Run Hermes Agent FREE With This NEW Model 🤯

**Julian Goldie** (0:00)
So there's a brand new free model from China called Tencent Hanyun, and you can actually use this with news research right now. So HY3, the new 295B Moe model from Tencent Hanyun, is now free in News Portal for the next two weeks. Now, this is the agentic model, it has 256K context window. If you wanna know how it performs, I'll show you in a second. And this literally just dropped a few hours ago. So you can basically run it inside Hermes Agent for free for the next two weeks. So you can see, for example, here we have HY3 set up with News Portal here. So we asked it how you did today, it did pretty well. And then if we wanna test it out, let's give it a little task here. So we're just gonna go inside Hermes and say, okay, code out beautiful landing page, and then we can wait for it to load. Now, if you're wondering, okay, how do you set up with News Portal and Hermes Agent for free? It's pretty simple and easy. So what you're gonna do is go to your terminal here, then you just type in Hermes model, like you can see. And once you've done that, then you shall go to News Portal at the top. So select that one. And once you've done that, then you can just grab it from News Portal. Now, also what's cool here is you can also get a free API for HY3. So you can see this is going away on July 21st. But if you don't want to set up Hermes Agent via News Portal, and you want to use Hermes Agent via the API instead, you can use OpenRouter and then just select Tencent HY3.
So that's pretty cool as well. And this is designed for agentic workflows so you can see here it says specifically designed for agentic workflows, build for reasoning, etc. Which is quite a cool way to get free API and then plug it into your Hermes Agent. Now, if you're wondering how it actually performs in reality, let's have a look here. So, for example, we said code out a beautiful landing page. You can see the test here. It's giving us a link.
Let's open up. Actually looks pretty nice. It's not going to be like Fable 5 level. It's pretty nice to use, pretty easy and simple to use. It was fairly responsive as well. It took about 60 seconds to build out the full landing page, which is not too bad at all. And then we can actually use tool use with this as well. So if you go inside the chat here and we're like, okay, open up this website for us, it actually works.
Then what we can also do is try for learn as an agent itself. So we can type forward slash learn and then give it a link to a guide that I've created here and see if we can actually learn about the guide.
So if you're not familiar with slash learn, basically you can teach your Hermes Agent a new skill based on the guide and then it will save it for future workflow. So you can see here typically when I use HY3 with Hermes, it takes about 60 seconds for each response. So it's not like super fast, it's not like a Chad Sheepardy incident or something.
But for a free model, not too bad. And bear in mind, you can just give it a task and it will work in the background. So that actually took about 30 seconds as you can see right here. And then what it's done is said, I read the page, here's a breakdown, here's what I've learned. And then also it can save that for a skill in the future, which is pretty cool too. So it works in three simple steps. So you've got Hermes and you can plug that inside your HNOS. Then you can use News Portal or OpenRouter as well for two weeks. And then you can use HY3 as a brain, which is good for coding and using tools and agented workflows.
This is open source model as well. And also one thing to note is it's also free inside KiloCode. So you can also get access to it on KiloCode as well. So OpenRouter, Hermes, KiloCode, all good options for using this. If you actually look at this comparison here, so they've compared Opus, Fable and HY3 in my own tests. It's nowhere near the same level as Opus 4.8 or Fable 5 And you can test it out on Goldiebench if you want to see the outputs that we've done with Tencent, HY3, but still, if it's free, you can't complain, can you really? And also you've seen that it's non-technical to set up. So you don't need to be technical to set this up. It's like a couple of terminal commands. You plug in the model, that's pretty much it.