Back to Models

DeepSeek: DeepSeek V3.2 Speciale

deepseek-v3.2-speciale

DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales post-training reinforcement learning...

Modalities

Input

text

Output

text
Pricing
Cost per 1 million tokens
Input
$0.48
Output
$1.44
Model Specs
Context Window
163,840
Max Output
65,536
Release Date
2025-12-01
Knowledge Cutoff
2024-07
Capabilities
Reasoning
Tool Calling
Vision

Last Updated: 2025-12-01

Provider: