MiniMax M2

minimax/minimax-m2

A MiniMax MoE model (230B total, 10B active) with agentic capabilities, function calling, and advanced reasoning; 200K context with up to 128K output including chain-of-thought.

Pricing

Specifications

Use MiniMax M2

Point your existing OpenAI SDK at xKiro and pass minimax/minimax-m2 as the model. Nothing else in your code changes.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.xkiro.com/v1",
    api_key="YOUR_XKIRO_KEY",
)

response = client.chat.completions.create(
    model="minimax/minimax-m2",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

max_tokens · temperature · top_p · stream · tools · tool_choice

Related models

• MiniMax M2.1Free
• MiniMax M2.1 HighspeedFree
• MiniMax M2.5Free
• MiniMax M2.5 HighspeedFree
• MiniMax M2.7Free
• MiniMax M2.7 HighspeedFree