Legal
Service Level Agreement
This service level agreement describes how FastInfra measures availability of the public API gateway, how uptime is calculated from synthetic health checks over rolling windows, and when enterprise customers may qualify for service credits. GPU pods, CPU servers and dedicated machines are covered by their respective provider SLAs shown at order time. Live uptime and incident history are published on the status page so you can verify the numbers yourself.
Measured availability
Live gateway and backend uptime are published on Status, calculated from health checks over rolling windows. This is the source of truth for platform availability.
Enterprise credits
Financial service credits apply only where a signed enterprise order references this SLA. Standard prepaid accounts use measured uptime on Status without automatic credits.
Infrastructure products
GPU pods, CPU VMs and dedicated servers may have separate provider SLAs shown at order time in the console configurator.
Frequently asked questions
What uptime does FastInfra measure?
We publish live backend and gateway uptime on the status page, calculated from synthetic checks over rolling windows.
Are service credits automatic?
Credits apply only where a signed enterprise agreement references this SLA. Standard prepaid accounts rely on measured uptime on /status without a financial credit.
Does the SLA cover individual models?
The SLA covers the FastInfra API gateway. Individual upstream models can degrade independently; automatic failover routes around unhealthy routes where an alternative exists.
How do I claim a service credit?
Enterprise customers contact support with the affected time window and account; credits are assessed against the measured uptime for that period.
Reviewed by Ashish Kumar, Head of Product · Updated October 26, 2026. Prices and counts on this page come from the live catalog.