All systems operational
Last checked just now
API uptime (90d)
99.99%
within SLA
Median TTFT
138 ms
in-region
Error rate
0.002%
last 24h
Throughput
312 t/s
DeepSeek-V4 Flash
Components
Inference API/v1/chat/completions
Operational90 days ago99.99% uptimetoday
Streaming (SSE)token streaming
Operational90 days ago99.99% uptimetoday
Console & dashboardapp.hyperinfer.ai
Operational90 days ago99.97% uptimetoday
AuthenticationAPI keys & SSO
Operational90 days ago100% uptimetoday
Model deploymentprovisioning
Operational90 days ago99.95% uptimetoday
Regional availability
uae-central
Dubai
us-east
N. Virginia
us-west
Oregon
eu-west
Ireland
eu-central
Frankfurt
uk-south
London
apac-sg
Singapore
apac-syd
Sydney
Incident history
DegradedElevated latency in eu-centralJun 12, 2026
A subset of requests in eu-central saw TTFT above 400ms following a node-pool upgrade. Traffic was shifted to healthy nodes while the pool was rebuilt. No requests failed and no data was affected.
Resolved in 38 minutes · eu-central · Inference API
ResolvedModel deployment delaysMay 14, 2026
New private deployments queued longer than expected due to a provisioning controller bug. Existing inference traffic was unaffected throughout. A fix was deployed and the queue drained.
Resolved in 1 hour 12 minutes · Global · Model deployment
DegradedConsole dashboard slownessApr 28, 2026
The customer console loaded slowly for some users due to a database connection-pool saturation. The API and inference were fully operational. Pool limits were raised and monitoring added.
Resolved in 52 minutes · Console & dashboard
No other incidents in the last 90 days.