DeepSeek V4, a 1.6 trillion parameter open-weight model with strong tool calling capabilities, can be integrated with Claude Code through the Anti-Gravity framework to achieve approximately 100x cost reduction compared to Claude Opus ($6,250/session vs. $0.20/4-hour session), while maintaining comparable coding performance on benchmarks like Terminal Bench and MCP Atlas; this strategy works best for backend development, scripts, and algorithmic tasks, while Claude remains superior for creative design and UI/UX work.
Inmersión profunda
Prerrequisito
- No hay datos disponibles.
Próximos pasos
- No hay datos disponibles.
Inmersión profunda
DeepSeekV4 + Claude Code = 100X CheaperAñadido:
Imagine if you could use Claude Code 100 times cheaper. In this video, I'm going to show you exactly how to combine the Claude Code framework with the brand new DeepSeek V4. So, you can save thousands of dollars, build as much as you want with no rate limitations. And with this brand new repo, set it up in minutes, even if you're starting as a complete beginner. And if you don't know who I am, my name is Jack Roberts. I built and sold my last tech startup over 60,000 customers. Now, I'm building my own AI companies. and I share the stuff here that actually works. So, if you haven't already, grab that beautiful coffee and let's dive straight in. So, Claude, for 100 times cheaper, let's go into it. And by the way, I've also tested this myself extensively as well. Looked at all the benchmarks for you. So, I can tell you what the technical answer is, as well as my experience and when to use what for which you're going to find really helpful. So, let's have a look at what DeepS v4 is. 1.6 trillion parameters.
Not something you can probably run on your own computer, put it that way.
million uh context window and it's MIT open weights which means it's fully compatible with the clawed code ecosystem and one of the biggest benefits of deepseek is its tool calling ability so all the tool calling we do on anropic we can now do a deepsee that's what got me really interested in this originally as not just another connection but it's something really cool so same workflow significantly cheaper so you look at this claude opus is $6250 a session and this analogy deepseek v4 can significantly cheaper. Now, one thing to call on right now is they've got a promo on, which makes it even more cheaper than usual. After May 5th, it's still significantly cheaper, but less than it is at the moment for this week, cuz they're running a special promo. Deep Seek V4 Flash is even crazily more uh cheap. Basically 20 cents for 4 hour session compared to uh 6250 for Cordopus 4.7. All right, cool. So, does it actually code? This is what got a lot of people excited about it benchmark. So, sweet benchmark verified. You can see that is basically Deep Seek V4. How it compares to Sonet 4.6, how's uh basically um Opus 4.7. You got Terminal Bench and MCP Atlas. I know what you're thinking, Jack. She looks great on the Tinder profile, but how does Deep Seek actually show up when we take it on a day? What does that actually look like?
Because we don't want just to be a benchmark queen. We want it to actually work in practice. But I just say this to say that it's it's hitting benchmarks and it's baseline performance is good.
But as always, we've really got to check out what this physically looks like. So, I just want to call out one quick thing here, which is this is the the reason why this is a better strategy. The system I'm going to show in this video, by the way, works if you want to bring in DeepSeek or if you want to bring in a completely free model, you can do that.
But one of the big unlocks, even if you want to go 100% free, which by the way is an option, is that we have this dual terminal, which means that we can have a free model in one window. uh we can have deepseek in another one and then claude code in a third which means that if you wanted to do some work with claude code and then tag in deepseek to crush it or tag in a free model we can do all of this simultaneously using the strategy that I'm going to show you inside this video. Now to use deepseek there are two ways we can do this one is via open router but I found you get rate limited so much it's basically unusable so I'm going to show you a strategy of how we can use it with no rate limits as much as you want. So, we want to head here to platform.dec and create a brand new account. And if you want to do this completely for free, I'll also show you about strategy as well. So, go ahead and create a brand new account. And here you want to throw in a couple of dollars.
Could be $2, could be $5. Now, you can do this for free using open router and a series of things. It basically cycles free models, but again, it like you get rate limited and it's not great. And free is not free because actually the quality is less, you get charged more.
