All model families
gpt-oss-120b
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-oss-120b.
Provider latency, last 24 hours
30 minute buckets · UTCfastest provider, last 24h · hover to inspect9 lead changes
Current routing standings
gpt-oss-120b
1🏆nebius60.5%1.31s4.91s47%$0.262groq⚡36.7%1.60s3.65s44%$0.273fireworks2.8%2.95s6.55s82%$0.39Requesty policy25% faster
1.46sp504.49s p95
Pick one provider
1.95sp505.03s p95
fastest provider, last 24h · hover to inspect9 lead changes
Win share is simulated with the production router's Thompson Sampling over the last hour of gpt-oss-120b traffic.