Admin/AI Usage Metrics
AI Usage Metrics
Token consumption, latency and cost across AI providers.
Total Cost
$3.59
Tokens In
44,077
Tokens Out
19,436
Avg Latency
1607 ms
Tokens by Model
Distribution of input/output tokens per AI provider.
Call Log
Per-request AI usage detail.
| ID | Model | Tokens In | Tokens Out | Cost | Latency | Time |
|---|---|---|---|---|---|---|
| AI-2000 | gpt-4.1 | 2,551 | 1,531 | $0.436 | 1475 ms | — |
| AI-2001 | claude-sonnet | 1,215 | 1,776 | $0.034 | 2026 ms | — |
| AI-2002 | gemini-pro | 1,269 | 1,923 | $0.378 | 1835 ms | — |
| AI-2003 | gpt-4.1 | 3,901 | 1,328 | $0.255 | 2224 ms | — |
| AI-2004 | claude-sonnet | 4,266 | 1,430 | $0.604 | 1773 ms | — |
| AI-2005 | gemini-pro | 4,525 | 1,756 | $0.008 | 1796 ms | — |
| AI-2006 | gpt-4.1 | 4,997 | 1,818 | $0.032 | 1415 ms | — |
| AI-2007 | claude-sonnet | 5,065 | 518 | $0.097 | 1872 ms | — |
| AI-2008 | gemini-pro | 1,431 | 1,632 | $0.038 | 1187 ms | — |
| AI-2009 | gpt-4.1 | 2,645 | 1,289 | $0.616 | 1419 ms | — |
| AI-2010 | claude-sonnet | 4,077 | 722 | $0.429 | 1384 ms | — |
| AI-2011 | gemini-pro | 4,434 | 980 | $0.264 | 646 ms | — |
| AI-2012 | gpt-4.1 | 2,215 | 2,036 | $0.005 | 2121 ms | — |
| AI-2013 | claude-sonnet | 1,486 | 697 | $0.396 | 1318 ms | — |