llmtrace▌30D SPEND$374.58ANOM2ACTIONS0AGENT ACTIVEscan 1NEXT16:43:21 UTC
DAILY SPEND · 30Dwhich deploy spiked the bill?
TRACKED KEYS3 keys · anthropic
KEY
30D TREND
$/DAY
Δ
MODEL MIX
σ
STATUS
prod-frontend
$8.36
▲ 3.5×
62% haiku
5.2
HIGH
background-jobs
$2.24
━ flat
sonnet
·
OK
internal-tools
$1.88
━ flat
sonnet
·
OK
Autonomous Agent · Activescans 1 · last 16:28:21 UTC · next 16:43:21 UTC
Projected · prod-frontend$603/mobaseline run-rate $124/mo · this regression adds
+$479/mo if left unfixed
Spend Anomalies
ANOMALYprod-frontend2026-08-12
actual$20.85
baseline 7d$5.91
delta+$14.94
sigma5.2σ
calls830
ANOMALYprod-frontend2026-08-11
actual$12.92
baseline 7d$4.68
delta+$8.24
sigma28.0σ
calls838
Ask the Agent
>
Investigate Any DashboardGemini Vision
Drop a screenshot of any LLM billing dashboard: Anthropic, OpenAI, a Grafana panel.
Gemini reads the spend off the image, then the agent finds which deploy caused the spike.