Loading...
Side-by-side pricing across 9 marketplace listings. The A40 is 37.8% cheaper at median.
Side-by-side technical and market data. All prices in USD, listing-weighted median.
| Metric | A40 | L40 |
|---|---|---|
| Median Price (USD/hr) | $0.54 | $0.86 |
| Marketplaces Tracking | 4 | 5 |
| VRAM | 48 GB | 48 GB |
| FP16 TFLOPS (dense) | 150 | 181 |
| Category | Datacenter GPUs | |
See individual pages: A40 pricing · L40 pricing
Total rental cost at the listing-weighted median price for each GPU.
| Duration | A40 | L40 | You Save |
|---|---|---|---|
| 1 hour | $0.54 | $0.86 | $0.325 |
| 1 day (24h) | $12.84 | $20.64 | $7.80 |
| 1 week (168h) | $89.88 | $144.48 | $54.60 |
| 1 month (730h) | $390.55 | $627.80 | $237.25 |
Over a typical month, choosing the A40 saves $237.25 compared to the L40. That's a 37.8% cost reduction.
Decision logic based on workload type, derived from VRAM and FP16 compute heuristics.
181 FP16 TFLOPS vs 150 — faster gradient compute.
280.37 TFLOPS/$ vs 210.47 — better cost efficiency.
Marketplace partners carrying these GPUs, with their pricing for each side.
| Marketplace | A40 | L40 |
|---|---|---|
| RunPod | $0.44 | $0.82 |
| Hyperstack | $1.16 | $1.00 |
Other Datacenter GPUs GPU comparisons with similar price profiles.
Track A40 and L40 rental pricing across every marketplace, updated daily.