L40S rental prices: cheapest $/hr today
The cheapest on-demand L40S rental today is $0.96/hr on Spheron, updated 2026-10-06. 48 GB VRAM, NVIDIA.
Pricing at a glance
All current L40S offers
Provider, memory & availability
| GPU / provider | Billing | $/GPU-hour | GPUs / total per hour | Availability / details |
|---|---|---|---|---|
| L40SRunPod48 GB VRAM | community cloud | $0.79per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L40SSpheron48 GB VRAM | on-demand | $0.96per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L40SMassed Compute48 GB VRAM | on-demand | $0.97per GPU-hour+0.0% over 30 days | 1× $0.97per node-hour | Not reportedView provider2026-10-06Details
|
| L40SSpheron48 GB VRAM | spot / interruptible | $0.99per GPU-hour-7.5% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L40SRunPod48 GB VRAM | secure cloud | $1.09per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L40SKoyeb48 GB VRAM | serverless | $1.20per GPU-hour$0.000333/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L40SNebius48 GB VRAM | on-demand | $1.35per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L40SCrusoe48 GB VRAM | on-demand | $1.50per GPU-hour+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L40SDigitalOcean48 GB VRAMNVIDIA L40S 1x | on-demand | $1.57per GPU-hour30-day comparison unavailable | 1× $1.57per node-hour | Not reportedView provider2026-10-06Details
|
| L40SDataCrunch48 GB VRAM | on-demand | $1.57per GPU-hour+14.9% over 30 days | 1× $1.57per node-hour | Not reportedView provider2026-10-06Details
|
| L40SScaleway48 GB VRAM | on-demand | $1.65per GPU-hour-3.6% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L40SVultr48 GB VRAM | on-demand | $1.67per GPU-hour+0.0% over 30 days | 1× $1.67per node-hour | Not reportedView provider2026-10-06Details
|
| L40SOVHcloud48 GB VRAM | on-demand | $1.80per GPU-hour+0.0% over 30 days | 1× $1.80per node-hour | Not reportedView provider2026-10-06Details
|
| L40SAWS48 GB VRAMg6e.xlarge | on-demand | $1.86per GPU-hour30-day comparison unavailable | 1× $1.86per node-hour | Not reportedView provider2026-10-06Details
|
| L40SModal48 GB VRAM | serverless | $1.95per GPU-hour$0.000542/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L40SCerebrium48 GB VRAM | serverless | $1.95per GPU-hour$0.000542/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L40SCoreWeave48 GB VRAM | on-demand | $2.25per GPU-hour+0.0% over 30 days | 8× $18.00per node-hour | Not reportedView provider2026-10-06Details
|
| L40SReplicate48 GB VRAM | serverless | $3.51per GPU-hour$0.000975/sec+0.0% over 30 days | Node minimum and total not reported | Not reportedView provider2026-10-06Details
|
| L40SAWS48 GB VRAMg6e.48xlarge | on-demand | $3.77per GPU-hour30-day comparison unavailable | 8× $30.13per node-hour | Not reportedView provider2026-10-06Details
|
Try another provider or reduce the minimum memory.
Tables rank by price, lowest first. Commercial relationships never affect ordering. How we collect and rank prices.
Monthly view assumes 730 hours of continuous use. Daily view assumes 24 hours.
On-demand and secure rates do not require a reservation. Community and spot capacity can be interrupted. Prices are per GPU per hour, before storage/egress. Every row shows its update date.
L40S hardware specs
| Architecture | Ada Lovelace |
|---|---|
| VRAM | 48 GB |
| FP16 TFLOPS (dense) | 362 |
| Memory bandwidth | 864 GB/s |
| TDP | 350 W |
| Interconnect | PCIe Gen4 |
| Launched | 2023 |
Datasheet spec for the L40S variant. Source: resources.nvidia.com.
Compare L40S configurations
L40S purchase prices · Rent or buy calculator · Compare two GPUs
- RunPod L40S pricing
- Spheron L40S pricing
- Massed Compute L40S pricing
- Koyeb L40S pricing
- Nebius L40S pricing
- Crusoe L40S pricing
- DigitalOcean L40S pricing
- DataCrunch L40S pricing
- Scaleway L40S pricing
- Vultr L40S pricing
- OVHcloud L40S pricing
- AWS L40S pricing
- Modal L40S pricing
- Cerebrium L40S pricing
- CoreWeave L40S pricing
- Replicate L40S pricing
LLM memory estimates for this GPU
These models have an estimated inference footprint within 48 GB at one or more precisions. The scenario uses 4,096 tokens, batch 1, a 16-bit KV cache and 20% runtime headroom. A memory fit does not establish speed or software compatibility.
