All model families
glm-5.2
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-5.2.
Provider latency, last 24 hours
30 minute buckets · UTCfastest provider, last 24h · hover to inspectno lead changes
Current routing standings
glm-5.2
1🏆sference⚡61.6%2.20s27.7s88%$0.462tensorx15.6%5.24s33.1s82%$0.693nebius14.8%5.15s18.4s–$2.644fireworks4.8%8.14s44.9s90%$0.355inceptron2.4%17.7s172.5s77%$0.906zai0.8%12.1s40.8s71%$1.057doubleword0.0%18.6s43.8s3%$4.11Requesty policy61% faster
3.85sp5031.6s p95
Pick one provider
9.87sp5054.5s p95
fastest provider, last 24h · hover to inspectno lead changes
Win share is simulated with the production router's Thompson Sampling over the last hour of glm-5.2 traffic.