All model families
gpt-5.4
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-5.4.
Provider latency, last 24 hours
30 minute buckets · UTCfastest provider, last 24h · hover to inspect14 lead changes
Current routing standings
gpt-5.4
1🏆azure @francecentral⚡45.3%2.93s15.0s62%$1.932azure @swedencentral↑28.2%4.21s29.4s34%$3.553openai⚡26.2%3.90s19.6s45%$2.724azure0.1%24.0s99.4s47%$3.115azure @eastus20.1%12.3s22.3s34%$2.17Requesty policy62% faster
3.57sp5020.4s p95
Pick one provider
9.48sp5037.2s p95
fastest provider, last 24h · hover to inspect14 lead changes
Win share is simulated with the production router's Thompson Sampling over the last hour of gpt-5.4 traffic.