Cheapest NVIDIA GeForce RTX 4090 24GB for SDXL inference
24GB VRAM · 330 TFLOPS FP16 · 12GB min for SDXL inference
Best price: $0.240/hr/hr on Salad
on-demand · distributed · verify before purchasing
NVIDIA GeForce RTX 4090 24GB Prices — 13 offers
13 offers found
— from $0.240/hr
as of Apr 29, 2026, verify on provider site
Some links are affiliate links — we may earn a commission at no cost to you.Details.
| Provider | Configuration | Region | Billing | Availability | Price/hr | |
|---|---|---|---|---|---|---|
| Saladcheapest | 1x RTX 4090 | distributed | per-minute | on-demand | $0.240/hr | Rent → |
| vast | 1x RTX 4090 | eu-west | per-second | on-demand | $0.350/hr | Rent → |
| FluidStack | 1x RTX 4090 | eu-central | per-minute | on-demand | $0.440/hr | Rent → |
| RunPod | 1x RTX 4090 | us-east | per-second | on-demand | $0.440/hr | Rent → |
| DataCrunch | 1x RTX 4090 | eu-north | per-minute | on-demand | $0.490/hr | Rent → |
| TensorDock | 1x RTX 4090 | us-east | per-minute | on-demand | $0.490/hr | Rent → |
| Hyperstack | 1x RTX 4090 | eu-central | per-minute | on-demand | $0.550/hr | Rent → |
| genesis | 1x RTX 4090 | eu-central | per-minute | on-demand | $0.590/hr | Rent → |
| lambda | 1x RTX 4090 | us-west-1 | per-minute | on-demand | $0.790/hr | Rent → |
| together | 1x RTX 4090 | us-east | per-second | on-demand | $0.790/hr | Rent → |
| fal | 1x RTX 4090 | us-east | per-millisecond | on-demand | $0.890/hr | Rent → |
| Replicate | Nvidia RTX 4090 (24GB) | us-east | per-second | on-demand | $1.00/hr | Rent → |
| Modal | 1x RTX 4090 | us-east | per-second | on-demand | $1.10/hr | Rent → |
Compatibility
FAQ
Is the NVIDIA GeForce RTX 4090 24GB good for SDXL inference?
Yes. SDXL inference requires 12GB VRAM; the NVIDIA GeForce RTX 4090 24GB has 24GB.
What is the cheapest NVIDIA GeForce RTX 4090 24GB for SDXL inference?
Salad at $0.240/hr/hr (on-demand, distributed).
Last refresh: April 29, 2026. Verify on provider site.