---
title: 'Run Hermes Agent 100x Cheaper with Miniax M3'
source: 'https://youtube.com/watch?v=u6L9aedHqZc'
video_id: 'u6L9aedHqZc'
date: 2026-07-14
duration_sec: 0
---

# Run Hermes Agent 100x Cheaper with Miniax M3

> Source: [Run Hermes Agent 100x Cheaper with Miniax M3](https://youtube.com/watch?v=u6L9aedHqZc)

## Summary

The video introduces the Miniax M3 AI model, which offers unprecedented cost efficiency and high performance, making it ideal for running AI agents like Hermes Agent 24/7 for a fraction of the cost of competitors like Claude or GPT. The presenter demonstrates how to set up Hermes Agent with Miniax M3, showcases its capabilities in deep research, SVG animation, and game development, and highlights its novel sparse attention architecture.

### Key Points

- **Miniax M3 breaks price-performance line** [00:00] — For the first time, an AI model (Miniax M3) exceeds the price-to-capability line, offering more capability for less cost than any previous model.
- **Outperforms expensive models on benchmarks** [00:30] — Miniax M3 outperforms Gemini 3.1 Pro and GPT 5.5 on SWE-bench, Opus and GPT 5.5 on SVG-bench, and is comparable to GPT 5.5 on browse-comp.
- **Novel architecture: Miniax Sparse Attention (MSA)** [01:30] — MSA reads only relevant parts of the context, skipping irrelevant tokens, enabling a 1M token context window at 1/20th the compute of standard transformers.
- **Extremely low pricing** [02:30] — Miniax M3 costs $0.06 per million input tokens and $0.24 per million output tokens (50% off currently), making it 10-20x cheaper than Opus 4.8.
- **Token plans offer massive value** [03:30] — The $20/month plan gives 1.7 billion tokens (equivalent to $1,326 in API usage), and the $50/month plan gives 5.1 billion tokens (equivalent to $11,900 in API credits).
- **Setting up Hermes Agent with Miniax** [05:00] — Install Hermes Agent via GitHub, select Miniax plan, copy subscription key from Miniax console, and paste into terminal to configure.
- **Deep research comparison with Perplexity Computer** [08:00] — Hermes Agent with Miniax M3 performed deep research on events in Polish cities, producing a comparable report to Perplexity Computer ($200/month) but at a fraction of the cost.
- **Building a Doodle Jump game with Open Code** [10:00] — Using Miniax M3 in Open Code, a 2D platformer game was created for under $0.10, demonstrating coding capability and cost efficiency.
- **SVG animation creation** [12:00] — Miniax M3 generated a complex SVG animation of a rifle assembling and firing for $0.25, showcasing its multimodal strengths.
- **Open weights commitment** [14:00] — Miniax team will release open weights on Hugging Face and GitHub within 10 days (around June 10th), making it potentially the most powerful open-weight model.

### Conclusion

Miniax M3 is a game-changing AI model that delivers frontier-level performance at a fraction of the cost, enabling always-on AI agents and extensive usage without hitting limits. It is ideal for developers and power users who want to maximize capability while minimizing expenses.

