Last updated just now · Auto-refreshes every 60s
+18.2%
23,400
Requests (30d)
vs prior period
+24.5%
17.3M
Tokens Generated
last 30 days
-8.1%
312ms
Avg p99 Latency
time-to-first-token
+22.1%
$3.46
Est. Cost (30d)
at $0.20 / 1M tokens
Throughput & Latency (24h)
Tokens per second and p99 response time
TPSp99 ms
Tokens by Model
Last 30 days
Daily Token Volume (30d)
Total tokens processed per day
System Status
All operationalOnline
API Gateway
2ms
Online
Triton / vLLM
68ms
Online
TRT-LLM
41ms
Online
HF Transformers
Online
Redis Queue
1ms
Online
PostgreSQL
3ms
Uptime: 99.97% · Region: us-central1-a (GCP H100) · SLA: 99.9%