Rivian Automotive Aktie

Thanks, everyone, for joining us for the next session. Very pleased to have with us from Rivian, Claire McDonough, CFO.

So just to get started, Claire, I mean, a couple of things we want to sort of really touch on here. But I think first and foremost is the upcoming R2, right, which I think everyone is sort of pretty excited about. Maybe you can sort of just tell us about how the preparations for that vehicle are going. I think it start -- officially sort of maybe opening things up to configuration sort of in the coming weeks. So where we are in the process and sort of how investors should sort of think about the cadence of R2 over the balance of the year?

Sure. Well, first off, Joe, thanks so much for having us. For those of you in the audience that haven't seen it already, we do have an R2.

Sorry, I should have mentioned that. Yes.

So definitely the better than listening to me is to go and experience the vehicle directly yourself, and you'll understand what we're going to talk about a little bit more today in terms of the intentionality in the design, the technology and the utility and performance that gets unlocked with the smaller and more affordable package that we've brought to market with R2. So on June 9, we'll kick off the first deliveries externally. So we've been making deliveries to employees and spend a lot of time working through the overall validation process before we start external deliveries on June 9.

And then also on that date, we'll also kick off having test drives across our 100 different service and sales locations across the country as well. So really excited to get more customers behind the wheel of the R2 and have them have the opportunity to experience it for themselves.

Okay. And I think in terms of sort of your guidance, right, you mentioned about 9,000 to 11,000 deliveries -- total Rivian, I guess, for the second quarter. But obviously, when you look at what you did in the first quarter, what you expect to do for the second quarter, there's a big ramp-up sort of here in the back of the year, which is to be expected, obviously, with R2. The sense I get is you feel pretty comfortable about demand, although any sort of commentary there would be appreciated. I guess what's sort of the gating factor for sort of where you sort of really think you can fit in? Is it just sort of like the pace of the ramp and sort of how the supply chain comes along? Or maybe just sort of help us understand the cadence of the year and what could go better or worse?

As you mentioned, our overall guidance, we delivered just over 10,000 units in the first quarter, 10,000 units is roughly the midpoint of our range for the second quarter. So that implies an average of about just over 22,000 units a quarter in Q3 and Q4. And with the cadence of the ramp, you'll certainly see more of those shifting towards the fourth quarter relative to the third quarter. As we think about the overall execution of the ramp, it's heavily going to be supply chain driven.

Our teams have spent a lot of time with each and every one of our suppliers and while I wish there's more flexibility in the automotive industry, you can only ramp as quickly as your weakest supplier. And so our teams are on the ground to validate, assess the quality, the manufacturing environment that each of our supplier partners are executing against today to ensure all of them can work as part of a broader orchestra as we approach our overall ramp for the back half.

One of the things I noticed about sort of the -- what appears to be sort of the launch plans and maybe this is sort of the lesson learned from the R1 experience, right, is a little bit of simplification of an offering, I'd say, to start, right? But I think that also probably also helps with keeping future demand unlocks going forward as you sort of unveil new trims and variants and offerings. So maybe you could just sort of talk a little bit about some of the thinking there. Is it really just sort of a risk and execution mitigation strategy to sort of start very almost homogenous and then sort of offer more and more variants over time?

It's part of an overall strategy of how do you go slow to go fast. And in doing so, we've cultivated a smaller assortment of our launch variant product, which is our performance variant, which has a number of additional bundled features included as part of it that we'll launch with. And then over time, in the back half of this year, we'll introduce our premium variant. But as we think about the order backlog of R2s that we have, we're just inviting customers that are interested in configuring their launch edition version of the vehicle to configure that, order that.

So we can also shrink down the time line between order and delivery and better manage expectations within the order bank of customers as well. So on the night, we'll unlock that for a select handful of customers, will be invited to configure their very first.

So you invite people who have orders to configure basically, not -- you won't -- someone from the general public won't be able to go on the site and sort of configure a vehicle.

Right. So we'll go wave by wave through the orders that we have on hand. And then the other element of it is we're going to have a data sample from customers that may have ordered more recently. It will help us assess the conversion rates across the overall cohort as we are doing our modeling and work associated with the ramp and deployment of the overall delivery execution as well.

What can you say about, I guess, the launch edition? Is that sort of -- is it sold out? And will it remain as sort of a certain variant -- high-performance variant over time, just called something different? Or how should we think about that?

So you can think about the Launch Edition as being our performance variant, but with -- it will have lifetime autonomy in it. It has a tow package included as part of it. So there are certainly different elements of what in the future will become added options that are included as part of that Launch Edition bundle.

Okay. On the R1, which I know the focus is on the R2. But I guess like the EV market, particularly in the U.S., which is most relevant for you guys, obviously, -- it's been through a lot of sort of the crossroads. I guess I'm curious if you could sort of reflect a little bit on how you think performance of that vehicle has held up in what's obviously been a sort of changing and dynamic backdrop for electric vehicles broadly. And maybe also a little bit of color on sort of how you're sort of seeing the demand and the order intake for that vehicle currently and what you sort of expect as R2 begins to ramp and also sort of obviously broaden out into additional trim levels?

For the R1, it still to the day is the best-selling premium electric SUV over $70,000. And in the state of California as well as the best-selling premium SUV over $70,000, ICE or EV included as part of the underlying denominator of vehicles. It's also a vehicle that established the Rivian brand to the market. It has a tremendous amount of fans, following, consumer reports as a study on intent to repurchase and the Rivian vehicles are 14 points above the next best player in market, really being a class-leading program for us.

But it is a much smaller addressable market as we think about vehicles in the $70,000 to north of $100,000 arena. which is where the game changes as we look to R2 and the opportunity to unlock a much broader addressable market of customers that can afford a $45,000 to $57,000 vehicle, and we're really excited to tap into that demand and the interest that we've seen in market for R2.

I guess to round out the current -- the portfolio as well, let's talk about the van and the relationship with Amazon. I mean, you do disclose every quarter in the Q, the sales to Amazon, it looks like it's been pretty strong, implying pretty decent RCV deliveries. Maybe just like mark to market on sort of the status of that relationship and what Amazon is telling you in terms of how they continue to want to sort of try to electrify their fleet.

Amazon has a really strong relationship with Rivian. And part of the beauty of the overall offering of electric delivery vans for them is the total cost of ownership advantages that they provide. And Amazon has taken years to build out the charging infrastructure to support the electrification of their fleet.

And so it's been really interesting to be sort of their partner on this journey as they've been able to work through adding power to some of their DSP sites to prepare for the electrification of their fleet over time. We're now in a position where we're seeing them increase their volumes on a year-over-year basis. And so we saw that certainly in the first quarter, and we anticipate there to be strong demand from Amazon throughout the course of this year.

And is that -- are there lessons learned there for sort of broader electric van opportunities? I know you sort of had some pilot programs with some other customers. But it seems like, again, maybe the pain point in why Amazon went a little bit slower earlier on was what you just mentioned to alluded to the infrastructure sort of build-out. So what are you seeing from other customers here as they -- in those pilot programs in terms of building out a support structure to support the vans?

I'd characterize there being interest and curiosity to understand what does it take to make the transition. And as you look at Amazon, which is the largest fleet operator, they see all of the benefits that the transition makes. But it certainly is challenging as you think about the investments in infrastructure, the lead times to prepare a fleet to electrify. And that's the piece that I think both Amazon and Rivian appreciate and understand and why we wanted to be balanced as we think about the size of external customers beyond Amazon in the near term.

So are you ready to take Amazon and lessons learned there and almost as a case study as you sort of go and talk to other customers about what it takes, what's needed? Has that helped with that process at all?

It definitely helps with the overall process. I think the other piece is it takes some time to educate on the total cost of ownership. It's not just the -- if I'm working in procurement and I look at the upfront cost or even as I look at the underlying cost of fuel or power cost or energy costs that are going into the product and the comparable set. The piece that is critical is the uptime that the vans are able to deploy, the fact that we're using mobile service, the vast majority of the time to help support them. So their vehicles never leave the DSP. We're going to the Amazon DSPs to fix the vehicles in real time that helps again really reinforce the total cost of ownership and operational advantages of what we're able to bring to market.

I guess moving down the income statement a little bit just on your outlook for the year. You did reiterate your EBITDA guidance for the year, I think, somewhat encouragingly, right, because there's definitely been some inflation on some of metals and other inputs. And so -- and plus, I think I know there's some R&D sort of accelerated, I think you sort of talked more about '27, but I imagine some of that probably creeps into this year as well. So maybe you could just sort of talk a little bit about some of the puts and takes and what gave you the comfort to -- I know there's a range, but like what gave you the comfort to sort of be able to reiterate that range?

The overall comfort and the reiteration of our EBITDA guidance is driven by both some of the net positives that we've seen, whether those be IEEPA, tariff refunds, whether it's increasing our sales of regulatory credits beyond what we had originally planned for or modeled, the continued visibility that we have into the R2 launch and execution as that stands today. while also ingesting some of the rising raw material costs that we're seeing across the industry.

I don't think you quantified potential IEEPA because I think you did say there was none in the first quarter, but there might be some in the balance of the year that is embedded in that number. Is that fair?

That's fair.

And credits, is there an update there? Because I think your guidance there was to basically assume nothing.

Right. It was more that we were able to execute more credit sales in the first quarter. Nothing. We're still in the -- don't plan for anything in the back half.

Okay. And order of magnitude on a potential IEEPA benefit recovery, any color there?

In the tens of millions of dollars generally how we size it.

Okay. Let's move on to Georgia and DOE. And I think what really sort of just love to revisit some of your thinking and calculus in terms of the renegotiations that took place. Obviously, like you upsized that initial sort of capacity, you get the money earlier. But the other -- I guess, if I were to sort of say somewhat balanced on that, right, like you are maybe giving up some -- a larger amount of money over a longer period of time to sort of help fund a larger build-out. Like not to say you can't expand beyond $300,000 there over time, but it seems like at least now, that's going to require you to fund that more or sort of other sources. So internally, how did you sort of think about that striking that balance between those 2 things?

As we thought about the impact to the increase in the Georgia site, we looked at it through the lens of the cost efficiency on a unit of capacity that we're building into the bounty, Georgia, where you see a lot of efficiency as you go from 200,000 units to the incremental 300,000 units. And so as we were dialing in our planning and preparation for it, that was a highly attractive investment in the future that we could make. And we were able to also get the Department of Energy to increase the initial phase of the loan as part of our renegotiation efforts with them.

So we actually increased the principal proceeds by $600 million. And so it created this really hyper-efficient initial phase of Georgia that takes Rivian to meaningful scale with total capacity of 515,000 units, a path with that scale to free cash flow positive in the future. And so for us, that first phase is really critical as we think about rapidly accelerating our growth in capacity in the near term, which this work is pulling that forward for Rivian.

Yes. I'm glad you sort of tied those 2 concepts together because I mean, one of the other things you obviously mentioned that got some attention from the investment community is the free cash flow positive at sort of that, call it, plus or minus 500 million units. So in some respects, this is maybe that allows you to get there a little bit earlier, right, because you're putting more upfront. But I guess like just how would you, volume is obviously important to being able to generate cash. But what are some other factors or are there other things that Rivian can do in order to sort of try to get to cash flow positive, maybe even a little bit earlier or at a lower level than 500,000?

There are certainly levels, and I can't sit here today and predict the exact GPUs that we will need 3 years, 4 years down the line or the cost of that end market. But there are certainly areas of accelerated investment that we're making where there's opportunity for greater levels of efficiency that we see in sort of the current state of affairs within the business today that could help, I would say, flatten the curve or flatten the volumes required for Rivian to be free cash flow positive in the future. The other dynamic is that it's heavily dependent on how aggressive are we building the next phase of capacity expansion as well, which, again, is a key barometer. But ideally, we're in a position where there's a tremendous amount of demand available to Rivian, and we're accelerating towards capacity expansion to fulfill that demand overall.

Let's switch over to ADAS and autonomy, the other sort of exciting vector here for Rivian. And let's start with the universal hands-free product, which I know is evolving more to point-to-point, I think, still by later this year. So how can you -- what can you tell us about sort of that technology path and sort of the progress that the products make? I know we were in sort of some early versions earlier this year, but presumably, you've sort of seen some progress there as more data and better product out.

Right. Lots of progress being made behind the scenes, not yet released to customers. We have released our universal hands-free offering, which allows hands-free driving on 3.5 million miles of roadways across North America. But the key offering for consumers is truly adding in the overall point-to-point offering for them so that they can have peace in mind as they're navigating both in town, on highway for each and every one of their trips. Our teams have been making significant progress. I was in a development vehicle a couple of weeks back in San Francisco.

In an environment like that, or I'm sure if you were to do the same here in New York City, you see just so many different edge cases that are happening left and right. And it was great to see how our large driving model was handling quite a dynamic set of circumstances and environment as well as we continue to progress our efforts there. The other piece that's critically important to our autonomous road map for the future is the ramp and scaling of R2. And the R2 fleet provides so many more edge cases of data that we can take back, feed into our large driving model, feed into the data flywheel that we have at Rivian to make our model is that much better and the quality of the experience and safety associated with it.

Yes. I want to put a pin on that because I think that's also where maybe some of the Uber relationship can sort of tie in, in terms of sort of getting scale and data. But just before we sort of go there, pricing for the product, like I think you're starting it at right now $50 a month, maybe $2,500 to buy it. I think you've indicated in the past that clearly, like as more functionality comes into the system, like you might have to reevaluate the pricing. I'm curious how you sort of -- like is that sort of a little bit of like experimentation, almost A/B test? Like how do you sort of think -- how do you figure out sort of what the right level is and what the customer ability to pay for that functionality is?

I would say autonomy pricing has been one of the most heavily debated topics within Rivian over the years. The philosophy and approach that we took is we want there to be widespread adoption of our capabilities. That also helps feed our flywheel, our models, more drivers utilizing these features is better and will continue to help us accelerate our progress as well. And so we wanted to start with a very approachable level that lots of consumers could say yes to. And so that was really the genesis and approach that we took as we thought about the pricing dynamics.

Yes. You mentioned some of the development vehicles upfront. Are those sort of the next-generation with the Gen 3? So -- and that's still sort of on track for later this year as well. And there were some reports that like you might look to sort of bring some of the LiDAR capabilities in-house. Is there anything you could comment on that?

So I think that was more of an erroneous headline. No plans today to bring it in-house.

I'm glad you could clear the air there. All right. So let's talk about Uber, which is obviously also interesting, and you definitely get your vehicles out there. And I think it also, again, as you mentioned earlier, get the data, get the flywheel. But I am a little bit curious how you sort of think about that, right? Because presumably, at least the earlier ones, and maybe I'm wrong, but like will they still have a like almost a safety attendant in there? And I know it might need to be dependent on sort of the geography you sort of going in. And if so, like is that on you? Is that on Uber? Like -- or you're not going to sort of really open it up to the public until you can actually sort of take the safety driver out or the safety monitor out?

We've already started data capture collection in the launch markets that we're working towards in 2028. As we're sitting here today, so what you'll see is just a continuation of the progression with safety drivers effectively executing point-to-point and ultimately bridging that to an L4 capability in the future overall. So we'll certainly go with our own progress, but always trying to create value-added solutions along the way.

Okay. So by the time you're sort of at that sort of scale number that you sort of have put out with Uber, it's sort of driver out type of operations.

Right. So the expectation is the 2028 milestone timing that we talked about being in Miami and San Francisco, those are driver out milestones that we're executing towards.

And how do you think about -- right, so there's obviously sort of benefits from using a network like Uber in terms of leveraging their network and you get the benefit of the miles. I mean I do think, though, one of the things you maybe lose out a little bit on is sort of some element of the customer experience. Obviously, not sort of being in the car, but Uber as is widely seen like they are -- they plan to have multiple sort of AVs on their network. So what were some of the like strategic considerations in sort of putting your vehicles on that network? Because it almost seems like by trying to fragment the market, they're sort of trying to get rid of sort of differentiation of product and transportation on that front.

For us, the core consideration in partnering with Uber was to focus our investments and team on what we see as the highest impact area of robotaxi, which is focusing on the development of the driver. And so instead of trying to do everything all at once, being able to focus on that, which we think is great for robotaxi applications will also unlock consumer L4 opportunities, which we think is an enormous market in the future as well. That was our priority and focus. The other dimension, which is helpful as we're continuing to ramp up our capabilities and performance is the opportunity within the Uber application to occupy and grow your ODDs over time as well.

And so if you're starting up a service and you're just offering in-town rides in certain areas or locations to kick things off, that's a harder hurdle to get through versus within the Uber app, essentially Uber can direct rides that meet Rivian's ODD and then we can develop and grow as we continue to expand into all environments over time.

So -- but as the technology evolves and the -- let's say, like personally owned autonomy path and like the robotaxi autonomy path converge, and [indiscernible] sort of has always sort of talked about -- or he first started talking more about personally owned autonomy versus sort of like this robotaxi, right? So -- so how do you sort of think about, right, like as those converge down the road, someone owns an R2 and maybe they do want to be able to sort of monetize their vehicle while they're not using it and is the plan that they would also sort of be able to put it on an Uber or Uber-like network? Or down the road is -- are some elements of that transportation network company type infrastructure, something you would look to expand beyond Uber or even sort of handle internally?

