# DeepSeek V4 Flash vs Kimi K2.5 - AI Model Comparison

- Page: https://opencode.ai/data/compare/deepseek/deepseek-v4-flash/moonshotai/kimi-k2-5
- Updated: 2026-10-23T06:22:25.000Z

|  | DeepSeek V4 Flash | Kimi K2.5 |
| --- | --- | --- |
| Lab | DeepSeek | Moonshot |
| Context window | 1M | 262K |
| Max output | 384K | 262K |
| Input modalities | text | text, image, video |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Open weights | Yes | Yes |
| Release date | 2026-04-24 | 2026-01-27 |
| Input price per 1M tokens | $0.15 | $0.60 |
| Output price per 1M tokens | $0.60 | $3.00 |
| Cached input price per 1M tokens | $0.0030 | - |
| OpenCode tokens: past 2 months | 100T | 1.2B |
| Share of all tokens | 8.9% | 0% |
| Rank by tokens last week | #10 | - |
| Unique users | 2.1M | 6K |
| Weekly retention | 67.2% | 72.9% |

Model pages: [DeepSeek V4 Flash](https://opencode.ai/data/deepseek/deepseek-v4-flash.md), [Kimi K2.5](https://opencode.ai/data/moonshotai/kimi-k2-5.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.