Request logs
Open User → Request Logs. This view lists real inference calls through the Proxy: timestamps, keys, users, models, route groups, status, and more — useful for troubleshooting and reconciliation.

What to do in Admin
Section titled “What to do in Admin”- Open Request Logs.
- Narrow results with time range, status, model, user email, API key, vendor, route group, protocol, and other filters available on the page.
- Expand a row to inspect billing-audit snippets, request bodies, upstream bodies, and raw usage JSON (copy when provided).
- When reading money and timestamps, align with your system timezone and billing currency settings in Admin.
Billing display
Section titled “Billing display”Expanded panels may include charge-related JSON summaries; for exact formulas or finance reconciliation, follow your internal policy plus upstream docs linked from the GitHub technical reference.
Observe Provider Sticky
Section titled “Observe Provider Sticky”When a Route Pool has Provider Sticky enabled, expand route_trace.sticky in the request log:
lookupis the binding lookup outcome, such ashit,miss,expired,invalid_epoch,invalid_target, orinvalid_circuit.attempted_targetis the bound Target tried before normal priority tiers.resultshows whether the binding was kept, cleared, created, or rebound; it can also reportstorage_errororunchanged.
Compare Sticky outcomes with cache-read tokens and upstream failover counts. If hits are stable but cache benefit does not improve, verify that the upstream really shares Prompt Cache state. Frequent cleared / rebound results point to Provider 429s, 5xx responses, auth failures, or an unsuitable TTL.
- Audit logs — budget and account-side changes
- Routing — four strategies and Provider Sticky
- Simulator — browser-based calls to the Proxy with a real key