MiniMax M3 just landed, and it's one of the most impressive open-source AI models I've seen. It scores 59% on SWE-bench Pro (ahead of GPT 5.5), packs a 1 million token context window, reads images and videos natively, and costs about 15x less than Claude Opus. In this video, I plug MiniMax M3 into Claude Code and run it through three real tests: building a full-stack expense tracker from scratch, analyzing the entire FastAPI codebase with no RAG or chunking, and rebuilding a live landing page from a single screenshot. Then we break down the pricing, the token plans, and whether open-source models can actually replace the closed-source frontier models for your daily coding workflows. Try MiniMax M3 yourself at platform.minimax.io (12% off any token plan with the link above). This video is sponsored by MiniMax.
CHAPTERS: 0:00 An Open-Source Model Beat GPT 5.5 at Coding 0:37 In This Video: MiniMax M3 + Claude Code (3 Tests) 1:14 Why Open-Source AI Models Matter Now 2:19 The Rise of Open-Source Coding Models (DeepSeek, Kimi, MiniMax) 2:46 What is MiniMax M3? 2:54 MiniMax M3 Benchmarks (SWE-bench Pro, Terminal-Bench, BrowseComp) 3:21 1 Million Token Context Window & MiniMax Sparse Attention (MSA) 3:38 Native Multimodality: Images & Video 3:48 Open Weights on Hugging Face (428B Parameters) 4:17 How to Try MiniMax M3 (platform.minimax.io) 5:03 How to Install MiniMax M3 in Claude Code 5:58 Verifying the M3 Model Inside Claude Code 6:27 Demo 1: Building a Full-Stack Expense Tracker App 7:42 Demo 2: Analyzing the Entire FastAPI Codebase (1M Context Test) 9:15 Demo 3: Screenshot to Code (Rebuilding a Landing Page) 10:20 The Results: One-Prompt Website Rebuild 10:59 MiniMax M3 Pricing vs Claude Opus (15x Cheaper) 11:47 MiniMax Subscription Token Plans Explained 12:15 The Full MiniMax Model Ecosystem 12:33 My Verdict: Open-Source vs Closed-Source Models 13:19 Self-Hosting the Open Weights (Hardware & License Notes) 13:37 Who Should Actually Use MiniMax M3 14:12 Final Thoughts & Outro
------------------- Clips channel @jonlawclips
I do NOT sell any products of my own. Watch out for scams.
So some of the most interesting things, at least in my opinion, in the world of AI
right now aren't coming from OpenAI or Anthropic. They're coming from the world of open source
models and one of those open source models just hit 59% on the SWE BenchPro benchmark.
That is ahead of GPT 5.5 at coding. It has a million token context window. It can see images
and videos natively. And here's the kicker. It costs about 15 times less than Claude Opus.
And that's than Claude Opus. Forget the more modern, right? Your fable era models. It is
significantly cheaper for that degree of performance. Now that model is called Minimax
M3. And in this video, we're going to plug it into Claude Code. Claude Code is the agent that
I use every day. It's what you probably use. And so we're going to put Minimax M3 inside of Claude
Code through three tests, a real build, an entire code base, and a screenshots to code challenge.
And so by the end, you'll be able to understand and judge the quality of these open source
models. Do they meet the hype and can they actually replace the closed source frontier
models? That's the big question of AI right now. And we're going to tackle a little part of that
in this video. It's going to be a fun one. Let's go. Now, just quick context first on open source
and why releases like M3 matter. Basically until this class of models, if you wanted
native multimodality, million tokens of context and frontier level coding, you had zero options.
The frontier closed source models were just better across the board. That would be fine,
except for price where the margins that the closed source companies have are through the roof. And so
yes, the models are amazing. They're better than everyone else's, but the price reflects that.
Cloud Opus is $5 per million input tokens and $25 per million output tokens. So if you're running,
especially agentic coding workflows all day, where the model is reading through an entire
repo, it's rebuilding a code base that gets really expensive, really fast. Hence the term
token maxing that's come out in recent months. And so the open source question that has started
to arise is if I can get 95% of the performance or 5%, 1%, 0.1% of the cost, is that not a better
deal for me? And so over time, the open source models just kept getting better over the past year.
DeepSea, Kimi, the Minimax series, but they were still kind of iffy back and forth. They had really
great context, but sucked at coding. They were amazing at coding, but missing something else.
