Availability ranking: GPT 6.1 Sol last 24 hours

Request success rate over the last 24 hours; fake 200s, truncated streams and malformed responses all count as failures. The range is a 95% Wilson confidence interval based on sample size, so routes with fewer samples get wider intervals.

Data6 routes · 6 relaysSynced 11/20/2026, 09:40:44, updated every 15 minutes
Model: GPT 6.1 Sol
RankRangeModel relayAvailabilitySamplesFirst tokenSession costData security
1198.4%±2.11830.87 s¥0.444
22100.0%±3.7488.15 s¥0.842
33–6100.0%±3.7483.57 s¥0.440
43–6100.0%±4.3413.03 s¥0.510
53–6100.0%±7.2232.69 s¥0.260
63–693.8%±7.3486.14 s—0

FAQ

How is availability calculated?

Request success rate over the last 24 hours; fake 200s, truncated streams and malformed responses all count as failures. The range is a 95% Wilson confidence interval based on sample size, so routes with fewer samples get wider intervals.

What does “Range” mean?

We compute a 95% confidence interval from each route’s sample size, then count which routes are clearly better or worse to get the possible rank range. A route at 100% with only a few requests has a very wide range.

Why does the same relay appear more than once?

Each row is one “model relay” route. Different models and groups at the same relay can perform very differently, so they are ranked separately.

Ordering follows site rules, including partnership tiers and operational weighting; some data are display samples.