modelgrep

Small & Fast AionLabs Models

Quick answer · Updated June 2026

The small, fast AionLabs model is Aion-RP 1.0 (8B) — the efficient tier at 14 tokens/sec and $0.800 per million input tokens. It trades a few points of raw intelligence for speed and cost, the right call for high-volume, latency-sensitive work. Aion-1.0-Mini (1 t/s) is next.

14 t/sSpeed
$0.800Input /M
33KContext

Compact, efficient models — the small/mini/flash/haiku tier — ranked by output speed. These trade a little raw intelligence for low cost and high throughput, which is the right tradeoff for chat, classification, extraction and other high-volume work.

  1. 1A
    aion-rp-llama-3.1-8b
    $0.800/M · 783ms ttft · 33K ctx
    14 t/s
    Speed
  2. 2A
    aion-1.0-mini
    Reasoning$0.700/M · 1.6s ttft · 131K ctx
    1 t/s
    Speed

Frequently asked

What is the smallest, fastest AionLabs model?

The small, fast AionLabs model is Aion-RP 1.0 (8B) — the efficient tier at 14 tokens/sec and $0.800 per million input tokens. It trades a few points of raw intelligence for speed and cost, the right call for high-volume, latency-sensitive work. Aion-1.0-Mini (1 t/s) is next.

What's a good alternative to Aion-RP 1.0 (8B)?

Aion-1.0-Mini (1 t/s) is the closest alternative on this metric. See the full ranking above for the tradeoffs.

How many AionLabs models are there?

modelgrep tracks 4 AionLabs models with live benchmarks, speed, latency and per-provider pricing. 2 of them qualify for this ranking.

More AionLabs rankings

All rankings