MiniMax model product
MiniMax M2.1
1 is an enhanced large language model focused on multi-language programming and real-world complex tasks.
Updated Aug 12, 2026. Default version: MiniMax M2.1
LLMBoard score53.7MiniMax M2.1
Coverage100%15 benchmark families
Context window204.8KTokens
Official input price$0.30MiniMax (minimax.io) API
MiniMax M2.1 Specifications
Technical details for the model's default version.
- Version
- MiniMax M2.1
- Released
- Dec 23, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 230B
- Context window
- 204.8K
- Max output
- 131.1K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
MiniMax M2.1 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
MiniMax M2.1 Benchmark Results
Benchmark scores for MiniMax M2.1.
| OctoCodingBench | 26.1% | 01 | 1 | 100.0% | C | |
| SWE-Perf | 3.1% | 01 | 1 | 100.0% | C | |
| SWE-Review | 8.9% | 01 | 1 | 100.0% | C | |
| SWT-Bench | 69.3% | 01 | 1 | 100.0% | C | |
| VIBE | 88.6% | 01 | 1 | 100.0% | C | |
| VIBE Android | 89.7% | 01 | 1 | 100.0% | C | |
| VIBE Backend | 86.7% | 01 | 1 | 100.0% | C | |
| VIBE iOS | 88.0% | 01 | 1 | 100.0% | C | |
| VIBE Simulation | 87.1% | 01 | 1 | 100.0% | C | |
| VIBE Web | 91.5% | 01 | 1 | 100.0% | C | |
| Terminal-Bench | 47.9% | 02 | 25 | 95.8% | C | |
| Multi-SWE-Bench | 49.4% | 03 | 6 | 60.0% | C | |
| MMLU-Pro | 88.0% | 04 | 129 | 97.7% | C | |
| AA-LCR | 62.0% | 11 | 16 | 33.3% | C | |
| SciCode | 39.0% | 13 | 19 | 33.3% | C | |
| LiveCodeBench | 78.0% | 14 | 73 | 81.9% | C | |
| SWE-bench Multilingual | 72.5% | 14 | 34 | 60.6% | C | |
| IFBench | 70.0% | 18 | 29 | 39.3% | C | |
| Tau2 Telecom | 87.0% | 18 | 35 | 50.0% | C | |
| Toolathlon | 43.5% | 22 | 31 | 30.0% | C | |
| BrowseComp | 62.0% | 33 | 58 | 43.9% | C | |
| Humanity's Last Exam | 22.0% | 55 | 93 | 41.3% | C | |
| AIME 2025 | 81.0% | 69 | 114 | 39.8% | C | |
| SWE-Bench Verified | 67.0% | 71 | 105 | 32.7% | C | |
| GPQA | 81.0% | 83 | 234 | 64.8% | C |
MiniMax M2.1 Arena Results
Preference and agent-evaluation results for the default version.
| webdev | overall | 67 | 1386.8 | 7,299 | N/A | |
| text factuality | overall | 121 | 1411.2 | 16,744 | N/A | |
| text | overall | 141 | 1391.1 | 17,165 | N/A | |
| text style control | overall | 159 | 1384.2 | 17,165 | N/A |
MiniMax M2.1 Runtime Performance
Provider-specific output speed and catalog latency for MiniMax M2.1. Runtime does not affect the capability score.
