gpu catalog: rtx 4000 ada
Single-slot, 130 W, 20 GB: a compact card for quantized 13B inference, batch embeddings, and CI workloads.
| GPU | VRAM | Regions | Availability | Price / GPU | |
|---|---|---|---|---|---|
| RTX 4000 ADA | 20G | — | out of stock | — | |
RTX 4000 Ada is out of stock right now — these are live: Single-slot, 130 W, 20 GB: a compact card for quantized 13B inference, batch embeddings, and CI workloads. VRAM20 GB GDDR6 Memory bandwidth0.4 TB/s ArchitectureAda Lovelace InterconnectPCIe 4.0 Board power130 W CUDA cores6,144 Released2023 | |||||
| L40S | 48G | 4 regions | high availability | $0.80/hr | launch |
| L40 | 48G | 2 regions | high availability | $0.78/hr | launch |
| RTX PRO 6000 | 96G | 5 regions | high availability | $1.99/hr | launch |
| RTX 5090community | 32G | 8 regions | high availability | $0.35/hr | launch |
| RTX 6000 ADA | 48G | 2 regions | high availability | $0.65/hr | launch |
| RTX 4090community | 24G | 8 regions | high availability | $0.27/hr | launch |
| RTX A6000 | 48G | 2 regions | high availability | $0.45/hr | launch |
| A100 | 80G | 6 regions | high availability | $1.07/hr | launch |
| RTX PRO 4500 | 32G | 2 regions | high availability | $0.72/hr | launch |
| H100 SXM | 80G | 5 regions | high availability | $3.49/hr | launch |
| H200 SXMcommunity | 141G | 5 regions | high availability | $3.59/hr | launch |
| H200 SXM | 141G | 6 regions | high availability | $3.99/hr | launch |
| RTX 3090community | 24G | 6 regions | high availability | $0.12/hr | launch |
| A100community | 80G | 5 regions | high availability | $0.88/hr | launch |
| H100 PCIE | 80G | 2 regions | high availability | $1.98/hr | launch |
| RTX A4000community | 16G | 5 regions | available | $0.07/hr | launch |
| RTX 5080community | 16G | 7 regions | available | $0.16/hr | launch |
| L40Scommunity | 48G | 4 regions | available | $0.79/hr | launch |
| L4 | 24G | 4 regions | available | $0.44/hr | launch |
| A100 40GBcommunity | 40G | 6 regions | available | $0.56/hr | launch |
| RTX 4090 | 24G | 3 regions | available | $0.74/hr | launch |
| RTX 5090 | 32G | 2 regions | available | $0.99/hr | launch |
| RTX 3080community | 10G | 5 regions | available | $0.10/hr | launch |
| H100 NVL | 94G | 3 regions | available | $3.19/hr | launch |
| B200 | 192G | 3 regions | available | $6.79/hr | launch |
| B300 | 288G | 2 regions | available | $7.89/hr | launch |
| H200 NVLcommunity | 141G | 3 regions | available | $3.98/hr | launch |
| H100 PCIEcommunity | 80G | 2 regions | available | $2.13/hr | launch |
| RTX 2000 ADA | 16G | 2 regions | running low | $0.24/hr | launch |
| A40 | 48G | 2 regions | running low | $0.49/hr | launch |
| RTX 6000 ADAcommunity | 48G | 1 region | running low | $0.74/hr | launch |
| L4community | 24G | 2 regions | running low | $0.27/hr | launch |
| H100 SXMcommunity | 80G | 2 regions | running low | $2.27/hr | launch |
| RTX A5000community | 24G | 2 regions | running low | $0.23/hr | launch |
| RTX 4080community | 16G | 3 regions | running low | $0.18/hr | launch |
| B200community | 192G | 1 region | running low | $6.63/hr | launch |
| A100 40GB | 40G | 1 region | running low | $0.89/hr | launch |
| H100 NVLcommunity | 94G | 2 regions | running low | $2.71/hr | launch |
| V100community | 16G | 1 region | running low | $0.27/hr | launch |
| RTX PRO 4500community | 32G | 1 region | running low | $0.30/hr | launch |
| RTX A6000community | 48G | 1 region | running low | $0.41/hr | launch |
lowest live on-demand rate per GPU, refreshed continuously · per-second billing
faq
RTX 4000 Ada capacity is temporarily out of stock on GPU.ai. When available, pricing is the provider's raw rate with zero markup, billed per second. Check this page again. Stock and prices refresh continuously.
The NVIDIA RTX 4000 Ada Generation has 20 GB of GDDR6 memory with up to 360 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.
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.