On Deep Seek, throw in like $2, $5. You can start using it. Then on the left hand side, come over to API keys. go ahead and copy this API key. Then the next thing I'm going to do is come over to this GitHub repo right here. This is a beautiful little repo. It's trending quite strongly right now, but the idea is it helps us use what I call that dual terminal splitup, which means we can use the claw code harness with anything that we want to. So all you do is come on to code, click on copy, then head over to your IDE of choice. I'm going to be using anti-gravity for this one. So let's pull them up. Okay, wonderful. I am in anti-gravity. If this sounds like I'm speaking Spanish, check out this anti-gravity masterass. I'll take you from zero to singing anti-gravity in your sleep. Now, all you're going to do is come over here and say, "Hey, then I'd like you to install and clone this repo." And then what we're going to do is connect this to DeepSeek directly with the below API key. Now, the really cool thing we can do here, okay, is we can basically either connect to Deepseek or we can connect to Open Router by grabbing our Open Routter API key. And on Open.com, you come over, you literally can grab your API key from anywhere here. And the cool thing here is this obviously enables you to access any of the models on the entire planet that you want to. Um, so basically this applies for anything. And again, this enables us to use clawed on multiple different browsers at the same time. So now it's going to come down and grab that. What we want to do is grab the API key from DeepS. Now, as you can see, the repo is cloned and I can see exactly how it works. It's a proxy server that intercepts cloud API which enables us to have these multi- conversations. Then we just provide our deepseek API key.
Fantastic. That's now complete. also then ask it this which is I want you to create two short codes. One is to run normally and the other one is to dangerously skip permissions if you want to give it the ability to do that but it's just an option if you want to. You may not want to be too ham hock with it with it being a different model but it's there for you if you want to. So here's everything we've done. We've installed it. It's all ready to rock and roll and we've got all the keys here which is fantastic. And this just runs through everything it's got and our API keys are stored in thev side over there on the left hand side. Cool. So let's actually test that it's working now. Uh, so to do this is click on terminal, click on new terminal, and now it's up here. We're just going to type in DS for DeepSeek, and then Claude should appear, which is cool. And then just going to search like, hey, I don't know. Um, who is the tallest man to ever live? Something like that. Now, quick, by the way, if you ask this model, who is it? They will basically tell you it is Claude Sonnet 4.6. That's because they're reading the data that sits in it. That's not the actual model. So now we basically fully connected to DeepSeek. What we could now do if we wanted to, if I open up a brand new terminal, I can then just use Claude and now I'm actually now using Claude in this terminal. So I can say, "Hey, now this is Claude code. This here is DeepSeek." How cool is that? So let's call this one over here to Deepseek. And of course, we want to just make sure we're doing here. Could you just confirm that we're using DeepSeek V4, please?
Wonderful. So it looks like we were using the Flash model. And when I said just use basically this version, it did it. This is how cool this is. It will just update that for us over here. And by the way, if you're brand new to CL code, I should also call out by the way that I've got a full course in the community coming that covers everything from foundation setup, building websites, power features, memory systems, clawbar apps, build anything, design systems, how you monetize it.
It's releasing this month. So if you want to go deep, I just want to call that out right now because you might find that uh helpful and building cool stuff like this. So we've got Deepseek.
Now the interesting thing here is one of the biggest abilities here is its actual ability here to use skills. So let's put it to test very quickly. So, I want to use my bit.ly skill, which makes me shorten a URL. So, let's come down here and actually try that. So, I'll say, "Hey, I would like you to shorten this URL using my bit.ly skill." All right, let's come down here and do glido.com.
All right, which is actually what I'm using to speak type right now, which is really cool. So, let's see if it works perfectly cuz it's always been my biggest complaint with these things is that they don't actually use skills very well. And if you're using Claude Code, it's only really as good as its ability to effectively use skills. I'm yapping.
This is too busy just building. It's just building in the background. So, let's open this up and see what it does.
Cool. Yeah, we open that. That's fine.
And just like that. Now, we're on here.
Stop. Stop talking. Start typing if I didn't say so myself. Freaking awesome.
So, we validated this works. And we've also validated that you can now use your skills. And addition to that, we can also use cla code exactly at the same time. Beautiful. So, let's put Deep Seek to the test. But to do that, you need to understand when to use it and when not to use it. So, think about it like this.
And this is great just generally to know this. Okay? If you're building anything creative right now, the best model on the planet for that is Claude. It is, if you like, the design king. We put a king hat on him. If you're doing automations, quick scripts, anything algorithmic problems, unit tests, any that's kind of like dirty work behind the scenes that isn't visual or design related, we can bring in the giant well for that. Bring in Mr. Deepseeker himself. Obviously, UIUX polish, we can use Claude.
Multifile refactors, documentation, blah blah blah, we can use Claude. and then code review and audits. We can also tag in codec. So to do this, what we're going to do is build a website together and we're going to do the initial design and claw and then we're going to use deepseat to do a lot of the heavy lifting in the background. So to do that, I want you to do two very quick things. First one is head over to this group here which is awesome designer MD.
