DeepSeek V4.1 Flash 1017 Ultrafast
by Venice AI · family deepseek · listed Oct 2026RTVW
Fast DeepSeek model for efficient chat, coding help, and agent loops
Current rates USD per 1M tokens
Input$3.00
Output$12.00
Cache read$0.06
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
deepseek-v4-1-flash-1017-ultrafast- Context window
- 1M tokens
- Max output
- 131K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-10-23
- Last updated
- 2026-11-06
← All Venice AI listings