Model dossier

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...

ProviderDeepSeek Start comparison

Context163,840

Max output65,536

Pricing viewTVP price

Identity

DeepSeek: DeepSeek V3.2

Model ID: deepseek/deepseek-v3.2
Canonical slug: deepseek/deepseek-v3.2-20251201
Knowledge cutoff: n/a
Created: 12/1/2025

Capabilities

texttoolsstructured

Modalities

text->texttext

Capacity

Context163,840

Max output65,536

TokenizerDeepSeek