Deepseek V3.2
DeepSeek-V3.2, developed by DeepSeek, is a chat model that excels at reasoning, code generation, and text generation, thanks to its efficient attention mechanism, DeepSeek Sparse Attention (DSA), which reduces computational complexity while preserving performance. With a context window of 163,840 tokens, this model is well-suited for complex, long-context scenarios.
Input
Output
Context
164K
Max Output
164K
Parameters
685.4B
Technical Specifications
Model TypeChat
Context Window163,840 tokens
Max Output Tokens163,840 tokens
Parameters685.4B
Release DateDec 1, 2025
Training CutoffMay 1, 2025
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
22.2%
HLE
84.0%
GPQA
38.9%
SciCode
86.2%
MMLU Pro
92.0
Math
36.7
Coding
86.2%
LiveCodeBench
33.4
Intelligence
Resources & Links
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.