The great element that Rivian has is because we're a direct-to-consumer business, we have a service network across the country. We have charging infrastructure across the country. And so we have a lot of the core tenants and attributes that could make Rivian successful in terms of the operation of large-scale deterministic fleets. And if you look back, RJ's original thesis in creating the partnership with Amazon was this very training and learning of how do you run and manage a very large fleet of vehicles for the evolution of a shared mobility type of future as well. So we're certainly today looking at lots of different options and see lots of potential given the assets that Rivian has and the capabilities that we have in-house.

Okay. One of the things I think that's become a lot more in focus is and that we've been focused on as well, and I think investors have also is looking at what the core competency of the business is and whether there are -- whether that provides sort of additional opportunities beyond that. Rivian, I think, has probably been sort of more on the, let's say, the leading edge of this, right, like you've designed your own chip, right? You obviously sort of designed your own electric architecture. I think you designed some of your own power electronics. You have also, which I mentioned to you earlier, I keep getting in my social media feed and I'm tempted to try to buy one of those electric bikes, they look pretty cool.

And then obviously, robotics as well, where I think you own 38% of -- right Yes, 35% Okay. So look, I guess what I'm getting at is, I think -- one of the ways you could look at Rivian is that you have a very sort of specialized set of employees and know-how that know the convergence of software with hardware. And that you've got a big task in front of you, especially sort of R2, but there are also other potential applications of the resources and capabilities you have. So that's a big question, but how do you sort of think about that internally? How do you sort of go through the process of weighing whether this is something you should pursue? Because like even with bikes and robotics, like you did, at some point, make that decision to sort of commit some resources to that even if they sort of eventually have been and further capitalized by others.

I think to your point, Joe, at Rivian's core, we're a technology company. We're a technology company that's operating in the mobility space. but we are a technology company at our core. And one of our core advantages is our ability to attract and recruit top talent across electrical hardware, across the semiconductor space, across software development space that I think uniquely positions us within the broader automotive and mobility sector as a whole. These are becoming, I would say, more and more attractive resources to the industry as we think about the advent and introduction of more physical AI.

The other core attribute that Rivian has is our data. And so whether that's the data in our manufacturing environment, which is rich for the likes of Mind Robotics to learn, develop and grow from, whether it's the data of our fleet of vehicles that is capturing and helping to inform our large driving model for autonomous driving. Those are really central to the evolution and acceleration that we're seeing in the broader universe of physical AI applications. And we're really excited about the rate and speed of growth and advancement that we're seeing in each and every one of those areas.

Maybe we could just sort of zeroing on the chip, for instance, right? Like I think like when you put that out, it showed some pretty impressive performance. Now I know that was sort of specifically built for your use case, which I would sort of say is visual large language, right? And -- but to your point on physical AI, that clearly has maybe other sort of applications. So is there an organic effort to sort of try to widen the aperture for what that chip could do or where it could be applicable or sort of more you got to sort of focus on your task at hand. If someone comes to you, you're willing to engage in a conversation if the economics and opportunity are right?

As we think about the chip capabilities, we see it not just in automotive types of applications, but we see it lending itself quite well also to the universe of robotics. And I'm really excited about the potential, not just for Rivian, but for technology licensing as a whole across many different dimensions of what we're building in-house as well.

Okay. Within automotive or outside of automotive or both? It can be both. Maybe just a -- let's sort of close here or approach a close on the Volkswagen joint venture. I know you have the winter testing done. It came with some -- meeting some thresholds that got you some capital in the door. Can you just remind us one, what's left to do in that venture? I think the ID1, which I believe is the first vehicle is sort of scheduled to launch at some point next year. And how does the sort of P&L sort of change once the output of that JV starts to sort of get into vehicles? Like will you start getting payments right away? Or is there some sort of like bank that was sort of built up from like prepayments, if you will, that you sort of got to be eaten through first?

As you think about the $5.8 billion joint venture, there's sort of still to come payment of just about $1.5 billion. A $1 billion of that is a nonrecourse loan that Rivian expects to receive in October that has no milestones associated with it. And then the final payment will be the earlier of the first vehicle, so the ID1 in this case, being commercialized or January 2028. So there are -- from a payment standpoint, actually no physical milestones left because of the time-related feature of that final payment for Rivian. But regardless, we're really excited about the evolution of our in-house electrical architecture software stack and the opportunity to scale that with multiple different Volkswagen Group programs. So we completed the winter testing for 3 different brands and 3 vehicle programs at Volkswagen Group this past winter and are excited to help them commercialize those vehicles over the course of the next year or 2.

Okay. And then again, as those vehicles get into production, how does that change your P&L?

And then as you think about the P&L change, the piece that's important to recognize is about $2 billion of the overall consideration is associated with consideration for background IP. So we've been recognizing that $2 billion from the close of the JV, and that will be recognized through the middle of 2028. And then beyond 2028, we'll flip to VW paying Rivian $100 million a year of just ongoing fees.

Okay. So it's not like a per -- license fee per...

It's not a per vehicle license fee because we're sharing in the joint -- the development costs jointly. So VW pays for 75% of all of the shared development work that occurs within the joint venture and then Rivian pays for 25% of it. But because of those splits and dynamics, there's not an ongoing per unit fee that occurs.

And just since we're somewhat on sort of the capital front also, just going back to the DOE loan, that's expected to start coming in next year as you start -- and is the way it just functionally works is you build out part of the facility and they almost pay -- they loan the money as you sort of go in terms of sort of what you spend? And is there any timing mismatch on that? Or how does that work?

Yes. So the -- you can think about the DOE loan is really almost like a project finance instrument. So Rivian will contribute the equity of the project into the new Horizon entity. And then as we continue to build out the site, there'll be draws from both the equity pool from Rivian and then we have an up to 80% loan-to-value from the DOE. So they'll be reimbursing us along the way for the CapEx that's deployed.

Okay. And so that -- and -- but that capital or that loan, I should say, that basically we should think about it from time from sort of when -- when it sort of starts in earnest, I guess, at some point next year until sort of SOP at Georgia?

Correct.

Okay. Perfect. Claire, thanks very much for joining us this year. Really appreciate it, and thanks for the great conversation.

Thank you. Appreciate it.

Energy mobility, my partner, Davis Sunderland here. I'm very happy to have Rivian and Claire McDonough, the CFO. Joining us. Thank you, Claire. I appreciate it. I know it's a busy time for you guys.

Maybe if we could just level set, just I think everyone knows who Rivian is. If we could just level set maybe where you guys are right now, like what are the big things that you're focused on?

First off, Ben, thanks for having us. It's a really exciting time at Rivian. So next week on June 9, we'll start external deliveries, test drives of the R2. So if you go across North America to our sales showrooms to our service centers, you'll be -- have the opportunity to experience the product directly. We've been, over the course of the last handful of months going on and hosting R2 block parties at a number of sites across the country. We've seen thousands of people come wait 45 minutes an hour just to sit in the vehicle and experience it but not yet drive it.

And so we're really excited to have people and our future potential customers behind the wheel of R2. And this is just a tremendous amount of effort, energy that went into the engineering design of the product, the design of the technologies that feed the R2. And importantly, now the ongoing operations and scaling of our R2 production in normal Illinois.

Maybe just another context question, I guess, just to guide our conversation just about the broader EV landscape. And where Rivian kind of sits within that because we went through a period of excitement and then we kind of peeled back and had tariffs and losing tax credits, and now we're somewhere in between. And I wonder if you could just talk a bit about what you're seeing in the broad market, whether it be from the perspective of supply chain or consumer demand or however you'd like to take it?

Sure, as you take a step back, we always had the intention of building the best product. So RJ, our Founder and CEO, he wasn't out to create the best electric vehicle. He was ready to create the best vehicle full stop. And that was the mentality and approach that we took as we designed and developed the R1T and the R1S and our launch products.

And it certainly testament as we think about the opportunity to significantly reduce the cost of the R2, but create a vehicle that is incredibly fun to drive. I can't wait for many of you to get behind the wheel of an R2 to experience the thoughtfulness and intentionality that goes into thousands, if not millions of decisions in which we can design a product that keeps what makes Rivian essentially a Rivian, which is the adventurous spirit, the capability, utility and performance that customers have known to expect when they think about a Rivian, but doing that through a lot of underlying design and technology efficiencies that the R2 is now leveraging in market as well.

So maybe in normal, can you talk about just what production will be like there just from the R1, the EDV and R2 to start out and then we go from there.

Sure. Within our normal Illinois manufacturing facility, we have 215,000 units of total potential capacity split between three vehicle programs. So we've engineered the new body shop and general assembly for R2 support 155,000 units of annual capacity and then have a level of flexibility as we think about the R1 as well as the commercial van production that can complement the volume that we anticipate building at scale with R2.

We're starting first with just a single shift of operations. And we're starting with our launch products. So we have a more limited assortment of vehicles that we'll be building out of the gate that helps us streamline the supply base, streamline the efficiency as we continue to increase our volumes each week and ultimately scale up to full production.

I want to ask about Georgia capacity, too, but you brought up an interesting point about supply base and streamlining that. And wondering if you could just talk a bit about similar parts or similar technology or I guess, similar things that you can leverage in the R2 that were, I guess, preexisting from the R1 already?

One of the core foundations for R2 was Rivian's transition from our Gen 1 R1 to our Gen 2. And as you think about the core technology foundations of R2 in our electrical architecture, our software stack, our autonomous capabilities in the vehicle or even our propulsion with our drive units, again, all of them are foundational based off of the Gen 2 R1. They just take another step in terms of the efficiency and development from that point in time. So we often talk about the technology evolution from Gen 1 to Gen 2 as being even greater than the shift or leak that as we go from the Gen 2 R1 to the R2.

So one thing that I think investors are focused on is the R1 not being profitable. Can you talk about what R2 in the platform and how that changes?

Sure. For R2, we focused on both commercial negotiations with the supply base where we had a very different starting off point than we had when we started out with R1 and we're a preproduction company negotiating with suppliers. We also had the advantage of having just recently announced the Volkswagen $5.8 billion joint venture at the time when we started sourcing parts for R2. And so that was a real complement of validation for Rivian's future in the space and the opportunity for us to jointly source and procure with the Volkswagen Group, the electronic control units and common parts that come out of our joint venture together that ultimately drives another step change in terms of affordability and sourcing leverage for Rivian as well.

And then beyond the sourcing side, a lot of it is driven by engineering design efficiencies in the vehicle. So a couple of good examples are the suspension in R2, which is 72% less than -- or sorry, 72% of the cost of -- sorry, less than the R1. And that's driven by us evolving from an electrohydraulic dampening -- active dampening system to the MacPherson strut potential. So we still have tremendous off-road driving dynamics with the current suspension system in the R2, but are doing it in a much more cost-efficient manner as we think about the vehicle's execution.

For another great example that I love is as you look at the rear door frame of the R2. In the R1, we have a division bar. So you have multiple parts of glass in the vehicle. The R2 is able to design the door frame with no [ div ] bar included. It's actually aesthetically even more appealing with just a seamless single piece of glass in that door. And again, we're able to reduce 50% of the cost of the rear door as part of that specific example as well.

You mentioned in there, the partnership with Volkswagen in the $5.8 billion JV. One of many important relationships you guys have announced company life to date. I'm sure we'll dig more into each of them. But maybe just to level set on Amazon, now Uber most recently and then the Volkswagen partnership. If you could just give an overview on where those stand, that would be helpful.

Sure. Rivian has always wanted to be seen as a great partner for the industry. And our first partnership was with Amazon and centered around our electric delivery van. And it's been great to see Amazon scaling out their infrastructure from charging at their sites. That they're now in a position to increase the volume of EDVs that they're purchasing from Rivian, which is a key tailwind that we talked a little bit about on our prior earnings call as well that we'll continue to see over the course of of 2026.

As we think about the Volkswagen, joint venture was fantastic to execute and complete our winter test milestone, which was testing the electrical architecture and software across Volkswagen Group products, Audi and Scout products, and this past winter in Sweden and seeing the ongoing development and now commercialization, just about 1.5 years following the closing of the JV, which really demonstrates the extensibility of the technology that we're building and its application to many form factors in the future as well.

And then finally, our most recent partnership with Uber, which is centered around robotaxi deployments, the investments from Uber are allowing us to accelerate the development of our L4 capabilities as an organization that we see not only opening up new business models, such as the robotaxi deployment, where Uber is purchasing 10,000 units initially and up to 50,000 units in totality and each of those units with an associated software subscription for the autonomous driving from Rivian.

We also see it as a key catalyst for the end state of consumers where autonomy is going to be a more and more important part of the decision-making process that each of you make as you think about your next vehicle, the headroom, the performance, the capabilities that it can provide and the convenience that it can give each and every one of us our most valuable asset, which is our time back.

Just maybe going back to the VW partnership. I think that when you guys did it, at least I looked at as a way to monetize technology -- but I think there's probably more to that than that. Can you just talk about how it can benefit you from the P&L? You talked about from cost, but how it else?

So there's multiple vectors of savings and efficiencies as we think about the Volkswagen partnership. First and foremost, as we talked about the technology development, it allows Rivian to become a more global player faster with a broader R&D budget associated with localization efforts across the world and especially as we think about Volkswagen's position in Europe.

And so first and foremost, we think about it as the R&D pool of investments that can help Rivian continue to be at the leading edge of technology advancement and deployment within the vehicles. The shared development work is also split. 75% Volkswagen is paying for it and 25% Rivian is paying for it. And so there's inherent and out of the gates through 2028 R&D savings to Rivian where previously we're putting 100% of the bill of our team, whereas now they're focused on development for both parent companies as part of the joint venture.

We've talked a little bit about the sourcing leverage and opportunity, and we see there being potential to have additional adjacencies of sourcing leverage in the future together with them as well. And then the capital as a whole as we think about the $5.8 billion of total consideration.

And just as an offshoot from that, you recently got another one of those milestones of that capital stack that you guys will benefit from. What are the remaining steps to unlock the remainder of that?

So we anticipate receiving another $1 billion of nonrecourse debt in October. There's no milestone associated with the nonrecourse debt. And then there's an additional $460 million that will be paid when the very first Volkswagen Group programs are out in the wild commercially as well. So that will be the next payment, which we anticipate happening in '27.

So maybe let's talk about Uber and how that relationship started and the details about it.

Sure. As you all know, we've had autonomous ambitions for quite some time now as an organization. And we are working through the right cadence and timing and trade-offs as we thought about our own accelerated development towards L3 and then ultimately, L4 capabilities.

We spoke a little bit about this at our AI Day in December of this year. And as we continue to explore the importance of autonomous driving and the potential value creation, margin expansion and the fact that we see Rivian as one of just a few players that has the core ingredients of being able to be quite successful in this arena. We made the election to say let's go faster towards this future. But let's find a partner, as we found in Uber, who can help with some of the demand aggregation can help with some of the fleet management capabilities while we can really focus our efforts on building what we think is the most important part of the equation, which is the driver.

Maybe going back to that AI Day and talking a bit about that Rivian driver. And when you guys unveiled the Rivian autonomous processor, could you just talk a bit about the decision of why to make your own chip, what the competitive advantages may be? And then obviously, that's a supply chain that's very tight right now. If you could just talk about the relationships you have there to manufacture, that would be helpful, too.

In December, we revealed what we call RAP1, which is our very first Rivian Autonomous Processor. That will go into our R2s end of this year. And the core advantage for building a chip like this in-house was both speed. So our ability for our software teams to work on early releases of the product as we've seen over the course of the last year in the future development of the software stack and middleware that sits on top of the in-house chip.

It also allows us to really distill down to what matters most. And so if you think about an off-the-shelf offering, the shelf offering needs to suffice and build capabilities for a broad set of use cases beyond just the determinant of the physical AI in a camera-based application, which Rivian is clearly focused on. And so you get to a higher level of utilization of the core technology that you're developing because you're designing it to be a bespoke to your end use case. And the last piece is cost. The semiconductor universe of players certainly has great margins associated with it as well. And so the combination of speed, performance and cost really comes together as we think about the opportunity set for us on a go-forward basis.

I guess you get this question, we can go back to that. But are there other pieces that you want to monetize of your technology? Because it seems like people ask you that after VW and now you have Uber and is there anything else?

There certainly is a number of ways that we could continue to monetize the hardware and software for autonomous driving with other OEMs. Certainly, that is also true as we think about the electrical architecture and software that we've designed, developed in the JV and the proof point of having it situated in a number of different Volkswagen Group brands and products in market allows it to be a lighter lift as you think about what does it take to put it into an incremental vehicle program with another OEM as well. So we certainly have designed our technology stack for sizable scale in Rivian's long term, but certainly also see opportunities for partnership via licensing or monetization as well.

Continuing the Uber piece. And I guess going back to what you were talking about with Volkswagen and sharing some of the development expenses, could you just talk a bit about maybe some shared autonomy expenses or, I guess, ultimately, robotaxi expenses and how they might be split between you and Uber in the partnership?

So within the Uber partnership, Rivian is responsible for the development of the core technologies. Uber is investing in Rivian. And the way I think about it is we sort of shoehorn those Uber investments in Rivian to help offset the acceleration of our efforts in our L4 development road map within the business. But they are not sharing in the cost and the development directly.

