Requesty
All model families

gpt-6-luna

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-6-luna.

Provider latency, last 24 hours

30 minute buckets · UTC
fastest provider, last 24h · hover to inspect12 lead changes
1.0s2.0s5.0s10s04:0008:0012:0016:0020:0000:00openaiazure @eastus2azure @westeuropeazure @francecentralazure @swedencentralazure @germanywestcentral

Current routing standings

gpt-6-luna

1🏆azure @germanywestcentral↑52.4%2.16s36%2azure @francecentral12.2%3.66s34%3azure @eastus2↑11.5%3.77s78%4azure @swedencentral⚡9.7%4.25s38%5azure @westeurope⚡8.1%4.14s37%6openai↑3.5% err6.1%4.65s69%
Requesty policy19% faster
3.04sp5011.6s p95
Pick one provider
3.77sp5015.0s p95
fastest provider, last 24h · hover to inspect12 lead changes

Win share is simulated with the production router's Thompson Sampling over the last hour of gpt-6-luna traffic.