Transcription
[Music] [Applause] Hi, welcome to another video.
So, in recent times, a lot of stuff has come around. Some get enough attention while some don't. However, one thing that didn't get as much attention was Quen Code. Quen code, if you don't know, is basically a fork of Gemini CLI made by the Quen team in order to make it much more cohesive for their models.
Previously, you had to use some kind of provider in order to use Quen code, and there were no such free credits or anything, though you used to get some on their API platform, but that was a pretty negligible amount of like 1 million tokens. However, the Quen team has now given us access to Quen 3 coder for free with about 2,000 requests per day along with 60 requests per minute. You can easily get this configured in order to use it and it's actually quite great.
You'll not only be getting access to any plan of Quen 3 coder, but you'll also be getting access to the full precision Quen 3 coder 480B model that comes with an extrapolated 1 million token context window, meaning that it can be really good even for long context tasks. This is called Quen Coder Plus in their API endpoint. So that's great.
Anyway, it's not just that you can use it with Quen code, but you can actually use this in anything like Klein or Rukode or Open Code or anything else quite easily and that's super easy to do. I'll also show you how you can do that as well. But before proceeding, let me tell you about Ninja Chat.
Ninja Chat is an all-in-one AI platform where for just $11 per month, you get access to top AI models like GPT40, Claude for Sonnet, and Gemini 2.5 Pro, all in one place. I've been using Gemini for quick research. But what's really cool is their AI playground where you can compare responses from different models side by side. Their mind map generator is a gamecher for organizing complex ideas as well. The basic plan gives you 1,000 messages, 30 images, and five videos monthly with higher tiers available if you need more. Use my code king 25 for 25% off any plan or king 40 yearly for 40% off annual subscriptions. Check the link in description to try it yourself.
Now back to the video. So first of all, if you have it or not, just run this command. If you don't have it, then it will get installed. Otherwise, it will be updated to the latest version. Now, just run it and for the first time, it will ask you to set up OOTH or an API key as well. For the free access, you'll need to set up OOTH. If you had already set it up with an API key before, then you may not see it. So you can just run the off/ command and then you can easily configure the ooth method and stuff like that as well. Just get it set up accordingly. It will take you to Quen's site and then just create an account there and get signed up. Once done, you can now use Quen code as much as you want without any issues. It works seamlessly. So yeah, that's great.
But now you can also use it with anything else quite simply as well. Though there are sometimes a few compatibility issues in R code incline which are being addressed soon. As you can see there is a pull request in the final stages. So you might see it in R code pretty soon for sure and you should be able to just select the quen code option there in order to get pretty reliable results. Anyway, many of them don't have that yet, but you can configure it manually as well.
So, what you can do is just head on over to the Quen directory in your home folder, and then you'll see this OOTH file there. In this, you will find the API key or access token in order to configure your API in Klein or anything else. So just grab that and then go to something like Klein. There you can easily select the open AI compatible option and then you can just set the API base URL as portal Quen AI. Then enter the API key that you grabbed from there and then you can just enter the model ID here and save it accordingly. Now you can go ahead and use it as well. Also, this API key keeps refreshing, so you can go ahead and replace it when you start getting errors.
This is really awesome. It actually works amazingly well with Klein. Like, it's really great. The response at first can have a bit of an artifact, but still it works fine. And it can even do testing with the browser and everything if you need that, which is awesome as well. It's pretty great for sure. Like it's really good. It's fast, works well and Quen 3 coder in itself is also great to use.
Another thing that you can use is open code. It works well with that as well. So you can just go in there and then in the settings config file you can easily set up the provider for Quen Coder and keep using it as well. I think that it also works well but Quen code itself should also work well and you should give it a check as well. You shouldn't feel any issues in using it. It should also work with R code and Kilo code as well and the native integration should also be coming since the pull request is at its ending stages. So yeah, but this setup also works well without any issues.
You should even be able to use it with cloud code through the claude code router. You can set up the API there and then use it accordingly. That is majorly how it works. I'd highly recommend you to go ahead and give this a try because the free requests are pretty great and I don't think that it has any limits on token input or output which is quite awesome to see for sure. The API that this uses also has a 1 million token context window with very little performance hit which makes it really great for real life usage.
Also, Quen code should have received all the latest Gemini CLI updates along with some custom updates as well. So, you should have the custom/comands. I think VS Code integration is not yet available, but that should probably come soon as it's an upstream change. So yeah, there's that. Go ahead and give it a try once and use its API and stuff where you think the free API can come in handy. You can almost use it in anything that comes with the OpenAI compatible API option, even things like Open Web UI or something like that as well. So, go ahead and check it out. Overall, it's pretty cool.
Anyway, share your thoughts below and subscribe to the channel. You can also donate via Super thanks option or join the channel as well and get some perks. I'll see you in the next video. Bye. [Music]