Live Demo — this is simulated data. New requests appear every few seconds.
★ Star on GitHub

LLM Cost Monitor v0.1

demo
$
Total Spend
$0.0000
—
#
Requests
0
0 / hour
T
Tokens
0
in: 0 / out: 0
~
Avg Latency
0ms
per request
Spend Over Time
Cost by Model
Recent Requests
TimeProviderModelInputOutputCostLatencyTag