This is really cool because effectively what this does is grabs a design identity from a a gazillion and that is the correct term for this different um like websites and stuff. So this is BMWs for instance. So these are all the design systems of BMW. So if you want a BMW looking website that looks like BMW, you would come on to this website. If you want Apple, then you'd come on to Apple and so on and so on. You get the complete idea. So first step is come on this uh GitHub repo here. We're going to click on code and then go straight back over to anti-gravity. And then we come back over to anti-gravity and click on this claude here. And effectively what I'm going to do here and actually since it's a GitHub install, I can just use DeepSeek for this. I'm like, hey there dude, I'd like to go ahead and install this GitHub repo here, please. All right, come over and then just paste that one in there. Now, there's some questions about Jack. Is this going to China? What about the censorship, Jack?
What about Tanaman Square? What if I want to talk about Tanaman Square? Well, if you want to talk about that, um, don't use Deep Seek. But otherwise, yeah, it's fine. I mean, like obviously all these models like sense it in some shape or form. So, do be aware of that.
One legit call out though is that if you do not want to paste naked URLs, API keys into DeepSync, that is a big big big no no. So, never do that. Don't post that in this chat here is like sacred.
So, don't post anything in here that you wouldn't be okay with popping up on internet. Um, that's a general good rule to do with any model, but DeepSeek especially, just don't do that. So, this has come back and said, do you want to do that? I'll say yes, clone it, please.
Which is cool. And get it to clone that repo. So, that's going to be fantastic.
Cool. So, that's all complete. And again, that was quick. This is the cool thing about using it directly in DeepSeek is I'm not having to wait six business days for this thing to arrive.
Like, it's just there straight away. So now we've validated and got that done.
Let's come over to Claude here and give it a prompt. I'm going to say, "Hey there, using the design repo awesome designs of the left hand side, I want you to use the Apple design framework to build me a beautiful website about coffee." Okay. And then what I also want you to do is lean on and leverage certain design components from this GitHub repo right here. All right. I'm going to paste that one there. And then what we're going to do is come over to a secondary repo. And on this one, what you're going to do, again, this has got over 100,000 stars. Look at these. It just gives it some really beautiful and interactive components. And then once we copy it, we're going to come back over here and just send it this one here. And then I'm going to say, and I'd love to have a calculator that shows people how much productivity they get from drinking coffee. Have that as like the second thing on the website, please. Cool. So, we're going to give it a general idea and we're going to send that off. So, again, Claude's doing the design work, but when it comes to all the other heavy lifting, we're just going to tag in DeepSeek. Now, you could, if you wanted to, just get Deepseek to do this itself.
And in fact, I could even show you that.
But when I did it, what I basically found is that it just lacked creative imagination, which means we're going to keep it away from anything visual, tag in Claude. Anything that's not visual, we bring in DeepSeek. And once you've built the app, you'll find that so much of it is actually just the backend stuff anyway. And another little hack with websites, if you find a website that just has a design style that you think is gorgeous that you want to kind of lean on for your designs, you can copy that URL, head over to basically just Google HTML website extractor. You head over to this website right here. You literally drop it in like so. Click on view source. Then you'll get the source code for the website. You literally click on download and then save to your laptop. Then you can pretty much feed that to the model and lean on some HTML for inspiration. So I've built a couple of options for this. This is one very kind of Appleesque style which is pretty cool. Come down. you can see from a single batch of kitchen. Again, one idea of a website we could use if we like the look of it. Another one is what I call homeline the coffee. So, I just got this cool thing that I generated with AI. And again, you come down. This one's really fresh. You get the idea using some good inspiration HTML. This is quite crisp and quite nice. It's got a really beautiful feel and vibe to it. So, Homelander coffee, something the boys can definitely trust. So, what we're going to do now we got a basic design is get DeepS to basically supercharge it.
So to do that, we're going to come over to anti-gravity. And what we're going to do very quickly at the bottom of this is we're just going to clear the window like so. Get rid of all the context. And then just give it a prompt and say, "Hey, what I'd like to do on this website is add a sophisticated ROI calculator that basically drives multiple variables. One is going to be amount of caffeine it's conf basically consumed and productivity. Make it as sophisticated and as intelligent as humanly possible." Really cool. And then I'm just going to grab the URL for this so it knows what I'm talking about. Come back over and then drop that one off right there and let DeepSeek do its beautiful work in the background. Now guys, check this out. Now, I'll be honest, this is surprising to me. It's actually managed, if you look at this, to capture the exact HTML style. This is a cool thing. Deepsee by itself, if I asked it to do this, would struggle.
