DeepSeek-V3.2

Open weights Active Text LLM MoE deepseek-v3-2

Official successor to V3.2-Exp with sparse attention and thinking inside tool use.

Released
Dec 1, 2025
Context window
131K tokens
Max output
Not disclosed
Parameters
671B 37B active
Input price
Not disclosed
Output price
Not disclosed

Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.

Pricing

Launch priceDec 1, 2025
$0.28 in / $0.42 out
Current price
No longer sold

Specifications

Developer
DeepSeek
Model type
Text LLM
Architecture
MoE
Parameters
671B (37B active)
Input
Text
Output
Text
Knowledge cutoff
Not disclosed
License
MIT License
API access
No first-party API
Capabilities
Agentic Reasoning Tool use