DeepSeek V3.2
Cherry Studio users can now use the built-in CherryIN free trial of the service DeepSeek V3.2— DeepSeek's flagship sparse-attention MoE model released on December 1, 2025, which for the first time natively integrates "thinking" into tool calls, making it an ideal choice for advanced Agents and long-context scenarios.
🚀 What is DeepSeek V3.2?
DeepSeek V3.2 is an iteration based on V3.2-Exp, using a Mixture-of-Experts (MoE) architecture and introducing DeepSeek Sparse Attention (DSA) the sparse attention mechanism, significantly reducing long-context inference costs while maintaining an ultra-large total parameter scale.
Architecture: MoE + DeepSeek Sparse Attention (DSA) + Multi-Head Latent Attention (MLA)
Total parameters: 685B
Activated parameters per token: about 37B
Number of experts: 256 experts per layer
Open-source license: MIT
Release date: December 1, 2025 (V3.2-Exp released on September 29, 2025)
V3.2 also released an API-focused DeepSeek-V3.2-Speciale version, achieving gold-medal-level performance on the IMO, CMO, ICPC World Finals, and IOI 2025 in complex reasoning tasks.
📚 Continuing a solid training and alignment pipeline
DeepSeek V3.2 inherits the mature training pipeline of the V3 series and makes key extensions for Agent scenarios:
Large-scale pretraining: basic training completed on massive high-quality multilingual corpora, covering code, mathematics, and scientific knowledge.
Sparse attention introduction: the main model and lightning indexer were trained at a 128K sequence length, with each query token selecting 2048 key-value tokens for attention.
Large-scale Agent data synthesis: a new Agent training data synthesis method covering 1,800+ environments and 85,000+ complex instructions.
Integration of thinking and tool calling: V3.2 is DeepSeek's first model to natively integrate "thinking" into tool calls, supporting tool use in both "thinking mode" and "non-thinking mode".
⚙️ Flagship core capabilities
DeepSeek V3.2 aims for comprehensive capabilities on par with GPT-5, and is substantially enhanced for Agents and complex reasoning:
✅ Native thinking + tool calling: the first DeepSeek model to integrate thinking into tool-use
✅ Top-tier reasoning ability: V3.2-Speciale reached gold-medal level at IMO / CMO / ICPC World Finals / IOI 2025
✅ Code and development tasks: inherits the strong coding capabilities of the V3 series
✅ Long-context stability: document-length and codebase-level analysis capabilities brought by DSA
✅ Structured tool calling: suitable for building Agents that perform multi-step planning and execution
💡 DeepSeek Sparse Attention: longer, more efficient
DSA is the core technological upgrade of V3.2, achieving the following through lightning indexer + fine-grained token selection :
Fine-grained sparse attention implemented for the first time on a large model
reduces the core attention complexity from O(L²)
dramatically speeds up long-context training and inference while maintaining output quality almost identical to dense attention
Short conversations / simple Q&A
Direct call
Daily Q&A, summarization
Moderately complex tasks
Enable tool calling
Data analysis, code refactoring
Complex Agent tasks
Thinking + tool calling
Multi-step planning, codebase analysis, long document review
🌟 Open, usable, ecosystem-friendly
⚡ Long-context inference acceleration brought by DSA
💰 Through CherryIN in Cherry Studiofree to use
🖥️ Open-source weights, MIT license, Day-0 support in mainstream inference frameworks such as vLLM and SGLang
🧠 Focus on practical capabilities: code and Agents
DeepSeek V3.2 performs especially well in real-world development workflows:
Multilingual code generation and refactoring
Repository-level context understanding and patch generation
Agent toolchain: stable calls to external tools, search, and code execution
Mathematics and complex reasoning: supports competition-level problems
🧭 How to use it in Cherry Studio?
Open Cherry Studio and go to Settings → Model Services.
find CherryIN the service provider and enable it.
In the model list, select DeepSeek V3.2.
Return to the chat screen and switch to DeepSeek V3.2 at the top model selector to start chatting.
💡 Tip: The free model quota provided by CherryIN is covered by the official Cherry Studio team, making it suitable for daily use and evaluation; for production environments, it is recommended to use the official DeepSeek API.
📘 Try DeepSeek V3.2 now and embark on a flagship-level reasoning and Agent journey!
💡 Get help and submit feedback
If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to Feedback and Suggestions for the official channels provided.
Last updated
Was this helpful?