AI model · DeepSeek
DeepSeek V3.2 Exp
Model ID: deepseek/deepseek-v3.2-exp
- Input
- $0.27 per 1M tokens
- Output
- $0.41 per 1M tokens
- Context
- 164K tokens at once
- Max output
- 147K tokens per reply
- Released
- 29 Sep 2025 DeepSeek
What it can do
- YesReasoning
- YesTool calling
- NoImage input
- YesOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
Sources
- DeepSeek: DeepSeek V3.2 Exp on OpenRouter — read 2 Oct 2026