Models
One name per model, however many providers serve it.
AionLabs: Aion 3.5 Mini
Accepts- Text
Creates- Text
ToolsJSONReasoningAion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
aion-labs/aion-3.5-miniSep 23, 2026262K context252,784 Toman/M input tokens505,568 Toman/M output tokensAionLabs: Aion 3.5
Accepts- Text
Creates- Text
ToolsJSONReasoningAion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
aion-labs/aion-3.5Sep 23, 2026262K context1,082,872 Toman/M input tokens2,162,328 Toman/M output tokensAionLabs: Aion-3.0-Mini
Accepts- Text
Creates- Text
ToolsJSONReasoningAion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models.
aion-labs/aion-3.0-miniJul 7, 2026131K context252,784 Toman/M input tokens505,568 Toman/M output tokensAionLabs: Aion-3.0
Accepts- Text
Creates- Text
ToolsJSONReasoningAion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
aion-labs/aion-3.0Jul 7, 2026131K context1,082,872 Toman/M input tokens2,162,328 Toman/M output tokensAionLabs: Aion-2.0
Accepts- Text
Creates- Text
ToolsJSONReasoningAion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling.
aion-labs/aion-2.0Feb 23, 2026131K context290,360 Toman/M input tokens577,304 Toman/M output tokensAionLabs: Aion-RP 1.0 (8B)
Accepts- Text
Creates- Text
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-labs/aion-rp-llama-3.1-8bFeb 4, 202533K context290,360 Toman/M input tokens577,304 Toman/M output tokens
6 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

