Aion-RP 1.0 (8B) vs Aion-3.0-Mini
One line per model: the best value available from any of its providers at each point, which is what a caller routing to the healthy endpoint would see.
CompareAion-RP 1.0 (8B)Aion-3.0-Mini
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| Aion-RP 1.0 (8B) | 0/1 | — | — | — | — | 33K | $0.800 / $1.60 AionLabs |
| Aion-3.0-Mini | 1/1 | 100% AionLabs | 874ms AionLabs | 7.92s AionLabs | 59 tps AionLabs | 131K | $0.700 / $1.40 AionLabs |
History
Availability
Best uptime available from any provider. Axis starts at 90%; it expands to 0 when a model falls below.
Time to first token
Fastest p50 available from any provider. Logarithmic axis.
Throughput
Best median tokens per second available.