DeepSeek: DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

Modalities
Text
In / out price
₩114 / ₩316
1M
Context
1.31M
Released
Jul 31, 2026

Pricing

Prices are quoted in Korean won. Changes to the exchange rate or margin show up immediately.

Input (prompt)₩114 / 1M
Output (completion)₩316 / 1M
Cache read₩28 / 1M
Cache write

1,000 input tokens plus 1,000 output tokens costs about ₩0.429975.