## Transcript

You can actually run Hermes agent for 100 times cheaper. Here's how. So, a major AI breakthrough just happened. For the first time ever, an AI model broke the price to capability line where the more you pay, the more you get. And everything so far has been either on this line or below. But Miniax M3 is a new AI model that for the first time ever is above this line. But most people for some reason still only use cloth or GPD which is costing them hundreds of dollars per month every month while Miniax is nearly free. Oh, and it's also really really good. On SWE pro it outperforms not only Gemini 3.1 Pro but also GPT 5.5. On SVG Benbench it outperforms Opus GPD 5.5 and Gemini. And on browse comp, which is very important for Hermes agent, it is better than Opus and roughly similar as GPD 5.5. And this is just one of many reasons why Miniax M3 is perfect for Hermes agent. It's also cheap enough to run 24/7, which makes always on agents finally possible. Also, given the large context window of Miniax M3, it can do up to 1 million tokens. It can hold your entire project in memory, not forgetting anything. It's also built for long toolheavy loops such as the slash goal feature inside of Hermes. In fact, Miniax M3 can run for over 24 hours straight doing up to 2,000 different tool calls with no human intervention. That's incredible. Now, you might be thinking, "But David, how is all of this even possible? How come Miniax M3 can outperform models 10 to 50 times more expensive?" Well, the answer is the architecture. It has a novel architecture called MSA which stands for miniax sparse attention. And I know it sounds complex. It sounds difficult but actually it's very simple and very easy to understand. And understanding it will give you an unfair advantage over everyone else. So here is MSA clearly explained. Normal transformers read every single token in context every time. That's why long context workflows cost a lot of money. MSA on the other hand checks which parts of the context matter and then only reads those parts skipping everything else. So the result is a full 1 million context window at 120th of the compute. And of course the pricing of Miniax is just insane. For comparison, Opus 4.8 costs $5 for million input tokens and $25 for million output tokens. Miniax M3 costs 060 and 240. And on top of that, now it's 50% off, which makes it 10 to 20 times cheaper than Opus. This is how you can run Hermes Agent 24/7 for just a couple of dollars. real quick. Are you building something impressive? I'm going to be hopping on a call personally with people who are building impressive stuff with AI. So, if that's you, make sure to fill this out. Again, it's the second link below the video. It's completely free to apply. Now, to put the insane cost effectiveness of Miniax into perspective, when you get the $20 a month plan, you get 1.7 billion tokens per month. Not million, billion. And at the current pricing, okay, not the discounted 50% off pricing, the full pricing, this plan, 1.7 billion tokens, gives you a blended average of $1,326 per month of API usage, okay? Which if we compare that to Opus 4.8 tokens, would be $11,900 of monthly API credits. If you get the $20 plan for Miniax, I mean for the max plan which costs $50 a month, you literally get over 5 billion tokens per month, which I don't think you can get anywhere else. And since many of you are interested in running Hermes agent as cheaply and efficiently as possible, I reached out to the Miniax team to sponsor this video and agreed. So, if you want 12% off any of these paid plans, click the first link below the video and make sure to apply. Huge thank you to the Miniax team for sponsoring this video. With that being said, let's get to building. So, first go to Google while it still exists and type in Hermes agent GitHub to go to the official GitHub for Hermes agent. So, obviously Hermes is fully open source, so it's free to download. Scroll down here until you reach the quick install section, which gives you this one command. Click on that. Boom. Open any terminal on your computer. I'm just using the default Mac OS one, but you can use Cmax, T-Max, whatever you want. Paste it in. Hit enter. And this will begin installing Hermes Agent on your computer. If you don't have it installed, it will take like two minutes to install it. And then we need to select the miniax token plan. I have the $20 one, but I do recommend getting the $50 a month if you hit the limits, but it's very hard to hit limits on 1.7 billion tokens. Yeah, the the value you get for this is really incredible. Enthropic cannot compete with this at all. Like if you have the cloth $20 a month subscription, you're hitting limits constantly every single day, multiple times. With this, good luck. You'll have to be a serious AI engineer to hit limits, right? When the install finishes, you'll see the option to select the plans. So all the way scroll down here and you can see Miniax. Here we have three options. Minimax OF, Miniax default, and Minax China. So here, what you want to do is select the first one, Miniax. And we need to get the API key. So again, when you click the first link below the video, you'll be brought to the