The Known Good Updated 29 Jul 2026
Providers· Inference host· 4 tracked models

AionLabs — pricing & performance

Compare models All providers Data sources
Models served
4
of 947 tracked models
Mean output speed
52
tokens per second, averaged over
4 measured endpoints
Mean latency
1.0s
time to first token, averaged over
4 measured endpoints
Cheapest blended
$0.88
per 1M tokens at a 3:1
input:output blend
Output speed on AionLabs

Median output tokens per second for all 4 models on AionLabs with published throughput telemetry from OpenRouter. Higher is better. We do not run these measurements ourselves.

All 4 of 4 models
The Known Good
4 models on AionLabs
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
AionLabs: Aion-2.0 aion-labs $0.80 $1.60 $1.00 76 1.1s 131k
AionLabs: Aion-3.0 aion-labs $3.00 $6.00 $3.75 47 1.3s 131k
AionLabs: Aion-3.0-Mini aion-labs $0.70 $1.40 $0.88 74 0.9s 131k
AionLabs: Aion-RP 1.0 (8B) aion-labs $0.80 $1.60 $1.00 10 0.8s 33k
The Known Good
Source. Prices, endpoint availability and throughput for AionLabs are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.