Home › Docs › Savings dashboard
Control and visibilitySavings dashboard
See what you spend, your token and cache mix, and request-level metadata in /app/overview and /app/requests after signing up (or explore the live demo).
Every request metered to exact token and cache-read/write counts, with model, protocol, and cost settled in nano-USD accuracy.
Eligible /v1/chat/completions traffic tracks baseline comparison; native /v1/messages and /v1/responses currently report exact spend and cache tokens without automated baseline savings.
Inspect per-request metadata in /app/requests and aggregate spend and token trends in /app/overview (demo).
Per-request latency and HTTP status codes in /app/requests, alongside supported model tariffs via GET /v1/models (demo).
CFO-ready spend and optimization summaries reconciled with your usage export via /#book.
What gets logged
Request metadata only: timestamp, request ID, model, endpoint, input/output/cached token counts, latency, and cost. Never raw prompts or model outputs. See security and privacy.
Reconciled with your invoices
Dashboard numbers are reconciled against your provider invoices, so the savings you see are the savings you get. See the savings methodology.
Want us to find your 20%+?
Get a free 360° cost report. Bring last month's provider usage and we'll show you your biggest waste and the first fix we'd ship.
Get a Free 360° Cost Report