# Aion 1.0 Mini

Aion Labs

Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant of a FuseAI model that outperforms R1-Distill-Qwen-32B and R1-Distill-Llama-70B, with benchmark results independently replicated for verification.

## Capabilities

### Thinking

## Technical Specifications

**Context Window**  
131,072 tokens  
**Max Output**  
32,768 tokens

## Pricing

### Token Costs (per 1M tokens)

- **Cache Miss Input**: $0.70  
- **Non-Reasoning Output**: $1.40

## Snapshots

1

## Legacy

### Made legacy on February 17, 2026

#### Reason

Small distilled model; provider no longer actively maintained

#### Recommended Replacement

[Qwen3.6 Plus](/content/models/alibaba-qwen3.6-plus/index.html)