Minimax

MiniMax: MiniMax M2.5 Lightning

Chat
minimax/minimax-m2.5-lightning

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.

200K janela de contexto
131K tokens máx de saída
Lançamento: 2026-02-12
Protocolos Suportados:OpenAIopenaiAnthropicanthropic
Provedores Disponíveis:MinimaxMiniMax
Capacidades:Function CallingRaciocínioPrompt CachingBusca Web

Preços

TipoPreço
Tokens de Entrada$0.3/M
Tokens de Saída$2.4/M
Leitura de Cache$0.03/M
Escrita de Cache$0.375/M

Exemplos de Código

from openai import OpenAI
client = OpenAI(
base_url="https://api.ofox.ai/v1",
api_key="YOUR_OFOX_API_KEY",
)
response = client.chat.completions.create(
model="minimax/minimax-m2.5-lightning",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)

Perguntas Frequentes

MiniMax: MiniMax M2.5 Lightning na Ofox.ai custa $0.3/M por milhão de tokens de entrada e $2.4/M por milhão de tokens de saída. Pague por uso, sem mensalidade.

Discord

Junte-se ao nosso servidor Discord

Discord