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
deepseek
DeepSeek: R1 Distill Llama 70B
$0.70 in / $0.80 out
131,072 ctx
80
deepseek
DeepSeek: DeepSeek V3
$0.32 in / $0.89 out
163,840 ctx
89
deepseek
DeepSeek: DeepSeek V3 0324
$0.20 in / $0.77 out
163,840 ctx
90
deepseek
DeepSeek: DeepSeek V3.1
$0.15 in / $0.75 out
32,768 ctx
78
deepseek
DeepSeek: DeepSeek V3.2
$0.25 in / $0.38 out
131,072 ctx
91
deepseek
DeepSeek: R1
$0.70 in / $2.50 out
64,000 ctx
76