So R2 next week, I'm coming out to California. One great thing from my personal perspective is that you kept the brand similar. How big do you think the market is for the R2?

We think the market is enormous for R2. So if you look at the broader market across U.S., EMEA, the 5-passenger SUV and crossover space is the largest, fastest-growing and most attractive space to play in and R2 really sits at the epicenter of it as well. So we see this as being a product that we hope a lot of customers that may have been on the edge of buying their very first EV now have the opportunity, a form factor that shares the adventurous spirit of the Rivian brand for them to delve into their first EV as well.

I echo Ben's sentiment. I think the R2 is very cool. And I was very surprised at the R2 unveil event when you also unveiled R3. Could you also talk about R3, how that fits into the platform and when that might be coming after R2?

Sure. We get questions about all the time. And part of the reveal was when you're building vehicles that will be situated on the same common platform. You want to make sure that the design elements are done at a similar point in time. So for our Georgia facility, we'll be building units across the midsized platform. So that will house R2, R2 robotaxi for Uber, for example, we'll house R3 and additional variants in the future as well. So we're right now in the process of digging the foundations of our stamping press building in Georgia and are excited about the continued progress on the creation and erection of that site.

So maybe you could give us the sizing of Georgia. You have a loan guarantee you guys upped the size of it, I think. So just maybe if you could level set us on that.

Sure. So we recently increased the initial first phase of Georgia to be 300,000 units. And associated with that initial phase, have a $4.5 billion Department of Energy loan. We did modify from an original plan that was going to have two phases of 200,000 units and a slightly larger DOE loan associated with it.

But what was the advantage for Rivian was we were actually able to increase the size of the initial loan and are able to create 300,000 units of capacity alongside it that is more cost effective for Rivian as you think about what is the CapEx deployment per unit of capacity that we're achieving and then having it up to 80% loan to value to help finance it with U.S. treasury rate capital, which is fantastic for Rivian's cost of capital.

Going back to the profitability discussion around the R1 and on the R2, broadly speaking, could you just talk through some of the biggest buckets for margin improvement in either of the vehicle platforms?

In R1 or R2?

Either, yes.

In R1 or R2. Either, yes. The areas of margin improvement are -- we gave a couple of examples on R2 with the suspension system, the door. Another couple of examples there are the battery pack that we're using, which is also -- it's a structural pack. So it's also the floor of the vehicle. We've also moved to some large die castings in the vehicle as well that again, simplifies the manufacturing process for R2 and also reduces cost as well. R2 is also about 2,000 pounds lighter than R1. So that helps us drive range and efficiency. And then we've designed and developed what we call our Maximus drive unit, which again removes significant cost from the program while also creating a really fun 660-horsepower driving experience that I think will make most of you smile as you hit the accelerator as well.

When I -- when I said how big is the market, you said EMEA and you guys haven't talked about selling too much into Europe or the Middle East. So what's the strategy there?

So we definitely designed R2 to be a global platform. And so we do anticipate in the future, we'll start here in North America, where we have a robust service infrastructure, sales infrastructure. But as we scale a product over time, we certainly have ambitions to take it more global as well.

And you guys have your stores or spaces. Will you do that in Europe? Is that the thought?

Yes. Spaces in Europe as well.

So maybe thinking about other just potential hurdles, not to the R2 but to EV adoption one that comes up frequently is charging. Could you talk just a bit about the Rivian adventure network, where this stands and what the investment plan is for charging infrastructure going forward?

The Rivian Adventure network today has just under 1,000 chargers across about 145 locations in North America. We've continued to grow the network over time. It's also a network that we've opened up. So it's going to be in the evolution of now being more NAX native as a network, but having CCS capabilities for vehicles as well.

And in opening up the network, we're actually seeing broad adoption from all different types of EV owner. So it's a great touch point for new potential customers to have into the Rivian brand and ecosystem, and they really appreciate the high level of uptime and reliability that we have in the network as well. We've definitely been more modest in terms of the funding road map and have relied heavily to date on government grants and funding this helped augment the capital investments that we've made in the site, but certainly have large ambitions to continue to grow out the network over time.

And I think the Amazon relationship doesn't get talked about a lot. Could you just give us an update there and how they think about is it EDV and/or anything bigger than that?

With Amazon, we've designed from the ground up with their use case in mind for last mile delivery. And the great thing about the van is the total cost of ownership advantage that it provides Amazon. And as they think about the efficiency of not just the ownership experience, but the efficiency of utilization for their drivers and the execution of the deliveries that they have. We also are introducing a larger pack variant of the vehicle and an all-wheel drive variant as well so that they can start to use the EDV for more rural routes within their network, which is a big area of growth for Amazon. So we're excited about the road map for the future and to continue to scale and grow the bands for them.

I know we'll get to one on capital allocation and balance sheet before we close, but I want to separate this question on strategic priorities separate from capital priorities, just in thinking about R2 being front and center, recently announcing an autonomy partnership with Uber and seemingly so many things going on all at once. How do we think about what is the focus or what is the most near-term, I guess, obstacle for Rivian to tackle?

So I see them as very intertwined in that you can't have the R2 without the foundational technologies that power it. And you can't just have R2. R2 would not be the same vehicle that it is without those foundational technologies. And so as we think about the prioritization, it's really centered around the operational issuance of scaling R2, being able to get more customers behind the wheel, deliver on the ribbing experience at scale. While, at the same time, continuing to progress our technology road map, which is foundational to current products as well as the future products that we'll be bringing to market.

We can do one before capital allocation. You guys have invested in the robotics company. I think. Could you just talk about that?

Sure. So we saw -- and this sort of dovetails into the question on capital allocation and how do we think about prioritization. With the advent and growth that we're seeing in physical AI, we saw a huge opportunity to invest in robotics for industrial and manufacturing environments. And we recognize that as we think about the uses of capital in our core business that it was important for us to incubate and fund Mind Robotics, which we started last year with outside capital. And so RJ has been highly successful in raising additional capital for Mind Robotics, and we're really excited about the development road map and opportunity for Mind to partner back with Rivian as we think about the future of manufacturing.

And last one, just as we think about your cash runway and how we think about capital as you progress and ramp up the R2 and get to Georgia, how do we think about that?

Sure. As you think about the cash runway, we have a number of sources of capital. So we ended last quarter at Q1 with $5.4 billion of overall liquidity. As we look at this year, we anticipate receiving another $2.55 billion of capital between Uber and Volkswagen. $1.3 billion we already received sort of right after earnings time frame.

And then beyond that, there's another $700 million from Uber, another $460 million from VW and the $4.5 billion DOE loan, which puts us at sort of a total pro forma capital and liquidity of $13.6 billion. And beyond the capital that we've secured from these strategic partners in DOE, Rivian will continue to be opportunistic as we think about our road map for the future and ensuring that we're always maintaining a strong balance sheet.

Great. Thank you, Claire.

Thank you.

Good afternoon, and thank you for joining us for Rivian's First Quarter 2026 Earnings Call. Today, I'm joined by RJ Scaringe, our CEO and Founder; Claire McDonough, our Chief Financial Officer; and Javier Varela, our Chief Operations Officer.

Before we begin, matters discussed on this call, including comments and responses to questions, reflect management's views as of today. We will also be making statements related to our business, operations and financial performance that may be considered forward-looking statements under federal securities law. Such statements involve risks and uncertainties that could cause actual results to differ materially. These risks and uncertainties are described in our SEC filings and the earnings presentation we filed with the SEC today.

During this call, we will discuss both GAAP and non-GAAP financial measures. A reconciliation of historical non-GAAP to GAAP financial measures is provided in our earnings presentation and press release. Just before the earnings call, we posted our earnings presentation, which includes an overview of our progress over the recent months and replaces our shareholder letter. I encourage you to read it for additional details around some of the items we will cover on today's call.

Following our prepared remarks, we will be taking questions from sell-side analysts. In the interest of keeping our call to 1 hour, we would ask these analysts to limit any follow-on questions to one.

With that, I'll turn the call over to RJ.

Thanks, Chip. Good afternoon, everyone, and thanks for joining us for today's call. Last week, I was thrilled to celebrate the start of saleable R2 production with our team at our plant in Normal, Illinois. It's an exciting milestone in Rivian's history and the culmination of all the hard work and energy from so many people across the company. As I've said before, I believe the R2 will be a game changer for our customers and will be a key driver of our company's long-term growth and profitability.

In an American automotive marketplace starved for high-quality EV choice, I believe R2 is an attractively priced option sized for everyday ventures from school pickups to weekend trips that is targeting the very popular 5-passenger SUV and crossover segment.

With R2, we are taking our design, performance and technology and bringing it to a significantly broader audience without losing what makes Rivian unmistakably Rivian. We've started R2 deliveries to our employees, and I have to say I absolutely love having R2 as my daily driver. I could not be more excited to get this vehicle into the hands of lots of customers starting this spring.

In developing R2, our team relentlessly focused on achieving structural cost reductions while maintaining the desirability of the product. For R2, our bill of materials is expected to be approximately half of our R1 platform. For non-BOM cost of goods sold, we expect to see a reduction of more than 50%, resulting from a focus on design for manufacturing and leverage fixed cost efficiencies through higher production volumes. This is how we expect to profitably deliver R2 at an accessible price point at scale without compromising performance and utility customers love for Rivian.

Key design changes for R2 include part eliminations and reductions through the introduction of large die castings, a structural battery pack, a new highly efficient drive unit, the evolution of our next-generation electrical architecture, which removes miles of copper wire and the consolidation of our high-voltage electronics into a single enclosure. We are also seeing significant sourcing leverage relative to R1 across a variety of components.

Now as we begin to scale our operations in Normal with R2, we're very excited to partner with the U.S. Department of Energy to grow our manufacturing footprint in Georgia. R2 provides the opportunity to expand the Rivian brand to millions of drivers. As a result, we made the strategic decision to increase the production capacity for the first phase of our Georgia plant by 50%, bringing it to 300,000 units of annual production capacity for our midsized vehicle platform. This change is expected to boost cost efficiency while still providing significant room for future expansion in later phases and support thousands of jobs in Georgia as we grow American manufacturing and work to ensure the U.S. retains its leadership and innovation in technology and transportation. We remain on track for the production of our midsized vehicle platform to begin in Georgia in late 2028.

Turning to our technology road map. In March, we were excited to announce a new strategic partnership with Uber to accelerate our shared autonomous vehicle goals. In the not-too-distant future, I believe advanced autonomy capabilities will be a key differentiator for customers and the driver of market share. At the core of our third-generation autonomy hardware is the Rivian Autonomy Processor or RAP1. The development of our RAP1 chip is on track, and we are progressing well on validation and reliability testing. Our integrated approach allows our hardware team to rapidly iterate with our software team, and our autonomy feature development is progressing well, and we continue to expect to begin rolling out point-to-point capabilities by the end of the year.

Finally, in the coming weeks, we are excited to launch the Rivian Assistant on R1 and R2 vehicles. The Rivian Assistant is our new AI-powered voice assistant that is built to be a digital copilot with integration into the vehicle ecosystem and other external apps.

In closing, this quarter, our team has executed across many fronts, laying a strong foundation for the years ahead. As an American automotive technology company, we're building for a future that we believe will be fully electric, autonomous, and AI defined. With our category-defining brand, the launch of R2, which is our first mass market vehicle, vertically integrated and extensible technology and the direct-to-consumer sales model, I couldn't be more excited about the opportunity ahead for our customers and for our business.

With that, I'll pass the call over to Claire to discuss our financial results.

Thanks, RJ, and good afternoon, everyone. As RJ shared, the start of saleable R2 production and initial employee deliveries are a landmark moment for Rivian. By building R2 in Normal, we are strategically leveraging our existing manufacturing footprint in Illinois to drive greater fixed cost absorption across our entire vehicle portfolio. As discussed previously, R2 production is starting with a single shift operation, and we expect to scale to 2 shifts by the end of 2026 as we ramp towards our North Star target of profitably delivering 4,000 vehicles per week in normal. Delivering a strong 2026 exit rate for R2 production and deliveries is a key focus for our team as we believe it will directly translate into positive automotive gross profit for the business.

Turning to the results for the first quarter. As depicted on Slide 11 of the earnings presentation, our consolidated revenue in the first quarter was approximately $1.4 billion, an 11% increase over the same quarter last year. Consolidated gross profit was $119 million, and our gross margin was 9%. Gross profit included $122 million of depreciation and $27 million of stock-based compensation expense.

Adjusted EBITDA losses for the first quarter were $472 million, driven by our $119 million of gross profit and increased adjusted operating expenses as we prepare to scale R2 and invest in our autonomy road map. In the first quarter, we produced 10,236 vehicles and delivered 10,365 vehicles, which was the primary driver of our $908 million of automotive revenue.

Automotive gross profit loss was $62 million compared to $92 million of gross profit for the same quarter last year, primarily driven by the $100 million decrease in sales of automotive regulatory credits and lower production volumes, which resulted in a $45 million increase in depreciation and stock-based compensation expense combined. While current macro and geopolitical factors are creating added complexity, cost and uncertainty, our team continues to work hard to manage supply chain risk and offset elevated costs.

Our Software and Services segment reported another strong quarter as depicted on Slide 13. During the first quarter, the segment generated $473 million of revenue, a 49% year-over-year increase and $181 million of gross profit. $282 million or approximately 60% of Software and Services revenue was attributable to our joint venture with Volkswagen Group. We also experienced strong growth from remarketing and parts and service.

During the quarter, we also recognized $506 million gain in other income in our financials related to the Series A capital raise and related deconsolidation of Mind Robotics from our financial statements. We currently own approximately 38% of Mind Robotics on a shares outstanding basis.

Looking at our balance sheet, we ended the quarter with approximately $4.8 billion of cash, cash equivalents and short-term investments. With regard to our funding road map, in 2026, we expect to receive a total of $2.55 billion of capital from our strategic partners. Today, we received $1 billion from Volkswagen Group in exchange for equity following successful completion of the winter testing milestone by RV Tech. The testing program spans several months utilizing reference vehicles from the Volkswagen, Audi and Scout brands.

Later this quarter, we expect to receive $300 million from Uber in exchange for equity related to the signing of our partnership agreement, subject to certain conditions. And later this year, we expect to receive $1 billion in nonrecourse debt from Volkswagen Group and an additional $250 million from Uber in exchange for equity, subject to the completion of certain milestones and conditions related to robotaxi development.

As outlined on Slide 14, this brings total available liquidity and expected capital in 2026 of nearly $8 billion. Additionally, we're very excited to partner with the U.S. Department of Energy to grow our U.S. manufacturing footprint. The up to $4.5 billion DOE loan, which consists of approximately $4 billion of principal and approximately $500 million of capitalized interest provides low-cost financing for our 300,000 unit capacity greenfield expansion in Georgia, bringing Rivian to meaningful scale.

We expect the 515,000 total units of capacity between our Illinois and Georgia plants will provide Rivian a path to free cash flow positive once fully ramped. We expect to draw on the loan by early 2027, subject to certain conditions. Two weeks ago, our normal factory sustained damage from a tornado. I'm proud of the way our teams have rallied together to get production back up and running while we repair the damages. Despite the weather impact, our 2026 guidance remains unchanged.

We continue to expect full year deliveries of between 62,000 and 67,000 total vehicles across R1, R2 and our commercial vans. We also continue to expect to deliver approximately 9,000 to 11,000 vehicles in Q2 as we expect the ramp of R2 deliveries will be back half weighted. While we continue to believe our gross profit will increase year-over-year, we expect the complexity of a new vehicle launch will negatively impact our automotive gross profit in the second and third quarters before becoming a benefit for our overall operations in the fourth quarter as we ramp production and deliveries.

As a reminder, we believe this is a transition year for the Automotive segment's path towards long-term profitability as we scale R2. For 2026, we continue to expect an adjusted EBITDA loss of between $2.1 billion to $1.8 billion. While economic and geopolitical conditions, including supply chain and international conflicts pose risks, we remain steadfast in our plans to invest behind key growth drivers. We continue to progress our autonomy road map and the expansion of our sales and service footprint as we scale with R2. We believe these strategic investments will deliver long-term value to our shareholders.

Finally, for 2026, we are maintaining our capital expenditure guidance of $1.95 billion to $2.05 billion. Our CapEx spend primarily relates to finalizing construction and tooling for R2 in Normal, the continued build-out of our sales, service and charging infrastructure and kicking off construction of our greenfield plant in Georgia.

In closing, I'd like to congratulate our teams again for the successful start of saleable R2 production and the strong execution in the first quarter. We continue to believe that R2 and our technology road map will be truly transformative for the growth and profitability of our business.

I'd like to turn the call back over to the operator to open the line for Q&A.

[Operator Instructions] Our first question comes from Shreyas Patil from Wolfe Research.

Maybe first, just picking up on a comment that you made earlier, Claire. If you could help give us some more color on some of the actions you're taking to mitigate the increase in commodity costs and some of the metals prices that we've seen increase recently? And what's been the magnitude of increase, if you could help frame that?

