Availability & SLA
Router One is in the request path, so availability is the headline number. This page documents how it is measured, what fallback does, and what enterprise customers can lock in contractually.
Last updated:
Reported uptime
- Measurement
- Monthly availability is computed from synthetic probes — one HTTPS request per minute from each measurement city to api.router.one.
- Exclusions
- Numbers exclude scheduled maintenance announced ≥ 48 hours in advance via changelog and email to active accounts.
- Reporting cadence
- Monthly numbers are published with each changelog entry; per-incident detail is published on the live status feed in the footer.
Failover behavior
- Trigger
- When an upstream provider's error rate or p95 latency crosses configured thresholds, or a request returns a 5xx / times out, smart routing falls back to the next eligible provider within the same model family.
- Fallback latency
- Typical end-to-end fallback adds < 200ms over the failing request. The original failure and the eventual successful provider are both recorded in the per-request trace.
- Model family constraint
- Fallback only happens between providers serving the same model family (GPT → GPT, Claude → Claude). Router One does not silently swap a request to a different model.
Status visibility
- Public status
- Live incident state is published in the footer status link and emailed to addresses subscribed to status updates.
- In your trace
- For every request, the dashboard shows the upstream provider used, fallback chain (if any), latency, and status code. Outages are visible at the request level — you don't have to take our word for the aggregate.
Enterprise SLA
- Default contracts
- Annual enterprise contracts can include a written SLA with service credits for missed availability targets. Pay-as-you-go customers don't have a contractual SLA but get the same fallback infrastructure.
- Coverage
- The SLA covers Router One's reachability and routing layer. Per-model availability is constrained by upstream providers — the SLA accounts for that by measuring against the routed result, not any single provider.
- How to sign
- Contact sales via /contact to negotiate target, exclusions, and credit schedule.
FAQ
- Where can I see live incident status?
- The status link in the site footer publishes live incidents and a rolling 90-day uptime history. Email subscription is offered from the same page.
- Does Router One offer SLA credits for pay-as-you-go users?
- Contractual SLA with credits is included only in enterprise annual contracts. Pay-as-you-go users get the same routing and fallback behavior, but no written credit schedule.
- What counts as downtime in the SLA?
- Downtime is measured against the routed result reaching the customer. If smart routing successfully falls back within target latency, the request is not downtime even if the original upstream provider failed. Scheduled maintenance announced ≥ 48 hours in advance is also excluded.