MiniMax

​

Available models

​

Why MiniMax?

• Multi-file code editing — understands project context across files
• Bug fixing — diagnoses and fixes real GitHub issues
• Agentic workflows — works well with tool use and multi-step coding tasks
• Long context — 196K tokens covers large codebases

​

Recommendation

• Use minimax-m2.5 when you want a proven SWE-bench-focused agentic coding model.
• Use minimax-m2.7 when you want the newer MiniMax generation for agentic coding, debugging, and productivity workflows.

from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="minimax-m2.7",
    messages=[{"role": "user", "content": "Fix the race condition in this code: ..."}]
)