MiniMax: MiniMax M2
Analysis Summary
MiniMax M2 is a capable large model from MiniMax with an intelligence index of 36.1 and a standout agentic index of 56.3, one of the stronger agentic scores in the broader field. Its livecodebench score of 82.6 and math index of 78.3 are strong, and instruction-following benchmarks are high. Tool use and function calling are supported across a 200K context window.
For businesses, it is particularly well suited to agentic pipelines, multi-step automation, and structured content generation where reliable tool use and instruction following are critical. The combination of strong agentic performance and competitive pricing makes it attractive for teams running high-volume automated workflows. Coding performance is moderate relative to its agentic strength, so pure software engineering tasks may benefit from a coding-specialist model.
At $0.255 input and $1.00 output per million tokens, it offers strong value for its capability tier. Teams building agent-based systems or running large-scale content automation will find the price-to-performance ratio compelling, and it warrants serious evaluation alongside more established flagship models at similar price points.
Assessed June 6, 2026
Editorial notes
MiniMax M2 delivers a strong agentic index of 56.3, excellent livecodebench performance, and broad instruction-following capability at a very competitive price, making it a high-value option for agentic and content workflows.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How MiniMax: MiniMax M2 compares
MiniMax: MiniMax M2 ranks #75 of 377 AI models we track for overall intelligence, #93 of 314 for coding, #68 of 289 for agentic tasks. Its 205K-token context window is larger than 68% of the models we list. At $0.26 per million input tokens it is cheaper than 46% of comparable models.
About MiniMax: MiniMax M2
MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does MiniMax: MiniMax M2 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
minimax/minimax-m2
|
| Provider | minimax |
| Release Date | October 23, 2025 |
| Context Length | 204,800 tokens |
| Max Completion | 196,608 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.26 | $0.000255 |
| Output | $1.00 | $0.001000 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about MiniMax: MiniMax M2
How much does MiniMax: MiniMax M2 cost?
MiniMax: MiniMax M2 costs $0.26 per million input tokens and $1.00 per million output tokens.
What is the context window of MiniMax: MiniMax M2?
MiniMax: MiniMax M2 has a context window of 204,800 tokens (205K).
Is MiniMax: MiniMax M2 good for coding?
On our coding benchmark index, MiniMax: MiniMax M2 ranks #93 of 314 models, placing it in the broader range of the field for code generation and debugging.
What can MiniMax: MiniMax M2 do?
MiniMax: MiniMax M2 supports tool use and function calling.
Who created MiniMax: MiniMax M2?
MiniMax: MiniMax M2 is developed by MiniMax and was released on October 23, 2025.
