AI
AI Sentinel Cost Dashboard Admin Routing Tester
LiteLLM UI ↗ Gateway ↗

Cost Intelligence / AI Sentinel

Connecting...
Overview
By Provider
By Model
By Team
Cache Stats
Request Logs
Settings
Total Spend
—
— requests
Est. Savings
—
vs all-Sonnet
Cache Hit Rate
—
cache hits
Avg Cost/Request
—
per LLM call
By Provider
Load data...
Top Models
Load data...
Spend by Provider
Loading...
Spend by Model
Loading...
Spend by Team
Loading...
Cache Hits
—
$0 cost each
Cache Misses
—
sent to LLM
Cost Saved
—
from cache hits
Cache Performance
Recent Requests
Click tab to load logs
LiteLLM Connection