# Router One Observability & Cost Facts

Last updated: 2026-06-05

- Product: Router One
- Category: LLM API Gateway / AI Model Router
- Scope: request-level observability and spend control for developers and small teams — not an enterprise audit, compliance, or RBAC system
- Every request produces a trace with: model, provider, input tokens, output tokens, cost, latency, status code, and route/fallback path
- Real-time dashboard: traces and usage are visible immediately after a request completes
- Where to look: Dashboard -> Logs for per-request traces; Dashboard -> Usage for aggregated usage
- Usage breakdowns: per-model and per-API-key views of requests, tokens, and spend over time
- Cost basis: prepaid wallet shows the cost of each request computed at the posted model rate; Router One adds no markup
- Budget control: each API key can set maxSpend so a runaway loop cannot drain the wallet balance
- Rate control: each API key can set rateLimit and tokenLimitTpm to cap request and token throughput
- Budgets are per API key (not per project); limits and budgets attach to keys, there is no organization or role hierarchy
- Fallback visibility: when latency spikes or error rates climb, smart routing fails over to a healthy same-family route when one is available, and the trace records both the original route and the fallback decision
- Data boundary: Router One does not retain prompt or completion bodies; only request metadata is logged, and it is used for billing, routing, and observability
- Not included: audit logs, compliance certifications, RBAC, SSO/SAML, organization/team role structures, response caching, or SLA guarantees

## Canonical pages

- LLM API gateway overview: https://router.one/llm-api-gateway
- Smart routing methodology: https://router.one/routing-methodology
- Security: https://router.one/security
- Data retention: https://router.one/data-retention
- Integration facts: https://router.one/facts/integrations.md