Kovara
Loading your page…
You can continue using the navigation while this page loads.
You can continue using the navigation while this page loads.
B200 SXM 180GB has 275% more memory than L40 48GB (180 GB vs 48 GB). Its memory bandwidth is 826% more (8 vs 0.864 TB/s). In the cloud, the median on-demand B200 SXM 180GB price is $6.87 per GPU-hour against $0.86 for the L40 48GB. Per gigabyte of GPU memory, that is $0.038 vs $0.018 per hour.
Manufacturer figures as recorded by Kovara. Higher memory and bandwidth are highlighted; neither is a benchmark of your workload.
| B200 SXM 180GB | L40 48GB | |
|---|---|---|
| Manufacturer | NVIDIA | NVIDIA |
| Architecture | Blackwell | Ada Lovelace |
| Memory | 180 GB HBM3E | 48 GB GDDR6 |
| Memory bandwidth | 8 TB/s | 0.864 TB/s |
| Power (TDP) | 1000 W | 300 W |
| Form factor | SXM | PCIe dual-slot FHFL |
Public offers Kovara tracks, normalised to US dollars per GPU-hour. Prices use on-demand terms where available; spot and reserved offers are on each GPU’s price pages. Lower is highlighted.
| B200 SXM 180GB | L40 48GB | |
|---|---|---|
| Lowest price | $5.43 | $0.79 |
| Median price | $6.87 | $0.86 |
| Highest price | $8.60 | $1.25 |
| Median per GB of memory | $0.038 | $0.018 |
| Public offers (all terms) | 30 | 13 |
| Providers | 11 | 5 |
Lowest tracked price per provider. Open a provider to see every offer, region and term.
Right now the cheapest on-demand B200 SXM 180GB Kovara tracks is $5.43 per GPU-hour and the cheapest L40 48GB is $0.79. Medians are $6.87 and $0.86. The cheaper GPU per hour is not always cheaper per job: a faster or larger GPU can finish sooner or need fewer units.
The B200 SXM 180GB has more memory: 180 GB against 48 GB. Memory decides which models and batch sizes fit on one GPU.
No. This page compares manufacturer specifications and public prices. Real performance depends on the model, precision, software and interconnect. Kova can help you estimate cost for a specific workload.