and RunPod.
How much does 1,000 GPU-hours cost on the L40S vs the RTX 5090?
At the lowest rates listed today, 1,000 GPU-hours costs $668 on the L40S and $567 on the RTX 5090, a difference of $101 for the same runtime. Rates are per GPU per hour and update hourly.
How this comparison is calculated
Every price is normalized to a per-GPU hourly rate using the same pipeline as every other pricing surface on Aquanode, and only the cheapest qualifying offer per provider is shown. A dash means that provider does not currently list that GPU.
Architecture, compute capability and supported precisions come from each vendor's published datasheet for that generation, not from the marketplace feed. This page regenerates at most once per hour.
