# MiniMax-M2.5 vs test-novita-kimi k3 - AI Model Comparison

- Page: https://opencode.ai/data/compare/minimax/minimax-m2-5/moonshot/test-novita-kimi-k3
- Updated: 2026-10-02T10:37:25.000Z

|  | MiniMax-M2.5 | test-novita-kimi k3 |
| --- | --- | --- |
| Lab | MiniMax | Moonshot |
| Context window | 205K | - |
| Max output | 131K | - |
| Input modalities | text | - |
| Reasoning | Yes | - |
| Tool calling | Yes | - |
| Open weights | Yes | - |
| Release date | 2026-02-12 | - |
| Input price per 1M tokens | $0.30 | - |
| Output price per 1M tokens | $1.20 | - |
| Cached input price per 1M tokens | $0.03 | - |
| OpenCode tokens: past 2 months | 25B | 24K |
| Share of all tokens | 0% | 0% |
| Rank by tokens last week | #42 | #47 |
| Unique users | 37K | 1 |
| Weekly retention | 59.5% | - |

Model pages: [MiniMax-M2.5](https://opencode.ai/data/minimax/minimax-m2-5.md), [test-novita-kimi k3](https://opencode.ai/data/moonshot/test-novita-kimi-k3.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.