Usage
Every token. Every call. Every dollar.
A unified view across every provider you route through. No juggling five dashboards.
live · updated 0s ago
Requests
22,077
+12.4%
Tokens
298.4M
+18.1%
Spend
$1,434.60
+4.2%
P50 latency
142ms
-8.3%
Requests over time
22,077
↑ 12.4% vs previous 7d
d1d2d3d4d5d6d7
Breakdown by model
Model
Requests
Tokens
Spend
Share
gpt-5.5
128,412
42.1M
$526.40
32%
claude-opus-4.5
84,210
28.7M
$430.50
22%
deepseek-v4
214,800
68.3M
$37.60
18%
gemini-3.1-pro
92,310
51.2M
$358.40
14%
gpt-5.5-mini
310,200
88.9M
$35.60
8%
llama-4-405b
58,900
19.2M
$46.10
6%
Demo data · connect your API key to see live usage from your account.