Well, thanks, Shreyas, for the question. Yes, we're spending a lot of time, of course, focused on all the changes that are happening from a supply chain point of view. And in terms of raw materials and some of the cost of metals, specifically aluminum, this has been a big focus for us. Fortunately, we've -- our sourcing team has been sort of -- we've grown our sourcing team and evolved our sourcing team over the last handful of years where supply chain continues to be an area where there's a lot of unknowns, there's a lot of variability and a lot of a need for us to be very hands-on and very proactive. And so we've been proactive in both our relationship with existing suppliers, but also in making sure we have, particularly in some of these key commodities, alternative sources of supply.

Okay. Great. And then maybe, Claire, just to clarify, I think you've made a comment about how -- when Normal and the Georgia facility are fully ramped, you'd be getting to free cash flow positive. I just want to make sure if I understood that correctly. And if that's the case, that could be quite a while from now. So maybe just help us understand sort of the trajectory of CapEx maybe near term, but then also as we kind of think ahead and you start to kind of put more in the ground at Georgia?

Sure. Shreyas, the comment that I made on the Rivian's ramp up, its Normal facility plus Georgia facility is what takes Rivian to free cash flow positive in the future. And as we talked a little bit about in our prepared remarks, importantly, we have the $4.5 billion of capital from the Department of Energy loan, which provides up to 80% loan-to-value against the build-out of our future Georgia facility. So while we certainly will see an anticipated increase in our capital expenditures as we approach the start of production in Georgia, we do have significant offsets from a capital road map. And the $4.5 billion is just one component of the full $13.6 billion of total liquidity and expected capital through both the cash that we have on hand on our balance sheet, the added availability of our ABL facility, and then the expected capital from our partners with both Volkswagen and Uber that we expect to receive over the coming years as well.

Okay. Great. And maybe just one quick clarification. The DOE loan, has there been any change to that? I think the original amount was $6.6 billion that was available. Just curious if there's any change there.

Yes. So included within our financial release today, we provided an update on the Department of Energy loans. So we'll now have $4.5 billion of loan capacity that will go towards the build-out of our first phase of capacity expansion in Georgia. We've also increased the capacity of the Georgia site, the initial capacity from 200,000 units to 300,000 units. And so the comment that I made in my prepared remarks is really the importance of the funding road map, especially as we think about the Georgia site specifically taking Rivian to meaningful scale in the future.

Our next question is from Joe Spak from UBS.

Claire, just to maybe pick up on the DOE loan part and to clarify, like obviously, this first phase is an increase from that 200,000 to 300,000 units. But and again, admittedly just being able to skim the document, it does seem like maybe the total project scope is now capped at 300,000 units versus -- I know before it was supposed to be 200,000 units -- Phase 1, 200,000 units, Phase 2 for 400,000 units. So I want to make sure I understand that. And then if you still see an opportunity over time to grow further in Georgia.

So the strategic decision that we took was to increase the initial phase of production capacity to the 300,000 units. On our Georgia site, the full initial capacity will be put on the upper pad at the site. So we have the lower pad, which is still going to be entirely untouched greenfield for future expansion.

Okay. But -- and that might be funded more organically in the future, not necessarily with loan or it's TBD, I guess. But the loan is really only up for the 300,000 units, correct?

So the loan is for the initial phase. The important piece is we've increased the loan size associated with the initial phase as we've also scaled the production volume as well.

Okay. And then just I appreciate the comments on input costs and -- but I guess the other thing that I was wondering about was with tariffs, and this is sort of come with a lot of companies thus far. Can you remind us like what you've paid in IEPA roundabout over the past year? And have you filed for any reimbursement? And was anything booked in the quarter related to any potential reimbursements?

We did not book anything this quarter associated with IEPA tariffs, but we do believe that the recovery of those IEPA tariffs is possible in the future. And I contextualize the sizing to be in the tens of millions of dollars of future benefit.

Okay. But that -- and is that considered at all in your reiterated outlook or that would be upside? I guess it's not significant.

I would characterize it as considered within our current outlook.

Okay. And then just lastly, like I know you talked with Uber, you talked about pulling forward raising R&D in '27. Does any of that work start to seep into '26? And is there a change to the R&D outlook for this year? Or it's really more of a '27 factor?

You'll see the pace of acceleration increase in terms of the spend towards autonomy in '27, but we'll certainly see acceleration throughout the course of this year as well. If you look at Q1, our cash R&D expense increased about 22% this year for that quarter. You could directionally think about that as being more of a year-over-year type run rate as we look out over the remainder of the year.

Our next question is from Itay Michaeli from TD Cowen.

Just first, going back to the Georgia capacity optimization. Curious if it has any impact on your previous long-term financial targets of 25% gross margin. And maybe on that as well, if you can maybe share your initial kind of takeaways on kind of R2 demand generation since you kind of launched the trends.

Well, thanks, Itay. Yes. And I think, obviously, the decision to increase the capacity of the first phase in Georgia coincides with -- I should say, it reflects the level of confidence in our products and our business. I think most importantly, we've just started production on R2 out of our existing Normal, Illinois facility, and we've had early media events and early customer events and the level of enthusiasm for the product has just been outstanding.

So everything from the packaging of the vehicle to the way that it drives to the integration of technology, the overall response has been overwhelmingly positive. And so that bodes extremely well for the ramp-up happening over the course of this year and into next year, but it also sets up a wonderful foundation for us as we think about further capacity on this platform, both for R2 as well as R3 and variants of those vehicles out of the Georgia facility.

Terrific. And then maybe as a follow-up on the Uber announcement. I'm curious whether the robotaxis themselves that will go into the Uber network will have the kind of exact same hardware set as the personal vehicles. And I ask because if you're going to launch in 2028 in complex domains like San Francisco and Miami, would that not also imply a pretty wide ODD for the personal vehicles if they're both operating on the same hardware?

Yes. We talked about this during our Autonomy Day late last year. But I think it's important to recognize there's going to be a whole series of steps we make in terms of progressing towards Level 4. And so in that series of steps, the first later this year on our consumer vehicles is launching our point-to-point capability. And so that's the ability for the vehicle to drive entirely on its own to an address.

And I just this week had -- we do lots of regular rides internally, and I had a great ride with James and the team. And it's so exciting to see how much it's progressed and our technology has progressed even since our Autonomy Day late last year. And so we're very encouraged by this. But that first step of making point-to-point available to customers is going to be a really important step for our consumer vehicles.

As we continue to go into 2027, we'll be allowing in specific areas, eyes off. And so it's hands-off, eyes off, that's a Level 3 capability. And then as we go into 2028, as you said, that's when we'll have our first deployments of a Level 4 capability in a robotaxi. And in the robotaxi variant, there will be some additional sensing on the vehicle. So it will be different than the pure consumer vehicle.

But we are planning to have a personal version of Level 4 as well. And we've talked about that quite a bit. We think the market for a vehicle that you own being able to completely drive itself, do things like drop you at the airport, go to the grocery store, get groceries for you, pick up kids from a sports event. These are really high-value creating activities for the Level 4 capability, and we see them on both robotaxi applications and on personally owned applications.

Our next question is from Dan Levy from Barclays.

I wanted to first start with R2 and the path to getting to positive gross margin, which I think you said would be by the end of the year. Maybe you could just walk through the gating factors. Does -- even with the raw mats, do you still have the confidence you have the right BOM to achieve this? And what milestones do we need to see to make sure that the production ramp is still on track? What are the sort of most limiting factors that you still have to address on this ramp?

We've talked a lot about the cost structure of a vehicle and a huge component of this is, of course, the bill of materials. And the bill of materials is different than the non-bill of materials COGS is contractual. So these are negotiations that happen across hundreds of suppliers, and very different than when we sourced R1. We went into the R2 sourcing with a lot of momentum and much better supplier leverage. And just the level of confidence in Rivian as a business and the level of excitement around R2 helped us put together a set of suppliers that are both very enthusiastic, but that's demonstrated through attractive commercial terms.

And so as it stands, the bill of materials for R2 is about half that of R1. And there's, of course, things we can't predict like raw material changes and DRAM shortages, but the vast majority of the BOM is very stable, and we have a lot of confidence in being able to achieve that -- the target BOM, which supports the very healthy gross margins we've talked about in the past.

Now with regards to the plant, I'll invite Javier just to comment on some of the progress that's happening in terms of ramping up over the course of the next several months.

Yes. Thank you, RJ. Indeed, as you explained some minutes ago, we had last week, the celebration of the first saleable builds and delivers to customers this week. So very proud of the situation we are achieving now. The industrial process is ready. The people is ready as well. We have been through the right training and build cycles. And I would say plant is prepared, process are defined, and we are very confident in our capability to deliver.

I feel confident as well regarding what is our team in place. We have brought in a group of seasoned leaders that have done launches back in the past, big experience on that area. And we are, on the other hand, managing the supply chain, making sure that the supplier scales with us. We have boots on the ground supporting some key suppliers. And we are doing this with our mindset and supplier relationship of transparency and collaboration. Resilient supply chain, agility and intelligence are key factors for success.

Great. As a follow-up, RJ, I wanted to double-click on the point you gave in the prior question from Itay about getting to L4. You'll have point-to-point at the end of this year, and you'll only have the vehicles with the LiDAR end of this year, beginning of next year. It does seem like there's probably a lot of testing that has to happen between when you get those cars with the LiDAR out to the point where you have a launch. So just help us understand what the testing curve looks like, what you need to do from when you have the cars with the LiDAR to being able to unlock L4 because it does seem like there's a lot of miles that have to be driven on that new vehicle.

I think a really important point to make here is just the way the self-driving system is architected. So this is the platform that we launched actually on our Gen 2 R1 vehicles is designed around an end-to-end approach where we're building really what we call a large driving model, but think of it as a neural net or a foundation model for driving. And that model is being fed with all of our Gen 2 R1 vehicles and of course, our launch R2 vehicles and ultimately, as you said, R2 vehicles that include a LiDAR, but very different than previous architectures around self-driving where there were rules-based and more classically controlled.

As you add more perception and as you add more compute, the capability of the model only grows. You don't lose the previous knowledge embedded in the model. And so I often sort of compare it to imagine if you learn to drive with that vision and then I hand into your pair of glasses. You wouldn't forget your knowledge as a driver, you just suddenly be able to see and perceive things that you may have missed previously so you become a better driver.

And then imagine we could hand you a 10x multiplier to your compute capability effectively makes your brain 10x smarter. Again, you wouldn't forget what you knew before, but suddenly, you start to notice new patterns in more nuanced ways than you had in the past. And so that's very important to recognize is a very fundamental difference in how the model is built today and what we're creating versus the more AV 1.0 stack where they were, as I described, they're very rules-based and very classically controlled.

And so because of that, the data accumulation that's happened already on R1 and that will continue with the growth in our car park with R2, all feeds into our overall LDM into this large driving model. And even as we think about introducing new sensors, things like our LiDAR, this is not as if it's first on the vehicle when it's delivered to customers. We have lots of prototypes today that are running with those. If you're in the Bay Area and happen to be anywhere around Palo Alto, you'll probably see lots of Rivians with a lot of additional sensors and that's part of a ground truth fleet that, again, is feeding into this large driving model to accelerate the speed at which that model is learning. Think of it as a brain, the speed at which we're teaching it to drive.

And the work that will go into ultimately launching a customer-facing version of point-to-point, which today, I was -- as I said, I was in one of our cars driving around both point-to-point earlier this week, it's really exciting. But we want to have when it launches to customers had to be extremely robust. But all that work is accretive to what ultimately will be going into our Level 4 platform.

Our next question is from Andrew Percoco from Morgan Stanley.

Maybe just to start on the commercial side of your business. It looks like Amazon made up almost 50% of your auto revenue in the quarter, so a little bit above historical run rates. Can you just maybe talk to what you're seeing with that relationship and maybe even outside of Amazon, the level of maybe interest you're seeing in the commercial product since you launched that extended range version of the commercial vehicle?

Yes. Our relationship with Amazon continues to be something that we're very proud of. We've spent a lot of time on this program from its initial kickoff quite some time ago in 2019 through its initial launch and now ramping, deploying. That's everything from not only building the vehicles, but on the Amazon side, getting their operations and the infrastructure ready to ingest a lot of EVs. And what we're now seeing is a reflection of all that work, all the cumulative work that's happened to date that's allowing the volumes for our van program within Amazon to grow, as you point out, pretty meaningfully. And we expect that increased demand for vans to continue. And that's super rewarding to see. It's fun to see all the vans on the road, but that's going to continue to ramp up with Amazon.

Now in terms of other customers and other applications, of course, Amazon is by a significant degree, the largest operator. And so they're the ideal lead customer, if you will, but there are lots of other opportunities we've seen. But in the immediate term, our focus remains on Amazon and ramping to support them.

Okay. That makes sense. And then maybe just -- I just want to ask one more question on the DOE revised loan piece here. I understand the movement in Phase 1 and upsizing that. I'm curious why you might not want to use the DOE funding for the eventual Phase 2. Is this something initiated on your end? Or did maybe they approach you in terms of revising that? Just kind of curious the thought process around why not tap that low-cost funding for the eventual Phase 2 whenever that comes about.

Thanks, Andrew. As I mentioned in my prepared remarks, we're really excited to partner with the Department of Energy on Rivian's $4.5 billion loan, which enables thousands of American jobs and helps us establish the U.S.'s strength in technology and manufacturing leadership. The DOE loan is uniquely a very cost-efficient form of capital as we spent a little bit of time walking through Rivian's broader road map. But specifically, the importance of this $4.5 billion is the funding of Rivian's scaling its operation up to 515,000 units of overall capacity and the opportunity with that installed capacity base to be free cash flow positive in the future. We'll continue to be opportunistic as it pertains to our capital road map beyond the components that I had outlined in the existing $13.6 billion of liquidity and total expected capital that we've outlined today.

Our next question is from George Gianarikas from Canaccord.

So I know it's early days, but I was wondering if you could please give us any color on R2 order trends and maybe some color on the conversion ratios relative to previous orders.

George, as you said, it is early days for deliveries, but the signals I'd be looking at are just the reception around the product and how -- whether it's expert journalists, automotive journalists or lifestyle journalists or customers that are getting to experience the vehicle, the overall excitement around what we've been able to put together in terms of content features, packaging, just the overall value proposition is really resonating. And I'm really pleased with having spent a very large amount of time in the car and it's my daily driver. I couldn't be more pleased with the result. The work that the teams did to make something that's truly remarkable. And we had a few journalists say this might be the best vehicle ever made. That's wonderful for the teams to hear, and it's really encouraging for us as we get ready to ramp the vehicle.

And maybe just as a follow-up, I just wanted to confirm that the Gen 3 sensor suite was going to be available later this year on the R2?

That's correct. Yes. So the Gen 3 autonomy hardware suite, which is both our in-house RAP1 platform. And so this is our in-house inference platform, 800 tops per chip. We have 2 of those chips in the vehicle. So it's extremely powerful. It's a big increase, roughly a 4x increase relative to the NVIDIA-based platform. And then the inclusion of LiDAR, as was referenced before, along with some other enhancements across the rest of the perception stack.

Our next question is from Mark Delaney from Goldman Sachs.

Starting on Autonomy, I'm hoping you could provide more details on the monetization of Autonomy+ so far and any data points you can share on that? And what that might mean for growth in the Software and Services business more generally, including if you still think you can grow that segment revenue by about 60% this year?

We're encouraged by what we're seeing in the -- as you noted at the start of having paid Autonomy+, and it's exceeding our own models on this. So we're -- the take rate is higher than what we expected. And that bodes really well for us as we're going to be growing the feature set quite significantly over the course of this year. And the introduction of point-to-point, we think is a major value driver for customers.

To be clear, this is -- as I said, you can put the address for the location you're going to into the car and the car will fully drive you there. And then following that, allowing you to go eyes off in highway conditions and ultimately everywhere, that means you get your time back. And so we're very bullish on the long-term trajectory to monetize our autonomy on the consumer side. And that's for both hands off, eyes on, hands off, eyes off and then ultimately, Level 4 for personal consumption, we see as a really key driver of value in the long term.

Now in terms of what that does for our Software and Services growth, that is going to start to be something we'll see, but it's not something that we're going to be breaking out separately.

And then my other question was on demand for the R1. I'm curious if Rivian has seen any improvement in order rates for R1 maybe in response to the recent increase in gasoline prices and what that might all mean for R1 volumes this year? I think the company had assumed R1 would decline. Is that still your expectation?

We're encouraged by the continued enthusiasm for R1. It continues to be one of the market share leaders in the premium category. And in a number of states, it's the best -- not just one of the best-selling premium electric cars, but one of the best-selling premium SUVs, electric or nonelectric. So that's true in a handful of states, we've talked about that in the past.

I think it's hard to say ultimately what's going to happen around demand with the impact of gas prices going up. Of course, it's a consideration, and we do see that manifest in what people are trading in. We're seeing more trades of gasoline vehicles or vehicles are less efficient than what we're building. And so we do see that on the rise. But I think a lot of folks are wondering how long fuel prices are going to stay high like this.

Our next question is from Andres Sheppard from Cantor Fitzgerald.

