Available in synchronized catalog
L40S
Asia-Pacific / Community
- GPUs per machine
- 1
- VRAM per GPU
- 48 GB
- vCPU
- 24
- System RAM
- 252 GB
- Storage
- 131 GB
USD 0.90 / machine-hour
Evaluate NVIDIA L40S for inference, rendering, and AI development. Compare the exact configurations below using synchronized customer prices, not a fixed promotional rate.
Latest successful catalog synchronization: . This is a synchronized snapshot, not a reservation or a guarantee of capacity at launch. Prices and availability may change.
Catalog VRAM per GPU: 48 GB.
From USD 0.88 / machine-hour (1 GPU)
Available in synchronized catalog
Asia-Pacific / Community
USD 0.90 / machine-hour
Available in synchronized catalog
Asia-Pacific / Secure
USD 1.20 / machine-hour
Available in synchronized catalog
EU East / Community
USD 0.91 / machine-hour
Available in synchronized catalog
EU West / Secure
USD 1.20 / machine-hour
Available in synchronized catalog
US Central / Secure
USD 0.88 / machine-hour
Available in synchronized catalog
Asia-Pacific / Community
USD 1.78 / machine-hour
Available in synchronized catalog
US Central / Secure
USD 1.76 / machine-hour
Available in synchronized catalog
Asia-Pacific / Community
USD 3.54 / machine-hour
Available in synchronized catalog
US Central / Secure
USD 3.52 / machine-hour
Available in synchronized catalog
US Central / Secure
USD 7.04 / machine-hour
Benchmark your chosen precision and batch size. Multiple GPUs do not automatically combine into one memory pool.
For inference, rendering, and AI development, test a representative workload before committing to a larger deployment. Check model weights, runtime allocations, context or scene size, and any application licensing requirements.
The displayed rate covers one machine with the listed GPU count. VRAM is per GPU, not system RAM or automatically pooled memory. Prices are customer-facing catalog rates; account-specific terms and configuration changes must be reviewed in the Marketplace before launch.
The public feed chooses the lowest USD customer rate within each model, GPU count, VRAM, region, and capacity class. CPU, RAM, and storage describe that selected listing, not every machine in the region. The number of rows is not a count of available machines.
Read the GPU cloud guide and SSH guide to prepare the software environment and access settings. Capacity shown here is not reserved by viewing the page.