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.
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.
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.
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.
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.
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.
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.
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.
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.
Summarize any YouTube video in seconds
Get summaries like this one for any video, in your language, with the free Summ app.
Transcript
Full transcript of “NEW Deepseek R1 V2 FREE Coder Fully Tested for Vibe Coding with Cline and Openrouter FREE API Key”. Click a timestamp to open the video at that moment. Need another video? Use the YouTube transcript generator.
0:00 So Deepseek has recently introduced Deepseek R1 version 2 and I'm already testing it for different kind of coding task. For example, this particular one where I just built this interactive Rubik's cube simulation. The only problem is this demo is not working. There is a working version as well which is this one which is not working as it should but somehow it is like kind of it scrambles after that it tries to like solve but still there are some mistakes. So this particular version is without Deepseek R1 without Deep Think. So this is a Deepseek R1 version 2 but without Deep Think. This particular one is Deepseek R1 with Deep Think. Then I just created this basic 3D runner game. It's a shame that I have to like call it a game because being a game developer myself, I just cannot call it a game.
0:45 But these are things that I do for YouTube. But anyways, um so yeah, this is just like a very basic horrible 3D game. But anyways, the prompt was very simple. just create a 3D running game. Then it had its thinking for 17 seconds and after thinking for 17 seconds, it created this very basic HTML code and then created this very basic 3DRunner game. Similarly, I just created this basic landing page using DFCarvin and I was kind of like impressed by the first version because the prompt that I gave was very simple. It was like just create a SAS landing page. Then it had a thinking for like 11 seconds and after that it just like started writing code. Then there were a couple of changings and then just this is the finished version. So this looks kind of like
1:31 really professional so far. But yeah, I mean it's just like a standard SAS landing page. Then I also tested it inside client. So I'm actually using deepse R1 version 2 inside client through API key from open router. If you don't know about that, so you can just like go to open router. Open rotor is a platform where you can actually get all of these different like models. You can access all of these different models through API key. So this is deepseync R1. This model cost 050 per million input tokens and 2.18 per million output tokens. There is a free version as well. You can access that as well. So this is the free version deepsec R10528. This is the free version and it costs $0 per million input tokens and $0 per million output tokens. You can start using inside clone or any other AI uh coding
2:16 agent maybe rule code or maybe any other AI coding agent. You can start using it from here and this is absolutely for free. But in case if you want to like use it for your actual project. So I highly highly recommend you like using this version which is which cost you around $050 per million input tokens and around $218 per million output tokens. By the way, Deepsec R1 this particular version is around 2.5 times more costly than Deep Seek version 3 which is again a good enough model which was launched I think in March and Deep Sea version 3 is a 658 billion parameters model and it's mixer of expert model but this deepseek R1 is comparatively better in terms of like thinking in terms of overall reasoning and of course for coding tasks as well. context is 163,000 which is
3:01 kind of not enough when it comes like using it on a large code basis. It is good enough like basic HTML codes JavaScript code but when it comes like using it inside like a proper project where there's like thousand thousands of lines of codes so it might not be enough. Anyways this is 671 billion parameters model with 37 billion active in an interference pass. It's a fully open source model and it actually competes with a lot of other these famous models something like OpenAI3, Gemini 2.5 Pro and Quen 3 235B and Deepseek R1 of course. So this is a benchmark comparison if I compare it with all of these different famous models. So in this graph this is Deepseek R1 this light blue one and then
3:48 this one is Deepseek R1 version two. So this is the old Deepseek R1. This is our Deep Seek R1 version two. And you can see DeepSeek R1 version 2 beats almost all of these different models in all of these different benchmarks including this live codebench and humanities last exam. So, so the most shocking thing for me is this model is beating Gemini 2.5 Pro in some benchmarks. So that means this model is good enough. Now if you're interested in testing this model inside client or root code, you can simply just go to V studio and make sure that you have installed client and just go to settings. From here you can just like click on this API provider. From here just choose open router and from here you can just like provide this open router API key. As I told you earlier you can simply go to open router sign up. You are not required to attach any sort of credit card if you're not using
4:35 any of the paid models. So you can just like use this free one. This free model which costs $0 per million input tokens and $0 per million output tokens. You can then create an API key and then after that you can simply just provide that API key in here and then choose DPC car 10528 from this models drop-down section. Then you can actually provide custom instruction for this model if you want. The only problem is this model does not support images. It does not support browser use and it does not support prompt caching. For me the big downpoint is this model does not support images. Most of the times whenever I'm working on any sort of like project and like doing wipe coding so like providing images to my AI code editor actually helps me to explain my scenario in better way but this is actually a drawback that it does not support images
5:21 but if you still want to use it maybe like for code analysis or for any other coding task you can use it of course also you can use it for free inside chat.dec.com deepseec.com and you can use deep think as well from here and you can see let's suppose if you want like create any sort of like landing page or any sort of like tool or make this kind of like basic 3D game it can write code for you and of course it can then run that code for you. So let's suppose if just like wrote this code for you and then from here you can simply click on this run button and then it can run this code for you inside directly inside your browser.
