MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.
Compared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance.
To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns.
Recent activity on MiniMax M2.1
Throughput
| Providers | Min (tokens/s) | Max (tokens/s) | Avg (tokens/s) |
|---|---|---|---|
| MiniMax | 24.04 | 52.54 | 34.99 |
First Token Latency
| Providers | Min (ms) | Max (ms) | Avg (ms) |
|---|---|---|---|
| MiniMax | 1964 | 2927 | 2504.77 |
Sample code and API for MiniMax M2.1
pythonfrom openai import OpenAI client = OpenAI( base_url="https://zenmux.ai/api/v1", api_key="<ZENMUX_API_KEY>", ) # Chat Completion completion = client.chat.completions.create( model="minimax/minimax-m2.1", messages=[ { "role": "user", "content": "What is the meaning of life?" } ] ) print(completion.choices[0].message.content)