# DeepSeek-V3.1 vs DeepSeek V4 Flash - AI Model Comparison

- Page: https://opencode.ai/data/compare/deepseek/deepseek-v3-1/deepseek/deepseek-v4-flash
- Updated: 2026-11-13T22:13:42.000Z

|  | DeepSeek-V3.1 | DeepSeek V4 Flash |
| --- | --- | --- |
| Lab | DeepSeek | DeepSeek |
| Context window | 131K | 1M |
| Max output | 8.2K | 384K |
| Input modalities | text | text |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Open weights | Yes | Yes |
| Release date | 2025-08-21 | 2026-04-24 |
| Input price per 1M tokens | $0.27 | $0.15 |
| Output price per 1M tokens | $1.00 | $0.60 |
| Cached input price per 1M tokens | - | $0.0030 |
| OpenCode tokens: past 2 months | 0 | 28T |
| Share of all tokens | 0% | 2.0% |
| Rank by tokens last week | - | #48 |
| Unique users | 0 | 674K |
| Weekly retention | - | 57.9% |

Model pages: [DeepSeek-V3.1](https://opencode.ai/data/deepseek/deepseek-v3-1.md), [DeepSeek V4 Flash](https://opencode.ai/data/deepseek/deepseek-v4-flash.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.
