Two Ways to Save 96% of Your Money Using DeepSeek R1 in n8n

Key Takeaways

this is the riddle that we're going to send off to deep seek R1 and see if it can handle it you're in a room with three light switches each switch controls one of three light bulbs in a separate room but you can't see the light bulbs from where you are you can only enter the room with the light bulbs once how can you figure out which switch controls which bulb so we're going to send this riddle off to deep seek R1 right now it's thinking about the riddle it's going to assess its options and then it's going to tell us the result as well as all of the reasoning steps that it took in its brain to get to the answer so should be pretty cool see what it comes up with so it just finished up running if we click into this HTTP request we can see what we got back was content as well as reasoning content and so if we click into this next node just so we can read it a little better we get the answer as well as the steps that it took to get to this answer so this method uses both light status as well as heat to understand which bulb corresponds to the switch and only entering the room once so got some really exciting news yesterday deeps just released R1 which is a new model that is a reasoning model that is comparable if not better than open AI 01 reasoning model So today we're going to be looking at that a little bit breaking it down and then talking about the actual right way that you want to go ahead and use this within naden so let's jump into it and if you want to check out this report I will leave the link for that in the description if you want to read more about it and maybe read from the people that actually have developed this thing and understand it a lot better than I do anyways let's take a quick look at this LinkedIn post from shwam so as we can see deep seek just delivered what we want to call the impossible it's a model that matches open ai1 at just 12 27th of the cost so um we'll break up the cost in a sec but basically over here on the right we're seeing $60 which is um a million tokens for open ai1 output and then $ 2.19 per million tokens for um deep seek R1 output which is 96.4% cheaper and deep seek is 100% open source so when we're looking at the numbers that matter like I said here are the cost per million output tokens 60 compared to 2.19 Bucks performance comparisons as you can see R1 versus 01 they're very very comparable and R1 is um better in this metric and this metric um both in the top 3.17% of code forces anyways here's the wild part open eye and anthropic rely on traditional training methods but deep seek took a completely different path so they used pure reinforcement learning so no human supervision just exploration and learning like a child figuring out puzzles iterating over time and then what they're calling the aha moment which is during training R1 starts to develop its own problem solving strategies so it teaches itself and starts to completely understand how to do things based on what it's already done and just get smarter and smarter so the evolution here started as a base model learned through trial and error developed its own problem solving strategies and eventually matched open ai's leading models the real question here is if you're using open aai 01 why would you be paying 27 times more for the same performance so what exactly are you paying for and let's look at that in NN because if you've gotten there and you've you know con tried to connect open router to deep seek R1 or even deep seek V3 you you may have noticed some things about the way it's calling tools or the way that it's calling your vector database that maybe you weren't too happy with so let's talk about the right way to be using deep seek R1 in an here's another quick comparison Um this can also be found in that research report that I'll link down below but as you can see we've got R1 01 another version of R1 that has different parameters 01 mini and then deep seek V3 so as you can see in the on the far left of all these charts the dark blue with the stripes um deeps R1 is pretty much in the lead on everything and you can even see deeps V3 was super super powerful and how much R1 crushes V3 here's another quick breakdown of the costs we've got open AI input and output tokens $15 or $60 for per million tokens and then deep seek input and output 55 cents or $219 for million tokens so what that means is you can either use a million open AI input tokens or you could use 27.3 million deep seek R1 tokens so you know do the math there but I'm sure at this point you guys have all seen different LinkedIn posts different YouTube videos about deep R1 so the question is how do you actually use it in naad then the right way because if you watch my deep seek V3 video what we did is we connected this open AI chat model and a lot of you guys said you know you can't find Bas URL base URL is no longer an option here you have to get that by going into your credential and then you get your API key and then here's where you set up the base URL so um if you were confused about Bas URL that's where it is now but let's quickly talk about how to set this up and um how you configure this credential so I'm going to be walking through setting up a new credential with you guys so let's click into here create new credential and let's go grab our base URL as well as our API key so head over to open router. okay now that we're in open router we're going to go to our profile click on keys we're going to create a new one and then you can name it whatever you want once you hit create you will get this API key that you will be able to copy and then paste this back into naden once that's pasted into naden you're going to go up to the top left search for models as you can see deep SEC car1 is already right there very popular and then you're going to go to API down here what we have is um the base URL is what