Live
⚠ Could not reach /stats — is the server running?
Fire 8 live requests and watch RouteAI route them in real time
▶ Live Demo Feed
Cost Savings
vs GPT-4o baseline pricing
Actual Cost
Baseline (GPT-4o)
Saved
Total Requests
routed successfully
Total Tokens
processed across all models
Avg Latency
across recent requests
Active Keys
API keys enabled
Model Distribution
📊
No data yet
Send some requests to see model breakdown
Cost Analysis
Raw provider cost
Your cost (30% markup)
GPT-4o baseline cost
Dollar savings vs GPT-4o
Savings %
Cost per 1K tokens (actual)
Requests (last 60s)
Billing: 30% markup over raw provider costs
Recent Requests
Timestamp Model Provider Tokens Routing Reason Latency
🔄
Loading…