NVIDIA · Updated daily · last refresh 2026-10-01
L40S pricing
What the NVIDIA L40S costs right now: 9 tracked on-demand rates, the spread between them, the used market, and what the hourly number turns into when you own the card instead.
The headline on L40S pricing is the spread: the same card costs 2.4x more at the top of the market than at the bottom. The floor comes from Vast.ai (a peer-to-peer marketplace, cheapest but with host-trust trade-offs), the ceiling from AWS, where you are paying for the ecosystem around the GPU as much as the silicon. Every rate below is an on-demand list price; commit to reserved or spot capacity and 30-70% comes off. Ada silicon with 48 GB: strong FP8 compute, modest bandwidth. A favorite for image gen and mid-size LLMs.
L40S rental prices by provider
| Provider | $/GPU-hr | Notes |
|---|---|---|
| Vast.ai | $0.80 | Verified-listing rate, refreshed daily |
| Cudo | $0.87 | marketplace |
| Packet.ai | $0.92 | Dedicated |
| Hyperstack | $0.95 | neocloud |
| RunPod | $1.09 | neocloud |
| CoreWeave | $1.28 | neocloud |
| DigitalOcean | $1.57 | neocloud |
| Modal | $1.95 | Serverless (L40S class) |
| AWS | $1.96 | g6e.xlarge |
Buying instead: the used market
Working L40S pulls currently trade around $6,200, with warrantied refurb channel units above that. Amortized over 36 months at 60% utilization with industrial power, that is an effective ~$0.42 per GPU-hour, below even the cheapest rental in the table above. The crossover depends entirely on your utilization: run your own numbers in the ROI calculator, and read the second-life guide before buying pulled hardware.
Put the price in context
L40S specs and capability
What this card actually runs: memory, bandwidth, and the models that fit at each precision.
Convert to $/million tokens
Hourly pricing is the input. The estimator turns it into serving cost for any model.
A100 80GB vs L40S
Head-to-head specs, pricing, and which models fit on one but not the other.
L40S vs RTX 4090
Head-to-head specs, pricing, and which models fit on one but not the other.
L40S vs L4
Head-to-head specs, pricing, and which models fit on one but not the other.
All GPU pricing
The full table: every accelerator we track, cheapest to priciest, updated monthly.
Common questions
How much does a L40S cost to rent?
As of 2026-09, L40S on-demand rental runs from $0.80 per GPU-hour at Vast.ai to $1.96 at Amazon Web Services, with a median of $1.09 across the 9 providers we track. Reserved and spot pricing typically runs 30-70% below these list rates.
How much does a used L40S cost?
Working L40S pulls trade around $6,200 as of 2026-09, with warrantied refurbished units priced higher. At that price and 60% utilization, ownership works out to roughly $0.42 per GPU-hour over three years including power.
*Owned effective rate: 36-month amortization, 60% utilization, $0.08/kWh with cooling overhead; hosting and ops labor excluded. Full methodology.