MiniMax: MiniMax M2.1
Analysis Summary
MiniMax M2.1 is a capable mid-tier model from MiniMax with an intelligence index of 31.4 and a standout agentic index of 57.1, one of the stronger agentic scores outside the top flagship tier. Its tau2 score of 0.854 indicates reliable multi-step task completion, and math performance (82.7) and livecodebench (0.81) are strong for its price bracket. Tool use and function calling are supported across a 204K context window.
For businesses, M2.1 is well suited to agentic workflows, automated research pipelines, and structured data tasks where multi-step reliability matters more than raw reasoning depth. The 204K context window handles long documents comfortably. Its main limitation is the absence of vision support, which restricts multimodal use cases.
At $0.29 input and $0.95 output per million tokens, it offers reasonable value for agentic and tool-use workloads. Teams running autonomous agents or complex orchestration pipelines will find it a credible option at this price tier. Note that MiniMax is less established in enterprise tooling, so integration support should be verified before production deployment.
Assessed June 30, 2026
Editorial notes
MiniMax M2.1 delivers strong agentic performance (57.1 agentic index) and a high tau2 score of 0.854, with solid reasoning and math capability at a competitive price point for its tier.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How MiniMax: MiniMax M2.1 compares
MiniMax: MiniMax M2.1 ranks #72 of 385 AI models we track for overall intelligence, #71 of 293 for agentic tasks. Its 205K-token context window is larger than 67% of the models we list. At $0.29 per million input tokens it is cheaper than 44% of comparable models.
About MiniMax: 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..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does MiniMax: MiniMax M2.1 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
minimax/minimax-m2.1
|
| Provider | minimax |
| Release Date | December 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 | $0.29 | $0.000290 |
| Output | $0.95 | $0.000950 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about MiniMax: MiniMax M2.1
How much does MiniMax: MiniMax M2.1 cost?
MiniMax: MiniMax M2.1 costs $0.29 per million input tokens and $0.95 per million output tokens.
What is the context window of MiniMax: MiniMax M2.1?
MiniMax: MiniMax M2.1 has a context window of 204,800 tokens (205K).
What can MiniMax: MiniMax M2.1 do?
MiniMax: MiniMax M2.1 supports tool use and function calling.
Who created MiniMax: MiniMax M2.1?
MiniMax: MiniMax M2.1 is developed by MiniMax and was released on December 23, 2025.
