Live LLM Stats

Real-time usage, latency, and cost tracking across all AI endpoints.

—
Requests (today)
—
Tokens (today)
—
Cost (today)
—
Avg Latency (today)
—
All-time Requests
—
All-time Cost

Requests over time

Tokens over time

Model distribution (all-time)

Avg latency by model (ms)

Today's Model Breakdown
ModelProviderRequests Tokens InTokens OutCost ($)Avg Latency
Loading…