# MiniMax-M2.5 vs Kimi K2.6 - AI Model Comparison

- Page: https://opencode.ai/data/compare/minimax/minimax-m2-5/moonshotai/kimi-k2-6
- Updated: 2026-10-04T03:44:06.000Z

|  | MiniMax-M2.5 | Kimi K2.6 |
| --- | --- | --- |
| Lab | MiniMax | Moonshot |
| Context window | 205K | 262K |
| Max output | 131K | 262K |
| Input modalities | text | text, image, video |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Open weights | Yes | Yes |
| Release date | 2026-02-12 | 2026-04-21 |
| Input price per 1M tokens | $0.30 | $0.74 |
| Output price per 1M tokens | $1.20 | $3.72 |
| Cached input price per 1M tokens | $0.03 | - |
| OpenCode tokens: past 2 months | 25B | 272B |
| Share of all tokens | 0% | 0.0% |
| Rank by tokens last week | #42 | #38 |
| Unique users | 35K | 147K |
| Weekly retention | 59.5% | 55.9% |

Model pages: [MiniMax-M2.5](https://opencode.ai/data/minimax/minimax-m2-5.md), [Kimi K2.6](https://opencode.ai/data/moonshotai/kimi-k2-6.md)

## 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.