Inference Volume$52.1B+5.1%
Model Rankings165updated
AI Traffic624.8K+38.2%
Global Latency11msoptimal
API Calls102.4M+12.4%
Live Agents582,391+42.1%
AI Market Cap$58.2B+5.2%
GPU Nodes6,247+10.2%
Inference Volume$52.1B+5.1%
Model Rankings165updated
AI Traffic624.8K+38.2%
Global Latency11msoptimal
API Calls102.4M+12.4%
Live Agents582,391+42.1%
AI Market Cap$58.2B+5.2%
GPU Nodes6,247+10.2%
ΞRI|COMPUTE

Compute Network

Distributed AI Compute Infrastructure in Realtime

Monitor GPU infrastructure, AI workloads, distributed inference activity, node participation, and realtime compute utilization across the THALERION network.

7/8 clusters online
Active Nodes
9,547
+124 today
GPU Capacity
37,600
across 7 regions
Inference Jobs
284,391
24h processed
Requests/s
42,500
peak 48,200
Global Regions
7
1 in maintenance
Uptime
99.93%
last 30 days
AI Workloads
8
types active
Reward Pool
1.2M
THAL monthly
GPU Network
Node Marketplace
AI Tasks
Infrastructure

Compute Market (8 clusters)

7 ONLINE
ClusterTypeAvailableUtilizationRegionLatencyUptimePrice/hrStatus
H100 Cluster US-WestH1002,840 / 3,200
88.8%
US-West12ms99.97%$4.20online
H100 Cluster EU-CentralH1001,420 / 1,800
78.9%
EU-Central28ms99.91%$4.35online
A100 Cluster US-WestA1005,200 / 6,000
86.7%
US-West15ms99.95%$2.80online
A100 Cluster APACA1003,100 / 4,000
77.5%
APAC-Tokyo45ms99.82%$2.95online
RTX 4090 Cluster US-WestRTX 40908,400 / 10,000
84.0%
US-West10ms99.88%$0.85online
RTX 4090 Cluster EU-WestRTX 40904,200 / 5,500
76.4%
EU-West35ms99.79%$0.92online
MI300X Cluster US-CentralMI300X680 / 800
85.0%
US-Central18ms99.93%$3.50online
TPU v5 Cluster AsiaTPU v51,200 / 1,600
75.0%
APAC-Singapore52ms99.85%$3.20degraded