All Models

DeepSeek: DeepSeek V3.2 Speciale

Reasoning Open Weights

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...

Providers 1
Released Dec 1, 2025
Input Modalities text
Output Modalities text
Tarsk Use coding

Available Providers (1)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Kilo Gateway deepseek/deepseek-v3.2-speciale $0.40/MTok $1.20/MTok 163.8K 163.8K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output