Congratulations on the quarter and all the great progress. I think a lot of our questions have been asked. But RJ, I want to go back to a topic I know you're very passionate about, which is Autonomy. And so I guess with R2 beginning customer deliveries over the coming weeks and with the Autonomy+ now having started this month. Just curious on kind of your vision and how you are thinking about that Autonomy customer adoption? What type of Autonomy penetration rate do you expect for your customer-owned vehicles? Do you expect customers will prefer the monthly subscription or the onetime purchase? Just any color here on your overall vision and customer penetration adoption that you might be expecting?

Yes. Andres, we're extremely bullish on the importance of Autonomy for customers over the next, call it, 5 years, and the rate at which we see customers adopting and selecting Autonomy+. And then ultimately, as the feature set grows and the capability grows, that adoption rate growing with it. But I think that there's an even bigger question just from a society point of view, we've been on a journey of -- when we think about Autonomy where Level 2 is where your eyes are still on the road, but you're still responsible for driving the vehicle. That's like a small appetizer for what you can actually achieve when you get to higher levels of Autonomy where you can take your eyes off the road and truly get your time back and get your time back without the car, dinging you to say, hey, look back at the road or pay attention or put your hands on the wheel.

And so as that starts to occur and as people start to experience what it's like to truly have your time back, so take a 40-minute commute and the idea of getting those 40 minutes back in both directions. We think it's going to be a very sticky experience. And it's going to be something that once you experience it, even if it's indirect, let's say, in a friend's car, it's going to become a very important purchase criteria.

And the reason I call this out is we really believe over the next 5 years, the rate of progress of what we're going to achieve with Autonomy will look very, very different, and I'm talking here at an industry level versus what we've achieved over the last 5 years, means that the topology of customer expectations and therefore the way that the vehicle purchases are made and the criteria that are being used to make those vehicles is going to look very, very different in 2030, 2031 than it does today, where Autonomy will be a very critical criteria where customers are willing to pay for it because they want their time back. They want to not have to be paying attention. They want to be able to be on their phone, reading a book, taking a nap, truly getting time back while you're in the car.

And so as a result, as you've heard a few times throughout this call, this is an enormous focus area for us as a business. We're very much deploying a lot of our R&D dollars towards this category, and we've made long-term investments in the hardware and the vehicles to support that.

Got it. That's super helpful. I really appreciate all that color. Maybe just as a quick follow-up, one for Claire. So just regarding your delivery guidance for this year, which is unchanged. I know in the past you've given us some cadence for deliveries in Q2. I think you reaffirmed that on the call just now. Can you just remind us what kind of unit mix we should be expecting for the year across R2, R1 and EDVs? I think in the past, you might have mentioned R1 and EDV is relatively flat. So the delta should be the R2. But I guess for the R2, the $45,000 price range, right, that's on track for next year. Just curious if you can maybe remind us how we should think about unit mix for the rest of this year.

Sure. As you reiterated, as you think about the composition of the 62,000 to 67,000 deliveries, we anticipate R1 combined with the commercial vans to be roughly flat relative to our 2025 delivery results and then the remainder being comprised of the introduction and ramp of R2, which as implied by the 9,000 to 11,000 of Q2 deliveries suggests more of a back half weighted ramp associated with R2, which is implied within our outlook and guidance.

Our next question is from Edison Yu from Deutsche Bank.

I wanted to come back on robotaxi. Are there any sort of KPIs that you're sort of tracking or that you need to hit for some of the milestones with Uber? And I think in the past the industry has kind of turned to disengagements or miles between intervention. Any flavor on that would be great.

On the path to deploying in 2028, there are a number of milestones and some of those tied to the investment unlocks with Uber. The first of those is later this year we'll be deploying vehicles in both San Francisco and Miami with a safety driver. So the vehicles will be running, but with the benefit of a safety driver in the vehicle with them. And there's a handful of additional milestones ramping up to ultimately having the vehicles operate fully on their own as part of a service in 2028. But as we get closer and closer to that date, there will be -- there'll be lots of proof points, if you will, of the progress that's being made that will manifest on the road. You'll actually see them not only being tested, but you'll see them as part of some of these deployed fleets.

Understood. And just a kind of a separate question on more Autonomy more broadly. I think there were some reports that you guys were looking to potentially license some tech to other OEMs. Just wondering anything you can say about that? Is that something that we could potentially expect this year? Anything that would be great.

I think there's 2 broad categories of technology we think that as I referenced earlier that will be very, very important for growing or maintaining market share in the next several years. And so the first of those is shifting away from a domain-based network architecture where you have a very large number of supplier sourced ECUs that are -- think of them as little islands of code on little small computers where you might have, depending on the car anywhere from 50 to 150 of those little ECUs, those little computers that are in aggregate, providing the software for the vehicle.

But that architecture is incredibly hard to do updates on. It's very, very difficult to do cross-platform or cross-domain integrations. It makes the idea of integrating in a deep way AI into the vehicle and the vehicle experience very difficult borderline impossible to do it well. And so our view is every vehicle on the road will need to shift to a much more centralized compute where you have more of a zonal architecture. So essentially, think of it as a large consolidation of all those little computers into a single or a very small number of large computers that runs a common operating system and for which the code base that's running on the vehicle can be very easily updated without coordinating among, let's say, 50 to 150 suppliers.

And so that architecture I just described is, of course, what's in the Rivian vehicle today. It's also the basis of our relationship that we've forged with Volkswagen Group to deploy that technology. And the first application of that technology being deployed outside of Rivian as part of our partnership with Volkswagen Group is going to be in the ID1, which is -- it's an EV that will be launched in Europe with a price point of just over $20,000. And I can't wait for people to buy this car. I'm sure lots of people to buy it and take it apart and tear it down. And I'm certain they'll be blown away with the elegance of how we've executed the ECU -- or I should say, the network architecture and the compute stack topology.

And so that's one technology category or one area that we think has a lot of opportunity to be deployed in other manufacturers. And of course, the proof point that we're successfully deploying this into a very large established manufacturer within Volkswagen Group across multiple brands, across multiple price points, different form factors, different geographies is the proof point or the existence proof that the technology is scalable and that we're capable of supporting these types of complex deployments.

With that said, the other large category of technology that we see opportunities to have licensing deals is in the autonomy realm. And here, it's in a similar way, it's not just hardware and it's not just software, it's the 2 of them together. So it's the combination of our compute platform that we've developed, the RAP1 in-house inference platform I talked about and the associated computing platform we've designed around that, along with our perception platforms of the cameras, radar, LiDAR that exists. And then very importantly, the large driving model, this foundation model, this neural map that we've created that defines what driving or how to drive a vehicle.

And that's -- as hopefully, I made it clear before, is a much more flexible architecture to deploy into different vehicle embodiments. And so we're doing that already within Rivian. We'll be deploying that across R1T, R1S, R2, ultimately our commercial vans, robotaxi applications, but we do see this as a very scalable technology that can be deployed in many ways.

Our next question comes from Alex Perry from Bank of America.

Just one, I guess, a little bit further on the robotaxi strategy. So you have the Uber deal announcement. I guess is the plan to pursue a partnership model for now? Does the deal with Uber have sort of any exclusivity? And how else will you sort of look to tap into this important market?

When you think about the robotaxi space as a business, and so putting aside the technology for a moment, and I should say, and putting aside and recognizing that the technology for Level 4 in a robotaxi or in a personally owned vehicle is the same, meaning a personally owned Level 4 vehicle can't drive -- or should not drive worse than a robotaxi Level 4 vehicle. They're both very capable of managing the same levels of complexity and the same types of driving situations. So it's the same tech stack.

But when you think of it through the lens of a business model, the benefit of working to deploy this first with Uber is you have very large density of choice. And so if you're deploying entirely on your own, you have to build enough vehicles to have in the fleet or in the car park such that if you're a user, when you say I want to have a vehicle available, it's immediately available or it's available in a matter of minutes.

And so the scale of Uber's platform and the success they've had in creating a really healthy marketplace really makes them an ideal partner for us as we think about launching this technology in an R2 to deploy into providing robotaxi services. And as you've heard me say a couple of times, and we've talked about this in the past, that technology is going to also underpin a consumer personally owned variant as well. And I think we have to recognize that there's going to be lots of innovation around business model that start to emerge as we have Level 4.

And so if you think of it in a very simple sense, the 2 bookends in terms of business model are pure ownership or the vehicles dedicated entirely to your household. And the other end of the spectrum is purely mobility as a service, where you don't own the vehicle, you're not using the same vehicle every time, but you ask for a vehicle on a purely variable basis and it shows up. There will be things that emerge in the middle and not to be exhaustive here in the types of things, but you can imagine different forms of sharing vehicles amongst families or within neighborhoods or within apartment buildings. But there's going to be a very exciting time of innovation in terms of how we think about consuming mobility or consuming transportation.

And with all that said, just recognizing the trillions of miles that are driven today, the vast majority of those are driven in personally owned vehicles. And so robotaxi represents a portion of those, but we think there will be lots of new models that start to make up the topology of those trillions of miles that are driven.

Our final question comes from James Picariello from BNP Paribas.

So I want to ask about the Uber partnership. Can you share any color on the milestones that are associated with the 4 tranches of funding, right, regarding the $950 million in additional additive liquidity. And it does appear right that one of the tranches is already expected to hit this year, $250 million?

Yes. As RJ had just mentioned, there are a handful of milestones and the milestone that we more specifically expect to be in position to unlock the initial $250 million this year will be the operation of some Rivian vehicles in San Francisco and Miami with safety drivers later this year. And then as you think about the subsequent years, you can think about the ongoing trajectory towards full deployment in a couple of cities in 2028 and then 25 cities by 2031, that would fully unlock the remaining $700 million of capital from Uber.

Excellent. That's great color. And then just to maybe level-set expectations on automotive gross margins for the second and third quarters. I mean, this quarter was yet again another strong showcasing of the company's momentum toward positive auto gross profit, right? And this is the last quarter before the R2. Like is there anything you could share for these next 2 quarters regarding the temporary order-of-magnitude impact we can expect to auto profitability?

Sure. As we think about the subsequent quarters of Q2 and Q3, we'll see the introduction and turn on of both, all of the depreciation expense, the new manufacturing team that is established that will be producing the vehicles. But as they're in the process of ramping up the first shift of operation, we'll see some of the complexity associated with lower volumes on the new R2 line. And so as a result of those attributes, we do anticipate seeing an impact to our automotive gross profit over Q2 and Q3 before we start to see the overall benefits of the ramp, not just on the R2's unit economic profile, but also importantly, the fixed cost leverage that we'll see across the R1 program and EDV program overall.

So in total, we still anticipate that we'll exit 2026 with a trajectory of positive automotive gross profit with that being both R2 as well as total Rivian Automotive gross profit being positive, which is important for us as we go into '27 and really fully ramp up the R2 capacity in Normal.

This concludes the Q&A section of the call. I would now like to turn the call back to RJ Scaringe for closing remarks.

Thanks, everybody, for joining us today. Hopefully, you can tell we're really looking forward to getting R2s into customer hands. We're very pleased and excited with the product that we've developed and proud of the team for all the great work that went into creating such a special vehicle. Along with that, we are very much focused on the development of our Autonomy platform. And with that, we'll be starting to see some of the fruit of that significant effort, as I said, first, with our point-to-point capabilities later this year and then adding more functionality, more capabilities over the course of 2027 and '28.

And again, thank you everybody for joining this call. We're excited for all of you to hopefully experience an R2 and see them on the roads here very soon.

This concludes today's call. Thank you for joining us.

All right. Up next, we are pleased to be joined by Claire McDonough, CFO of Rivian; James Philbin, VP of AI and Autonomy at Rivian. Before -- so thank you for joining. Before we get started, just important disclosure here. So for important disclosures, please see the Morgan Stanley research disclosure website at www.morganstanley.com/researchdisclosures. All right.

With that out of the way, Claire, maybe I'll kick it off with you. Would love for you just to set the stage for us. A lot's changed with Rivian over the last few years, but it's also a very pivotal year with the R2 launch. So what's changed? What's working better? And what do you think matters most for investors over the next 12 months?

Sure. As you look back at Rivian's history, our intention was to bring the R1 program to market that was really going to be Rivian's handshake with the world. That was going to showcase the performance, utility, capabilities that could be captured in an electric adventure vehicle. And I think the R1 has done that for us in spades. So the R1S, for example, is the best-selling electric SUV over $70,000 across North America. And in the state of California, it's actually the best-selling premium SUV sort of combustion engine or EV as well. So we need more states to sort of take a cue from California in that regard as we think about the adoption rates for the future as well.

But as we think about what's coming next with R2, if we can just harness even a fraction of the market share and performance we were able to achieve with R1 in a much larger addressable market with R2. R2 will be a home run beyond our wildest dreams as well. So it showcases the intentionality of the product road map.

And then beyond the product road map itself, R2 is also -- you can think about it as a vessel for all of our advanced technology. So it's not just a vehicle program, but it's our next generation of electrical architecture, software. And then I think one area of the business that has probably made the furthest advancements or changes since we started with our launch products is centered around autonomy with full in-house hardware and software stack, which James is going to tell us a little bit more about today as well. So that's critically important as we think about R2, which represents the scale, growth and profitability potential for the business. But also, I think one of the other elements that has evolved over Rivian's history is seeing Rivian as a technology provider for the industry at large.

And that is illustrated through the $5.8 billion joint venture that we did with Volkswagen Group and now the opportunity for us to potentially license autonomous hardware and software capabilities in addition to the electrical architecture and software to other OEMs across the industry as they see the need for transformation and the opportunity set in a world where in the not-too-distant future, if you don't have a software and AI-defined vehicle with advanced autonomy, you're not going to be able to generate the share position that you would want to have in the industry as well.

Yes, that makes sense. And we agree with you that it feels like autonomy is really the driving force behind EV adoption going forward. And it become synonymous with buying an EV is what's the autonomous driving platform that you have layered on top of the vehicle. So James, maybe I'd love to pass it to you to discuss how does Rivian differ? What's the strategy been when you think about building out your autonomy platform? It feels like every OEM has a slightly different strategy in terms of how they're approaching it. So I'd love to hear how Rivian differs, what gives you the confidence on kind of the road map going forward on your autonomous driving offerings?

Yes. So I think the first thing to point out is that Rivian is really a developer of the technology. We're not just an integrator, right? So I think most OEMs when they're talking about their L2+ or their ADAS solutions, what they're really saying is that they're taking a solution from a Tier 2 or a Tier 1 and integrating into their vehicles. I think we're very different in that we really have built this sort of integrated end-to-end approach all the way from the sensors, all the way through to the compute and then the software that runs there through to the experience that the customer has.

So I think that gives us a tremendous sort of nimbleness and velocity that other OEMs don't have. With the launch of Gen 2, we spent a lot of time building the right architecture, the right foundation really around the sort of data flywheel approach, right? So every vehicle that's on the road today from the Gen 2 R1s actually has a very powerful collection -- data collection mechanism in it that can trigger, can pull that data, can learn from customer driving. And so all of that feeds back into the system.

So we launched Gen 2 in 2024. Early last year, we launched our first hands-free product. And because of that flywheel, we were able to massively expand that with the launch of UHF, which was the end of last year. So that's actually the in my opinion, the best hands-free system on the market today, can cover more than 3.5 million miles of roads in the U.S. And so that's just the beginning, right? So we're on this amazing trajectory that this year, we're planning to get our first customer in a point-to-point system. We demoed that actually at AI Day and really building towards those much higher levels of autonomy.

Yes, that's great. And maybe just build upon that a little bit on the road map for eyes-on, hands-off point-to-point because I think that's a pretty big step function improvement in the technology. And then eventually, you've talked about getting to true eyes-off hands-off point-to-point. What needs to go right to get there? And what does that scaling look like? Is that a start in a very geofenced area like you did with the universal hands-free highway driving where it's on a select number of miles and then you eventually expanded it? Or would you wait to roll it out until it's available to the broader universe of customers? And maybe a secondary question to that is like how -- and maybe this is more for Claire, but how linked is it to the success of R2 and the data collection from R2? Or do you have enough, I guess, with the R1 vehicles on road from a data standpoint to get to that eyes-off level?

Yes. So I think the way I think about it is that we have in the fleet that's deployed today, a very large funnel. And in fact, it's not like we're recording and sending back all of that data, right? There's -- most of the data is not interesting. So if you just sat in the middle of the road, there's not much going on. We don't need to collect more of that data. So as we've deployed this system and as we've deployed UHF last year, we've also been improving like the triggering mechanism.

So how do we find those interesting use cases, those interesting tail events so that we -- the system learns as quickly as it can. So that's, I think, a big part of it. R2 ramp will definitely increase the volume. And the thing to remember about our vehicles is that they're actually -- we have 11 cameras, 5 radars, essentially one of the best sensor sets of any vehicle on sale in North America. So the data we get back is actually much more valuable than just a camera and data set.

And then with the LiDAR launch later this year, we'll actually have an even more powerful data set that's -- we think of it actually like a ground truth fleet. So we essentially have the biggest ground truth fleet in the world essentially. And all of that will feed back in, make the system much, much better, much, much faster.

That makes sense. And I think there's a debate in the market as well around simulation versus actually real-world data capture. And obviously, a lot of other competitors out there promoting simulation as a way to really expedite that eyes-on or even eyes-off, hands-off driving for some of the maybe more incumbent OEMs that haven't taken this in-house. How do you view that? How much do you leverage simulation? And are you a believer that this needs to be done on the road and like in the real world to get to a point where you solve that 0.1% edge case that you need to ultimately solve to make sure it's safe? Or is the sim good enough to get there?

