MiniMax M2.1
MiniMax M2.1 is a lightweight large language model developed by MiniMax, designed specifically for coding tasks and agentic workflows. It features a large context window and built-in reasoning and tool-calling capabilities to assist in modern application development.
MiniMax M2.1 specs and pricing
- Provider: MiniMax
- Released: December 23, 2025
- Context window: 205K tokens
- Max output: 131K tokens
- Input: text
- Output: text
- Price: $0.30 input / $1.20 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What MiniMax M2.1 is good at
- Writing and debugging software code
- Building complex agentic workflows
- Developing modern software applications
To-dos to try with MiniMax M2.1
- Analyze this codebase and suggest an optimized refactoring for the authentication module
- Write a script that uses tool-calling to fetch data from an API and format it into a JSON report
- Step through this logic error in my function and explain the reasoning behind the fix
FAQ
- What is the primary focus of the MiniMax M2.1 model? The model is optimized for coding, agentic workflows, and modern application development.
- Does this model support complex task execution? Yes, it includes built-in reasoning and tool-calling capabilities to support agentic workflows.
- How much does MiniMax M2.1 cost? MiniMax M2.1 costs $0.30 per million input tokens and $1.20 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.01 credits ($1 = 100 credits).
- What is the context window of MiniMax M2.1? MiniMax M2.1 can read up to 205K tokens at once and write up to 131K tokens in one reply.
- Can I use MiniMax M2.1 without coding? Yes. In todo.is you pick MiniMax M2.1 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.