DeepSeek: DeepSeek V3.2

deepseek/deepseek-v3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Modalities
Text
In / out price
₩472 / ₩702
1M
Context
163.84K
Released
Dec 1, 2025

Pricing

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

Input (prompt)₩472 / 1M
Output (completion)₩702 / 1M
Cache read₩236 / 1M
Cache write

1,000 input tokens plus 1,000 output tokens costs about ₩1.17.