Recommendation inference — user-item scoring queries per second per GPU. · DLRM-v2 · collaborative filtering · v4.1 / v5.0 · on-demand pricing
| GPU | Scenario | samp/s per GPU | |
|---|---|---|---|
| NVIDIA H200-SXM-141GB | Offline | 79,668 samp/s | |
| NVIDIA H100-SXM-80GB | Offline | 75,264 samp/s | |
| NVIDIA H200-SXM-141GB | Server | 73,151 samp/s | |
| NVIDIA H100-SXM-80GB | Server | 69,513 samp/s |
| Provider | GPU | Scenario | Price | samp/$ | |
|---|---|---|---|---|---|
| Nebius | NVIDIA H100-SXM-80GB | Offline | $2.15/GPU·hr 11m ago | 126,022,605 | |
| Lambda Labs | NVIDIA H200-SXM-141GB | Offline | $2.29/GPU·hr 11m ago | 125,241,878 | |
| Nebius | NVIDIA H200-SXM-141GB | Offline | $2.45/GPU·hr 11m ago | 117,062,816 | |
| Nebius | NVIDIA H100-SXM-80GB | Server | $2.15/GPU·hr 11m ago | 116,393,220 | |
| Lambda Labs | NVIDIA H200-SXM-141GB | Server | $2.29/GPU·hr 11m ago | 114,997,162 | |
| Nebius | NVIDIA H200-SXM-141GB | Server | $2.45/GPU·hr 11m ago | 107,487,143 | |
| Hyperstack | NVIDIA H200-SXM-141GB | Offline | $2.79/GPU·hr 11m ago | 102,797,097 | |
| Hyperstack | NVIDIA H100-SXM-80GB | Offline | $2.72/GPU·hr 11m ago | 99,613,456 | |
| Hyperstack | NVIDIA H200-SXM-141GB | Server | $2.79/GPU·hr 11m ago | 94,388,352 | |
| Hyperstack | NVIDIA H100-SXM-80GB | Server | $2.72/GPU·hr 11m ago | 92,001,994 | |
| RunPod | NVIDIA H100-SXM-80GB | Offline | $2.99/GPU·hr 11m ago | 90,618,261 | |
| RunPod | NVIDIA H100-SXM-80GB | Server | $2.99/GPU·hr 11m ago | 83,694,121 | |
| DigitalOcean | NVIDIA H200-SXM-141GB | Offline | $3.44/GPU·hr 11m ago | 83,373,227 | |
| DigitalOcean | NVIDIA H100-SXM-80GB | Offline | $3.39/GPU·hr 11m ago | 79,925,841 | |
| DigitalOcean | NVIDIA H200-SXM-141GB | Server | $3.44/GPU·hr 11m ago | 76,553,343 | |
| DigitalOcean | NVIDIA H100-SXM-80GB | Server | $3.39/GPU·hr 11m ago | 73,818,709 | |
| Crusoe | NVIDIA H100-SXM-80GB | Offline | $3.90/GPU·hr 11m ago | 69,474,000 | |
| Lambda Labs | NVIDIA H100-SXM-80GB | Offline | $3.99/GPU·hr 11m ago | 67,906,917 | |
| RunPod | NVIDIA H200-SXM-141GB | Offline | $4.39/GPU·hr 11m ago | 65,331,185 | |
| Crusoe | NVIDIA H100-SXM-80GB | Server | $3.90/GPU·hr 11m ago | 64,165,493 | |
| Lambda Labs | NVIDIA H100-SXM-80GB | Server | $3.99/GPU·hr 11m ago | 62,718,151 | |
| RunPod | NVIDIA H200-SXM-141GB | Server | $4.39/GPU·hr 11m ago | 59,987,130 | |
| Crusoe | NVIDIA H200-SXM-141GB | Offline | $6.00/GPU·hr 11m ago | 47,800,650 | |
| CoreWeave | NVIDIA H200-SXM-141GB | Offline | $6.31/GPU·hr 11m ago | 45,452,282 | |
| CoreWeave | NVIDIA H100-SXM-80GB | Offline | $6.16/GPU·hr 11m ago | 43,985,162 | |
| Crusoe | NVIDIA H200-SXM-141GB | Server | $6.00/GPU·hr 11m ago | 43,890,584 | |
| CoreWeave | NVIDIA H200-SXM-141GB | Server | $6.31/GPU·hr 11m ago | 41,734,311 | |
| CoreWeave | NVIDIA H100-SXM-80GB | Server | $6.16/GPU·hr 11m ago | 40,624,257 | |
| OCI (us-ashburn-1) | NVIDIA H200-SXM-141GB | Offline | $10.00/GPU·hr 56d ago | 28,680,390 | |
| OCI | NVIDIA H200-SXM-141GB | Offline | $10.00/GPU·hr 11m ago | 28,680,390 | |
| Azure (eastus2) | NVIDIA H200-SXM-141GB | Offline | $10.60/GPU·hr 11m ago | 27,056,972 | |
| GCP (us-central1) | NVIDIA H200-SXM-141GB | Offline | $10.84/GPU·hr 11m ago | 26,445,752 | |
| OCI (us-ashburn-1) | NVIDIA H200-SXM-141GB | Server | $10.00/GPU·hr 56d ago | 26,334,350 | |
| OCI | NVIDIA H200-SXM-141GB | Server | $10.00/GPU·hr 11m ago | 26,334,350 | |
| OCI (us-ashburn-1) | NVIDIA H100-SXM-80GB | Offline | $10.75/GPU·hr 56d ago | 25,204,521 | |
| OCI | NVIDIA H100-SXM-80GB | Offline | $10.75/GPU·hr 11m ago | 25,204,521 | |
| Azure (eastus2) | NVIDIA H200-SXM-141GB | Server | $10.60/GPU·hr 11m ago | 24,843,727 | |
| GCP (us-central1) | NVIDIA H200-SXM-141GB | Server | $10.84/GPU·hr 11m ago | 24,282,504 | |
| GCP (us-central1) | NVIDIA H100-SXM-80GB | Offline | $11.53/GPU·hr 11m ago | 23,506,003 | |
| OCI (us-ashburn-1) | NVIDIA H100-SXM-80GB | Server | $10.75/GPU·hr 56d ago | 23,278,644 | |
| OCI | NVIDIA H100-SXM-80GB | Server | $10.75/GPU·hr 11m ago | 23,278,644 | |
| AWS (us-east-1) | NVIDIA H100-SXM-80GB | Offline | $12.29/GPU·hr 11m ago | 22,046,265 | |
| Azure (eastus) | NVIDIA H100-SXM-80GB | Offline | $12.29/GPU·hr 11m ago | 22,046,265 | |
| Azure (eastus2) | NVIDIA H100-SXM-80GB | Offline | $12.29/GPU·hr 11m ago | 22,046,265 | |
| GCP (us-central1) | NVIDIA H100-SXM-80GB | Server | $11.53/GPU·hr 11m ago | 21,709,909 | |
| AWS (us-east-1) | NVIDIA H100-SXM-80GB | Server | $12.29/GPU·hr 11m ago | 20,361,711 | |
| Azure (eastus) | NVIDIA H100-SXM-80GB | Server | $12.29/GPU·hr 11m ago | 20,361,711 | |
| Azure (eastus2) | NVIDIA H100-SXM-80GB | Server | $12.29/GPU·hr 11m ago | 20,361,711 |