Minimax M3 as an open source model checks all of those boxes. That's how the AI community has
reacted to it. And so that's why we're looking at it in this video. So in that note, what is
Minimax M3? And then after this, we'll jump right into my computer for the demos. So as the name
implies, Minimax M3 came after the M2 series out of the AI Lab Minimax. Again, it ranks 59% on the
SWE Bench Pro. That puts it ahead of GPT 5.5 and slightly behind Opus at real-world engineering
tasks. And then 66% on Terminal Bench 2.1. And then on BrowseComp, which tests autonomous
research and tasks. The score is 83.5, which actually beats BOD Opus. Now the context window
is up to a million tokens of context, and that's with a guaranteed minimum of 512,000. And that
works because of a new architecture out of the lab called Minimax Sparse Attention, or MFA.
Basically, it just means your inference is cheaper, and so costs are going to drop. And then it is
natively multimodal, so it can directly read things like images and videos and visuals across
the board because it was trained on things like that. So it can do all of that as part of coding
tasks. And then now, again, to stress, this is an open source model. The weights are completely
open. It is all on HuggingFace right now. It's about 428 billion total parameters with about
23 billion active per token. So you can literally download the thing. You do not have to pay the
companies to use this. You can go to HuggingFace, and you can download it. Now we're going to get
into my computer. Now this video, thankfully, was sponsored by Minimax. Everything I'm about
to show you is real. It is completely uncut. So thanks for the Minimax team for letting me
showcase the model. And now I recommend that you try this out for yourself while you're watching
the video. Just follow along with what I'm doing because that means you'll learn better. It's
better use of your time. You can do that at platform.minimax.io that is on the screen here,
or again, platform.minimax.io in the description. Now if you want to use the model through the
official Minimax platform, you can get 12% off using the link in the description. Or again,
it's open source and you can download it. So if you want easier UI UX, a better interface,
you can use it through the platform and you can pay a monthly subscription, or you can again,
use it in its full open source sense. Now let's go ahead and take a look at the model and wire
it into Cloud Code. That's coming up right now. Okay, so we're going to start off here with the
install of the M3 model inside of Cloud Code. And to do this, we'll be following this article. We'll
put the link in the description if you want to see that. And we'll go to terminal. Now inside
of terminal, we want to start by clearing the prior API keys for Cloud. And as a whole high
level process, what we're doing here is keeping everything about Cloud Code the same, but switching
the brain from the Andropic models to the M3 model and this platform. So let's use this command. So
unset these two tokens, a click to enter. We'll run this as a quick check. Nothing came back.
Looks good. Now we're going to have to blur this, but basically what we're doing is pasting
this command right here to install the M3 model. Let's click enter. Now we can verify that looks
right. So that is the entire install right there. Again, we're basically just swapping out the keys.
So now to test whether this works, let's just go ahead and type Cloud to open the Cloud Code
portal. And then we can do forward slash model to see the model that's being used. And then here
we can go ahead and see the default model, minimax M3 down through the custom model right
here. So let's stick with default and that will be the custom minimax M3 model. So it works and
that in mind, we can get into our first proper demo. So again, this looks and feels like Cloud,
but the brain behind it, despite the interface we're used to is going to be the cheaper M3 model.
And so let's start off by giving it this prompt, right? Build a full stack expense track for web
app, react front end with the dashboard, express backend and so on. We're going to post that
locally so we can go ahead and see, Hey, how good is M3 actually at programming? Let's give it that
prompt. Okay. Let's proceed. We're going to work out of download. Okay. We are proceeding here.
And if you want to check your usage, you can go to the minimax platform dashboard right here.
Okay. It's going through these steps and creating the project structure,
then working on the backend and then finally the front end. Okay. There we go. It's all finished.
We can see it's been saved in the expense tracker project. And then to open the app,
we'll just paste this URL. So we're at an incognito tab. Let's paste that. And here we go.
Here's our expense tracker. Let's see if import CSV works. It does. And then we can also add
transactions manually and store the transactions. So that gives you an idea of what it can do
in terms of programming ability. But again, one of the big differentiators of this model
is the fact, but again, one of the big differentiators of this model is its context
window. And so for that, what I want to do is go to a repo. This will be the fast API repo.
Basically it's very large. And so what we're going to do is we're going to clone this. We're
going to download it and then ask the model, Hey, can you do some inferential tasks where you have
to go to different parts of this very large database and understand it and interpret things
about it and then see how well it can do that. Let's head back into terminal and go into a new
tab. I'll paste this command to download that repo. That's done. Now we're going to launch
quad inside of here, and then we're going to give it this prompt. So read the entire code base and
explain how the modules inside of it connect and do some other works. Let's give it that prompt
and we'll let it read for a minute. And keep in mind, there's no rag workarounds,
no chunking going on here. We just copied in the repo and we're letting it run. We can see here,
it's set up, it's setting up a task tracking and then reading those affected files. Okay.
