As previously detailed, Starlink engineering teams have been focused on improving the performance of our network – driving latency as low as possible, with the goal of delivering a service with stable 20 millisecond (ms) median latency and minimal packet loss.
Latency refers to the amount of time, usually measured in milliseconds, that it takes for a packet to be sent from the Starlink router to the internet and for the response to be received. This is also known as “round-trip time”, or RTT. Latency is one of the most important factors in perceived experience when using the internet – web pages load faster, audio and video calls feel closer to real-life, and online gaming is responsive.
Starlink has also deployed the largest satellite ground network ever. More than 100 gateway sites in the United States alone – comprising a total of over 1,500 antennas – are strategically placed to deliver the lowest possible latency, especially for those who live in rural and remote areas. Starlink produces these gateway antennas at our factory in Redmond, Washington where we rapidly scaled production to match satellite production and launch rate.
To measure Starlink’s latency, we collect anonymized measurements from millions of Starlink routers every 15 seconds. In the U.S., Starlink routers perform hundreds of thousands of speed test measurements and hundreds of billions of latency measurements every day. This high-frequency automated measurement assures consistent data quality, with minimal sampling bias, interference from Wi-Fi conditions, or bottlenecks from third-party hardware.
As of June 2025, Starlink is delivering median peak-hour latency of 25.7 milliseconds (ms) across all customers in the United States. In the US, fewer than one percent of measurements exceed 55 ms, significantly better than even some terrestrial operators.