| Model | 16-bit GB | 8-bit GB | 4-bit GB |
|---|---|---|---|
| Qwen2.5 0.5B | 1.2 ✓ | 0.7 ✓ | 0.4 ✓ |
| Qwen2.5 1.5B | 3.8 ✓ | 2.0 ✓ | 1.1 ✓ |
| Qwen2.5 3B | 7.6 ✓ | 3.9 ✓ | 2.0 ✓ |
| Qwen2.5 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| Qwen2.5 14B | 36.4 ✓ | 18.7 ✓ | 9.8 ✓ |
| Qwen2.5 32B | 79.9 | 40.6 ✓ | 20.9 ✓ |
| Qwen2.5 72B | 176.1 | 88.9 | 45.2 ✓ |
| Qwen2.5 Coder 0.5B | 1.2 ✓ | 0.7 ✓ | 0.4 ✓ |
| Qwen2.5 Coder 1.5B | 3.8 ✓ | 2.0 ✓ | 1.1 ✓ |
| Qwen2.5 Coder 3B | 7.6 ✓ | 3.9 ✓ | 2.0 ✓ |
| Qwen2.5 Coder 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| Qwen2.5 Coder 14B | 36.4 ✓ | 18.7 ✓ | 9.8 ✓ |
| Qwen2.5 Coder 32B | 79.9 | 40.6 ✓ | 20.9 ✓ |
| Qwen3 0.6B | 2.4 ✓ | 1.5 ✓ | 1.0 ✓ |
| Qwen3 1.7B | 5.4 ✓ | 3.0 ✓ | 1.8 ✓ |
| Qwen3 4B | 10.4 ✓ | 5.6 ✓ | 3.1 ✓ |
| Qwen3 8B | 20.4 ✓ | 10.6 ✓ | 5.6 ✓ |
| Qwen3 14B | 36.2 ✓ | 18.5 ✓ | 9.7 ✓ |
| Qwen3 32B | 79.9 | 40.6 ✓ | 20.9 ✓ |
| Qwen3 30B A3B | 73.8 | 37.1 ✓ | 18.8 ✓ |
| DeepSeek R1 Distill Qwen 1.5B | 4.4 ✓ | 2.3 ✓ | 1.2 ✓ |
| DeepSeek R1 Distill Qwen 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| DeepSeek R1 Distill Qwen 14B | 36.4 ✓ | 18.7 ✓ | 9.8 ✓ |
| DeepSeek R1 Distill Qwen 32B | 79.9 | 40.6 ✓ | 20.9 ✓ |
| DeepSeek R1 Distill Llama 8B | 19.9 ✓ | 10.3 ✓ | 5.5 ✓ |
| DeepSeek R1 Distill Llama 70B | 170.9 | 86.3 | 43.9 ✓ |
| Mistral 7B v0.3 | 18.0 ✓ | 9.3 ✓ | 5.0 ✓ |
| Mixtral 8x7B v0.1 | 112.7 | 56.7 | 28.7 ✓ |
| Mistral Small 24B 2501 | 57.4 | 29.1 ✓ | 14.9 ✓ |
| Mistral Nemo 2407 | 30.2 ✓ | 15.5 ✓ | 8.2 ✓ |
| phi 4 | 36.2 ✓ | 18.6 ✓ | 9.8 ✓ |
Compare model memory requirements or change context and memory assumptions on a model's page.
When to choose L40S
Use the model memory estimates above to check whether your weights, context and batch size fit within 48 GB. Then compare the exact variant, node size and software support. Capacity alone does not establish inference speed or training throughput.
If your workload fits within 32 GB, compare RTX PRO 4500 rental prices from $0.72/GPU-hour. The smaller memory budget is the trade-off; price alone does not make the cards interchangeable.
L40S price changes
- 30 days: 1.0% across 10 matching firm-price configurations since 2026-09-06.
- 90 days: -3.3% across 9 matching firm-price configurations since 2026-07-08.
Changes use the geometric mean of price ratios for the same provider, variant, tier, GPU count, instance and region. New listings are not counted as price changes.
Price history
on-demand rate per day · median on-demand rate per day (dashed), since 2026-07-05: $0.38 low · $0.99 high. Full ledger on the history hub.
FAQ
The cheapest L40S rental we have is $0.96 per GPU-hour on Spheron (on-demand), updated 2026-10-06.
48 GB.
Spheron has the cheapest verified on-demand rate today at $0.96 per GPU-hour; interruptible spot/community capacity starts at $0.79. Verified 2026-10-06.
Related
All 48 GB+ GPUs · GPUs under $1/hr · Price movers this week · Spheron review · A100 vs L40S · L4 vs L40S · L40S vs RTX 4090 · Best Cloud GPU to Rent for Stable Diffusion & ComfyUI · Cloud GPU for batch inference
Should you rent or buy?
Compare L40S purchase prices and quote availability, then enter your usage and electricity costs in the rent-versus-buy calculator. Purchase listings have their own variants, stock status and update dates.