It'd probably be in crayons in the corner thinking about things. But because I've got an existing brand guidelines and style, it's just replicated. So, I've got daily cups.
Let's have a look and look at this. How where am I at on this? Where's Jack Roberts at? Jack probably sits here.
Okay, I'm five cups of coffee. I want to have the whole bean. Awesome. My hourly rate is Let's just put it all up here.
It's 250. It's a bit above that, but hours work a day. Uh let's put that at like, I don't know, 13. Caffeine sensitivity, I think I'm probably quite low. How many hours do I sleep? I sleep like 89 hours. And there you go. You can see this annual ROI is 84, guys. Where do I freaking stand? So, you get the idea here. This is all done by Deepseek at a fraction of the rate and there's just one example that we could use within DeepSeek. And obviously if you want the source of how to build websites like this and actually publish them online and host them, I'll put my website masterclass so you can check that one out when you get your own homelander coffee. Now obviously if you want to use a free model you can come over to openroo.ai create a brand new API key here for example. Then once you've got that, come back over to anti-gravity and you just say, "Hey, instead of using DeepSseek V4, I want you to default to a series of free models within Open Router. Use the ones that try not to rate limit me and cycles through any of the free models. Please, here is my API key." And effectively once you restart and follow the instructions, we've now got all of these free models. Quentry coder, Nvidia, Needron 3 Super, and it would cycle through. Now you'd be doing the exact same thing that we're doing with Deepseek, but instead of DeepSeek, we're using a free model or any other model that we want to. Now, the other thing that I would love you to do if you haven't integrated chat GPT 5.5 and Gemini into your Claude system, definitely check out this video on screen where I show you the full system.
But where this goes from good to out of this world is what we can do now is the following, which is this. Hey there, what I'd like you to do is to tag in GPT 5.5 codecs to review the code to improve it in any way and just make sure that it's actually working perfectly. Now, what's cool about this is this leverages your existing chat GPT plus subscription and you can use dozens of these different things. In that video, I show you exactly how you set it up. It's super straightforward and we can tag in the best model, which means we get free reviews essentially from chat GPT, which in many respects is kicking butt right now as a model. This will now bring in codeex. Again, I'm doing it in the claw chat here, but it work just as easily in DeepSeek. We can bring in any model that we want to. So, with that in mind, now that's the full pipeline, right? claw for design, deepseat for the heavy lifting, and then codeex for the review.
But where does it really fall down as a model? And what's important to know?
Well, first of all, you promise go to China. So again, no tenment square questions. And again, bear in mind about naked text. Second of all is UI taste.
It is not great at UI. The one caveat I found is if it's already within an existing UI framework like you saw, I thought that did really well personally.
So I think it's good for adding additional things within frameworks but don't use it as your first design artist. It's no kind of uh Michelangelo if you like. And uh also the the the rate is very very cheap but there's a promo now. So instead of getting 100 times cheaper it might be slightly less than that. So what should I be doing if I'm right now? Well basically if you are corporate do not use this because again there's a corporate database. If you're doing a lot of healthcare finance, so basically really highly regulated stuff, just keep DeepSeek out of the picture a little bit. You wouldn't want to put it near your, you know, burning bludging IP that's changing the planet or like all the healthcare data. But look, if you're a solo dev using cloud credits on projects, if you're learning CL code workflows, if you're building open source stuff or prototyping hardware throw scripts, this is freaking awesome for reducing down your costs. Claude for the hard stuff and then tag in obviously chat GBT to do the reviews. Now, Deepseek is reducing our cost, but we now need to increase performance, which we can do by using super skills by watching this video right
Videos Relacionados
Agentforce NOW AMA: Build with React and Salesforce Multi-Framework
SalesforceDevs
490 views•2026-05-28
How agent o11y differs from traditional o11y — Phil Hetzel, Braintrust
aiDotEngineer
450 views•2026-05-28
WEB TECHNOLOGIES UNIT-2 | Degree 4th sem BCOM Computers web technologies unit-2 full explanation💯✅
LearnwithSahera
1K views•2026-05-29
More tests are always better? How to use AI to identify tests that bring little value
Alliance4Qualification
335 views•2026-05-29
Search Algorithms Explained in 60 Seconds! 🤖💨
samarthtuliofficial
218 views•2026-06-01
People of Game of Thrones using JavaScript DOM
AltCampus
296 views•2026-05-30
Introduction to Problem Solving Part - 1 | Lecture 1 | Intermediate DSA
ascensionix
107 views•2026-05-29
So What's Odin Lang Even Good For
TechOverTea
131 views•2026-06-01











