OpenRouter’s new routing cuts GLM 5.3 Flash’s first-token latency by 40%

發生什麼事

OpenRouter reports that, over the past month, GLM 5.3 Flash users saw first-token latency (TTFT) drop 40%, throughput rise 10%, and the price per million tokens fall 17%. The company credits a new routing algorithm that gives more traffic to providers delivering higher-quality inference (@OpenRouter).