AionLabs: Aion-1.0 reasoning
Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as Tree...
Context Inputs Outputs Input Price Cache Read Price Cache Write Price Output Price131k4.00- -8.00
AionLabs: Aion-1.0-Mini reasoningAion-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...
Context Inputs Outputs Input Price Cache Read Price Cache Write Price Output Price131k0.70- -1.40
AionLabs: Aion-2.0 chatAion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....
Context Inputs Outputs Input Price Cache Read Price Cache Write Price Output Price131k0.800.20 -1.60
AionLabs: Aion-RP 1.0 (8B) chatAion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...
Context Inputs Outputs Input Price Cache Read Price Cache Write Price Output Price32k0.80- -1.60