# MiniMax-M2.5 Usage, Cost & Rank | OpenCode Data

> MiniMax-M2.5 ranked #42 by tokens across OpenCode last week, with 0% of tokens over the past two months. MiniMax-M2.5 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens.

Prior MiniMax coding model for agent workflows, office edits, and automation

- Page: https://opencode.ai/data/minimax/minimax-m2-5
- JSON: https://opencode.ai/data/minimax/minimax-m2-5.json
- Model ID: minimax/MiniMax-M2.5
- Lab: MiniMax
- Updated: 2026-10-02T09:36:21.000Z

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 205K |
| Max output | 131K |
| Knowledge cutoff | - |
| Release date | 2026-02-12 |
| Input modalities | text |
| Output modalities | text |
| Reasoning | Yes |
| Tool calling | Yes |
| Open weights | Yes |
| Weights | [Hugging Face](https://huggingface.co/MiniMaxAI/MiniMax-M2.5) |

## Pricing: USD per 1M tokens

| Input | Output | Cached input | Cache write |
| --- | --- | --- | --- |
| $0.30 | $1.20 | $0.03 | - |

## OpenCode usage: past 2 months

| Metric | Value |
| --- | --- |
| Rank by tokens last week | #42 |
| Tokens | 25B |
| Share of all tokens | 0% |
| Change vs previous 2 months | -32% |
| Unique users | 37K |
| Completed sessions | 42,028 |
| Average tokens per session | 603K |
| Average cost per session | $0.0719 |
| Total spend | $3,023 |
| Input tokens served from cache | 84.5% |
| Weekly retention | 59.5% |

## Daily usage: past 2 months

| Date | Tokens | Unique users | Sessions |
| --- | --- | --- | --- |
| 2026-08-08 | 404M | 911 | 9 |
| 2026-08-09 | 456M | 830 | 7 |
| 2026-08-10 | 718M | 1K | 12 |
| 2026-08-11 | 821M | 979 | 1 |
| 2026-08-12 | 606M | 953 | 0 |
| 2026-08-13 | 505M | 1.1K | 0 |
| 2026-08-14 | 488M | 1.5K | 0 |
| 2026-08-15 | 394M | 835 | 0 |
| 2026-08-16 | 440M | 846 | 1 |
| 2026-08-17 | 1.2B | 1.4K | 0 |
| 2026-08-18 | 884M | 1.3K | 93 |
| 2026-08-19 | 690M | 881 | 105 |
| 2026-08-20 | 589M | 830 | 114 |
| 2026-08-21 | 385M | 1.1K | 66 |
| 2026-08-22 | 330M | 721 | 52 |
| 2026-08-23 | 421M | 712 | 23 |
| 2026-08-24 | 1B | 1K | 177 |
| 2026-08-25 | 810M | 765 | 41 |
| 2026-08-26 | 544M | 781 | 48 |
| 2026-08-27 | 632M | 673 | 30 |
| 2026-08-28 | 433M | 575 | 35 |
| 2026-08-29 | 442M | 522 | 241 |
| 2026-08-30 | 324M | 458 | 158 |
| 2026-08-31 | 643M | 757 | 142 |
| 2026-09-01 | 621M | 621 | 185 |
| 2026-09-02 | 878M | 562 | 134 |
| 2026-09-03 | 469M | 588 | 146 |
| 2026-09-04 | 525M | 752 | 466 |
| 2026-09-05 | 494M | 442 | 354 |
| 2026-09-06 | 363M | 446 | 346 |
| 2026-09-07 | 463M | 516 | 950 |
| 2026-09-08 | 362M | 429 | 1,649 |
| 2026-09-09 | 434M | 362 | 1,415 |
| 2026-09-10 | 456M | 680 | 4,337 |
| 2026-09-11 | 196M | 551 | 2,140 |
| 2026-09-12 | 152M | 436 | 1,436 |
| 2026-09-13 | 369M | 452 | 1,143 |
| 2026-09-14 | 739M | 637 | 1,826 |
| 2026-09-15 | 543M | 605 | 1,485 |
| 2026-09-16 | 386M | 659 | 1,901 |
| 2026-09-17 | 557M | 721 | 1,838 |
| 2026-09-18 | 319M | 603 | 1,652 |
| 2026-09-19 | 282M | 484 | 2,716 |
| 2026-09-20 | 169M | 469 | 2,967 |
| 2026-09-21 | 548M | 610 | 2,205 |
| 2026-09-22 | 334M | 665 | 2,152 |
| 2026-09-23 | 251M | 503 | 1,432 |
| 2026-09-24 | 184M | 466 | 1,351 |
| 2026-09-25 | 304M | 419 | 1,581 |
| 2026-09-26 | 279M | 453 | 1,034 |
| 2026-09-27 | 371M | 473 | 1,143 |
| 2026-09-28 | 58M | 191 | 375 |
| 2026-09-29 | 0 | 0 | 0 |
| 2026-09-30 | 0 | 0 | 0 |
| 2026-10-01 | 4.2M | 13 | 16 |
| 2026-10-02 | 8.8M | 152 | 298 |

