Reliability
Status
Live status
Gateway healthy · 217 models live · 121 free · 33,800 requests / 30d
Counts and status are fetched server-side from /ai/v1/models and /ai/v1/health and refreshed at most once per hour.
For the live model + vendor breakdown right now, see /live.
Uptime targets
InferAll targets 99.9% monthly uptime for the gateway control plane (~43 minutes of allowable downtime per month), backed by tiered service credits on paid plans. Full commitments, exclusions, and the credit schedule — plus the failover behavior that protects against individual upstream provider incidents — are documented on the SLA page.