System status

All systems operational.

Operational UPDATED MAY 19, 2026 · 14:08 UTC

Gateway

90-day availability per service.

API · /v1/chat/completions
99.98%
118 ms p50
Operational
API · streaming / SSE
99.95%
112 ms TTFT
Operational
Management API · /v1/management
100.00%
42 ms p50
Operational
Dashboard & billing
99.99%
Operational

Routed regions

Routing-pool health and median latency per region.

US East · Ashburn
99.97%
95 ms p50
Operational
US West · Los Angeles
99.96%
102 ms p50
Operational
EU · Frankfurt
99.99%
88 ms p50
Operational
APAC · Singapore
99.94%
128 ms p50
Operational
APAC · Tokyo
99.96%
134 ms p50
Operational
APAC · Sydney
99.95%
141 ms p50
Operational
Incident history

Past 90 days.

Elevated TTFT in APAC · Singapore

Streaming time-to-first-token rose to ~340 ms for approximately 22 minutes on a single upstream pool. Auto-failover redirected affected traffic to APAC · Tokyo within 90 seconds; remaining latency was upstream-side. No request failures recorded.

14:18 – 14:40 UTC · 22 min · 0 failures

Brief 5xx spike on /v1/chat/completions · US West

A bad config push to one US-West replica raised the 5xx rate to 0.8% for 4 minutes before auto-rollback triggered. Affected requests returned idc-failover: true and were retried successfully against the US East pool.

09:12 – 09:16 UTC · 4 min · 318 retries

Scheduled maintenance · EU Frankfurt

Capacity upgrade in EU · Frankfurt. Traffic was drained to neighboring regions for roughly 11 minutes. No user-visible failures; some EU customers saw a temporary idc-region header value of eu-ams.

03:00 – 03:11 UTC · 11 min · 0 failures

Want status by email or webhook?

We push incidents to a status webhook for every Scale and Enterprise account. Drop us a line and we'll wire it up.