Yes. So there's sort of two types of simulations. So there's what I would call open-loop simulation where you actually take a real scenario and you replay it through the system. So we already do a lot of that today. In fact, we resimulate millions of miles even for releases today before any customer sees them. Then there's another type of simulation, almost more like a video game style where you're sort of recreating camera imagery. That, we think, is important, but much less useful, especially for us because we have this incredible diversity of data from all across the country and all these different weather conditions.

Just to give you an example, for UHF that we launched last year, although we haven't done much validation specific work around snowy conditions, because of all that data that we collected since the launch of Gen 2, the system was actually very capable in those conditions. I had multiple people texting me saying, wow, this is the best system in snow. And so it's like that emergent property that we got because we had that incredible diversity. We didn't have to go specifically, oh, collect snowstorm data, collect data here. That already is coming to us.

That's great. And maybe R2 sounds like it's the marquee platform that's going to help you scale to be a scaled player and the R1 demonstrated the technology chops that you guys have. And I think that's very clear. As we think about the R2, you're launching it, I guess, in a week from today. You're starting the configuration process, start to build an order book. What does success look like to you? I know you've given a guidance for the amount of vehicles that you want to deliver this year. But outside of that, is it margin? Is it production time line? Like how should investors track over the course of the next few months as you start to build that order book, whether or not you're ramping or you hit your kind of successful milestones on R2?

Sure. As we take a step back and look at what success looks like, first and foremost, it's expanding the addressable market of Rivian consumers. So tapping into and not just prior EV owners, but also creating new choice where a consumer today may be on the fence in their first EV purchase decision and the opportunity for Rivian to take the 90% of consumers today that are still purchasing a combustion engine vehicle and get them behind the wheel of their very first EV. So that, I think, is critically important as we think about what success of R2 looks like as well.

The other elements of R2 are the operational efficiencies that we deploy as we execute our production ramp and path to profitability on the product. So we believe R2 has a path to exit 2026 with positive gross profit margins and Rivian to be positive on an automotive gross profit basis as well as we exit '26. And a lot of that is enabled through the fixed cost leverage that R2 brings to our existing Normal, Illinois plant, where last year, we delivered just over 42,000 units. The Normal plant once fully ramped with R2 is capable of producing and delivering north of about 215,000 units in total.

And so that enables not just a path to significant gross profit contribution from the R2 product, but also how it helps enable a path to expanded profitability in R1 and the commercial van as well. And we spoke a little bit about it as R2 as being the conduit for many of our next-generation advanced technologies. We also see their success looks like high levels of take rate in our Autonomy+ offering, which is our new paid autonomous offering for consumers, high utilization and engagement with our AI assistant, seeing the consumers that are really taking advantage of a lot of the core functions and features that make their R2 and the Rivian truly unique as well.

Yes. And I want to double-click on the gross profit improvement, the path to profitability with R2. Totally makes sense on the fixed cost leverage, operating leverage side. But talk a little bit more about bill of material. There's been a lot of conversation, especially at this conference about memory pricing and costs and bottlenecks. You got lithium pricing, copper pricing. How do you balance that? Are you comfortable with where you're at in terms of achieving the 50% reduction in bill of material that you guys have talked about historically? Like how has that changed over the last 6 to 9 months as we've seen the commodity inflation really accelerate?

So while we've certainly seen commodity inflation for some of the core raw material inputs in R2 increase over the last year, we also have always planned for a future where some of these elements were intact. So we weren't just building towards the establishment of the at-market pricing of where aluminum may have been or where lithium prices may have been. We're working towards a product set that has durability through different raw material cycles as well.

And so that certainly went into and contributed to the design and development and the enablement for us to create a product that could be roughly half of the material cost of an R1, but certainly is by no stretch half of the vehicle. So one of the early reviewers of the product said, if you had blindfolded him, put him behind the steering wheel, so to speak, of an R2, he actually probably couldn't have told you the difference. He would have told you he was driving an R1, not an R2. And that just exemplifies the core foundational technologies that enable a path through vertical integration to structural cost advantages that allow us a path to provide such a compelling value proposition to the end consumer as well. So that's certainly central to a lot of the trade-offs that we made that enabled us a path to that cost structure.

Yes. And on the fixed cost side, with ramping at Normal, you should get some benefit there. Talk a little bit about your plans with Georgia, right? I think there's potentially a risk that if you ramp too quickly in Georgia, then you're at the same place from like a fixed cost absorption standpoint that you are today with R1 just given the amount of capacity you have. So just talk a little bit about how you're planning on ramping and expanding Georgia and making sure that matches the demand profile that you're seeing with R2 and eventually R3 as well.

Sure. It's important to note that the Georgia plant is going to be a plant that will house production of our midsize platform. So that reflects R2, the R3 product. You can imagine additional variants of those vehicles that will be situated on the same platform as well. And again, that reinforces just the strength of the technologies that sit at the foundation of our product roadmap as well that we can then leverage to meet lots of different consumer choices, lifestyles to a form factor that truly meets your specific needs. So there's certainly significant runway as we think about the size of the total addressable market that the midsize SUV and crossovers address. Georgia will also be a key launch point for us to begin exporting products to Europe and building brands. So it's not just the North American market share and potential. It's really how do we take what's designed as a global platform and take full advantage of that as well over the longer term.

Yes. And on the demand side, maybe I'll pull James back in for a second. We talked about how autonomy feels like it's a big driver for EV demand going forward. We hear that there's a lot of people who own EV today that maybe one of your peers is EVs and that they want to switch, but they want to wait until they have the equivalent of an FSD on the vehicle. How much are you hearing that? And does that make you or do you wish to maybe accelerate your path to launching some of those programs or some of those offerings so that you can compete with some of the other players in the market and make sure that you are really ramping into the capacity and the R2 demand is really going where you want it to go?

Yes, absolutely. I think you see that from consumers more and more as these features get better. And actually -- as well as consumers get more familiar with like robotaxi efforts, they require more of their own vehicle. And so I think we definitely see that in the market and are working very quickly to improve the system to get us to that point. So as I said, with the launch of UHF last year, best-in-class hands-free system.

This year, we're really shooting for that point-to-point early system that will start to get customers in customers' hands end of this year. We actually demoed that at the AI Day. So we're making very rapid progress. A lot of that is powered by this large driving model that is essentially learned from all of the human supervised driving data that we've collected from our fleets. So it's very capable, very powerful. It has this amazing generalization that you can take it to new areas and it kind of just works. So a lot of the work this year will be sort of finessing that system, putting the right guardrails around it so that we can get that product out.

So I think consumers should feel confident that the Autonomy+ today is just the start. We're going to be improving that system to be best-in-class within that package. And so -- yes, and then with R2, with the new chip and the LiDAR, then we can take it to that next level. And I do think that there's probably -- there's a step change coming with -- once we get to sort of true eyes-off, that's something that would really give you your time back on a long commute. And I think there, you'll see consumer preferences really start to shift where that now becomes not just like a nice additional feature, but a must-have. You can imagine people buying not one R2, but two R2s, right, because both members of the household need to have that feature. So I think, yes, it's a very exciting future, I think.

That's great. And when we come back to the demand side, I think you talked about R1 and the commercial vehicle demand profile you're expecting to be roughly stable or flat year-over-year. Talk a little bit about -- you even mentioned that the influencer said that when they sat in the R2, it felt like it was the R1. So how do you balance that from like a cannibalization standpoint to ensure that demand for R1 is still strong given the fact that R2 is much more accessible for a lot of people at that price point?

So one of the distinct advantages we have is truly a different form factor. So there are many households where they need to have a three-row, seven-passenger SUV to meet their personal lifestyle needs. And for those consumers, they're still going to gravitate towards an R1. And for some of the more price-conscious consumers, we also have the opportunity to sell them a used R1 as well as they think about their specific choice. But there will be many consumers that R2 is certainly the right form factor for their personal needs and use cases. And as we look at the evolution of the R1 product portfolio, R1 will continue to skew more premium and create a pretty big gap relative to the price point and sizing of the R2 over time as well.

Got it. And on the commercial side of the business, the commercial vehicle, talk a little bit about what you're seeing there with Amazon and maybe outside of Amazon, the traction you're getting with some new customers. Amazon has been a big customer for you in that vehicle historically. But what are you seeing from others? And maybe what are some of the gating factors to getting some other corporates or commercial customers to actually adopt an electric vehicle as a last-mile delivery option?

This year, we do expect to see growth of the commercial van. That growth is predominantly driven by Amazon specifically. We're launching new variants for Amazon, including a larger battery pack variant of the van and all-wheel drive variant so that they can use the EDV for more rural routes within their network. And this growth is also a testament to the total cost of ownership that the EDV does provide.

And as we think about the opportunity for other fleet operators and owners, it's the continued education of the TCO benefits of managing, operating a software-defined vehicle. So in the case of Amazon, we're also very well integrated into their own software applications. We have a FleetOS, a fleet management software subscription attached to each vehicle in the fleet and are really proud about the opportunity to electrify the delivery space at scale with the largest customer in the last mile delivery.

I think it will take some time as well for other fleet operators to make the infrastructure investments and begin to more holistically electrify their fleets. But back to the conversation on autonomy, I think we will certainly see that as sort of another catalyst that will significantly advantage the TCO of an autonomous commercial van in the future as well.

Yes. Yes. That will be interesting to see how it eventually when all these vehicles are autonomous and presumably, you're planning on rolling it out to the commercial vehicles at some point as well. But on the -- you mentioned software and services. That seems to be a bright spot where you always exceed expectations in that part of your business. Talk a little bit about -- you've got the JV in there and then you've got your core software services business. Talk about the path to profitability and the drivers there in terms of the growth that you're seeing and that you're expecting this year? And how should we as investors or sell-siders expect or model that out going forward in terms of really driving that path to profitability for Rivian?

So in 2025, our software and services was just about $1.6 billion in total revenue. And as we look at the year ahead, we anticipate the growth to begin to approach about 60%. And that's driven both by the growth of the joint venture, but also importantly, as the car parc continues to grow and expand, we see a compounding of many of the other services within the portfolio. So we talked a little bit about the launch of Autonomy+. So in April, we'll start our paid subscriptions within the software and services component and see that as being a long-term catalyst for margin expansion opportunity for us as well.

The other large components outside of the joint venture are centered around our remote remarketing program. So we're very focused on how do we preserve the residual values of our product and play a very active role in the used market for Rivian. We also have a large component coming from our maintenance, repair, serviceability. And then as we've talked a little bit about our FleetOS offering, our Connect+ offering, which is our advanced infotainment offering. And then beyond that, financing, insurance, so there's so much value that can be created throughout the ownership lifetime of a vehicle outside of just the initial purchase. And so being a direct-to-consumer player like Rivian is a distinct advantage as you think about the opportunity to expand and enhance the lifetime value of each potential vehicle and each potential customer as well.

Yes. And it's very clear there's -- you're working on a lot of things, autonomy, R2, eventually R3, Georgia, ramping Normal. How should investors think about how you fund all of this, right? There's a lot of exciting things that you're doing. But how do you bridge that gap until you really ramp R2 and you start becoming to a point where you're self-funding the business? What does that look like? And what are kind of the sources of funding that you're expecting to tap into?

So we ended 2025 with $6.1 billion of cash. There's another $2.5 billion of payments, $2 billion of which we anticipate receiving in 2026 from Volkswagen Group. And then as we think about the build-out of Georgia, the Department of Energy loan is really a construction type project-based finance instruments that you can imagine will help us fund some of the growth of both the product portfolio and plant and facilities there as well over the future. And then beyond that, we'll remain opportunistic as it pertains to additional sources of capital.

Great. I want to pause real quick and see if there's any questions in the room. All right, it's none. You talked about it a little bit in your opening remarks about international potential expansion. What does that look like? Europe is becoming -- it feels like a very competitive market, especially on EVs. Why would it make sense to go to Europe just given that competitive dynamic? And where do you see yourselves really playing in that market relative to some of the competitors there?

We think there's a distinct advantage that stems from being a true clean sheet operator. So having an in-house electrical architecture, software stack, advanced autonomy, a fantastic product design and a great brand reputation as well that allows Rivian to compete not just in North America, but to compete on a more national stage as well. So we were also encouraged by having a number of international reviewers come test drive the R2 as well and the glowing feedback that they provided for the product and excitement. They're saying -- begging us to get the R2s as quickly as possible into the continent of Europe as well. So excited about the opportunity to really stretch the brand even further, and -- and that design also is not just part of R2, but also as we think about R3 and that being a very compelling form factor being sort of a smaller crossover vehicle for the continent of Europe.

Is it just Europe or would Middle East or Latin America, any other markets that screen attractive given the form factor? Or is it just Europe was like the first international plan for you guys?

There certainly is a lot of interest beyond just Europe, but we also need to be methodical as we think about the building blocks of infrastructure and scaling the product in multiple locations across the world as well.

Got it. And you also mentioned the partnerships that you have with Volkswagen and potentially expanding that or finding other partnerships with other OEMs. Can you talk about what that discussion looks like? What are some of the limitations in terms of like why others haven't come to the table and done a similar deal that Volkswagen has done? Just trying to get a sense for -- that ultimately would be a very attractive way to monetize the technology beyond just scaling up internally with R2 and R3. So just trying to get a sense for what's the time line? What are some of the gating factors to actually making that happen with other partners?

Today, only Rivian and Tesla are the two Western OEMs that have a zonal electrical architecture in the product. And as we think about some of the design capabilities that will enable us to reduce the cost structure of R2, the electrical architecture is really central to that equation overall. As you think about other OEMs, we certainly see a world where the future is fully autonomous and software and AI defined. And so you will have to have those embedded capabilities in your product to compete in the future. And so I do imagine that there certainly will be OEMs that are either exploring things in their own stand-alone way, navigating this with Tier 1 partners and ultimately, we'll seek or explore opportunities potentially with Rivian in the future, given how compelling the electrical architecture platform is.

And if you take a step back and you look at what we're doing for Volkswagen Group, which is the second largest OEM in the world and probably one of the more complex ones given the variety of brand and breadth of form factors and price points within their portfolio. Rivian's ability to service the Volkswagen Group is really our best calling card as we think about other OEMs that may be interested in these capabilities in the future as well.

Got it. And to dovetail off of that, James, maybe for you, the RAP1 chip that you guys announced late last year, I think you also talked about potentially finding buyers of that chip. How do you think about the evolution of that as a product, right? Is RAP1 good enough to get you to all the way to like eyes-off, hands-off and beyond? Or will you have to keep iterating on that? And what does that look like from like a spend perspective going forward in terms of the capital intensity of the business?

Yes. So as you mentioned, on the AI Day that we had last year, we announced the -- our in-house silicon effort. That's actually not something we did on a whim. That's a multiyear long effort to design and build and source that chip. And yes, the goal is for that chip to be in R2 at the end of this year. It will actually, as far as we know, be the most powerful automotive computer in the market, certainly in the U.S. So yes, it's really an incredible chip, incredible capability. It's really been designed for these transformer architectures, which are these modern building blocks of LLMs. And yes, we think that, that has certainly the capability to get all the way through to L3 and then personal Level 4.

Yes. Great. And maybe to just close it out with a very high-level question for you, Claire. What do you think the market is getting wrong about Rivian and your story that you obviously portray today? What do you think we're missing? What do you think the market is missing about your strategy and your story more broadly?

I think one of the elements that sometimes is missed or not fully understood is just the core technology advantages that a player like Rivian has. And that's seen through our ability to recruit phenomenal talent like we see on James's team, as we see on our in-house silicon team to bring together the best minds as we think about the evolution of our technology foundations for the future in a variety of different areas within the business as well.

I also think that AI will be a distinct advantage for players that are in the direct-to-consumer space as well, where through the ownership -- the end-to-end ownership control, there are so many elements in which we can ultimately improve the ownership experience while also reducing cost over the longer term as well. But I think some of those key advantages within the story are sometimes overlooked or not necessarily fully appreciated. And as you think about the complexities to build these capabilities in-house from the ground up to have these proven technologies that are operating and driving value to consumers already today and then the future road map as we look to sort of package those technologies into R2 and the opportunity to scale with the mass market program.

Well, great. Well, I think we're out of time here. I appreciate it, and thanks for everyone for joining.

Thank you.

Thank you.

Good morning, everyone. My name is Avi Steiner, and I am the automotive analyst here at JPMorgan. It's our pleasure to have with us today from Rivian, Chief Financial Officer, Claire McDonough, who has graciously agreed to be peppered in a fireside chat Q&A format this morning.

As always, I'm going to start with some Q&A up here, and then I'm going to open it up to the audience for questions, hopefully, if time allows, and then we'll go from there.

Claire, thank you for joining us today.

Thanks for having me, Avi.

Excellent. Okay. Let's start here. You've done a great job. The company has done a great job of reducing the bill of materials for next-generation R1, both year-over-year and sequentially. Can you walk us through how the company achieved those savings?

