AionLabs: Aion-1.0-Mini

Aion LabsID: aion-labs/aion-1.0-mini

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 available on its [Hugging Face page](https://huggingface.co/FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview), independently replicated for verification.

Pricing per 1M Tokens

Input (Prompt)$0.70
Output (Completion)$1.40
Cache ReadFree
Cache WriteFree
ImageN/A

Specifications

Context Length131K
Max Output Tokens33K
Input ModalitiesText
Output ModalitiesText
TokenizerOther
Instruct TypeN/A
Top Provider Context131K
Top Provider Max Output33K
ModeratedNo

Compare this model

See how AionLabs: Aion-1.0-Mini stacks up against other models.

vs AionLabs: Aion-2.0vs AionLabs: Aion-1.0vs AionLabs: Aion-RP 1.0 (8B)

More from Aion Labs

AionLabs: Aion-2.0
Input$0.80
Context131K
AionLabs: Aion-1.0
Input$4.00
Context131K
AionLabs: Aion-RP 1.0 (8B)
Input$0.80
Context33K

Last updated: March 23, 2026

First tracked: March 23, 2026