# DeepSeek V4 Pro 0813 vs Gemini 3.8 Flash - AI Model Comparison

- Page: https://opencode.ai/data/compare/deepseek/deepseek-v4-pro-0813/google/gemini-3-8-flash
- Updated: 2026-10-24T21:01:47.000Z

|  | DeepSeek V4 Pro 0813 | Gemini 3.8 Flash |
| --- | --- | --- |
| Lab | DeepSeek | Google |
| Context window | 1M | 1M |
| Max output | 384K | 66K |
| Input modalities | text | text, image, video, audio, pdf |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Open weights | Yes | No |
| Release date | 2026-08-13 | 2026-09-02 |
| Input price per 1M tokens | $1.32 | $1.50 |
| Output price per 1M tokens | $3.96 | $7.50 |
| Cached input price per 1M tokens | $0.04 | $0.15 |
| OpenCode tokens: past 2 months | 72M | 200K |
| Share of all tokens | 0% | 0% |
| Rank by tokens last week | - | #57 |
| Unique users | 26 | 2 |
| Weekly retention | - | - |

Model pages: [DeepSeek V4 Pro 0813](https://opencode.ai/data/deepseek/deepseek-v4-pro-0813.md), [Gemini 3.8 Flash](https://opencode.ai/data/google/gemini-3-8-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.