VS Codium + Continue + OpenRouter + Qwen3 Coder: Free, No Credit Card, Powerful Coding Assistant

This guide is prepared for developers who:

• Have limited hardware resources (CPU/RAM) and cannot run local LLMs,
• Want to use powerful AI models without sharing credit card details,
• Value privacy, cost-efficiency, and accessibility.

It explains step-by-step how to use the Qwen3 Coder 480B A35B model — a massive, coding-optimized AI — inside VS Codium, completely free, with open-source tools, and without sharing any financial information.

🎯 Why This Stack?

• VS Codium: Fully open-source, Microsoft-free IDE.
• Continue: Plugin that integrates local or cloud AI models directly into your editor.
• OpenRouter: Unified API for 400+ models — no credit card required, just email signup.
• Qwen3 Coder: A powerful, coding-specialized model (estimated 480B parameters), listed as free on OpenRouter.

This combination enables high-quality AI-assisted development — even on older hardware.

🔧 1. Create an OpenRouter Account

1. Go to https://openrouter.ai.
2. Click “Sign Up” in the top-right corner.
3. Register with Google, GitHub, or email.
   → No credit card is required!

🔑 2. Get Your API Key

1. After logging in, go to the “Keys” section in the left menu.
2. Click “Create Key”.
3. Give it a name (e.g., vscodium-qwen3) and click “Create”.
4. Copy the generated key (example: sk-or-v1-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx).

⚙️ 3. Install the Continue Extension

1. Open VS Codium.
2. Go to the Extensions sidebar (puzzle icon).
3. Search for “Continue”.
4. Install “Continue: Code Autocomplete, Chat, and More”.
5. Restart VS Codium.

📝 4. Create the Config File

In your terminal, create the config directory:

mkdir -p $HOME/.continue

Then create the config file:

nano $HOME/.continue/config.yaml

📋 5. Paste the Following Content (Replace with Your API Key)

name: Qwen3 Coder 480B A35B
version: 1.1.0
schema: v1
models:
  - name: Qwen3 Coder 480B A35B
    provider: openrouter
    model: qwen/qwen3-coder:free
    apiKey: sk-or-v1-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
    defaultCompletionOptions:
      contextLength: 262144
    capabilities:
      - tool_use
    roles:
      - apply
      - chat
      - edit

💡 Notes:

• Use apiKey (camelCase, no underscore).
• The model name must be exactly qwen/qwen3-coder.
• YAML is indentation-sensitive — use 2 spaces for nested lines.

💾 6. Save and Exit

If using nano:

• Ctrl+O → Enter (to save)
• Ctrl+X (to exit)

🧪 7. Test It

1. Open a .py file in VS Codium.
2. Open the Continue chat panel (usually a 🤖 icon in the bottom-right).
3. Ask:

   Write a Python function to scrape a webpage using Scrapy.

If everything is set up correctly, Qwen3 Coder will generate a clean, powerful code snippet within seconds.

🔒 Security & Privacy Notes

• OpenRouter does not store your prompts by default (opt-in only).

• Never share your API key or commit it to version control (git).

• You can use an environment variable for extra safety:

  apiKey: “${OPENROUTER_API_KEY}”

Then launch VS Codium from the terminal:

export OPENROUTER_API_KEY="sk-or-v1-..."
codium .

💡 Performance Tips

• You get $1 of free usage (~80,000–100,000 tokens).
• Network latency may cause 1–3 second delays — be patient.
• The model supports 262K context length, so long inputs are welcome.

🌍 Final Words

This setup is a true convergence of free software, privacy, and accessibility.
It unlocks the power of the strongest AI models —
without compromise, without tracking, and without payment.

As the Seqular community, we aim to make such solutions open, sustainable, and available to all.

Happy coding! 💚

— Kansu Köse & Qwen
Seqular Community