# DeepSeek Chat vs DeepSeek V4 Flash Vision Exp - AI Model Comparison

- Page: https://opencode.ai/data/compare/deepseek/deepseek-chat/deepseek/deepseek-v4-flash-vision-exp
- Updated: 2026-10-25T11:33:03.000Z

|  | DeepSeek Chat | DeepSeek V4 Flash Vision Exp |
| --- | --- | --- |
| Lab | DeepSeek | DeepSeek |
| Context window | 1M | 1M |
| Max output | 384K | 384K |
| Input modalities | text | text, image |
| Reasoning | No | Yes |
| Tool calling | Yes | Yes |
| Open weights | Yes | Yes |
| Release date | 2025-12-01 | 2026-08-21 |
| Input price per 1M tokens | $0.22 | $0.22 |
| Output price per 1M tokens | $0.66 | $0.66 |
| Cached input price per 1M tokens | $0.0070 | $0.0070 |
| OpenCode tokens: past 2 months | 0 | 6.7T |
| Share of all tokens | 0% | 0.6% |
| Rank by tokens last week | - | #24 |
| Unique users | 0 | 268K |
| Weekly retention | - | 63.0% |

Model pages: [DeepSeek Chat](https://opencode.ai/data/deepseek/deepseek-chat.md), [DeepSeek V4 Flash Vision Exp](https://opencode.ai/data/deepseek/deepseek-v4-flash-vision-exp.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.