P
Peekr Cloud
DemoAcme Agents

Costs

Where the LLM budget goes.

Which feature is burning the budget?

Projected /mo
$282
from last 24h × 30
Top feature
code_assist
30% of spend · $85 /mo
Top spender
u_heavy_19
3.6% of spend
Heavy 5%
52%
47 users drive this share
By featureBy userBy modelWhich feature is burning the budget?
FeatureShare of spendCallsUsersAvg in / outTop model24hProjected /mo
code_assist
30%
57270 / 666claude-opus-4-7$2.85$85.38
chat_summary
26%
84390 / 394claude-opus-4-7$2.48$74.52
support_bot
23%
119480 / 244claude-opus-4-7$2.18$65.27
data_extraction
16%
71310 / 1420claude-sonnet-4-6$1.51$45.37
search_qa
4%
90400 / 273gpt-4o$0.369$11.07
moderation
0%
60280 / 65gpt-4-mini$0.002$0.070

Knowing where the money goes is half the answer.

Insights → turns these breakdowns into concrete actions: model swaps, prompt-caching opportunities, output caps, and fine-tune ROI estimates.