Usage Dashboard

—

Total Requests

—

Today: —

Total Cost
—
Today: —

Input Tokens

—

tokens in

Output Tokens

—

tokens out

Judge Accuracy

—

routing precision

Cache Hit Rate

—

cached tokens

Loading…

Auto-refreshes every 30s

Time	Model Requested	Tier	Confidence	Latency	Tokens	Status
Loading…

Loading…

⚠️ Copy your new key now — it won't be shown again:

Choose how ClawRouter routes your model: "auto" requests.

Auto (Balanced) Intelligent routing balancing cost, quality, and speed

Cost Optimized Prefer cheaper models; use standard/reasoning only when needed

Quality First Prefer higher-quality models; fast only for trivial requests

Fast Only Always use fast tier (Haiku / Gemini Flash)

Standard Only Always use standard tier (Sonnet)

Reasoning Only Always use reasoning tier (Opus)

Loading…