All model families
glm-5.3-flash
Median total latency per provider over the last 24 hours, from live production traffic. This is the signal Requesty's latency router samples when it picks a provider for glm-5.3-flash.
Provider latency, last 24 hours
30 minute buckets · UTCfastest provider, last 24h · hover to inspect15 lead changes
Current routing standings
glm-5.3-flash
1🏆sference⚡24.5%1.61s25.5s69%$0.082melious↑24.5%1.44s11.6s75%$0.033tensorx⚡21.7%1.76s15.3s16%$0.104lyceum18.5%2.06s28.9s58%$0.095deepinfra↑6.5%2.25s7.53s51%$0.086runware⚡2.6%4.36s26.2s76%$0.037together0.9%5.80s37.0s53%$0.128fireworks0.4%7.86s74.7s47%$0.059novita0.3%11.8s76.3s62%$0.0810zai0.2%6.60s41.5s87%$0.03Requesty policy58% faster
1.90sp5019.9s p95
Pick one provider
4.55sp5034.5s p95
fastest provider, last 24h · hover to inspect15 lead changes
Win share is simulated with the production router's Thompson Sampling over the last hour of glm-5.3-flash traffic.