deepseek

DeepSeek: 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...

Quality Score
84/100
composite of price, context, capability
Input Price
$0.40
per 1M tokens
Output Price
$1.20
per 1M tokens
Context Window
163,840
tokens
Model ID
deepseek/deepseek-v3.2-speciale
Vendor
deepseek
Tokenizer
DeepSeek
Input Modalities
text
Output Modalities
text
Max Output
163,840 tokens
Tool Calling
not supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

Similar models