Model Library/MiniMax M2.5
MiniMax M2.5

MiniMax M2.5

minimax/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.

Características

API serverless

Documentación

minimax/minimax-m2.5 is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.

Serverless disponible

Ejecuta consultas de inmediato, paga solo por el uso

Entrada$0.3 / M Tokens
Lectura de caché$0.03 / M Tokens
Salida$1.2 / M Tokens

Usa los siguientes ejemplos de código para integrarte con nuestra API:

1from openai import OpenAI
2
3client = OpenAI(
4    api_key="<Your API Key>",
5    base_url="https://api.novita.ai/openai"
6)
7
8response = client.chat.completions.create(
9    model="minimax/minimax-m2.5",
10    messages=[
11        {"role": "system", "content": "You are a helpful assistant."},
12        {"role": "user", "content": "Hello, how are you?"}
13    ],
14    max_tokens=131100,
15    temperature=0.7
16)
17
18print(response.choices[0].message.content)

Información

Proveedor
MiniMax
Cuantización
fp8

Funcionalidad compatible

Longitud del contexto
200K
Salida máxima
128K
Serverless
Compatible
Function Calling
Compatible
Structured Output
Compatible
Reasoning
Compatible
API de Anthropic
Compatible
Capacidades de entrada
text
Capacidades de salida
text

Todo lo que necesitas para crear IA de producción.

Más de 200 modelos, GPUs bajo demanda y entornos de ejecución seguros para agentes, unificados bajo una API. Gratis para empezar, escala a medida que creces.