MiniMax M2.1

About MiniMax M2.1

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. Learn more about using reasoning_details to pass back reasoning in our [docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#preserving-reasoning-blocks).

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

MiniMax Model Lineup

Compare all models from MiniMax to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

DeepSeek V3

DeepSeek

Input: $0.32

Output: $0.89

Context: 164k

WizardLM-2 8x22B

Microsoft

Input: $0.62

Output: $0.62

Context: 66k

Codestral 2508

Mistral

Input: $0.30

Output: $0.90

Context: 256k

GLM 4.6V

Zhipu Ai

Input: $0.30

Output: $0.90

Context: 131k

💡 Cheaper Alternatives

Same Brand (MiniMax)

Cross Brand

🚀 Quick Start

Get started with MiniMax M2.1 API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="minimax/minimax-m2.1",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision