MiniMax-M2 1.5B: pricing, context window and benchmarks
MiniMax-M2 1.5B is a small open-weight model from MiniMax. It offers a 16,384-token context window, costs $0.84 per million input tokens and $2.96 per million output tokens, and averages 54.6 across the index's benchmark suite.
Pricing
MiniMax-M2 1.5B costs $0.84 per million input tokens and $2.96 per million output tokens. A blended 3:1 input-to-output mix works out to about $1.37 per million tokens. Cached input is listed at $0.09 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $0.84 | per 1M tokens |
| Output | $2.96 | per 1M tokens |
| Cached input | $0.09 | per 1M tokens |
| Blended 3:1 | $1.37 | estimate per 1M tokens |
| 1M in + 1M out | $3.80 | 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 | 59.6 | 531 | 12th | |
| GPQA Diamond | 49.9 | 525 | 13th | |
| SWE-bench Verified | 42.8 | 492 | 18th | |
| HumanEval | 58.3 | 520 | 13th | |
| MATH-500 | 53.5 | 530 | 12th | |
| AIME 2025 | 39.6 | 543 | 10th | |
| LiveCodeBench | 41.5 | 530 | 12th | |
| IFEval | 65.9 | 521 | 13th | |
| TruthfulQA | 63.0 | 492 | 18th | |
| HellaSwag | 72.0 | 500 | 17th | |
| MMMU | 54.6 | 501 | 17th | |
| Arena Elo | 1238.4 | 516 | 14th |
What MiniMax-M2 1.5B is good for
MiniMax-M2 1.5B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $0.84 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $0.84 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
Trade-offs
- Context window of 16,384 tokens is small for long-document work.
- Average benchmark score is below the index median; test it on your own task.
- Less reliable on open-ended reasoning and complex multi-step instructions.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Yi-Large 7B | 01.AI | 4096 | $0.83 | 55.0 |
| Phi-4 8B | Microsoft | 32768 | $0.96 | 54.9 |
| Mixtral Groq 8B | Groq | 32768 | $0.77 | 54.8 |
| GLM-4.6 1.5B | Zhipu AI | 4096 | $0.92 | 54.7 |
| MiniMax-M2 1.5B | MiniMax | 16384 | $0.84 | 54.6 |
| Mixtral 7B | Mistral AI | 16384 | $0.70 | 54.1 |
FAQ
How much does MiniMax-M2 1.5B cost?
MiniMax-M2 1.5B is listed at $0.84 per million input tokens and $2.96 per million output tokens. Cached input is $0.086 per million tokens. A blended 3:1 input-to-output mix is about $1.37 per million tokens.
What is the context window of MiniMax-M2 1.5B?
MiniMax-M2 1.5B has a context window of 16,384 tokens and can emit up to 16,384 output tokens per request in this index.
Is MiniMax-M2 1.5B open weights?
Yes. MiniMax-M2 1.5B is listed as an open-weight model under a open weights licence.
How does MiniMax-M2 1.5B score on benchmarks?
MiniMax-M2 1.5B averages 54.6 across the scored benchmarks in this index, ranking #527 of 600 models. Its strongest relative result is Arena Elo at 1238.4.
What is MiniMax-M2 1.5B best for?
MiniMax-M2 1.5B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $0.84 per million input tokens it can handle a large share of production traffic.