# DeepSeek: DeepSeek V3.2 Exp

Provider: deepseek  
Category: llm  
Model ID: `deepseek/deepseek-v3.2-exp`

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...

## Specs

- Context length: 163840 tokens
- Max output: 65536 tokens
- Modalities: text
- Released: 2025-09-29

## Pricing

- Input: $0.27 per million tokens
- Output: $0.41 per million tokens

## Providers

- **deepseek** — ctx 163840, input $0.27/M, output $0.41/M

---
Last verified: 2026-04-23T23:46:29.618Z  
Canonical URL: https://switchy.build/models/deepseek-v3-2-exp