Loading...
Side-by-side pricing across 11 marketplace listings. The L40 is 76% cheaper at median.
Side-by-side technical and market data. All prices in USD, AIMC reference price (median across marketplaces).
| Metric | H200 NVL | L40 |
|---|---|---|
| Median Price (USD/hr) | $3.71 | $0.89 |
| Marketplaces Tracking | 4 | 7 |
| VRAM | 141 GB | 48 GB |
| FP16 TFLOPS (dense) | 989 | 181 |
| Category | Datacenter GPUs | |
See individual pages: H200 NVL pricing · L40 pricing
Total rental cost at the AIMC reference price for each GPU.
| Duration | H200 NVL | L40 | You Save |
|---|---|---|---|
| 1 hour | $3.71 | $0.89 | $2.815 |
| 1 day (24h) | $88.92 | $21.36 | $67.56 |
| 1 week (168h) | $622.44 | $149.52 | $472.92 |
| 1 month (730h) | $2,704.65 | $649.70 | $2,054.95 |
Over a typical month, choosing the L40 saves $2,054.95 compared to the H200 NVL. That's a 76% cost reduction.
Decision logic based on workload type, derived from VRAM and FP16 compute heuristics.
141GB VRAM vs 48GB — fits larger models.
266.94 TFLOPS/$ vs 203.37 — better cost efficiency.
Marketplace partners carrying these GPUs, with their pricing for each side.
| Marketplace | H200 NVL | L40 |
|---|---|---|
| QuantaCloud | $3.43 | $0.94 |
| Massed Compute | $3.62 | $0.86 |
| RunPod | $3.79 | $0.82 |
Other Datacenter GPUs GPU comparisons with similar price profiles.
Track H200 NVL and L40 rental pricing across every marketplace, updated daily.