Inference Volume
$52.1B
+5.1%
Model Rankings
165
updated
AI Traffic
624.8K
+38.2%
Global Latency
11ms
optimal
API Calls
102.4M
+12.4%
Live Agents
582,391
+42.1%
AI Market Cap
$58.2B
+5.2%
GPU Nodes
6,247
+10.2%
Inference Volume
$52.1B
+5.1%
Model Rankings
165
updated
AI Traffic
624.8K
+38.2%
Global Latency
11ms
optimal
API Calls
102.4M
+12.4%
Live Agents
582,391
+42.1%
AI Market Cap
$58.2B
+5.2%
GPU Nodes
6,247
+10.2%
TH
Λ
L
Ξ
RION
TH
CAPITAL
λI
MARKETPLACE
ΞRI
BEEHIVE
ΩN
ALE
Giriş Yap
Kayıt Ol
ΞRI
Compute Market
GPU Network
Node Marketplace
AI Tasks
Deployments
Rewards
Infrastructure
Regions
Status
Analytics
GG Robot
ΞRI
/
GPU Network
Total Nodes
32,900
Online
27,040
Utilization
17.8%
Clusters
8
H100 Cluster US-West
online
Type:
H100
Nodes:
2840/3200
Latency:
12ms
Price:
$4.2/hr
88.8% utilized
H100 Cluster EU-Central
online
Type:
H100
Nodes:
1420/1800
Latency:
28ms
Price:
$4.35/hr
78.9% utilized
A100 Cluster US-West
online
Type:
A100
Nodes:
5200/6000
Latency:
15ms
Price:
$2.8/hr
86.7% utilized
A100 Cluster APAC
online
Type:
A100
Nodes:
3100/4000
Latency:
45ms
Price:
$2.95/hr
77.5% utilized
RTX 4090 Cluster US-West
online
Type:
RTX 4090
Nodes:
8400/10000
Latency:
10ms
Price:
$0.85/hr
84.0% utilized
RTX 4090 Cluster EU-West
online
Type:
RTX 4090
Nodes:
4200/5500
Latency:
35ms
Price:
$0.92/hr
76.4% utilized
MI300X Cluster US-Central
online
Type:
MI300X
Nodes:
680/800
Latency:
18ms
Price:
$3.5/hr
85.0% utilized
TPU v5 Cluster Asia
degraded
Type:
TPU v5
Nodes:
1200/1600
Latency:
52ms
Price:
$3.2/hr
75.0% utilized