Minax pricing plan. Here you can go to the top right, click on console after you create an account, which is super easy. You can just create one with Google. Takes like 10 seconds. So in here inside of the minmax platform, go to the left and click on plan details. And here you have your subscription key. This allows you to use your subscription to power Hermes agent and many other AI agents such as open code which I'm going to show you later in the video which actually you can use Miniax M3 to build anything build any type of software whether it's a AI startup whether it's internal software whether it's just a cool demo for you for your friends for your family. You can use it inside of Open Code which is also free and open source with the subscription key from here. And again, I'm going to show you that later in the video, but first, copy it. Switch back to the terminal and paste that in. Okay, here it's asking for the base URL. You can just hit enter. And for the model, obviously, select Miniax M3. Okay, here you can keep current messaging platforms. We can skip that for now. And we can click done. And just like that, we've set up Hermes agent locally. So, I can do clear and type in Hermes. And this should launch the Hermes agent TUI terminal user interface. Here we go. We have Minimax M3 here. We can do Hey. And this is powered with my token plan, right? So I'm using the $20 a month plus plan from Miniax to power Hermes Agent. And again, this gives me 1.7 billion tokens per month. So you can literally use Hermes Agent 24/7 and you'll probably not run out. And if you do run out, you upgrade to the 50 plan, which gives you 5.1 billion tokens, and then you will not run out. So, what I'm going to do is I'm going to CD into a folder and I'm going to launch Hermes agent in here and I'm going to tell it use the following repository to save any and all files. Do not create or modify files outside of this project. Okay, send the limiter and I'm going to send it the prompt. So, this is a DB research prompt and basically I'm going to compare it how good it would perform against something like Perplexity Computer. So I'm going to send the same prompt into Proplexity computer which of course cost $200 a month. Uh that's a lot more expensive and the usage is way less. Okay. So we can easily run out of these $200 a month these credits inside of Perplexi computer. But for uh minimax you can actually check your plan plan usage and you can see that so far we are at 1% of our weekly quota. Okay. So you can do many many deepes with this and you're not going to hit your limit. So this Hermes agent will be running and doing this deep research about events in Katoitz, Krakov and Warso over the next 90 days. So different AI tech business events and I want to put everything into a single MD file. So yeah, it's going to do this deep researches and I'm going to let it run. In the meantime, let me show you how to build anything with Miniax M3 by using it inside of Open Code. So if you don't know Open Code, it's like a open source alternative to Cloud Code. And again, it's completely free. So you can just go to opencode.ai AI and copy this oneliner installer command. And while this is running, I'm going to do a new terminal. And I'm going to paste that in to install it locally on my MacBook. So you can see it's pretty fast. Boom. There it is. So let me do clear and type in open code. And of course, we want to use miniax inside of open code. So type in /connect to connect a new provider. I'm going to type in miniax. There it is. Minimax.io. And we need to put in the same API key. So let's go back to plan details here and copy the subscription key. Boom. Paste that in and hit enter. Select Minimax M3. And here here we are inside of open code. Literally how fast was that? Like 20 30 seconds and we are chatting with Minax M3 inside of another agent. Right. So not only do we have Hermes agent here doing a deep research using the subscription here we have open code also using the minimax token plan subscription but here we can optimize it for coding. So I'm going to give it a prompt. So the first thing I want to test is a simple 2D game, Doodle Jump platformer game as a single contained HTML file. So let's see how good it is at that very use case. And inside of Open Code, we can see the usage at the bottom. So so far we've spent 1 cent, one penny. We're going to see how expensive this is. But I already know that this is not even going to be comparable to Opus or GBD 5.5 because of how insanely efficient Miniax M3 is. And let me highlight this once more because I think a lot of you don't realize the significance of this. So far, every single model has been on this line or below, which means you have to pay more to get more capability. But Minimax M3 broke the line. It's the first model that gives you way more for the same amount. Completely crushing Sonet 4.6, by the way, which is not only over 10 times more expensive, but also worse at long horizon coding tasks, which is the type of stuff we're currently testing, right? And again, I'm going to be jumping on a call with a few of you who are building the most impressive things with AI completely for free. So, make sure to fill