Loading...
Side-by-side pricing across 12 marketplace listings. The L40 is 73.5% cheaper at median.
Side-by-side technical and market data. All prices in USD, AIMC reference price (median across marketplaces).
| Metric | H100 | L40 |
|---|---|---|
| Median Price (USD/hr) | $3.39 | $0.90 |
| Marketplaces Tracking | 6 | 6 |
| VRAM | — | 48 GB |
| FP16 TFLOPS (dense) | — | 181 |
| Category | Datacenter GPUs | |
See individual pages: H100 pricing · L40 pricing
Total rental cost at the AIMC reference price for each GPU.
| Duration | H100 | L40 | You Save |
|---|---|---|---|
| 1 hour | $3.39 | $0.90 | $2.493 |
| 1 day (24h) | $81.43 | $21.60 | $59.83 |
| 1 week (168h) | $569.99 | $151.20 | $418.82 |
| 1 month (730h) | $2,476.74 | $657.00 | $1,819.89 |
Over a typical month, choosing the L40 saves $1,819.89 compared to the H100. That's a 73.5% cost reduction.
Decision logic based on workload type, derived from VRAM and FP16 compute heuristics.
Insufficient spec data — see individual GPU pages.
Lower hourly cost — better cost efficiency for inference at scale.
Marketplace partners carrying these GPUs, with their pricing for each side.
| Marketplace | H100 | L40 |
|---|---|---|
| Massed Compute | $2.73 | $0.86 |
| DataOorts | $3.67 | $0.91 |
Other Datacenter GPUs GPU comparisons with similar price profiles.
Track H100 and L40 rental pricing across authorized marketplaces, updated daily.