DeepSeek

DeepSeek is one of the mainstream domestic large-model providers. Its V3 / R1 series is well known for coding and reasoning tasks, and it is affordable.

Get API Key

• Go to DeepSeek Platform Register account
• API Keys → Create API Key, copy sk-... key
• Top up any amount (you can activate it with as little as ¥1)

Configure in Cherry Studio

• After opening Settings → Model Services, find deepseek Provider to enter the details page
• API key Enter sk-...
• API Address By default https://api.deepseek.com, no need to modify
• Click Get model list

Recommended usage

Model	Suitable scenarios
deepseek-chat	General chat, extremely cost-effective
deepseek-reasoner	Math, code, complex reasoning. Note that the output will include <thinking> thinking block

Native web search

Models in DeepSeek that support web connectivity can directly use the provider's native web search. When selecting a model, check whether there is a 🌐 icon next to its name; the specific support scope may change with provider updates, so it is not recommended to judge based only on the model name.

After turning on 🌐 in the conversation, if [Settings] → [Web Search] has [Prefer configured search service] enabled, Cherry Studio will prioritize the configured search service; only after disabling this option will it prioritize the model's native web connectivity. See Web Connectivity Mode for details.

Combination with global memory

DeepSeek itself does not have embedding models. If you want to use a knowledge base:

• It is recommended to use embedding models from another provider (for example SiliconFlow of bge-m3 or OpenAI of text-embedding-3-small)
• You can still use DeepSeek for the chat model

• DeepSeek charges by token, and cache hits can greatly reduce costs (refer to its official documentation)
• deepseek-reasoner The reasoning content will be rendered in the conversation by default, and can be Chat settings toggle "Auto-collapse reasoning content" in

---

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.