this out. It's the second link below the video. All right, let's check on Hermes how it's doing. Still deep researching. So far, used 13% of the context window, 60,000 tokens inside of Open Code. We are at still one penny. That's insane. Let's check the plan details here. Let me reload plan usage. Okay, so we're at 9% of our 5hour limit and still 1% of our weekly limit. Incredible. I want to see how good this game will be. And actually, one more thing I want to test while these two are still running is how good Miniax M3 is at creating SVG files, right? And animations with SVG because it's crashing on the SVG bench eval. So, what I'm going to do is I'm going to open a new terminal command N. Type in open code. We can launch another Open Code instance while the previous one is running. And we can tell it build the following SVG animation. And I'm going to paste in a description of what I want to build. a single self-contained SVG file utilizing animate animate transform blah blah blah. It's a pretty long prompt describing exactly what I want. So, what this should show is a looping animation of different rifle parts assembling, shooting a shot, and then fading out. So, it's not just a simple image, static image. It should be a SVG animation. And we can see that there's already thousands of tokens of Miniax. Let's check the usage. This is the main thing, guys, because I'm telling you, you can still less than 1% of the weekly limit. Incredible. Let's look at the Hermes deep research. It's still researching. It's being very very thorough. Running for 12 minutes. I told you it can run for over 24 hours doing nearly 2,000 tool calls without any human interruption. And again, if you want 12% off any of the token plans from Miniax, make sure to click the first link below the video and get any of these plans for yourself. You're going to get 12% off of this already incredible price. Okay, so it seems like Hermes agent is finalizing the deep research with 20 different events happening over the coming weeks and months. And the huge benefit is that obviously Hermes agent is open source running locally. Miniax is going to be open source. So far they open source previous models. And the cheapest plan is 10 times cheaper than the cheapest perplexity computer plan which obviously is $200 a month. And again, I'm running out of this usage pretty often. Like even for $200 a month, this doesn't last at all. With this, you'll probably get like 50x more deep researches inside of Hermes than uh with Perplexi Computer. And again, this is cloud hosted, so who knows where these files are stored. You kind of have to trust Perplexity with all of this and all your data. Okay, there it is. So, here's uh the formatting coverage by city, Katavita 3, Crack of 7, Warso 10. I mean, yeah, Warso is the biggest city, so that makes sense. Top five local recommendations. Cyber security expo forum katvita June 1516. Interesting. And here we have all the sources at the bottom. Very clean report. Not overly bloated. That's also important. It's not like hundreds of pages of just AI slop. Let's look at what perplexity computer gave us. A lot of these events are the same. I mean, you cannot really invent, you know, other events like that. Okay. So, the events it recommended are different. Interesting. Actually, what we can do, I'm going to kill this Hermes agent. Clear Hermes and say list out all folders in this repo and list out all files in /reports folder. This is a separate HMS a separate session. So, it will have no bias towards which is better. And we can have Miniax analyze these two reports and compare them. Okay. Now analyze both of these markdown files, read them in full and give me a clear and objective comparison. Be very concise. Right? The SVG should be finishing up now. So let's look at it. Comparison format. This is pros per event selection. This is a structured table. Yeah. Event overlap. Okay. Unique to perent computer. So some events are unique. Some of them overlap. Perplexity was stronger on small free meetups. Events is stronger on big conferences. The top five picks were different. And let's get the verdict. Evans MD is the stronger calendar. Progress is better niche meetups. Neither is complete merging them. So that's crazy. The fact that these are comparable deep research reports where one of them is 10 times cheaper and gives you probably like my best estimate is like 40 to 100 times more deep researches per month compared to what you would get on the 200 month plan here. It's really insane. the efficiency of the minimax token plan. We're at 3% of a weekly limit and we're running multiple things here still. This SVG is going to be crazy. I don't know why it's cooking for so long, but this better be good. And look at the spend 9 pennies, 9 cents. And let me remind you that this is not some cheap 7B model. In fact, artificial analysis puts it as one of the top models in terms of intelligence. literally neck-to-neck with Gemini 3.1 from Google which is way bigger model way more expensive to run and on the intelligence index it literally is ranked as one of the best models in the world so this is not just some AI model a small model that's cheap to run this is literally