This model is 19 months old. A newer version of it has since shipped: DeepSeek V4 Flash Vision Exp (2026-08-21). The details below are still accurate for this model — it just is not what we would recommend today.

DeepSeek R1 Distill Qwen 32B

DeepSeek🇨🇳 China
active
Context window33K tokens
Input / 1M tokens$0.29
Output / 1M tokens$0.29

Version History

1.0major

DeepSeek releases distilled 32B model using R1 reasoning outputs applied to Qwen 2.5 32B. Claims state-of-the-art performance for dense models at $0.29/M tokens.