Dashboard
LIVE2:44:20 AMRequests / min
3,284
Tokens / min
184.2K
Avg Cost / req
$0.0042
Error rate
0.42%
Request Volume
SuccessError
10:3610:5611:16
Token Usage
InputOutputCached
10:3610:5611:16
Cache Hit Rate
42.5%
of input tokens cached
Cached: 8.4K Input: 20.2K
Cost
10:3610:5611:16
Model Usage
gemma3:1bclaude-3.5gpt-4o
10:3610:5611:16
Latency
AvgP95P99
10:3610:5611:16
Provider Gauge
GPU utilization · cluster avg
Throughput Heatmap
req/min · last 7d × 24h
Top Customers by Spend
Northwind Labs$4,820
Apex Robotics$4,120
Helio Studio$3,210
Tessera AI$2,840
Mercer Group$2,120
Ferra Health$1,488
Quill & Quartz$920
Live Event Stream
last 60s
- 02:44:20REQnorthwind-labs → gpt-4o · 1.2k tok
- 02:44:20REQnorthwind-labs → gpt-4o · 1.2k tok
- 02:44:20REQapex-robotics → gemini-1.5 · 4.1k tok
- 02:44:20CACHEhit on embedding batch #88 (saved 412 tok)
- 02:44:20ENFORCEferra-health hit Pro hard limit
- 02:44:20ERRORrate limit · anthropic 429
Recent Requests
| request | customer | model | tokens | latency | cost | status |
|---|---|---|---|---|---|---|
| req_0 | northwind | gpt-4o | 4,224 | 1853 ms | $0.0123 | OK |
| req_1 | apex | llama-3.1-70b | 4,928 | 203 ms | $0.0538 | ERR |
| req_2 | helio | llama-3.1-70b | 528 | 617 ms | $0.1752 | OK |
| req_3 | tessera | gpt-4o | 1,634 | 1832 ms | $0.0749 | OK |
| req_4 | mercer | claude-3.5-sonnet | 4,872 | 829 ms | $0.0634 | OK |
| req_5 | ferra | llama-3.1-70b | 2,197 | 713 ms | $0.0912 | OK |
| req_6 | olive | gpt-4o-mini | 1,890 | 992 ms | $0.0426 | OK |
| req_7 | northwind | claude-3.5-sonnet | 2,632 | 505 ms | $0.0433 | CACHE |