Loading...
Side-by-side pricing across 28 marketplace listings. The L40S is 79% cheaper at median.
Side-by-side technical and market data. All prices in USD, AIMC reference price (median across marketplaces).
| Metric | B200 SXM | L40S |
|---|---|---|
| Median Price (USD/hr) | $6.05 | $1.27 |
| Marketplaces Tracking | 15 | 13 |
| VRAM | 192 GB | 48 GB |
| FP16 TFLOPS (dense) | — | 366 |
| Category | Datacenter GPUs | |
See individual pages: B200 SXM pricing · L40S pricing
Total rental cost at the AIMC reference price for each GPU.
| Duration | B200 SXM | L40S | You Save |
|---|---|---|---|
| 1 hour | $6.05 | $1.27 | $4.78 |
| 1 day (24h) | $145.20 | $30.48 | $114.72 |
| 1 week (168h) | $1,016.40 | $213.36 | $803.04 |
| 1 month (730h) | $4,416.50 | $927.10 | $3,489.40 |
Over a typical month, choosing the L40S saves $3,489.40 compared to the B200 SXM. That's a 79% cost reduction.
Decision logic based on workload type, derived from VRAM and FP16 compute heuristics.
192GB VRAM vs 48GB — fits larger models.
Insufficient spec data — see individual GPU pages.
Marketplace partners carrying these GPUs, with their pricing for each side.
| Marketplace | B200 SXM | L40S |
|---|---|---|
| Hydra Host | $4.25 | $0.95 |
| io.net | $4.99 | $0.89 |
| Massed Compute | $5.43 | $0.97 |
| UpCloud | $6.05 | $1.27 |
| Packet.ai | $6.99 | $0.92 |
| Qubrid AI | $5.63 | $2.48 |
| RunPod | $7.99 | $1.09 |
| Verda | $7.80 | $1.69 |
Other Datacenter GPUs GPU comparisons with similar price profiles.
Track B200 SXM and L40S rental pricing across every marketplace, updated daily.