AI Orbit A2Z Logo

🇨🇳 China · China

DeepSeek models explained

Hangzhou-based DeepSeek became famous for high-performing, low-cost models released with open weights. Its models power the free DeepSeek chat app and a low-price API.

All model families

General chat

DeepSeek-V series

Best for: Everyday chat, writing, coding

Large mixture-of-experts models; the default model in the app.

AppAPIOpen weights

Reasoning

DeepSeek-R1 (reasoning)

Best for: Maths, logic, step-by-step problems

Shows its reasoning; used in the app’s “DeepThink” mode.

AppAPIOpen weights

Small open reasoning models

R1 distilled models

Best for: Running reasoning locally on a laptop

Smaller models (based on Qwen and Llama) trained to reason like R1 — e.g. ollama run deepseek-r1:7b.

Open weights

Code

DeepSeek Coder

Best for: Code generation and completion

Code-specialised models.

Open weightsAPI

Model names and versions change often. Check the official documentation for the newest releases.

⚡ Which model should you use?

  • Free online: chat.deepseek.com.
  • Private and offline: distilled R1 via Ollama.
  • Low-cost API for apps: DeepSeek API.

Data, privacy and your region

Cloud services from Chinese companies process data under Chinese law and the provider’s privacy policy. Many organisations in the UK, EU and US restrict their use for sensitive data. The open-weight models can instead be run locally or on your own servers, where your data stays under your control.

Frequently asked questions

Is DeepSeek safe to use?

The open-weight models run fully on your computer when used locally. For the cloud app, your data is processed in China under DeepSeek’s policy — avoid sensitive information and follow your organisation’s rules.

Can I run DeepSeek on my laptop?

Yes — the smaller distilled versions run on ordinary laptops with Ollama or LM Studio. See our step-by-step guide.

Step-by-step guideFull tool review

More AI companies