4models tracked · ranked by intelligence, speed & price
its fastest is Aion-2.0 at 37 tokens/sec, and its cheapest is Aion-1.0-Mini at $0.700 per million input tokens. All 4 AionLabs models are compared below by intelligence, speed, latency, context and price.
| Model | Intel | Speed | Latency | In $/M | Context |
|---|---|---|---|---|---|
| aion-2.0 Reasoning | — | 37 | 2.0s | $0.800 | 131K |
| aion-1.0 Reasoning | — | 9 | 1.4s | $4.00 | 131K |
| aion-1.0-mini Reasoning | — | 9 | 1.3s | $0.700 | 131K |
| aion-rp-llama-3.1-8b | — | 27 | 818ms | $0.800 | 33K |