Aion-2.0 vs Aion-3.0
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-2.0Aion-3.0
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| Aion-2.0 | 1/1 | 100% AionLabs | 769ms AionLabs | 2.68s AionLabs | 61 tps AionLabs | 131K | $0.800 / $1.60 AionLabs |
| Aion-3.0 | 1/1 | 100% AionLabs | 1.35s AionLabs | 8.03s AionLabs | 42 tps AionLabs | 131K | $3.00 / $6.00 AionLabs |
Measured 4m ago. Each figure is the best available across that model's providers.
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.