All model families
gpt-4.1
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-4.1.
Provider latency, last 24 hours
30 minute buckets · UTCfastest provider, last 24h · hover to inspect5 lead changes
Current routing standings
gpt-4.1
1🏆azure @germanywestcentral95.6%719ms1.00s––2azure @swedencentral3.4%1.16s1.99s77%–3azure @francecentral1.0%1.76s5.98s––4openai⚡0.0%4.78s8.09s21%–Requesty policy65% faster
744msp501.09s p95
Pick one provider
2.11sp504.27s p95
fastest provider, last 24h · hover to inspect5 lead changes
Win share is simulated with the production router's Thompson Sampling over the last hour of gpt-4.1 traffic.