MiniMax-M2.5

MiniMaxMiniMaxOpen WeightMIT · Uso Comercial

Descripción

MiniMax M2.5 is the world's first production-level model designed natively for Agent scenarios. Building on the M2.1 foundation, M2.5 delivers significant improvements in programming, tool calling, search, and office productivity. With only 10B activation parameters from its 230B MoE architecture, it achieves competitive performance against top international models like Claude Opus 4.6 while maintaining high throughput and efficient inference. M2.5 supports full-stack development for PC, App, and cross-platform applications, and excels in agentic workflows including automated customer support, data-analysis pipelines, and complex task execution.

Fecha de lanzamiento

2026-02-12

Parámetros

230.0B

Longitud del contexto

205K

Modalidades

image, text

Radar de capacidades

general

coding

reasoning

scienceest.

agents

multimodal

Science usa un proxy de razonamiento cuando los benchmarks científicos dedicados no están disponibles.

Rankings

Dominio	#Posición	Puntuación	Fuente
Capacidad agéntica	20	65.0	LS
Ranking de codificación	80	71.0	AA
Ranking general	62	73.0	AA
Ciencia	75	65.0	AA

Puntuaciones de benchmarks (LLM Stats)

Agents

BrowseComp

76.3%Aut.

MEWC

74.4%Aut.

SWE-Bench Pro

55.4%Aut.

VIBE-Pro

54.2%Aut.

Code

SWE-Bench Verified

80.2%Aut.

Multi-SWE-Bench

51.3%Aut.

Finance

GDPval-MM

59.0%Aut.

General

BFCL_v3_MultiTurn

76.8%Aut.

Índices de evaluación AA

Intelligence Index

33.7

Tau2

1.0

Gpqa

0.8

Ifbench

0.7

Lcr

0.7

Scicode

0.4

Terminalbench Hard

0.3

Hle

0.2

Puntuaciones por categoría LLM Stats

Frontend Development

Agents

Multimodal

Reasoning

Finance

General

Code

Precios

Precio de entrada$0.3 / 1M tokens

Precio de salida$1.2 / 1M tokens

Precio mixto (3:1)$0.525 / 1M tokens

Precio de lectura caché$0.03 / 1M tokens

Precio de escritura caché$0.375 / 1M tokens

Velocidad

Tokens/seg245.4

Retraso del primer token8.23s

Tiempo hasta la respuesta16.38s

Ranking de Precios por Proveedor

41 proveedores

Más barato: MiniMaxMás caro: Regolo AI

ProveedorEntradaSalida

1MiniMaxMás barato

2CrofAI

$0.11

$0.95

3OpenRouter

$0.15

$0.9

4Chutes

$0.15

$1.2

5Deep Infra

$0.15

$1.15

6routing.run

$0.193

$1.238

7DInference

$0.22

$0.88

8Inceptron

$0.24

$0.9

9Kilo Gateway

$0.25

$1.2

10D.Run (China)

$0.29

$1.16

11NanoGPT

$0.3

$1.2

12SiliconFlow (China)

$0.3

$1.22

13OpenCode Go

$0.3

$1.2

14Alibaba (China)

$0.3

$1.2

15Hugging Face

$0.3

$1.2

16ZenMux

$0.3

$1.2

17NovitaAI

$0.3

$1.2

18Weights & Biases

$0.3

$1.2

19OpenCode Zen

$0.3

$1.2

20Nebius Token Factory

$0.3

$1.2

21Amazon Bedrock

$0.3

$1.2

22Baseten

$0.3

$1.2

23FrogBot

$0.3

$1.2

24CloudFerro Sherlock

$0.3

$1.2

25Meganova

$0.3

$1.2

26DigitalOcean

$0.3

$1.2

27Friendli

$0.3

$1.2

28SiliconFlow

$0.3

$1.2

29Vercel AI Gateway

$0.3

$1.2

30LLM Gateway

$0.3

$1.2

31Together AI

$0.3

$1.2

32HPC-AI

$0.3

$1.2

33Clarifai

$0.3

$1.2

34OrcaRouter

$0.3

$1.2

35Merge Gateway

$0.3

$1.2

36Cortecs

$0.32

$1.18

37Venice AI

$0.34

$1.19

38Synthetic

$0.6

39MiniMax (minimax.io)

$0.6

$2.4

40MiniMax (minimaxi.com)

$0.6

$2.4

41Regolo AI

$0.8

$3.5

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas

LLM Stats Artificial Analysis