Sure. As you look at our cost of goods sold for per unit delivered in the fourth quarter of 2025, we saw a $7,000 reduction versus the fourth quarter of 2024. And we were able to achieve that through a significant reduction in our material cost of the product. Those were achieved by both the transition that we made from our first-generation R1 to our second generation, which improved all of the core technologies in the vehicle itself, bringing us to a lower cost basis in our material costs on R1 program.

We also saw a slight increase in terms of our commercial van deliveries in the fourth quarter, so had some additional favorability from a mix standpoint as well. But the important piece is, as you look at the fourth quarter, on a cash basis, we made over $2,000 a unit, and that sets us up really nicely as we now think about the added volumes that will come into play with the ramp and rollout of R2 that will start first external deliveries of R2 in the second quarter.

We'll build for the most -- the majority of the year on a single shift, and then we'll add a second shift of operation. So as we look towards the fourth quarter of 2026, we'll see a key inflection point in terms of the overall production volumes and with that, the fixed cost leverage that benefits not just the R2 that is coming to market, but also importantly, the underlying unit economics of our R1 program as well as our commercial van.

You touched on a lot there, and hopefully, we will get to address a bunch of those things.

I want to shift to the R2. It's expected to be a game changer for the company. The reviews so far have been pretty positive. If anyone hasn't seen them, I encourage you to go online. That's not me saying that, that's other companies.

But more importantly, recognizing launch is proceeding deliberately, as you kind of just touched on one shift, what are the biggest financial and operational challenges you're preparing for as the company scales production? How is Rivian mitigating or getting in front of any potential supply chain bottlenecks?

First off, thanks for the shout out on the early release of reviews. We couldn't have asked for better reviews out of the February launch where we had about 10 media outlets, drive the R2 product. Some of the favorite quotes that came out of that experience from my standpoint were one reviewer called it the Best EV that he's ever experienced. Others said that if you had not told them and just put him in -- behind the wheel of the driver seat, he would have thought he was driving an R1S, but instead driving an R2 with a much more affordable price point associated with it as well.

Now as we look at the road map for R2s ramp, we're critically focused on the supply chain right now. And in early January, we started our first manufacturing validation builds on our lines in Normal, Illinois. So over the course of the last 1.5 years, we built out an expansion in our Normal facility to accommodate a brand-new body shop and general assembly of the R2 product.

And we've been going through the cycles each and every week to improve the production quality, improve our processes, system, training of the team. So it's -- you can think about it really as a continuous road map as we reach salable production on the product first, and then ultimately get to a point where we're inflecting and adding a second shift of operation as well.

And the strategy that we've deployed to run most of this year with a single shift is focused on getting the quality right and the assurance that we're keeping the supply base working in lockstep with Rivian as they increase their production rates and volumes ahead of the second shift and ultimately in 2027, the addition of a third shift of operation for R2.

So with the first shift and really the R2 deliveries, I think, starting in the second quarter of this year, remind us as to how we should think about the margin evolution here from launch to -- I'll use the word steady state. I don't know if you can kind of quantify that. And is that after 2 shifts, 3 shifts? Just how to think about that whole evolution.

For R2, we have the advantage of starting with a low material cost basis on the product. And we were able to achieve that through the demonstration of the brand strength with the development and sales of R1 program as well as our commercial van offering that allowed us to get to much lower levels of -- I would characterize cost with the supply base as a whole as we work through the negotiation of the R2 program over the course of 2024.

And that enables us to have a very fast path to variable profitability on the product. And we anticipate by the end of 2026 that we'll be in a position where both R2 and our overall automotive gross profit will be positive within the business. As we look at the quarter sequential mix, you'll see Q2 as -- and Q3 as being more of a headwind associated with the early stages of ramping up a brand-new product. But then as we look at Q4 and the exit rate, R2 starts to be a net beneficiary of our underlying unit economics.

Okay. Maybe one more on R2, if I can. So I think it's March 12, you'll correct me if I'm right.

Yes.

On March 12, you plan to reveal the different configurations that consumers can select for the R2. And what I'm really curious about, you've had -- companies had pretty good learnings, if that's the right word, from the R1 to guide it, and this is obviously a lower-priced vehicle aimed at different consumers. What are some of the puts and takes in terms of how management thinks about combinations, price points that it might make available to the consumer within that -- the enormous backlog that was once noted for that vehicle?

One of the key learnings that we're employing with R2 is to focus on simplicity. So to narrow the SKU assortment, ensure that we're focusing in a way that enables the acceleration of our ramp and road map for the future.

And so as we look at the conversion of our preorder base of customers, we're going to invite those customers to say, are you interested, first and foremost, in configuring a launch edition vehicle for Rivian, not saying everyone come and configure the exact variant that they want, but instead say, this is what we're building today and you can queue up to put in your preorder for that launch edition variant out of the gate that will help us bring up the supply chain, reduce complexity with the ramp and hopefully be more successful as a result of the simplification of the build plan.

Okay. Terrific. And then Rivian unveiled the RAP1 chip at its Autonomy Day last year. Walk us through the capabilities that provides and the timing in terms of introduction of Gen 3 Autonomy, which is really the genesis of this question. And when will it be commercially available or included in the R2? And relatedly, if I can ask, any thoughts on whether the different tech that is available at launch versus maybe later in the year impacts -- might impact at all R2 sales?

First off, we've introduced to the world our Rivian Autonomy Processor at our Autonomy and AI Day back in December of 2025. The core advantage that we're deploying with an in-house silicon program is the opportunity for us to have rapid cycles in terms of development, a product that is custom built for the universe of heavy camera and sensor-based AI physical world applications, which allows us to use the vast majority of the TOPS or processing power of this chip relative to other players in market that are trying to solve for many more versus just the use case of autonomy or advanced physical AI and robotics.

And then the other element is cost as well. And so we had the opportunity with the talent that we had within our team to recruit a world-class semiconductor organization to Rivian to build this program out for Rivian. Today, we have production and intent silicon that we're testing and developing with our teams, and those will go first into vehicles at the end of 2026.

And then you'll see us scale up the R2 volumes in 2027 with this new Gen 3 hardware set, which includes the Rivian Autonomy Processor chip, but also includes LiDAR, the first LiDARs that will go into Rivian's as well. And this is 1,600 TOPS. And so as you think about the overall compute and processing power, it's twice as powerful as what we have in our Gen 2 products or the first R2s that will go in market as well.

However, with that said, R2 will be at launch, still one of the most advanced vehicles in terms of its autonomy capabilities, the level of compute that's in the vehicle as well. And for those first orders, they'll have full access to a point-to-point navigation. So any road that has a painted line on it, they can use a point-to-point navigation to have the car effectively drive them hands-free to their destination.

That's great. And there was a lot in there, so I probably should have broken that up into a couple of questions.

I'm going to build off of that, if I can. If you could talk about the company's NAND and DRAM needs, how that might be impacted given everybody is talking about the shortage and obviously, the pull from AI. And obviously, you've had plenty of learnings again to use that word, just from your build in R1 and different shortages. Just talk about how you might be navigating that?

Sure. The fundamental challenges within the memory space was factored into our guidance for 2026. And as we think about some of the core advantages of a player like Rivian, we do have the flexibility because of our vertical integration in terms of the electronic control units that we design in-house. We work directly with contract manufacturers on the production of those boards that enables us to be more agile in an environment like this.

So back in 2021, when we were going through the semiconductor crisis, for example, we were able to redesign some of our ECUs to move away from constrained parts within the industry as a whole and gravitate towards new supplier partners that had availability towards Rivian. So we're -- our teams are working around the clock to ensure we have the memory for our products. We do use a sizable amount of memory given the advanced technologies and autonomous capabilities of the product itself. But we also do have, I would say, a core inherent advantage in the level of vertical integration that we have and deploy.

Okay. As a reminder to the audience, I'm going to open up to questions in a couple.

Let me kind of take a bigger picture view here, if I can. There are a couple of cross currents as we see it for electric vehicles at the moment. On the one hand, the administration has effectively unwound the incentives that were meant to spur adoption of electric vehicles.

And on the other hand, we see as consequences, I guess, with the former of the D3 and other manufacturers have begun to meaningfully pull back from the EV product, right? And so I'm sure you don't necessarily view them as competitors, and I don't say that in a pejorative or negative way. But just thinking about how folks are moving to hybrids, there's been some discussion of maybe Tesla pulling back on some vehicles. Just how you think about your position, Rivian's position and these 2 kind of crosscurrents either benefiting or hampering demand for Rivian's vehicles?

So we very strongly believe that the future is going to be autonomous, software-defined. And if you look at the characteristics of those 2 capability sets, they often come in the package of being a fully electric vehicle as well. And so we believe that the steadfast clarity of our focus in the road map in each of these core technologies that we think will transform consumer buying behaviors in the future will put Rivian in a great position as others are actually taking a step back from their electrification initiatives as a whole.

And we also want to just bring the very best product to market. So we often get asked about some of the dynamics in market with EVs. Our ambition as a company is to create the best vehicle full stop. And whether you're coming to Rivian because you want an electric powertrain, you're coming to Rivian because you love the design of the product, or you love the technology of the product or the performance. We think we're bringing a fantastic product to market. And our intention is to take a large percentage of the customers today that are still buying combustion engine vehicles and convince them to buy their very first EV with R2 as well.

Right. I'm going to dig into that maybe a little bit further from a different angle. So RJ on the last earnings call listed a number of states that the R1S, I think, is the best-selling EV. And if you look at those states, and again, I don't mean this negatively, but California, New York, New Jersey, Oregon, Washington, D.C. and Virginia, I think they all -- that was very quick, but they all adhere or subscribe or a part of CARB, right? And they're more EV focused for lack of a better definition.

And really, the question is, how does the company increase awareness and adoption? Everything you just talked about, about how you view this as transformative technology and you want to reach those ICE consumers or those ICE vehicle owners. How do you increase awareness adoption in other states and really countrywide to get them to make the switch?

We've seen a lot of power in the strength of our Rivian community. And the best influencers for Rivian are our customers. So the customers that are going out at their Little League baseball game, talking to their neighbors, talking to their teammates, friends about the experience that they have driving their Rivian, that's the best marketing that we can have.

Now the other challenge is we need more consumers to test drive our products because the best way to showcase the performance capability and utility of a Rivian is to get behind the wheel. We have a couple of Rivians downstairs. So for those of you in the audience that have never driven a Rivian, please take us up on the offer to do just that because you can listen to -- Avi and I go back and forth about the business and strategy, but I truly believe that getting behind the wheel makes the vertical integration, makes the intentionality of our technology stack and the true differentiation of Rivian all come together in one driving experience and package that is incredibly well thought out as well.

So that's another strategy of how do we continue to have more customers grow their awareness of Rivian, whether they're in market today for a vehicle or whether they're considering their very first EV for their next product, having more of those experiences is critically important for us.

And the other element is the continued growth and build-out of our physical infrastructure. So our service infrastructure, our sales infrastructure, our charging infrastructure that supports many consumers in many additional geographies as well.

Can you size the infrastructure you put in place, service centers, et cetera, on the one hand? And then just finishing off that last question, if I can. Is there ever a role for a traditional marketing campaign in Rivian's future? Or this is just you want to keep going on the word-of-mouth experience path, which has been great.

So today, from a physical infrastructure standpoint, we have just under 100 service center locations across North America. We have 35 dedicated, we call them spaces, which you can think about them as experiential retail hubs for the business. And we'll add another 40 locations over the course of 2026 as we scale up for the launch and growth of the R2 as well.

One of the keys from a physical infrastructure standpoint is the opportunity for us to be very asset efficient. And in the case of service, the majority of our service can be done through mobile service applications. So we have hundreds of mobile service vans that are deployed across each of our 100 service locations and the majority of events can be done in -- at your home. So there's nothing more convenient than a Rivian service van coming to your home or workplace that can do the job for you without you ever having to lift a finger or bring the car in for services as well.

And one of the core advantages of EVs is they require very limited services as well. And I think that, that's an area where many new owners are just completely surprised and delighted by the efficiencies and reduction in their total cost of ownership through service overall.

Okay. I'm going to open it up to the audience for any questions. I ask because it's webcast that you wait for the mic to come by, so you can ask your question into the microphone. Does anyone have any questions in the audience?

What's the status of the build-out in Georgia? As a resident of Atlanta, I drive through the I-20 Corridor, I see what looks to be infrastructure improvements around where a site may potentially land, but what's the status of that built-out?

Well, great to have you as a Georgian and adjacent customer in our community.

For the Georgia site, we focused on a lot of the long lead time items. So those are oriented around bringing power and utilities to the site. We've done a lot of work with the state on building a lot of the transportation infrastructure, logistics infrastructure. So there's a new overpass new rail spur that's going into effect as well, such that when we get to vertical integration in -- sorry, vertical construction in 2026, we can go much faster with the anticipation of the very first vehicle builds happening at the end of 2028 at the site.

One question upfront.

Can you delve a little deeper into the Tesla decision to get out of the X&S and what that means for you as an opportunity? And also was your perspective on the logic of canceling those programs. Those were obviously the benchmark programs for that EV platform or had been for a long time before the lower-cost versions. Is there any read-through that you guys have about your platform and vision going forward for EVs generally?

So fully agree with you on Model S and Model X as being benchmark programs. Those were really the first programs in the EV space that showcase the capability, performance, desirability of an electric product.

As we look at Rivian's opportunity now, there's certainly customers that Rivian can recruit and look to continue the continued sales of our R1S, which is a 7-passenger large SUV and our R1T electric pickup truck as well. I can't opine on Tesla's strategic rationale in their own decision-making.

But similar to Rivian, we used the R1 platform as really our handshake with the world or opportunity to build brand to showcase the on-road and off-road capability performance of what a Rivian can do, and then now have the opportunity with our mass market price point with R2 to significantly grow the addressable market of consumers that can now consider Rivian as part of their purchasing decision.

Okay. Great. I'm going to turn it back to myself and ask a couple more questions. Can you update us on the relationship between Rivian and VW on the one hand, a couple of reports have been out there intermittently. But more importantly, can you also remind us in the audience what the time line and milestones are to the next payments from VW to Rivian and both timing and amounts?

Sure. Rivian maintains a very strong relationship with Volkswagen Group. We were incredibly proud to have delivered multiple vehicles back to Volkswagen at the end of 2025 for the start of winter testing. And that's a testament to the extensibility of the software and electrical architecture that we've rebuilt, and the joint venture is leveraging for future vehicles as well.

And so in that 13-month time frame, we were able to modify our Gen 2 architecture, which is what powers our R1 -- our Gen 2 R1s as well as what will power R2 and build that into multiple different brand programs for the Volkswagen group, which is multiples faster than they would have ever been able to execute against, working with their own supply base and ecosystem as a whole.

So it showcases the speed and the utility of the foundation of the IP that sits at Rivian and now at Volkswagen Group as part of the joint venture as well and as we think about the ongoing deployment of these products working our way through multiple Volkswagen Group launches in the as well.

And as it pertains to the incremental capital from Volkswagen, as part of the $5.8 billion of consideration for the joint venture, there's a $2.5 billion of that, that is still yet to come to Rivian. We anticipate receiving $2 billion of that this year in 2026, $1 billion tied towards winter test -- successful winter testing and $1 billion, which is a nonrecourse loan from Volkswagen Group to Rivian as part of the consideration and then another $0.5 billion that will come in equity in '27.

Perfect. And then on your last call, and I think during the Autonomy Day as well, the company talked about the potential to license its software-defined vehicle technology to other OEMs. And beyond what it is doing with VW, importantly to note, is it possible to size the opportunity or how we should think about it here? Is this something that can reasonably be expected before all the VW benchmarks have been reached, as you just discussed, and those vehicles launch in '27? Just how do we think about that possibility?

Sure. There's multiple avenues for Rivian and the joint venture to execute on being a technology partner for the industry. And so within the joint venture itself, we have housed our electrical architecture and software stack that powers the key functions of the vehicle itself. Outside of the joint venture is all of our initiatives around autonomy.

And so as we think about what the opportunity is for Rivian, as I mentioned, we believe that all OEMs will and the future need to have a zonal electrical architecture, be a software-defined vehicle and have high levels of autonomy to be part of the consideration set for consumers or risk losing a meaningful market share overall.

And so we see there being a huge opportunity for Rivian to play a meaningful part in that transition for many other OEMs as well. And through our large commercial relationships with both Volkswagen Group and Amazon have built and are building a muscle of how do we work collectively with large complex organizations and customers as we look to that future state of being a technology provider to the industry.

Okay. Very much a stay tuned. We are at a debt conference. So I'm going to go maybe one on the balance sheet and cash use, if I can.

Based on the company's full year guidance, it's likely Rivian will burn another $4 billion of cash just from EBITDA and CapEx spend, right? And then we have working capital, which is an outflow. I don't think you've sized it, but it's -- you're growing this year, it makes sense it will be something not small. And then you have the incoming dollars from VW. You're in a net cash position today. But just walk us through; a, if my math is right; and b, how you think about your liquidity evolving as you head into '27?

We ended 2025 with $6.1 billion of cash. We'll receive another $2 billion this year from Volkswagen Group. Your math is correct around our guidance for adjusted EBITDA and CapEx as well as the fact that we do expect there to be an outflow of capital from working capital as we ramp up for R2.

