Requesty
All model families

gpt-6-sol

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-sol.

Provider latency, last 24 hours

30 minute buckets · UTC
fastest provider, last 24h · hover to inspect12 lead changes
500ms1.0s2.0s5.0s10s20:0000:0004:0008:0012:0016:00openaiazure @westeuropeazure @francecentralazure @swedencentralazure @eastus2azure @germanywestcentral

Current routing standings

gpt-6-sol

1🏆azure @germanywestcentral25.4%3.24s51%2azure @westeurope24.3%3.27s64%3azure @francecentral20.3%3.78s70%4azure @swedencentral19.0%3.75s50%5openai9.2%4.92s49%6azure @eastus21.8%4.37s85%
Requesty policy7% faster
3.63sp50
Pick one provider
3.89sp50
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-sol traffic.