Aion Labs
PolôniaAion 3.5 is an AionLabs reasoning model with a 256K context window and low, high, and max reasoning efforts.
Aion 3.5 Mini is an AionLabs reasoning model with a 256K context window and low, high, and max reasoning efforts.
Aion 3.0 Mini is a multi-model text system built on the DeepSeek family of models. It uses multiple specialized models during generation to improve narrative structure, tension, conflict, and mature-theme handling.
Aion 3.0 is a multi-model text system built on the GLM family of models. It uses multiple specialized models during generation to improve narrative structure, tension, conflict, and mature-theme handling.
Aion 2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It accepts text inputs and produces text outputs.
Aion-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.
Aion 2.5 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It accepts text inputs and produces text outputs.
Aion 1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It accepts text inputs and produces text outputs.
Aion 1.0 Mini is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic.