MiniMax-M2 8B: pricing, context window and benchmarks
MiniMax-M2 8B is a small open-weight model from MiniMax. It offers a 32,768-token context window, costs $1.65 per million input tokens and $8.35 per million output tokens, and averages 61.7 across the index's benchmark suite.
Pricing
MiniMax-M2 8B costs $1.65 per million input tokens and $8.35 per million output tokens. A blended 3:1 input-to-output mix works out to about $3.32 per million tokens. Cached input is listed at $0.19 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $1.65 | per 1M tokens |
| Output | $8.35 | per 1M tokens |
| Cached input | $0.19 | per 1M tokens |
| Blended 3:1 | $3.32 | estimate per 1M tokens |
| 1M in + 1M out | $10.00 | 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 | 65.4 | 446 | 26th | |
| GPQA Diamond | 56.9 | 442 | 26th | |
| SWE-bench Verified | 50.0 | 423 | 30th | |
| HumanEval | 65.8 | 433 | 28th | |
| MATH-500 | 62.2 | 441 | 27th | |
| AIME 2025 | 53.4 | 429 | 29th | |
| LiveCodeBench | 50.0 | 448 | 25th | |
| IFEval | 71.8 | 431 | 28th | |
| TruthfulQA | 67.5 | 425 | 29th | |
| HellaSwag | 76.2 | 425 | 29th | |
| MMMU | 59.0 | 440 | 27th | |
| Arena Elo | 1300.9 | 419 | 30th |
What MiniMax-M2 8B is good for
MiniMax-M2 8B 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 $1.65 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $1.65 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
Trade-offs
- 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 |
|---|---|---|---|---|
| Sonar Nano | Perplexity | 4096 | $4.37 | 61.9 |
| GLM-4.6 7B | Zhipu AI | 16384 | $1.52 | 61.8 |
| GPT-NeoX | EleutherAI | 16384 | $1.57 | 61.7 |
| MiniMax-M2 8B | MiniMax | 32768 | $1.65 | 61.7 |
| Auto Mini | OpenRouter | 4096 | $4.24 | 61.6 |
| Mistral Large 3 8B | Mistral AI | 16384 | $1.62 | 61.6 |
FAQ
How much does MiniMax-M2 8B cost?
MiniMax-M2 8B is listed at $1.65 per million input tokens and $8.35 per million output tokens. Cached input is $0.19 per million tokens. A blended 3:1 input-to-output mix is about $3.32 per million tokens.
What is the context window of MiniMax-M2 8B?
MiniMax-M2 8B has a context window of 32,768 tokens and can emit up to 32,768 output tokens per request in this index.
Is MiniMax-M2 8B open weights?
Yes. MiniMax-M2 8B is listed as an open-weight model under a open weights licence.
How does MiniMax-M2 8B score on benchmarks?
MiniMax-M2 8B averages 61.7 across the scored benchmarks in this index, ranking #435 of 600 models. Its strongest relative result is Arena Elo at 1300.9.
What is MiniMax-M2 8B best for?
MiniMax-M2 8B 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 $1.65 per million input tokens it can handle a large share of production traffic.