MiniMax-M2 Base: pricing, context window and benchmarks
MiniMax-M2 Base is a multimodal model from MiniMax. It offers a 65,536-token context window, costs $4.20 per million input tokens and $21.42 per million output tokens, and averages 76.4 across the index's benchmark suite.
Pricing
MiniMax-M2 Base costs $4.20 per million input tokens and $21.42 per million output tokens. A blended 3:1 input-to-output mix works out to about $8.51 per million tokens. Cached input is listed at $0.53 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.20 | per 1M tokens |
| Output | $21.42 | per 1M tokens |
| Cached input | $0.53 | per 1M tokens |
| Blended 3:1 | $8.51 | estimate per 1M tokens |
| 1M in + 1M out | $25.62 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 80.0 | 184 | 69th | |
| GPQA Diamond | 72.6 | 207 | 66th | |
| SWE-bench Verified | 62.8 | 259 | 57th | |
| HumanEval | 80.0 | 233 | 61th | |
| MATH-500 | 79.5 | 223 | 63th | |
| AIME 2025 | 75.2 | 152 | 75th | |
| LiveCodeBench | 66.3 | 269 | 55th | |
| IFEval | 83.0 | 244 | 59th | |
| TruthfulQA | 79.9 | 182 | 70th | |
| HellaSwag | 87.8 | 150 | 75th | |
| MMMU | 73.3 | 210 | 65th | |
| Arena Elo | 1404.3 | 197 | 67th |
What MiniMax-M2 Base is good for
MiniMax-M2 Base is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $4.20 per million input tokens, it sits in the mid-range of the index, and the 65,536-token context window is enough for large files and multi-file diffs.
Strengths
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- No standout weakness in the indexed specifications, but real-world behaviour still needs testing.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Claude Sonnet 4.5 Mini | Anthropic | 32768 | $11.43 | 76.5 |
| Qwen3-Max Mini | Alibaba Cloud | 128000 | $11.13 | 76.5 |
| Yi-Lightning Instruct | 01.AI | 128000 | $4.16 | 76.5 |
| MiniMax-M2 Base | MiniMax | 65536 | $4.20 | 76.4 |
| Nemotron 4 Instruct | NVIDIA | 65536 | $4.10 | 76.4 |
| Llama 3.1 | Meta AI | 200000 | $4.16 | 76.3 |
FAQ
How much does MiniMax-M2 Base cost?
MiniMax-M2 Base is listed at $4.20 per million input tokens and $21.42 per million output tokens. Cached input is $0.53 per million tokens. A blended 3:1 input-to-output mix is about $8.51 per million tokens.
What is the context window of MiniMax-M2 Base?
MiniMax-M2 Base has a context window of 65,536 tokens and can emit up to 65,536 output tokens per request in this index.
Is MiniMax-M2 Base open weights?
Yes. MiniMax-M2 Base is listed as an open-weight model under a open weights licence.
How does MiniMax-M2 Base score on benchmarks?
MiniMax-M2 Base averages 76.4 across the scored benchmarks in this index, ranking #209 of 600 models. Its strongest relative result is Arena Elo at 1404.3.
What is MiniMax-M2 Base best for?
MiniMax-M2 Base is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $4.20 per million input tokens, it sits in the mid-range of the index, and the 65,536-token context window is enough for large files and multi-file diffs.