MiniMax-01
MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context of up to 4 million tokens. The text model adopts a hybrid architecture that combines Lightning Attention, Softmax Attention, and Mixture-of-Experts (MoE). The image model adopts the “ViT-MLP-LLM” framework and is trained on top of the text model. To read more about the release, see: https://www.minimaxi.com/en/news/minimax-01-series-2
minimax/minimax-01
- Contexto
- 1M tokens
- Máx. completion
- 1,000,192
- Tools
- No
- JSON
- No
- Lanzamiento
- 2025-01-15
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": "minimax/minimax-01",
"messages": [{"role": "user", "content": "Hola"}]
}'Consigue tu API keyPreguntas frecuentes
- ¿Qué es MiniMax-01?
- MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context of up to 4 million tokens. The text model adopts a hybrid architecture that combines Lightning Attention, Softmax Attention, and Mixture-of-Experts (MoE). The image model adopts the “ViT-MLP-LLM” framework and is trained on top of the text model. To read more about the release, see: https://www.minimaxi.com/en/news/minimax-01-series-2 MiniMax-01 corre en el API de Geek Hub (compatible con OpenAI). Id: minimax/minimax-01.
- ¿MiniMax-01 es gratis?
- No. El input cuesta $0.218 / 1M tokens y el output $1.1991 / 1M tokens en Geek Hub (markup incluido).
- ¿Cuál es el contexto de MiniMax-01?
- MiniMax-01 tiene una ventana de 1M tokens. Soporta hasta 1,000,192 tokens de completion.
- ¿MiniMax-01 soporta tool calling y structured outputs?
- MiniMax-01 no publica tool calling en este endpoint. No lista structured outputs en este endpoint.
- ¿Cuándo se lanzó MiniMax-01?
- MiniMax-01 se lanzó el 15 de enero de 2025.
Más modelos de MiniMax
- MiniMax M1MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture pa
- MiniMax M2MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it de
- MiniMax M2-herMiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in
- MiniMax M2.1MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated par
- MiniMax M2.5MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon th
- MiniMax M2.7MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evoluti