Side-by-side pricing across 13 marketplace listings. The L40 is 0.6% cheaper at median.
Side-by-side technical and market data. All prices in USD, listing-weighted median.
| Metric | L4 | L40 |
|---|---|---|
| Median Price (USD/hr) | $0.87 | $0.86 |
| Marketplaces Tracking | 7 | 6 |
| VRAM | 24 GB | 48 GB |
| FP16 TFLOPS (dense) | 121 | 181 |
| Category | Datacenter GPUs | |
See individual pages: L4 pricing · L40 pricing
Total rental cost at the listing-weighted median price for each GPU.
| Duration | L4 | L40 | You Save |
|---|---|---|---|
| 1 hour | $0.87 | $0.86 | $0.005 |
| 1 day (24h) | $20.76 | $20.64 | $0.12 |
| 1 week (168h) | $145.34 | $144.48 | $0.84 |
| 1 month (730h) | $631.52 | $627.80 | $3.65 |
Over a typical month, choosing the L40 saves $3.65 compared to the L4. That's a 0.6% cost reduction.
Decision logic based on workload type, derived from VRAM and FP16 compute heuristics.
48GB VRAM vs 24GB — fits larger models.
210.47 TFLOPS/$ vs 139.87 — better cost efficiency.
Marketplace partners carrying these GPUs, with their pricing for each side.
| Marketplace | L4 | L40 |
|---|---|---|
| RunPod | $0.49 | $0.82 |
Other Datacenter GPUs GPU comparisons with similar price profiles.
Track L4 and L40 rental pricing across every marketplace, updated daily.