Key Concepts
- Quen Code: A fork of Gemini CLI by the Quen team, optimized for their models.
- Quen 3 Coder: Quen's coding model, now available for free with limitations.
- Quen Coder Plus: The full precision Quen 3 coder 480B model with a 1 million token context window.
- OAUTH: Authentication method required for free access to Quen 3 Coder.
- API Key/Access Token: Used to configure Quen 3 Coder in other platforms like Klein, Open Code, etc.
- OpenAI Compatible API: A standard that allows Quen 3 Coder to be used in various platforms.
- Context Window: The amount of text the model can consider at once (1 million tokens for Quen Coder Plus).
- Ninja Chat: An all-in-one AI platform offering access to multiple AI models.
Free Access to Quen 3 Coder
- Availability: The Quen team is now offering free access to Quen 3 coder.
- Limitations: 2,000 requests per day and 60 requests per minute.
- Model: Access to the full precision Quen 3 coder 480B model (Quen Coder Plus).
- Context Window: Extrapolated 1 million token context window, suitable for long context tasks.
- Authentication: Requires setting up OAUTH for free access.
Setting up Quen Code
- Installation/Update: Use the command
[command mentioned in video]to install or update Quen Code. - OAUTH Configuration:
- Run the
off/command to configure OAUTH. - Create an account on Quen's site and sign up.
- After setup, Quen Code can be used without issues.
- Run the
Using Quen 3 Coder with Other Platforms (Klein, Open Code, etc.)
- Manual Configuration:
- Locate the OOTH file in the Quen directory (
~/Quen). - Find the API key or access token within the OOTH file.
- Locate the OOTH file in the Quen directory (
- Klein Setup:
- Select the OpenAI compatible option in Klein.
- Set the API base URL to
portal Quen AI. - Enter the API key from the OOTH file.
- Enter the model ID.
- Save the configuration.
- API Key Refresh: The API key refreshes periodically, requiring updates in the configuration when errors occur.
- Open Code Setup: Configure the provider for Quen Coder in the settings config file.
- Cloud Code Setup: Use the Claude Code Router to set up the API and use Quen 3 Coder.
Ninja Chat AI Platform
- Description: An all-in-one AI platform offering access to models like GPT40, Claude for Sonnet, and Gemini 2.5 Pro.
- Pricing: Starts at $11 per month.
- Features:
- AI playground for comparing responses from different models.
- Mind map generator for organizing complex ideas.
- Basic Plan: 1,000 messages, 30 images, and 5 videos monthly.
- Discount Codes:
king 25for 25% off any plan.king 40 yearlyfor 40% off annual subscriptions.
Performance and Compatibility
- Klein: Works "amazingly well" with Klein, even with browser testing capabilities. Initial responses may have artifacts.
- Open Code: Compatible and works well.
- R Code & Kilo Code: Native integration is in progress (pull request in final stages). Manual setup works in the meantime.
- Token Limits: No apparent limits on token input or output.
- Context Window: The API uses a 1 million token context window with minimal performance impact.
- Updates: Quen code has received Gemini CLI updates and custom commands. VS Code integration is expected soon.
Key Arguments and Perspectives
- Value of Free Access: The free requests offered by Quen are valuable and useful.
- Real-World Usage: The 1 million token context window makes Quen Coder Plus suitable for real-life applications.
- Versatility: Quen 3 Coder can be used in various platforms that support the OpenAI compatible API.
Conclusion
Quen is offering free access to its powerful Quen 3 Coder model, specifically the Quen Coder Plus variant, which boasts a 1 million token context window. This access, while limited to 2,000 requests per day, provides a significant opportunity to leverage a high-performance coding model for free. The model can be integrated into various platforms like Klein and Open Code through manual configuration using the API key found in the OOTH file. While native integration for some platforms is still in progress, the current setup offers a versatile solution for developers seeking to utilize Quen's capabilities. The speaker encourages viewers to try it out and share their thoughts.
AI summaries can miss context or contain errors. Check important details against the original video.





