Setup Pi Agent with Nvidia’s FREE AI Models (Step-by-Step)

Hello friends, Tony here. Welcome. In this video, I'm going to show you how to use PI agent with Nvidia models. I have showed you another video how to work with PI and local models using this OMX. And here I'm going to open the Pi right now. Yeah. And also using the open router because right now as you can see I'm using open router Kim K 2.6. But if I want to use models from local models, as you can see here is the OMX Quen 3.6 27 billion, Quen 3.6 35 billion and also from open routers. But now let's show you how to work with Nvidia models. So first you need to go to build.envidia.com and create an account here and then go to models. And here you can find all the models. Also we can filter free ones. So I'm going to say apply here. Selected this. Check this free. And now selected. And yeah, as you can see this is free endpoint. Free endpoint. Free. And let's say I want to use uh let's use this minimax M2.7. As you can see is free. Let's select this one and I'm going to say just hi here. Okay. So here also can we can see this is reasoning complete. Hello, how can I help you? Now let's go to view code. I'm going to generate an API key. So let's click and here is the API key. I'm going to delete this. So just don't copy my key here. And yeah, here is the model. Maybe just let's zoom in one more time. Yeah, here is the key. This is the base URL and this is the model I have chos. Now let's open I have open thepy/agent directory and this one I'm going to open with VS code or with any code editor or you want and here I have opened the models.json the JSON I have providers and yeah here I have the OMX provider base this URL API API key models I have added only two of them so quen 3.6 27 billion and 3.6 635 billion and I have added some defaults here. Now let's do the same thing for the Nvidia. I'm going to add another one which is going to be yeah not Azure but Nvidia. Now we need to add the base URL here. So let's go and copy the base URL we have here. paste it. The API is OpenAI compulsion. So just remove this. The API key is the key we have generated. So copy and paste it also the API key models. Now let's copy the model. Here is the model in my case with copy the model. I'm to paste it here. And yeah, also let's add the name the just minimax 2.7. And yeah, let me also choose another model free one. Apply. So let's choose a GLM.7. View the code and copy the model here. I'm going to paste it right here. and also GLM and we can save for the defaults. Let's see what we have also here because we have one one and we have max tokens to this one. Let's copy this. Okay, so this is one. This is one and we have to be this number. I'm going to save. And now let's go here and open the pi agent again. Okay, I am in the open design. I created a video about this. So let's see now what as we can see we have Nvidia is selected but yeah say model and here is the minimax 2.7 and also the GLM 4.7. We are on the minimax so we are okay. Let's say just high. Okay. So here is the response. The user say hi. A simple greeting. Okay. Now let's see also with the other model which is the GLM. Here I'm going to ask which skills do you have? And yeah, here is a response. I have the skills available. Caveman diagnos skills. grill me and so on. So this is how we can set up the PI agent to work with Nvidia free models in this case MiniAX M2.7 and GLM 4.7. Okay friends that's it all about this video what I wanted to show you how to set up and work with PI agent using Nvidia free modus. Now, if you like such a videos, don't forget to subscribe, like, and share with your friends.