gpu catalog: l40s
The universal data center Ada card: 48 GB and strong FP8 throughput make it a favorite for mixed inference, fine-tuning, and rendering fleets.
| GPU | VRAM | Regions | Availability | Price / GPU | |
|---|---|---|---|---|---|
| L40S | 48G | 4 regions | high availability | $0.80/hr | launch |
The universal data center Ada card: 48 GB and strong FP8 throughput make it a favorite for mixed inference, fine-tuning, and rendering fleets. VRAM48 GB GDDR6 Memory bandwidth0.9 TB/s FP16 tensor183 TFLOPS ArchitectureAda Lovelace InterconnectPCIe 4.0 Board power350 W CUDA cores18,176 Released2023 Regionsasia-pacific, eu-west, us-central, us-east | |||||
| L40Scommunity | 48G | 5 regions | available | $0.61/hr | launch |
| RTX PRO 6000 | 96G | 5 regions | high availability | $1.99/hr | launch |
| L40 | 48G | 2 regions | high availability | $0.78/hr | launch |
| RTX A6000 | 48G | 2 regions | high availability | $0.40/hr | launch |
| RTX 4090community | 24G | 7 regions | high availability | $0.31/hr | launch |
| A100 | 80G | 5 regions | high availability | $1.07/hr | launch |
| RTX 5090community | 32G | 7 regions | high availability | $0.35/hr | launch |
| RTX 6000 ADA | 48G | 2 regions | high availability | $0.65/hr | launch |
| RTX PRO 6000community | 96G | 4 regions | high availability | $1.69/hr | launch |
| A100community | 80G | 6 regions | high availability | $0.95/hr | launch |
| H200 SXMcommunity | 141G | 5 regions | high availability | $3.59/hr | launch |
| RTX PRO 4500 | 32G | 1 region | high availability | $0.72/hr | launch |
| H200 SXM | 141G | 6 regions | high availability | $3.99/hr | launch |
| H100 SXM | 80G | 5 regions | high availability | $2.54/hr | launch |
| RTX 3090community | 24G | 6 regions | high availability | $0.15/hr | launch |
| RTX 4090 | 24G | 4 regions | high availability | $0.74/hr | launch |
| RTX A4000community | 16G | 5 regions | available | $0.08/hr | launch |
| L4 | 24G | 4 regions | available | $0.44/hr | launch |
| H100 NVLcommunity | 94G | 5 regions | available | $2.37/hr | launch |
| H200 NVLcommunity | 141G | 5 regions | available | $3.47/hr | launch |
| A100 40GBcommunity | 40G | 5 regions | available | $0.67/hr | launch |
| RTX 3080community | 10G | 3 regions | available | $0.07/hr | launch |
| H100 PCIE | 80G | 2 regions | available | $1.98/hr | launch |
| H100 NVL | 94G | 3 regions | available | $3.19/hr | launch |
| H100 SXMcommunity | 80G | 3 regions | available | $1.87/hr | launch |
| H100 PCIEcommunity | 80G | 2 regions | available | $2.54/hr | launch |
| B200community | 192G | 3 regions | available | $5.32/hr | launch |
| RTX 5080community | 16G | 5 regions | running low | $0.16/hr | launch |
| RTX 4080community | 16G | 4 regions | running low | $0.17/hr | launch |
| A40 | 48G | 2 regions | running low | $0.49/hr | launch |
| RTX 5090 | 32G | 2 regions | running low | $0.99/hr | launch |
| B200 | 192G | 1 region | running low | $6.79/hr | launch |
| B300 | 288G | 2 regions | running low | $7.89/hr | launch |
| RTX A5000community | 24G | 4 regions | running low | $0.15/hr | launch |
| L4community | 24G | 2 regions | running low | $0.27/hr | launch |
| RTX A6000community | 48G | 3 regions | running low | $0.41/hr | launch |
| RTX 3090 | 24G | 1 region | running low | $0.50/hr | launch |
| H200 NVL | 141G | 1 region | running low | $3.29/hr | launch |
| A100 40GB | 40G | 1 region | running low | $0.89/hr | launch |
lowest live on-demand rate per GPU, refreshed continuously · per-second billing
| Provider | Price / GPU / hr | Notes |
|---|---|---|
| GPU.ai (Secure Cloud) | $0.800/hr | Vetted data center capacity, per-second billing |
| GPU.ai (Community Cloud) | $0.610/hr | Marketplace capacity from independent suppliers |
| CoreWeave | $2.25/hr | Public on-demand list rate |
| AWS | $1.86/hr | Public on-demand list rate |
| Azure | $2.50/hr | Public on-demand list rate |
competitor rates are public on-demand list prices, refreshed daily · gpu.ai prices are live floor rates with zero markup · market data via Compute Prices
faq
L40S cloud instances on GPU.ai currently start at $0.610 per GPU per hour, billed per second. That is the live floor price across every provider in our fleet. We route your launch to the cheapest provider with stock and add zero markup.
The NVIDIA L40S has 48 GB of GDDR6 memory with up to 864 GB/s of bandwidth. GPU.ai reports the minimum VRAM actually delivered across our fleet, so the figure you see at launch is the figure you get.
Yes: real 8× L40S nodes are launchable right now, from $0.800 per GPU per hour. We only advertise node sizes that exist in live inventory, not theoretical configurations.
GPU.ai aggregates a dozen-plus GPU clouds and passes through each provider's raw price with no markup, so the same silicon is typically far cheaper than hyperscaler list rates. The comparison table on this page shows the current public on-demand list prices side by side.
Billing is per second, starting when your instance is SSH-ready and stopping the moment you terminate. There are no minimum commitments, no reservation fees, and no egress surprises: you pay the listed hourly rate pro-rated to the second.