> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/pre-basic/providers/cherryai/free-deepseek.md).
# DeepSeek V3.2
Cherry Studio users can now use the built-in **CherryIN** free trial of the service **DeepSeek V3.2**ā 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.
***
## š 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.
***
## š 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:
1. **Large-scale pretraining**: basic training completed on massive high-quality multilingual corpora, covering code, mathematics, and scientific knowledge.
2. **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.
3. **Large-scale Agent data synthesis**: a new Agent training data synthesis method covering 1,800+ environments and 85,000+ complex instructions.
4. **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".
***
## āļø Flagship core capabilities
DeepSeek V3.2 aims for comprehensive capabilities on par with GPT-5, and is substantially enhanced for Agents and complex reasoning:
* ā **Native thinking + tool calling**: the first DeepSeek model to integrate thinking into tool-use
* ā **Top-tier reasoning ability**: V3.2-Speciale reached gold-medal level at IMO / CMO / ICPC World Finals / IOI 2025
* ā **Code and development tasks**: inherits the strong coding capabilities of the V3 series
* ā **Long-context stability**: document-length and codebase-level analysis capabilities brought by DSA
* ā **Structured tool calling**: suitable for building Agents that perform multi-step planning and execution
***
## š” 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(LĀ²)
* dramatically speeds up long-context training and inference while maintaining output quality almost identical to dense attention
| Scenario | Recommended usage | Example |
| --------------------------------- | ----------------------- | ------------------------------------------------------------ |
| 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 |
***
## š Open, usable, ecosystem-friendly
* ā” Long-context inference acceleration brought by DSA
* š° Through CherryIN in Cherry Studio**free to use**
* š„ļø Open-source weights, MIT license, Day-0 support in mainstream inference frameworks such as vLLM and SGLang
***
## š§ 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
***
## š§ How to use it in Cherry Studio?
1. Open Cherry Studio and go to **Settings ā Model Services**.
2. find **CherryIN** the service provider and enable it.
3. In the model list, select **DeepSeek V3.2**.
4. Return to the chat screen and switch to **DeepSeek V3.2** at the top model selector to start chatting.
> š” 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.
***
š **Try DeepSeek V3.2 now and embark on a flagship-level reasoning and Agent journey!**
***
### š” 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](/docs/en-us/question-contact/suggestions.md) for the official channels provided.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.cherryai.com.cn/docs/en-us/pre-basic/providers/cherryai/free-deepseek.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.