MiniMax M2.7 is available through the MiniMax API directly and via OpenRouter. Here’s how to set it up.

Via OpenRouter (easiest)

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="your-openrouter-key"
)

response = client.chat.completions.create(
    model="minimax/minimax-m2.7",
    messages=[
        {"role": "system", "content": "You are a senior developer."},
        {"role": "user", "content": "Write a rate limiter middleware in Express"}
    ],
    temperature=0.3
)
print(response.choices[0].message.content)

Via MiniMax API directly

client = OpenAI(
    base_url="https://api.minimax.chat/v1",
    api_key="your-minimax-key"
)

response = client.chat.completions.create(
    model="MiniMax-M2.7",
    messages=[{"role": "user", "content": "Refactor this to use dependency injection"}]
)

JavaScript/TypeScript

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://openrouter.ai/api/v1',
  apiKey: 'your-openrouter-key',
});

const response = await client.chat.completions.create({
  model: 'minimax/minimax-m2.7',
  messages: [{ role: 'user', content: 'Write unit tests for this module' }],
});

With coding tools

Aider

aider --model openrouter/minimax/minimax-m2.7

OpenCode

{"providers": {"openrouter": {"apiKey": "your-key"}}, "defaultModel": "minimax/minimax-m2.7"}

Pricing

	Input	Output
MiniMax API	$0.30/1M	$1.20/1M
Via OpenRouter	~$0.30/1M	~$1.20/1M

At $0.30/1M, a full day of heavy coding (~1M tokens) costs about $0.50. Compare to Claude Opus at $15/1M.

Tips

1. Use low temperature (0.1-0.3) for coding — reduces randomness
2. M2.7 is fast (100 tok/s) — great for interactive use
3. Combine with Claude for hard problems — use M2.7 for 80% of tasks, Claude for the remaining 20%
4. The 200K context window is generous — load full project context

Related: MiniMax M2.7 Complete Guide · What is MiniMax? · OpenRouter Complete Guide · Best Free AI APIs 2026