| MiniMax | 353.425 tok/s | 0.992 s | 1M | 1M |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
MiniMax M2.1 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.30 input, $1.2 output per 1M
- Official provider
- MiniMax (minimax.io)
- Lowest third-party
- From $0.27 input, $1.1 output per 1M via LLM Gateway
- Tracked offerings
- 22
| MiniMax Token Plan (minimax.io) | MiniMax-M2.1 | global | N/A | N/A | 204.8K | |
| MiniMax Token Plan (minimaxi.com) | MiniMax-M2.1 | global | N/A | N/A | 204.8K | |
| LLM Gateway | minimax-m2.1 | global | $0.27 | $1.1 | 204.8K | |
| Meganova | MiniMaxAI/MiniMax-M2.1 | global | $0.28 | $1.2 | 196.6K | |
| OpenCode Zen | minimax-m2.1 | global | $0.30 | $1.2 | 204.8K | |
| 302.AI | MiniMax-M2.1 | global | $0.30 | $1.2 | 1M | |
| ZenMux | minimax/minimax-m2.1 | global | $0.30 | $1.2 | 204K | |
| Amazon Bedrock | minimax.minimax-m2.1 | global | $0.30 | $1.2 | 204.8K | |
| MiniMax (minimax.io) | MiniMax-M2.1 | global | $0.30 | $1.2 | 204.8K | |
| Kilo Gateway | minimax/minimax-m2.1 | global | $0.30 | $1.2 | 204.8K | |
| Merge Gateway | minimax/minimax-m2.1 | global | $0.30 | $1.2 | 204.8K | |
| Vercel AI Gateway | minimax/minimax-m2.1 | global | $0.30 | $1.2 | 204.8K | |
| NovitaAI | minimax/minimax-m2.1 | global | $0.30 | $1.2 | 204.8K | |
| OpenRouter | minimax/minimax-m2.1 | global | $0.30 | $1.2 | 204.8K | |
| Hugging Face | MiniMaxAI/MiniMax-M2.1 | global | $0.30 | $1.2 | 204.8K | |
| Jiekou.AI | minimax/minimax-m2.1 | global | $0.30 | $1.2 | 204.8K | |
| MiniMax (minimaxi.com) | MiniMax-M2.1 | global | $0.30 | $1.2 | 204.8K | |
| NanoGPT | minimax/minimax-m2.1 | global | $0.33 | $1.32 | 200K | |
| Cortecs | minimax-m2.1 | global | $0.359 | $1.44 | 196K | |
| Moark | MiniMax-M2.1 | global | $2.1 | $8.4 | 204.8K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
MiniMax M2.1 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| MiniMax M2.1 | 53.7 | 230B | 204.8K | 131.1K | Yes | MIT |
What is MiniMax M2.1?
Key information about MiniMax M2.1 and its available data.
1 is an enhanced large language model focused on multi-language programming and real-world complex tasks. 5.
1 significantly strengthens native Android and iOS development, delivers enhanced design comprehension and aesthetic expression for web/app scenarios, and provides more concise responses with improved speed and reduced token consumption.
It excels across various coding agent frameworks including Claude Code, Droid (Factory AI), Cline, Kilo Code, Roo Code, and BlackBox.
Data as of 2026-08-11.
MiniMax M2.1 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to MiniMax M2.1
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MI
MiniMax M2.5
MiniMax
MI
MiniMax M2.7
MiniMax
MI
MiniMax M2
MiniMax
MI
MiniMax M1 80K
MiniMax
MI
MiniMax M3
MiniMax
MI
MiniMax M1 40K
MiniMax
FAQ
Common questions about MiniMax M2.1.
When was MiniMax M2.1 released?
MiniMax M2.1's default version was released on Dec 23, 2025.
How much does MiniMax M2.1 cost?
MiniMax M2.1's official API price is $0.30 per million input tokens and $1.2 per million output tokens via MiniMax (minimax.io). The lowest tracked third-party offer starts at $0.27 input and $1.1 output via LLM Gateway.
Who created MiniMax M2.1?
MiniMax M2.1 was created by MiniMax.
What is the context window for MiniMax M2.1?
The default version has a 204.8K token context window.
Is MiniMax M2.1 open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer MiniMax M2.1?
22 provider offerings are linked to the default version.
What models should I compare MiniMax M2.1 with?
Nearby ranked alternatives include GLM 4.6, Grok 4 Fast, GPT-5.5-Instant.