gpu catalog: rtx 4090
The community-cloud staple: consumer Ada with 24 GB, still one of the best price/performance ratios for quantized LLM inference.
| GPU | VRAM | Regions | Availability | Price / GPU | |
|---|---|---|---|---|---|
| RTX 4090community | 24G | 7 regions | high availability | $0.34/hr | launch |
The community-cloud staple: consumer Ada with 24 GB, still one of the best price/performance ratios for quantized LLM inference. VRAM24 GB GDDR6X Memory bandwidth1.0 TB/s ArchitectureAda Lovelace InterconnectPCIe 4.0 Board power450 W CUDA cores16,384 Released2022 Regionsasia-pacific, ca-central, eu-east, eu-west, us-central, us-east | |||||
| RTX 4090 | 24G | 3 regions | available | $0.74/hr | launch |
| L40S | 48G | 4 regions | high availability | $0.80/hr | launch |
| RTX 5090community | 32G | 8 regions | high availability | $0.44/hr | launch |
| A100 | 80G | 6 regions | high availability | $1.07/hr | launch |
| RTX PRO 6000 | 96G | 4 regions | high availability | $2.09/hr | launch |
| RTX 3090community | 24G | 7 regions | high availability | $0.15/hr | launch |
| H100 SXM | 80G | 5 regions | high availability | $3.49/hr | launch |
| RTX A6000 | 48G | 3 regions | available | $0.40/hr | launch |
| RTX 6000 ADA | 48G | 2 regions | available | $0.65/hr | launch |
| H100 PCIE | 80G | 2 regions | available | $1.98/hr | launch |
| A100 40GBcommunity | 40G | 6 regions | available | $0.40/hr | launch |
| RTX A4000 | 16G | 1 region | available | $0.12/hr | launch |
| L4 | 24G | 3 regions | available | $0.49/hr | launch |
| RTX PRO 4500 | 32G | 2 regions | available | $0.72/hr | launch |
| RTX A4000community | 16G | 4 regions | available | $0.09/hr | launch |
| H200 SXMcommunity | 141G | 3 regions | available | $3.59/hr | launch |
| RTX 5080community | 16G | 6 regions | available | $0.25/hr | launch |
| RTX 3080community | 10G | 4 regions | available | $0.11/hr | launch |
| L40 | 48G | 3 regions | available | $0.78/hr | launch |
| H200 SXM | 141G | 3 regions | available | $4.59/hr | launch |
| B300 | 288G | 2 regions | available | $7.89/hr | launch |
| H100 NVLcommunity | 94G | 5 regions | available | $2.59/hr | launch |
| A100community | 80G | 4 regions | available | $0.96/hr | launch |
| RTX 4000 ADAcommunity | 20G | 2 regions | running low | $0.20/hr | launch |
| RTX 2000 ADA | 16G | 2 regions | running low | $0.24/hr | launch |
| RTX A5000 | 24G | 2 regions | running low | $0.27/hr | launch |
| RTX 4000 ADA | 20G | 2 regions | running low | $0.28/hr | launch |
| A40 | 48G | 2 regions | running low | $0.49/hr | launch |
| RTX 3090 | 24G | 2 regions | running low | $0.50/hr | launch |
| L40community | 48G | 2 regions | running low | $0.69/hr | launch |
| RTX PRO 6000community | 96G | 1 region | running low | $1.69/hr | launch |
| B200 | 192G | 2 regions | running low | $6.79/hr | launch |
| RTX 4080community | 16G | 3 regions | running low | $0.21/hr | launch |
| L4community | 24G | 3 regions | running low | $0.33/hr | launch |
| L40Scommunity | 48G | 1 region | running low | $0.80/hr | launch |
| RTX 5090 | 32G | 1 region | running low | $0.99/hr | launch |
| H100 NVL | 94G | 1 region | running low | $3.19/hr | launch |
| H200 NVL | 141G | 1 region | running low | $3.29/hr | launch |
| RTX A6000community | 48G | 1 region | running low | $0.41/hr | launch |
| H100 SXMcommunity | 80G | 1 region | running low | $3.73/hr | launch |
| H200 NVLcommunity | 141G | 2 regions | running low | $4.49/hr | launch |
| RTX PRO 4500community | 32G | 1 region | running low | $0.35/hr | launch |
| B200community | 192G | 1 region | running low | $9.38/hr | launch |
lowest live on-demand rate per GPU, refreshed continuously · per-second billing
Our floor price for the RTX 4090, sampled continuously across every provider in the fleet and rolled up to one point per day. A dot on the zero line is a day we checked and found nothing launchable; a shaded break is a day we did not sample. Those are different facts, so this chart never draws one as the other.
Daily trend, updated hourly · Full 15-minute history available via API
| Provider | Price / GPU / hr | Notes |
|---|---|---|
| GPU.ai (Secure Cloud) | $0.740/hr | Vetted data center capacity, per-second billing |
| GPU.ai (Community Cloud) | $0.335/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 4090 cloud instances on GPU.ai currently start at $0.335 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 4090 has 24 GB of GDDR6X memory with up to 1,008 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× RTX 4090 nodes are launchable right now, from $0.470 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.