Stability ranking: GPT 6.1 Sol last 24 hours
A stability score out of 100 that combines success rate, latency and latency variation over the last 24 hours; higher is better. Success rate is taken conservatively by sample size, so a route with few samples cannot rank high just because every request happened to succeed.
| Rank | Model relay | Stability | Samples | Availability | Session cost | Data security |
|---|---|---|---|---|---|---|
| 1 | 95.5 | 183 | 98.4% | ¥0.44 | 4 | |
| 2 | 79.8 | 48 | 100.0% | ¥0.84 | 2 | |
| 3 | 88.5 | 48 | 100.0% | ¥0.44 | 0 | |
| 4 | 84.0 | 41 | 100.0% | ¥0.51 | 0 | |
| 5 | 82.8 | 23 | 100.0% | ¥0.26 | 0 | |
| 6 | 77.7 | 48 | 93.8% | — | 0 |
FAQ
How is stability calculated?
A stability score out of 100 that combines success rate, latency and latency variation over the last 24 hours; higher is better. Success rate is taken conservatively by sample size, so a route with few samples cannot rank high just because every request happened to succeed.
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.