Recommendation

Recommendation inference — user-item scoring queries per second per GPU. · DLRM-v2 · collaborative filtering · v4.1 / v5.0 / v5.1 / v6.0 · on-demand pricing

Throughput — per GPU

GPUScenariosamp/s per GPU
NVIDIA H200-SXM-141GBOffline79,668 samp/s
NVIDIA H100-SXM-80GBOffline75,264 samp/s
NVIDIA H200-SXM-141GBServer73,151 samp/s
NVIDIA H100-SXM-80GBServer69,513 samp/s

Efficiency — samp/$ · ranked

ProviderGPUScenarioPricesamp/$
Lambda LabsNVIDIA H200-SXM-141GBOffline$2.29/GPU·hr
19m ago
125,241,878
Lambda LabsNVIDIA H200-SXM-141GBServer$2.29/GPU·hr
19m ago
114,997,162
HyperstackNVIDIA H200-SXM-141GBOffline$2.79/GPU·hr
19m ago
102,797,097
HyperstackNVIDIA H100-SXM-80GBOffline$2.72/GPU·hr
19m ago
99,613,456
HyperstackNVIDIA H200-SXM-141GBServer$2.79/GPU·hr
19m ago
94,388,352
HyperstackNVIDIA H100-SXM-80GBServer$2.72/GPU·hr
19m ago
92,001,994
RunPodNVIDIA H100-SXM-80GBOffline$3.29/GPU·hr
19m ago
82,355,198
RunPodNVIDIA H100-SXM-80GBServer$3.29/GPU·hr
19m ago
76,062,439
NebiusNVIDIA H100-SXM-80GBOffline$3.85/GPU·hr
19m ago
70,376,260
CrusoeNVIDIA H100-SXM-80GBOffline$3.90/GPU·hr
19m ago
69,474,000
Lambda LabsNVIDIA H100-SXM-80GBOffline$3.99/GPU·hr
19m ago
67,906,917
NebiusNVIDIA H100-SXM-80GBServer$3.85/GPU·hr
19m ago
64,998,811
CrusoeNVIDIA H100-SXM-80GBServer$3.90/GPU·hr
19m ago
64,165,493
DigitalOceanNVIDIA H200-SXM-141GBOffline$4.47/GPU·hr
19m ago
64,161,946
NebiusNVIDIA H200-SXM-141GBOffline$4.50/GPU·hr
19m ago
63,734,200
Lambda LabsNVIDIA H100-SXM-80GBServer$3.99/GPU·hr
19m ago
62,718,151
RunPodNVIDIA H200-SXM-141GBOffline$4.59/GPU·hr
19m ago
62,484,510
DigitalOceanNVIDIA H100-SXM-80GBOffline$4.41/GPU·hr
19m ago
61,439,592
DigitalOceanNVIDIA H200-SXM-141GBServer$4.47/GPU·hr
19m ago
58,913,535
NebiusNVIDIA H200-SXM-141GBServer$4.50/GPU·hr
19m ago
58,520,778
RunPodNVIDIA H200-SXM-141GBServer$4.59/GPU·hr
19m ago
57,373,312
DigitalOceanNVIDIA H100-SXM-80GBServer$4.41/GPU·hr
19m ago
56,744,994
CrusoeNVIDIA H200-SXM-141GBOffline$6.00/GPU·hr
19m ago
47,800,650
CoreWeaveNVIDIA H200-SXM-141GBOffline$6.31/GPU·hr
19m ago
45,452,282
CoreWeaveNVIDIA H100-SXM-80GBOffline$6.16/GPU·hr
19m ago
43,985,162
CrusoeNVIDIA H200-SXM-141GBServer$6.00/GPU·hr
19m ago
43,890,584
CoreWeaveNVIDIA H200-SXM-141GBServer$6.31/GPU·hr
19m ago
41,734,311
CoreWeaveNVIDIA H100-SXM-80GBServer$6.16/GPU·hr
19m ago
40,624,257
OCINVIDIA H200-SXM-141GBOffline$10.00/GPU·hr
19m ago
28,680,390
Azure (eastus2)NVIDIA H200-SXM-141GBOffline$10.60/GPU·hr
19m ago
27,056,972
GCP (us-central1)NVIDIA H200-SXM-141GBOffline$10.84/GPU·hr
19m ago
26,445,752
OCINVIDIA H200-SXM-141GBServer$10.00/GPU·hr
19m ago
26,334,350
OCINVIDIA H100-SXM-80GBOffline$10.75/GPU·hr
19m ago
25,204,521
Azure (eastus2)NVIDIA H200-SXM-141GBServer$10.60/GPU·hr
19m ago
24,843,727
GCP (us-central1)NVIDIA H200-SXM-141GBServer$10.84/GPU·hr
19m ago
24,282,504
GCP (us-central1)NVIDIA H100-SXM-80GBOffline$11.53/GPU·hr
19m ago
23,506,003
OCINVIDIA H100-SXM-80GBServer$10.75/GPU·hr
19m ago
23,278,644
AWS (us-east-1)NVIDIA H100-SXM-80GBOffline$12.29/GPU·hr
19m ago
22,046,265
Azure (eastus)NVIDIA H100-SXM-80GBOffline$12.29/GPU·hr
19m ago
22,046,265
Azure (eastus2)NVIDIA H100-SXM-80GBOffline$12.29/GPU·hr
19m ago
22,046,265
GCP (us-central1)NVIDIA H100-SXM-80GBServer$11.53/GPU·hr
19m ago
21,709,909
AWS (us-east-1)NVIDIA H100-SXM-80GBServer$12.29/GPU·hr
19m ago
20,361,711
Azure (eastus)NVIDIA H100-SXM-80GBServer$12.29/GPU·hr
19m ago
20,361,711
Azure (eastus2)NVIDIA H100-SXM-80GBServer$12.29/GPU·hr
19m ago
20,361,711