we're looking for so we're going to copy this base URL and then paste that into the base URL in NN so right here this is currently pointing to open.com and that's why we'd be able to choose from a list of models which would be gbt 40 40 mini all that kind of stuff so we're going to change this base URL and now we're going to be pointing towards open router and then once we save this credential real quick we can see that now we have the option to um put in a different model so when this is pointed to open a you have a drop- down list of all of the different open models but what we're going to do is Chang this to expression and then we need to go find the actual deep seek model or any sort of open router model that we want to use and then paste that in here so back over to open router if we just scroll up to the top of the deeps R1 right here is what we're looking for all we have to do is hit copy to clipboard and then we're going to paste that into the model section in n8n we paste that right in here you're going to get this red um error symbol that says the value deep seek is not supported but don't worry about that you're going to hit save and now you're pretty much hooked up to deep seek through open router but what I've noticed is that through testing even with deep seek V3 and now with deep seek R1 um if we want to use this it sometimes has errors with its tool calling with its um time with its endless Loops so I was testing this with with some rag and um it was hitting the pine con Vector store over and over and over like 12 times in a row and it just wouldn't stop sending queries so that was an issue I've also been experiencing this issue where I just want to say hello just to make sure that I'm actually connected and we know that are connected because we're not getting an error right away that's saying credentials are invalid or we're not hooked up to a chat model so we know it's working but going through open router I've seen stuff on community forums as well that people are just having this issue where it's taking minutes and minutes to come back so obviously this is not ideal and you know if you want to test this out with different functions in nadn you can't be waiting 15 minutes for each run so let me show you the way that right now I would start to implement deep seek R1 into my workflows real quick just wanted to say if you want to download this workflow you can do so for free by joining my fre School community that way you can just download it right away get this into your a into your NN environment and then you can just put in your API key and then you're good to go right away like I said once you join the free school Community click on YouTube resources click on the post associated with this video and then you'll be able to download the workflow right here then if you're looking to take your skills with nadn and a automation a little bit farther check out my paid Community the link for that will also be down in the description got a great community of members who are also learning nadn and sharing their resources as well as obstacles that they're running running into got a great classroom section with deep dive topics as well as a calendar with five live calls per week get questions answered make sure you're not getting stuck so I'd love to meet you guys in these calls anyways let's get back to the video what we're going to be doing is accessing deep seek R1 through an HTTP request where in here we're able to access the model and we're able to give it sort of a system prompt as well as an actual user prompt so in here it's just your helpful assistant and then I'm using the previous tool to set a query which in here is you're in a room with three light switches each switch controls one of three light bulbs in a separate room but you can't see the light bulbs from where you are you can only enter the room with the light bulbs once how can you figure out which switch controls which bulb so we're going to send this riddle off to deep seek R1 right now it's thinking about the riddle it's going to assess its options and then it's going to tell us the result as well as all of the reasoning steps that it took in its brain to get to the answer so should be pretty cool to see what it comes up with so just finished up running if we click into this HTTP request we can see what we got back content as well as reasoning content and so if we click into this next node just so we can read it a little better we get the answer as well as the steps that it took to get to this answer so first of all it said to determine which switch controls each bulb with only one entry here's what you should do turn on switch a and leave it on for two to 3 minutes this allows that bulb if it's controlled by switch a to heat up turn off the first switch then immediately turn on switch B enter the room and observe the bulbs if the bulb that's on is control by switch B the bulb that's off but warm is controlled by switch a and then the bulb that's off but cold is controlled by switch C so this method uses both light status as well as heat to understand which bulb corresponds to the switch and only entering the room once so I'm not going to read all this reasoning but as you can see it's it's a pretty robust um amount of reasoning that this model did in order to Think Through what it what um the answer to this riddle is and so yeah this is a fun use case of riddles but let's say that we're actually doing a multi-step process like resolving inqueries sending emails um doing some sort of analysis on data and then taking action this is going to be super super cool because you're going to understand exactly why the model did what it did and that will also help you reprompt stuff later and it's going to just provide full transparency as to what is happening and why as you can see it started off by saying it's a classic puzzle um the challenge is figuring out which which