one of the best models out there that's also the most costefficient model to run okay so we have this SVG file finally took a while because it kept overthinking so I told it to write the file let's see okay great it's written so I Okay, now open this SVG for me in Brave browser as a new tab. You can literally do anything if you just speak English. Like you need to verbalize your faults and describe what you want the agent to do and it can just do it. All right, so there it is. Rifle is being assembled. Okay, that's actually pretty good, right? Chambered. Shot the gun. Now it should disappear. This is impressive, guys. And again, 0.25 25 cents SVG animation that can be used in video games, in graphics, in videos, video editing, landing page on your site, and the shell is running out. Guys, this is this is good. This is good for 0.25. Pretty insane. Let's see the other um instance. This building the 2D game. This is a bigger project admittedly, but I also had to tell it to stop overthinking because this model is very perfectionist, right? I mean, there's a reason why it's performing really well on all these benchmarks. This model likes to think a lot. It likes to reason a lot. And sometimes that's good when you want a really detailed report, a really impressive refactor. But if you want something simple and quick, you need to kind of tell it like stop planning, stop thinking, do not overthink. Just write the file now. So hopefully we can test the game soon. So the 5 hour limit, we're at 25%. And by the way, this resets in 10 minutes, right? So we cannot even get to How do you even use this out? Like I'm using three agents, two open codes, one Hermes agent. I'm even struggling to hit the limit. This is pretty impressive. Okay, you literally need to be running four to eight agent in parallel 24/7 to even like hit these limits. Anyways, we already know it can do detailed deep research on the level of perplexity computer or even better while doing that for a fraction of the cost. We already know it's great at SVGs. In fact, it outranks other Frontier models at SVG Bench. So, let's see how good it is at 2D games. Uh, and yeah, this is the beautiful multimodality of Miniax M3. It's great at video, images, coding, text, all of the things you would expect a Frontier AI model to do in 2026. And by the way, the Miniax team has committed to open weights. So, this model will be open weights on Hugging Face and GitHub within 10 days of its release. So that's going to be around June 10th, which means it will probably make Miniax M3 the most powerful open weights model in the world. Uh the moment they open weights it, it's not open source, but it's going to be open weights. And in fact, we have the HTML file done. So I'm going to say open that in Brave browser as a new tab. And let's see how the game performs. It's 1,100 lines of code. And uh here we are. Hopper. Okay. The graphics are nice. Okay. Okay, how do we play it? Resume. We need to jump. Okay, look at the sounds. Okay, I need to pause my music. Okay, the sounds are pretty solid. Is there some boost? No. What are the mech? What are the keyboard controls? Answer in short. Okay. A and D and Okay. So, the issue is some of these. Look at this. Graphics are nice. The sounds are nice. There's no double jump. Okay. Make sure the platforms are closer to each other. That is the main issue. Most of these levels have the platforms too far apart. Okay. This one should be playable. Look at this. Let's jump to the left. Okay. Too far. Yeah, it needs to be either a double jump mechanic or the platforms need to be a bit closer. But not a bad game. Certainly not a bad graphics. And again, open weights model all available for like what? 0.4. Pretty crazy. All right, let's let's reload this. Actually, the gap should be smaller. All right, here we go. Let's see how it does. What is this? Some boost. Oh, it crashed. Okay, I'm going to send it a screenshot and obviously we can fix it and keep improving it forever. This uh type of platform crashes the game. It's going to analyze that image and you know fix the bug. You get the point. So you can build any type of software with it. Whether it's a 2D game, whether it's SVG graphics, whether it's deep research, full stack web app, internal software. This model is inherently multimodal and it's competent on all of the frontier and agent capabilities. Can basically do anything you needed to do for a fraction of the cost that other other models are. So again, most people are stuck to just using cher cloth. If you sit down and if you actually watch this video again and implement Miniax, you're going to be able to do everything these models can do for like 10 to 20 times less. So, if you care about costs and if you want to run Hermes agent in the most efficient way possible, set up the Miniax token plan connected like I did in the video. And again, it's the first link below video, just choose the plan that works for you. If your budget is limited, go with the $20 month. If you want 5 billion tokens per month, go with the max plan. But either way, click the first link below video to get 12% off. And with that being said, thank you guys for watching and have a wonderful rest of the