## Top countries: past 2 months

| Rank | Country | Tokens | Share |
| --- | --- | --- | --- |
| 1 | United States | 5B | 19.6% |
| 2 | Brazil | 2.4B | 9.6% |
| 3 | China | 2.3B | 9% |
| 4 | Germany | 1.8B | 7.2% |
| 5 | Canada | 1.7B | 6.8% |
| 6 | Vietnam | 1B | 4.1% |
| 7 | Indonesia | 1B | 3.8% |
| 8 | Singapore | 900M | 3.6% |
| 9 | France | 700M | 2.7% |
| 10 | Spain | 600M | 2.5% |
| 11 | United Kingdom | 500M | 2.2% |
| 12 | Japan | 500M | 1.8% |
| 13 | India | 400M | 1.8% |
| 14 | Finland | 400M | 1.7% |
| 15 | Switzerland | 400M | 1.6% |

## Nearby models by tokens last week

| Rank | Model | Lab | Tokens |
| --- | --- | --- | --- |
| 38 | [glm-5.1](https://opencode.ai/data/zhipuai/glm-5-1.md) | Zhipu | 2.5B |
| 39 | [qwen3.6-plus](https://opencode.ai/data/alibaba/qwen3-6-plus.md) | Qwen | 1.9B |
| 40 | [test-novita-dsf4.1](https://opencode.ai/data/deepseek/test-novita-dsf4-1.md) | DeepSeek | 986M |
| 41 | [qwen3.7-max](https://opencode.ai/data/alibaba/qwen3-7-max.md) | Qwen | 922M |
| 42 | [minimax-m2.5](https://opencode.ai/data/minimax/minimax-m2-5.md) | MiniMax | 721M |
| 43 | [gpt-5-nano](https://opencode.ai/data/openai/gpt-5-nano.md) | OpenAI | 290M |
| 44 | [test](https://opencode.ai/data/openai/test.md) | OpenAI | 281M |
| 45 | [exo](https://opencode.ai/data/unknown/exo.md) | - | 533K |
| 46 | [qwen3.8-27b](https://opencode.ai/data/alibaba/qwen3-8-27b.md) | Qwen | 62K |
| 47 | [test-novita-kimi k3](https://opencode.ai/data/moonshot/test-novita-kimi-k3.md) | Moonshot | 24K |

## Benchmarks

| Benchmark | Score | Metric | Source |
| --- | --- | --- | --- |
| SWE-Bench Verified | 75.8 | resolved | https://www.swebench.com/ |
| SWE-Atlas Codebase QnA | 10.3 | score | https://labs.scale.com/leaderboard/sweatlas-qna |
| SWE-Atlas Refactoring | 19.52 | score | https://labs.scale.com/leaderboard/sweatlas-refactoring |
| SWE-Atlas Test Writing | 18.6 | score | https://labs.scale.com/leaderboard/sweatlas-tw |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.