NEW Deepseek R1 V2 FREE Coder Fully Tested for Vibe Coding with Cline and Openrouter FREE API Key

Brief Summary

The video introduces and tests Deepseek R1 version 2, a new coding model, comparing it with other models like Gemini 2.5 Pro and Deepseek version 3. It showcases its capabilities through tasks like creating a Rubik's cube simulation, a 3D runner game, and a landing page. The video also explains how to access and use Deepseek R1 version 2 for free via Open Router, highlighting its strengths and weaknesses, such as its lack of image support.

• Deepseek R1 version 2 is a powerful coding model that competes with top models like Gemini 2.5 Pro.
• It can be accessed for free through Open Router, making it accessible for various coding tasks.
• Despite its strengths, it lacks image support, which can be a drawback for certain projects.

Introduction to Deepseek R1 Version 2

The presenter introduces Deepseek R1 version 2 and shares initial tests, including an interactive Rubik's cube simulation. While one demo isn't fully functional, another version attempts to solve the cube with some errors. The presenter distinguishes between versions with and without "Deep Think," highlighting the model's problem-solving capabilities.

Testing Deepseek R1 Version 2 with a 3D Runner Game

The presenter describes creating a basic 3D runner game using Deepseek R1 version 2. The prompt was simple: "create a 3D running game." After a 17-second thinking period, the model generated basic HTML code for the game.

Creating a Landing Page with Deepseek R1 Version 2

The presenter discusses using Deepseek R1 version 2 to create a landing page, expressing satisfaction with the initial result. Given the simple prompt "create a SAS landing page," the model thought for 11 seconds before generating code, which, after a few changes, resulted in a professional-looking landing page.

Accessing Deepseek R1 Version 2 via Open Router

The presenter explains how to access Deepseek R1 version 2 through Open Router, which allows users to access various models via API keys. Deepseek R1 costs $0.050 per million input tokens and $2.18 per million output tokens, while a free version (Deepseek R1 0528) is also available. The presenter recommends the paid version for actual projects due to its superior performance.

Cost and Performance Comparison

Deepseek R1 is 2.5 times more expensive than Deepseek version 3, a 658 billion parameter model launched in March. Deepseek R1 excels in reasoning and coding tasks, with a context window of 163,000 tokens. While suitable for basic HTML and JavaScript, it may not suffice for large projects with extensive codebases. The model has 671 billion parameters, with 37 billion active during inference, and competes with models like OpenAI 3, Gemini 2.5 Pro, and Qwen 3 235B.

Benchmark Results

Deepseek R1 version 2 outperforms many models in benchmarks, including live codebench and humanities last exam, even surpassing Gemini 2.5 Pro in some tests. This indicates its strong capabilities in various coding and reasoning tasks.

Using Deepseek R1 Version 2 in Client

The presenter details how to use Deepseek R1 version 2 in client by installing client in VS Code, selecting Open Router as the API provider, and entering the API key. Users can choose the free Deepseek R1 0528 model and provide custom instructions. However, the model does not support images, browser use, or prompt caching, with the lack of image support being a significant drawback.

Alternative Access and Capabilities

Despite its limitations, Deepseek R1 version 2 can be used for code analysis and other coding tasks. It is also accessible for free on chat.deepseek.com, where users can utilize Deep Think to generate and run code for tasks like creating landing pages or basic 3D games directly in the browser.