Skip to content

MiniMax M2.5

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.

Pricing

Input
$0.2835per 1M tokens
Output
$0.9975per 1M tokens
Cache read
$0.0315per 1M tokens
Max output
32,768tokens

OpenRouter's price plus OpenRouter's 5% platform fee. Deference adds no markup.

opencode.json

{
  "provider": {
    "deference": {
      "npm": "@ai-sdk/openai-compatible",
      "options": { "baseURL": "https://deference.si/v1", "apiKey": "{env:DEFERENCE_API_KEY}" },
      "models": { "minimax/minimax-m2.5": { "limit": { "context": 204800, "output": 32768 } } }
    }
  }
}
OpenCode, set up for MiniMax M2.5

Find us on