MiniMax M2.5

MiniMax-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 the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.

ChatMiniMax205k tokens$0.2943 / $1.0356 · 1M

minimax/minimax-m2.5

Contexto
205k tokens
Máx. completion
32,768
Tools
Sí
JSON
Sí
Lanzamiento
2026-02-12

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-m2.5",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es MiniMax M2.5?
MiniMax-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 the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning. MiniMax M2.5 corre en el API de Geek Hub (compatible con OpenAI). Id: minimax/minimax-m2.5.
¿MiniMax M2.5 es gratis?
No. El input cuesta $0.2943 / 1M tokens y el output $1.0356 / 1M tokens en Geek Hub (markup incluido).
¿Cuál es el contexto de MiniMax M2.5?
MiniMax M2.5 tiene una ventana de 205k tokens. Soporta hasta 32,768 tokens de completion.
¿MiniMax M2.5 soporta tool calling y structured outputs?
MiniMax M2.5 acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
¿Cuándo se lanzó MiniMax M2.5?
MiniMax M2.5 se lanzó el 12 de febrero de 2026.

Más modelos de MiniMax