DeepSeek

DeepSeek is one of the leading domestic large-model providers. Its V3 / R1 series is well regarded for programming and reasoning tasks, and it's affordable.

Get an API Key

• Go to DeepSeek Platform Register account
• API Keys → Create API Key, copy sk-... Key
• Top up any amount (minimum ¥1 to activate)

Configure in Cherry Studio

• Open Settings → Model Services, find deepseek Provider to enter the details page
• API key Fill in sk-...
• API address 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

with global memory

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

• For embedding models, it is recommended to use another provider's (such as SiliconFlow of bge-m3 or OpenAI of text-embedding-3-small)
• The chat model can still use DeepSeek

• DeepSeek pricing is billed by token; cache hits can significantly reduce costs (see its official documentation)
• deepseek-reasoner Its thinking content is displayed in the chat by default; you can Conversation settings toggle "Auto-collapse thinking 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 the official channels provided there.