All model families
gpt-5-nano
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 gpt-5-nano.
Provider latency, last 24 hours
30 minute buckets · UTCfastest provider, last 24h · hover to inspect3 lead changes
Current routing standings
gpt-5-nano
1🏆openai79.6%5.39s17.1s8%$0.282azure @swedencentral12.2%17.8s65.5s4%$0.313azure @francecentral8.2%17.0s51.4s39%$0.21Requesty policy41% faster
7.86sp5025.8s p95
Pick one provider
13.4sp5044.7s p95
fastest provider, last 24h · hover to inspect3 lead changes
Win share is simulated with the production router's Thompson Sampling over the last hour of gpt-5-nano traffic.