DeepSeek v3.2
DeepSeekFlagship
ThinkingTool UseStructured Output
About this model
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
Performance Tier
Flagship
DeepSeek v3.2 is a flagship model from DeepSeek : the most capable in their lineup.
Best-in-class model from this provider. Highest performance across benchmarks, ideal for demanding tasks.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.260 |
| Output (completion) | $0.380 |
| Cache read | $0.130 |
Capabilities
Context Length164K
Max Output Tokens—
TokenizerDeepSeek
Inputtext
Outputtext
Release DateDecember 1, 2025
Benchmarks
General Intelligence
MMLU
90.8%
GPQA Diamond
82.4%
Mathematics
MATH-500
92%
Programming
HumanEval
90.5%
SWE-bench Verified
73.1%
Reasoning
IFEval
86.5%
Recommended Use Cases
CodingMathematicsAnalysisResearch
Strengths
- Excellent price-to-performance ratio
- Top-tier math reasoning for an open model (AIME 93.1%)
- Open-weight model (transparency and self-hosting)
- Strong coding with Sparse Attention for efficient inference
Limitations
- May lag behind top proprietary models on creative tasks
- Less extensive safety tuning than Claude/GPT
Resources
This model may use your data for training
