How to Seamlessly Integrate DeepSeek AI into IntelliJ IDEA for Java Development

Introduction

The article begins by noting the rapid rise of AI coding assistants in 2025 and introduces DeepSeek as a high‑performance tool that can be integrated into IntelliJ IDEA to boost Java development productivity.

1. Environment Preparation

IDEA version : Use IntelliJ IDEA 2023.x or newer for optimal compatibility with the CodeGPT plugin, which serves as the proxy for DeepSeek.

Python installation : Install Python 3.7+ and add it to the system PATH so the DeepSeek helper can run. Example command on macOS:

python --version
Python 3.12.8

2. Install the CodeGPT Plugin

Open IDEA, go to Settings (Windows/Linux) or IntelliJ IDEA → Preferences (macOS).

Select Plugins, switch to the Marketplace tab, search for "CodeGPT", view details and click Install.

Restart IDEA when prompted.

3. Configure DeepSeek

3.1 Create an API Key

Visit https://www.deepseek.com/, open the API Open Platform, and generate an API key under the "API keys" menu.

3.2 Set Up DeepSeek in IDEA

In IDEA, open the settings for the installed CodeGPT plugin and locate the Custom OpenAI section. Fill in three parts:

API Key : Paste the key created in step 3.1.

Chat model :

URL: https://api.deepseek.com/chat/completions Model name: deepseek-chat Inference model :

Enable Enable code completions and Parse response as Chat Completions.

FIM template: DeepSeek Coder.

URL: same as chat model.

Model name: deepseek-reasoner.

Click Apply and OK to save the configuration.

4. Using DeepSeek in Coding

4.1 Getting Ideas and Code

Open the CodeGPT component, select Custom OpenAI, and type a prompt such as "Use Java to write a method that filters numbers and provide a test". The assistant returns complete code, for example:

public class TestNumberFilter {
    public static String filterNumbers(String input) {
        // Use regex to keep only digits
        return input.replaceAll("[^0-9]", "");
    }
    public static void main(String[] args) {
        String testInput2 = "SSFSDFS结论萨芬122432的噶大都是4无人区是14认识832safsss";
        String result = filterNumbers(testInput2);
        System.out.println("Filtered numbers: " + result); // Output: 123456
    }
}

4.2 Code Completion

While typing, press Ctrl + Space (or a custom shortcut) and DeepSeek analyses the surrounding context to suggest the next code fragment, dramatically speeding up development.

4.3 Code Explanation

Select a code block, right‑click, and choose CodeGPT. DeepSeek returns a natural‑language description of the logic, helping with maintenance and debugging.

4.4 Asking Questions

Highlight code or describe an issue, then choose CodeGPT: Ask Question. The assistant provides targeted solutions, acting as an on‑demand programming mentor.

5. DeepSeek Usage Statistics

The article shows screenshots of the token usage dashboard on DeepSeek’s website, illustrating daily token consumption and associated cost for the "deepseek-chat" model.

Conclusion

By following the outlined steps, developers can successfully embed DeepSeek into IntelliJ IDEA, leveraging AI‑driven code generation, completion, explanation, and troubleshooting to enhance Java development efficiency.