gpu catalog: rtx 5090
The fastest consumer GPU ever shipped: 32 GB of GDDR7 at 1.8 TB/s, and the best raw price/performance for single-GPU inference today.
| GPU | VRAM | Regions | Availability | Price / GPU | |
|---|---|---|---|---|---|
| RTX 5090community | 32G | 7 regions | high availability | $0.37/hr | launch |
The fastest consumer GPU ever shipped: 32 GB of GDDR7 at 1.8 TB/s, and the best raw price/performance for single-GPU inference today. VRAM32 GB GDDR7 Memory bandwidth1.8 TB/s ArchitectureBlackwell InterconnectPCIe 5.0 Board power575 W CUDA cores21,760 Released2025 Regionsasia-pacific, ca-central, eu-east, eu-west, us-central, us-east | |||||
| RTX 5090 | 32G | 1 region | running low | $0.99/hr | launch |
| L40S | 48G | 3 regions | high availability | $0.80/hr | launch |
| L40 | 48G | 2 regions | high availability | $0.78/hr | launch |
| RTX A6000 | 48G | 1 region | high availability | $0.45/hr | launch |
| RTX PRO 6000 | 96G | 4 regions | high availability | $1.99/hr | launch |
| A100 | 80G | 5 regions | high availability | $1.07/hr | launch |
| RTX 4090community | 24G | 7 regions | high availability | $0.31/hr | launch |
| RTX 6000 ADA | 48G | 1 region | high availability | $0.65/hr | launch |
| A100community | 80G | 7 regions | high availability | $0.95/hr | launch |
| RTX PRO 4500 | 32G | 2 regions | high availability | $0.72/hr | launch |
| H200 SXMcommunity | 141G | 5 regions | high availability | $3.59/hr | launch |
| H100 SXM | 80G | 5 regions | high availability | $2.54/hr | launch |
| H200 SXM | 141G | 6 regions | high availability | $3.99/hr | launch |
| RTX 3090community | 24G | 7 regions | high availability | $0.15/hr | launch |
| RTX A4000community | 16G | 5 regions | available | $0.08/hr | launch |
| L4 | 24G | 4 regions | available | $0.44/hr | launch |
| RTX 4090 | 24G | 3 regions | available | $0.74/hr | launch |
| L40Scommunity | 48G | 4 regions | available | $0.61/hr | launch |
| H100 NVLcommunity | 94G | 4 regions | available | $2.59/hr | launch |
| H100 SXMcommunity | 80G | 4 regions | available | $1.87/hr | launch |
| H200 NVLcommunity | 141G | 5 regions | available | $3.47/hr | launch |
| RTX 3080community | 10G | 3 regions | available | $0.07/hr | launch |
| H100 NVL | 94G | 3 regions | available | $3.19/hr | launch |
| B200 | 192G | 2 regions | available | $6.79/hr | launch |
| B300 | 288G | 2 regions | available | $7.89/hr | launch |
| A100 40GBcommunity | 40G | 5 regions | available | $0.67/hr | launch |
| H100 PCIE | 80G | 2 regions | available | $1.98/hr | launch |
| H100 PCIEcommunity | 80G | 2 regions | available | $2.48/hr | launch |
| RTX 5080community | 16G | 6 regions | running low | $0.17/hr | launch |
| RTX 4080community | 16G | 4 regions | running low | $0.17/hr | launch |
| RTX A5000community | 24G | 2 regions | running low | $0.23/hr | launch |
| B200community | 192G | 2 regions | running low | $5.32/hr | launch |
| L4community | 24G | 2 regions | running low | $0.27/hr | launch |
| RTX PRO 6000community | 96G | 1 region | running low | $1.69/hr | launch |
| RTX A6000community | 48G | 2 regions | running low | $0.42/hr | launch |
| H200 NVL | 141G | 1 region | running low | $3.29/hr | launch |
| V100community | 16G | 1 region | running low | $0.17/hr | launch |
lowest live on-demand rate per GPU, refreshed continuously · per-second billing
| Provider | Price / GPU / hr | Notes |
|---|---|---|
| GPU.ai (Secure Cloud) | $0.990/hr | Vetted data center capacity, per-second billing |
| GPU.ai (Community Cloud) | $0.370/hr | Marketplace capacity from independent suppliers |
| CoreWeave | — | Public on-demand list rate |
| AWS | — | Public on-demand list rate |
| Azure | — | 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
faq
RTX 5090 cloud instances on GPU.ai currently start at $0.370 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 GeForce RTX 5090 has 32 GB of GDDR7 memory with up to 1,792 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 16× RTX 5090 nodes are launchable right now, from $0.881 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.