Aion-3.0
Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.
aion-labs/aion-3.0
- Contexto
- 131k tokens
- Máx. completion
- 32,768
- Tools
- Sí
- JSON
- Sí
- Lanzamiento
- 2026-07-07
Llámalo desde Geek Hub
El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "aion-labs/aion-3.0",
"messages": [{"role": "user", "content": "Hola"}]
}'Consigue tu API keyPreguntas frecuentes
- ¿Qué es Aion-3.0?
- Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict. Aion-3.0 corre en el API de Geek Hub (compatible con OpenAI). Id: aion-labs/aion-3.0.
- ¿Aion-3.0 es gratis?
- No. El input cuesta $3.2702 / 1M tokens y el output $6.5404 / 1M tokens en Geek Hub (markup incluido).
- ¿Cuál es el contexto de Aion-3.0?
- Aion-3.0 tiene una ventana de 131k tokens. Soporta hasta 32,768 tokens de completion.
- ¿Aion-3.0 soporta tool calling y structured outputs?
- Aion-3.0 acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
- ¿Cuándo se lanzó Aion-3.0?
- Aion-3.0 se lanzó el 7 de julio de 2026.
Más modelos de Aion Labs
- Aion-2.0Aion-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, ma
- Aion-3.0-MiniAion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multip
- Aion-RP 1.0 (8B)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 eac