nRouter runs on managed container infrastructure with edge health probes and revision-scoped post-deploy log scans. Targeted uptime is 99.9% across every plan tier: the same SLA on Pay as you go as on Enterprise.
Failures rarely take down everything at once. Each surface is reported separately so partial degradations show up honestly. Never papered over by a single green light.
All systems operational
As of September 7, 2026
API proxy — US-Central (primary)
OpenAI-compatible /v1 endpoint, intelligent router
Provider routing & fallback
Routing strategies, fallback chains, retry policies
Authentication
Login, signup, SSO/SAML, session management
RLS-scoped Supabase
Tenant-isolated Postgres with Row-Level Security
Virtual key validation
Per-key auth, RPM/TPM enforcement, budget caps
Credit ledger
Reserve + settle, atomic balance mutations
Stripe billing & webhooks
Checkout, top-ups, subscription, webhook ingest
Management dashboard
Keys, teams, analytics, guardrails, settings
Observability & logging
Request logs, callbacks, alerts, latency metrics
Anthropic
Claude Opus 4.8, Sonnet 4.6, Haiku 4.5 — live today
Google Vertex AI
Gemini, Imagen, Veo, embeddings — live today
OpenAI
GPT-5.5, GPT-5, o-series — live today
AWS Bedrock
Live — Claude, Llama, DeepSeek, Nova, Qwen
0 customer-impacting incidents this quarter (as of September 7, 2026). Major incidents (P0/P1) get a postmortem in the changelog within 7 days: timeline, root cause, remediation.
Azure, Google, OpenAI, Anthropic, and AWS Bedrock are all live and routing production traffic today. See the model catalog for what is live today.
Committed on every plan tier
Design target
Design target — no published latency study yet
Customer-impacting, as of the snapshot date
Uptime is an output. The inputs are synthetic probes, deploy-time gates, and customer-configurable alerts that fire before a ticket gets filed.
An edge health probe polls the gateway’s /health endpoint on a fixed interval and removes an unhealthy origin from rotation. After every release a post-deploy watch window additionally runs a real inference probe with a virtual key against the live proxy path. We do not yet run continuous per-region synthetic checks between releases.
Every production revision must pass a revision-scoped log scan and a health check before it is accepted, and a bounded post-deploy watch window re-scans logs and re-probes health and inference after the roll. A 200 on /health is necessary, not sufficient. Rollback is an operator decision, not an automatic one.
Configure per-org alerts for budget burn (balance thresholds, daily and monthly spend caps, and per-budget utilization), delivered to webhook, email, Slack, or Teams.
Not yet. And we will not pretend otherwise. This board reflects the operational posture as of the snapshot date and changes with the deploy that resolves any incident. A live, server-backed feed is on the roadmap. We chose not to embed a third-party vendor widget (Statuspage / Better Stack) because it requires a separate account and a public page that drifts from our deploys.
Honestly: not continuously, and not yet as a published number. An edge health probe polls /health on a fixed interval, and every release is gated by a revision-scoped log scan plus a bounded post-deploy watch window. The 99.9% figure is the target we commit to in the legal SLA, not a measured result — we publish no continuous uptime history, and a Service Credit claim is assessed from our own records for the cycle. We count only customer-impacting incidents; cosmetic and self-healing transient errors do not. Any P0/P1 gets a changelog postmortem.
Major incidents (P0 / P1) get a postmortem in the changelog within 7 days, with timeline, root cause, and remediation. As of the snapshot date there are no open or recent customer-impacting incidents.
Notice an issue?
If you are seeing routing errors or latency spikes that are not reflected here, our engineers want to know. Reports are triaged within an hour during business windows.
Security-sensitive reports. Please email security@nrouter.ai instead of filing a public issue.