switch controls which bulb so first thing is that you know the main constraint is that you can only enter the room once so you need to be a little creative about how you figure out which switch controls which bulb um they talk about being able to use heat because the model understands that if a bulb is on for a long time it's going to warm up more than a bulb that was just flipped on right away it even goes right here and says but wait this relies on the bulbs being incandescent and producing heat if they're LED or CFL they might not get as hot hm but the problem doesn't exactly specify the type of bulbs maybe we can assume they're traditional bulbs that generate heat anyways and it breaks down more approaches it tells you exactly the way it got to its answer um therefore the solution is to manipulate the switches in a way that allows you to use both both light and heat as indicators but as far as setting this up it's going to be super super simple you're going to go to deep seek.com you want to click up in the top right click on API platform and then all you have to do is first of all you want to top up with some credits I put in two bucks um a while ago and as you can see I've hardly tapped into that at all um and then what you need to do is grab your API key um and so we'll walk through an example real quick so I'm going to create a new key we'll call this one test two we'll grab this API key and copy that down for later and then on left hand side you're going to go to Docs once you get here this page is going to pull up that says your first API your first API call it's going to walk through a base URL it's going to walk through the different headers and parameters that we need to put in but all you really have to do is right here you have to grab this curl and click copy back in ended end we're going to grab an HTTP request and then all we have to do is click on import curl paste that curl in there hit import and now it fills out the HTTP request for us so as you can see it turned it into a post method it grabbed our right endpoint for us it said that we need to obviously put in our API key so right here it's going to be Bearer space your API key so let me put that in real quick okay so there's my API key just make sure you have a space between Bearer and the start of the token as well as at the end make sure we have no leading or sorry trailing white space and then down here we have our actual Json body parameters that we're sending over to the model so let's look into here and see what we got we have a system prompt which is you are helpful assistant and then we have the user prompt which is just saying hello and right now keep in mind the model is deep seek chat and if we go back to the documentation we can see that the Deep seek D chat model has been upgraded to deep seek V3 the API remains unchanged however if you want to use the latest reasoning model deep seek R1 you need to do deep seek Reasoner in the model so we're going to copy deep seek Reasoner back in end and end we're going to get rid of deep seek chat as the model parameter and change that to deep seek Reasoner and now that's pretty much it we can hit test step it's going to be sending over the message hello so DC is going to come back by saying something like hi so as you can see it said the user greeted me with hello so I should respond in a friendly way and welcoming manner let me make sure my response is approachable and offers help maybe something like hello how can I assist you today and straightforward opens the conversation I don't want to over complicate it keeping it professional and still warm and ended up saying hello how can I assist you today so obviously what I did in the previous example is I made the content and expression based on what we Dragged In from the previous field so you would obviously need to reference different variables and you could even change up the system prompt if you wanted to help have this agent do something very specific for you but let's say we said something like tell me a joke and we sent this off to deep seek um it's going reason about you know like the user asked me for a joke um it may talk about different senses of humor or whatever but so the joke we got is here's a light-hearted one for you why did the Scarecrow win an award because he was outstanding in the field okay um user asked for a joke let me think of a good one I want it to be light-hearted and not offensive maybe something with a pun people usually like those hm how about a classic setup with a Punchy with a punny punch line why did the Scarecrow win an award okay and as you can see it even went way more down it gave some other jokes and it explained them um but ultimately at the end it said that the Scarecrow one was safe and familyfriendly so present Clarity around it um all right it's it's super cool stuff so that's going to be the way to set up deep seek R1 as an HTTP request in here that you still have a lot of customization as far as the system prompt and the role prompt going in of course this will be super cool in the future though being able to give your agents the brain to do all the different tool calling within um you know by using deeps car1 it'll be cool once idend creates a native node for deep SE rather than having to go through open router because that's where I think the issues are coming from right now let's say if we tried to do this again and say um tell me a joke this one will probably not come through but as we saw when we did it down below with this HTTP request how quickly those those results came back so I I just figured some of you guys may be running into this issue so I wanted to show another way that you can connect to deep seek R1 in Ed end pretty easily so if you guys enjoyed this one please leave a like definitely helps me out um but besides that appreciate you guys making it to the end of this one and I will see you in the next video