Skip to content

Analytics

Under Analytics, review gateway operations for cost reviews, capacity planning, and incident triage. Metrics come from real Proxy traffic (Chat, Images, Tools). Playground probes do not feed this usage pipeline.

Typical views (labels follow the UI):

ViewUse
ModelsRequests, tokens, and spend by model
ProvidersUsage and cost by upstream vendor
UsersConsumption and activity by user / customer
ReliabilityFailure rates, latency, availability signals
  1. Open the Analytics sub-page you need.
  2. Pick a time range; narrow by model, provider, or user when useful.
  3. Cross-check spikes or failure clusters in Request logs.
  4. Tune route priority, backup providers, budgets, or the Tools Active engine based on what you find.
PageFocus
AnalyticsAggregated trends and comparisons
Request LogsPer-call detail and pricing summaries
Audit LogsBudget charges and user / key lifecycle