The refactor is completely complete. All 24 effective tests passed. We can see the
architecture overview here, the core app and routing, the tendency injection list goes on here
with all the refactoring and the changes that were made. And then you can see right here,
we went ahead and committed that. So it's done. It is fully good to go. Pretty impressive check
mark on the context window. And now let's jump into the third demo. We want to stress test here.
And now the last big point that we want to stress test on the model is the fact that again,
it's natively multimodal, meaning they can understand images and videos. So one useful
flow I like with that kind of feature is rebuilding visual things that you like to
see on the internet. So here's a website of a company called Crusoe. So I've opened up a new
terminal tab here. Let's go ahead and get into the cloud. And then what I'm going to do is
screenshot this tab. I'm going to jump back into the terminal. I'm going to paste the image,
and then I'm going to give it this prompt. Here's a screenshot of a landing page design,
rebuild it in this way. And so we're directly feeding that image to the AI so we can understand
and extract the information we want it to. And we don't have to sit here typing out,
use this kind of font. This is the design for the page and so on. So let's let it run. Okay.
It went ahead and finished the image. Let's give that a test here. And there we go. This is a real
page that was programmed by the bot. This is the real website. This is one prompt on M3 to rebuild
it. And we can see it even built out the full page here. But this is really, really good,
right? I mean, you don't, I don't have to say it. This looks borderline exactly the same.
What we don't see here are the animations and the movement. So that's what we would want it
in a second follow-on prompt to add. But for one prompt, honestly, this is the most impressive
thing out of what we've looked at that I've seen out of M3. So that's looking really good. And that
wraps up our dive to minimax M3. So we've looked at performance. Now the other side of that,
of course, is going to be cost. And not like I've been saying with the whole open source trend is
really where you start to see the argument for why people are liking open source over closed.
So we can perform at the caliber that we've taken a look at today. But here's the cost,
$0.30 per million input tokens, $1.20 per million output tokens. That compares to $5 in $25 out
from a model like Opus, much less stable. So that's a 15x price spread. 1x, 2x, 5x would be
ridiculous. 15x is next level. And that is really, again, where if you're a CFO and it's like, hey,
can I collapse my costs by 15x on half of my usage for a net 7x decrease? That takes your bill
from $10 million a month to $1.5 million a month. And now the way the pricing for M3 works is you
can do it via API. You can also go off a subscription token plan. That's your $20,
$50, $100 a month options. And that's $20 a month for 1.7 billion tokens of M3 usage monthly,
and then $5.1 billion for the $50 a month option. Now, also the way that Minimax works as a whole,
this is a company with a lot of models out there. Minimax M3 is the new one, but they also have
2.7, 2.5, and then your audio and your video models as well. All of that is wrapped into
the same platform. So there you go. That's the model. I hope you judged for itself based on
what you've seen in these demos. Again, those are uncut. You don't hide or remove anything.
My take on it again is still closed source models are better, right? Opus across the board is going
to be better for tasks as well as stable. If you need absolute maximum capacity and performance,
and you don't care about cost, those closed source models are what you should go with.
I think the fundamental argument of the Minimax M3 model that you saw here and open source as a
whole is, hey, if you can pay 5, 10, 15, 20, 50 times less, whatever the number is for 90 plus
percent of the performance to be there, is that a worthwhile trade for you on some or most tasks?
And for nearly all of you, for me, the answer is absolutely yes. And if you do intend on self
hosting the open weights, that does take some pretty serious hardware, and you should check
the license terms there for any kind of commercial use. That's just standard disclaimer for whatever
you're doing in the open source world. So the token plans and the API through the platform are
going to be what a lot of people want to do. If you do want to go all the way in to open source,
again, go to Hugging Face, download. So overall, I think this is for any of you and myself,
to be honest. We spend a lot of money on tokens. You do it with all the frontier models. And
there's that meme of like using stable, using a flamethrower to light a match. That's kind of
what it is to use the leading closed source models on all of your tasks with AI that you let
agents do for you. So that's where you're at. Then just start to cycle in models like these.
You'll save money. Performance will be the same. Life will be good. And so that in mind, again,
that's the video. I hope you understand this model now. And you can go again to platform.minimax.io
to support the channel and to give it a go yourself. And you do get a 12% off any token plan
if you do that. So drop a comment with what AI model you want us to take a look at next.
That in mind, I appreciate you all being here and I will see you in the next one.