The load level on a server system is regulated by determining time-to-live (TTL) values to provide to requesting devices that request a content resource from the server system, thereby affecting the frequency of subsequent requests. This dynamic determination of TTL values may provide resilience to system load, for example by using longer TTL values when the system is under greater load to reduce the rate at which subsequent requests are received. A dynamic TTL service may calculate a TTL value based on one or more factors, such as overall system load, resource load, hardware load, and/or software load.