Beyond that, as we look ahead to the Georgia site and facility, we do have a project-based finance loan with the Department of Energy that we anticipate being able to utilize for the continued build-out of our Georgia site and the tooling associated with the future vehicles that will be housed at that site. And beyond that, we'll remain opportunistic as it pertains to maintaining a strong balance sheet position for the future.

Okay. I want to give our audience one more chance to ask questions, we've got about 6 minutes left. If not, I've got more questions. Anyone in the audience have a last question for Claire? Don't be shy again.

Okay. Great. I'm going to keep at it. And Claire, thank you for enduring this. I appreciate it very much.

So there's been a relatively less conversation around Amazon. You just touched on it and Rivian's EDV offering. Can you update us on how the company is delivering on their electric fleet goals and remind us what the initial agreement was, if you can?

And then just beyond that, how do you -- I guess, I believe it's not exclusive is where I should be going with this. So maybe talk about the opportunity set there beyond just with Amazon?

Amazon's initial order was for 100,000 commercial vans by 2030. Part of the work that we've been doing alongside Amazon over the course of the last couple of years has been the build-out of infrastructure to support the electrification of the Amazon fleet. And they've put that foundation in place. And so as we look at our guidance for 2026, we do anticipate there being an increase in our volumes of delivery vans to Amazon, which is embedded within our guide for the year.

And we're also launching a couple of new variants for Amazon. So we're adding a larger battery pack unit and all-wheel drive configuration so that they can use the electric vans for more rural routes versus today where more of the commercial van deliveries in our products are being deployed in suburban and urban types of environments overall.

So Amazon is a great partner of Rivian's, and we're really excited about the continued deployment of this offering. There's roughly 30,000 vans as reported by Amazon on the road from our electric delivery vans for them. And then as we look to the future for other customers, we see there as an opportunity over the longer term to continue to educate large fleet operators on the advantages of an EV fleet.

And we see that through the total cost of ownership advantages that our EDV offers to Amazon and their appreciation of the efficiency and deployment of these vehicles within the fleet. But I will say that it does require a level of investment as Amazon has done in their charging infrastructure. And so that's an area where we're continuing to educate fleet customers. So don't anticipate significant volumes outside of Amazon in the near term, but remain confident that over the longer term, we will see more fleets electrify.

Terrific. I want to go back to Georgia, if I can. So recognizing that's going to create a ton of jobs, and that's obviously a positive, but we also have an administration that in various areas as it relates to grants and electrification has maybe pulled back a little bit. I'm curious, has anything changed in your conversations with the administration at all, and just how your outlook may have evolved, if at all, for the plan?

We're very aligned with the administration on the opportunity to bring more manufacturing jobs to the U.S. Rivian will be adding 2,000 jobs in our Normal, Illinois facility as we ramp up R2, and we'll be adding another 7,500 jobs in Georgia as well.

Beyond the job creation, Rivian is also a leader in the advancement of technologies as we think about the evolution of the automotive industry and the role that Rivian can play as a key enabler for the transition for many more traditional OEMs as well through the feature set and capabilities that Rivian can provide. So there's broad-based alignment as you think about our capabilities and the job growth and creation that Rivian can bring to market.

Okay. So the relationship is great. Everything is on track. Perfect.

Maybe my last question here as we're running out of time. I think at one point, Rivian was contemplating selling the R2 into Europe, which at the price point and given the market dynamics there broadly would seem to be attractive, at least from my perspective. Any updated thoughts on potential timing? And -- or is the focus just specifically at this point, getting the R2 right, getting the rollout right and then going from there?

So R2 is designed for global markets and not just to be a North American-centric product. We have large international ambitions as well as a company. And there's been a huge level of interest from a lot of Europeans that follow Rivian, that track the brand, part of the media reviews was through a couple of elite outlets out of Europe as well, all who had glowing reviews of the product. So we're really excited about the opportunity now that we'll have R2 in place to begin to build out the brand and integrate Rivian's across the continent of Europe over time.

Okay. That's a great stay tuned. A great place to stop. Claire, thank you so much. Rivian, thank you so much for being here. I appreciate all the time.

Good afternoon, and thank you for joining us for Rivian's Fourth Quarter and Full Year 2025 Earnings Call. Today, I'm joined by RJ Scaringe, our CEO and Founder; Claire McDonough, our Chief Financial Officer; and Javier Varela, our Chief Operations Officer. Before we begin, matters discussed on this call, including comments and responses to questions, reflect management's views as of today. We will also be making statements related to our business, operations and financial performance that may be considered forward-looking statements under federal securities law.

Such statements involve risks and uncertainties that could cause actual results to differ materially. These risks and uncertainties are described in our SEC filings and the shareholder letter we filed with the SEC. During this call, we will discuss both GAAP and non-GAAP financial measures. A reconciliation of historical non-GAAP to GAAP financial measures is provided in our shareholder letter. Just before the earnings call, we published and filed our shareholder letter, which includes an overview of our progress over the recent months. I encourage you to read it for additional details around some of the items we will cover on today's call.

Following our prepared remarks, we will be taking questions from sell-side analysts. In the interest of keeping the call to 1 hour, we would ask these analysts to limit any follow-on questions to one. With that, I'll turn the call over to RJ.

Thanks, Chip. Good afternoon, everyone, and thanks for joining us for today's call. 2025 was a year focused on execution at Rivian as we laid the foundations for scaling our business. Our team progressed the development of our technology road map in R2, while simultaneously driving continued improvement in our customer experience and our path to profitability.

In founding Rivian, I wanted to demonstrate how a clean sheet technology-focused vehicle could eliminate long accepted compromises and provide consumers choice. Our goal with the launch of our R1 products was to establish the Rivian brand by delivering a combination of efficiency, on-road performance, off-road capability, functional utility and product refinement that simply didn't exist in the market. The first vehicles established Rivian as a brand that enables people to do the things they love, enable adventure as well as transcend different segments, form factors, use cases and geographies.

In the fourth quarter of 2025, the R1S was the best-selling premium electric vehicle priced above $70,000 in California, New York, New Jersey, Oregon, Virginia and Washington, D.C. And it was the best-selling SUV EV or non-EV, over $70,000 in the state of California. Now I'm excited that we are months away from starting customer deliveries of R2, our first mass market vehicle. One of the things that's often overlooked around EVs is that there is a surprising lack of high-quality choices at prices around or below $50,000 for a new vehicle in the United States, there are only a few compelling EV choices as compared to hundreds of internal combustion or hybrid options that have a wide range of form factors and design aesthetics.

From the lens of the customer, if you want to buy a midsized SUV with robust technology, autonomous capabilities and a reasonable price point, you've really only got one choice, and it's been that way for a long time. This is a reflection of a market that's being underserved. We believe R2 is going to change that. R2 is an extension of the experience we delivered in R1 with design elements and performance to inspire adventure, but in a smaller form factor and importantly, at an attractive lower price point. Launch Edition R2 variants will be well equipped with a dual motor all-wheel drive setup that provides more than 650 horsepower and over 300 miles of range. In mid-January, I was thrilled to drive our first R2 manufacturing validation build off the production line in our factory in Illinois.

As you've seen from the extremely positive, media reviews of our preproduction vehicles over the last few days, R2 is an exceptional vehicle, and I believe will be a game changer for our customers, our company and the industry. One reviewer said, the R2 is an exceptional vehicle, quite possibly the best all-around electric vehicle I've ever driven. We look forward to getting investors and more media in R2 for demo drives so they can experience the capabilities of the vehicle. We plan to provide additional product, pricing and lineup details on March 12. Turning to our AI and Autonomy Day. It was great to see so many of our stakeholders at our offices in Palo Alto this past December. We were excited to showcase our innovation across our vertically integrated hardware, software and autonomy teams and unveil RAP1. Developing our own chip was driven by the need for velocity, performance and cost efficiency and is a key development of our autonomy platform.

Near the end of last year, we released universal hands-free, which expanded our advanced assisted driving capabilities for Gen 2 customers to more than 3.5 million miles of roads across North America. Since its release, customer utilization of our autonomy features has doubled. Rivian is also making significant progress in making software and AI core to everything we do from the way we design, develop, manufacture and service our cars to the way our customers interact with their vehicle. This is enabled by the Rivian Unified Intelligence, a common AI foundation that understands our products and operations as one continuous system and personalizes the experience for our customers. It also defines how applications will integrate in our vehicles in the future. We were excited to demo the Rivian Assistant at AI and Autonomy Day and expect to launch this feature early this year.

Finally, we continue to see the extensibility of our electrical hardware and software platform with the work happening in our joint venture with Volkswagen Group. I'm very pleased that we have delivered vehicles for winter testing for multiple Volkswagen Group brands, 13 months after the formation of the joint venture. In closing, 2025 was a foundational year for scaling Rivian, and I could not be more excited for the year ahead. I believe 2026 will be an inflection point for our business. As an American automotive technology company that develops and manufactures incredible electric vehicles, we believe that the future of the automotive industry will be fully electric, autonomous and AI defined. I've never been more confident in the opportunity ahead for Rivian than I am today.

I firmly believe Rivian's technology, along with our direct-to-customer ownership experience, position our company to build a category-defining brand with a strong mass market product portfolio for the U.S. and global markets. With that, I'll pass the call over to Claire to discuss our financial results.

Thanks, RJ, and good afternoon, everyone. As RJ discussed, we believe 2026 will be an important year as we scale our business. Launching R2 will extend our brand to the mass market, and we expect R2 will drive meaningful automotive segment growth and profitability over time. Now before I dive into the quarter, there are a few key financial metrics that I'd like to highlight for 2025. First, on a full year-over-year basis, we delivered nearly $5,500 of improvement in average sales price due to the introduction of our second-generation R1 quad models, a higher mix of R1 units and increased base prices for the 2026 model year.

Second, on a full year-over-year basis, we achieved an approximately $9,500 improvement in automotive cost of goods sold per unit due to material cost reductions and operational efficiencies. Finally, the improvement in unit economics in our Automotive segment, when combined with our strong software and services performance, resulted in greater than $1.3 billion of improvement in full year gross profit, making 2025 our first full year of positive gross profit.

Additionally, our gross profit performance, coupled with our focus on cost management, enabled our adjusted EBITDA for 2025 to be at the favorable end of our guidance. All of these metrics represent our continued progress in the operational efficiency and profitability of our business, which sets a strong foundation for 2026 and beyond. We expect the gross profit per unit for R1 and the commercial vans to be further enhanced as we ramp up production and deliveries of R2, coupled with the gross profit contribution of R2 over time. Turning to the results of the fourth quarter. Our consolidated revenues were approximately $1.3 billion.

Consolidated gross profit was $120 million, and our gross profit margin was 9%. Gross profit included $108 million of depreciation and $26 million of stock-based compensation expense. Adjusted EBITDA losses for the fourth quarter were negative $465 million, $137 million improvement from Q3 2025 due to higher gross profit and lower operating expenses. Now looking at our Automotive segment. During the fourth quarter, we produced 10,974 vehicles and delivered 9,745 vehicles from our manufacturing facility in Normal, Illinois. This was the primary driver of the $839 million of automotive revenue. Automotive gross profit for the fourth quarter was negative $59 million, a $71 million improvement from Q3 2025 due to a higher mix of commercial vans, which resulted in the lowest cost of goods sold per unit in our history.

Our Software and Services segment reported another strong quarter with $447 million of revenue and $179 million of gross profit. $273 million or approximately 60% of software and services revenue was attributable to our joint venture with Volkswagen Group. We also experienced strong growth from our marketing and vehicle repair and maintenance. Looking at our balance sheet, we ended the year with approximately $6.1 billion of cash, cash equivalents and short-term investments. In 2026, we expect to receive an additional $2 billion of capital as part of our joint venture with the Volkswagen Group. $1 billion is an investment subject to the successful completion of winter testing, which RJ discussed earlier and $1 billion is nonrecourse debt, which we expect to receive in October. Finally, for our 2026 guidance, we expect to deliver between 62,000 and 67,000 total vehicles across R1, R2 and our commercial vans.

We expect total deliveries of approximately 9,000 to 11,000 per quarter in the first half of 2026. We plan to start production of the R2 launch variant with a single shift and expect to add a second shift towards the end of the year. While we believe our gross profit will increase year-over-year, we expect the complexity of a new vehicle launch to negatively impact our automotive gross profit in the second and third quarters before becoming a benefit to our overall operations in the fourth quarter as we ramp production and deliveries. As a reminder, we believe this is a transition year for the Automotive segment's profitability.

Delivering a strong exit rate for R2 production and deliveries will be a key focus for our team. For 2026, we expect an adjusted EBITDA loss of between $2.1 billion and $1.8 billion. Our adjusted EBITDA guidance also includes a step-up in R&D spend as we accelerate investments in our autonomy road map and look to deliver LiDAR, our first RAP1 chips and limited point-to-point functionality for our customers by the end of the year. We believe autonomy will be a key fundamental long-term differentiator for our business.

We also plan on the continued growth of our SG&A, driven by the expansion of our service and sales footprint as we scale with R2. Finally, for 2026, we expect capital expenditures of $1.95 billion to $2.05 billion related to finalizing construction and tooling for R2 and normal, kicking off vertical construction for our greenfield plant in Georgia and the continued build-out of our sales, service and charging infrastructure. In closing, thank you again to the team for delivering a great 2025.

As we look forward to 2026, we remain steadfast in our belief that R2 and our technology road map will be truly transformative for our growth and profitability. I'd like to turn the call back over to the operator to open the line for Q&A.

[Operator Instructions]. Our first question comes from Emmanuel Rosner with Wolfe Research.

My first question is on the cadence that Claire, you just highlighted with the 9,000 to 11,000 units per quarter in the first half and then obviously, 62,000 to 67,000 on a full year basis. Is that 10,000 per quarter or so, is that your expectation for R1 plus EDV for this year in 2026? And then the upside in the second half would be essentially delivering the R2?

Thanks, Emmanuel. As you think about the cadence, as RJ articulated in his prepared remarks, we expect first deliveries to begin for R2 in the second quarter. Like any ramp, the number of deliveries will be rather small as you think about the Q2 impact of R2 contribution to the 9,000 to 11,000 units per quarter that we anticipate in the first half of the year.

And then as we get into the second half of the year, we expect to see the continuation of the ramp of R2, coupled with the ongoing deliveries of our commercial van as well as R1. So on a full year basis, you can think about the R1 commercial van being roughly in line with our 2025 total volumes.

Okay. And then another one on the cadence side, but more from a financial point of view, I think in the past, you had targeted, I think, by the fourth quarter of this year, some level of profitability on R2 to sort of like demonstrate essentially the potential. Is that still the expectation for this year?

Yes. As I mentioned, we expect 2026 will be a transformational year for our automotive gross profit, and we expect that both R2 [Audio Gap].

Our next question comes from Dan Levy with Barclays.

First, I wanted to start with just a question on the R2 volume assumptions, which you just talked about a moment ago. As you're going into the launch, do you have a feel for what the aggregate demand is? And maybe you could just talk to the question of your confidence on people wanting to take delivery of R2 before the new ADAS platform or hardware is put into the vehicle? How much of a current the lack of that new hardware will be on deliveries?

Dan, thanks for the question. With regards to R2, I've had chance to spend a lot of time in it over the last several months and really over the last month or so, driving our validation vehicles that are produced in our plant off of our manufacturing validation build. And the vehicle is just absolutely incredible. It's the combination of features, the packaging, the vehicle dynamics, the steering wheel, we're incredibly bullish on. And as I talked about a lot in the past, we ultimately think the market is really hungry for some choice in this segment.

As I said in my opening remarks, just the lack of choice that exists in and around this $50,000 price point has led to very high market share concentration of one vehicle. And so this is the first time there's going to be a real alternative. And this is important for folks that are in internal combustion vehicles today, midsized SUVs and looking for something that fits their form factor needs, their aesthetic needs, their packaging needs. And so we're very, very focused on putting this together. And with that said, we have a lot of confidence in the overall demand of course, that's why we leaned so much into the program and lean so much into what we're about to launch.

And just the issue of the ADAS platform, people taking it before the new hardware comes in?

Yes. With new technology, there's always -- especially for us as a business, given that we've got an enormous focus on developing new technology, there's always something new coming and recognizing that there are a lot of customers that are just waiting to get a great midsize SUV. And so given the enormous backlog of demand we have as well, the short period that we have where we'll be launching with essentially an upgraded version of our Gen 2 autonomy stack before our Gen 3 autonomy stack comes -- we don't think that's going to be a significant issue for those that want to wait for it, they certainly can and for others that are going to be excited the vehicles in a short time frame, be available prior to that.

Okay. Great. As a follow-up, I wanted to ask about partnership or licensing deals with other automakers. And maybe you could just give us a sense of the tone or tenor of discussions on licensing the network architecture to others. And you said at your Autonomy Day that one of the opportunities on your in-house processor was not only that it could be used for your vehicles, but you could also sell this to others. It's a better, what you said, bang for buck. So I know it's early days, that still isn't out and the initial units of that process are going to need to be for you. But what types of discussions are you having with automakers on potentially selling that or licensing that to them?

So as I said in the opening remarks, we've had in the first 13 months of establishing a joint venture with Volkswagen, we've testing on multiple VW Group products. And I think the true demonstration and existence proof, if you will, of the scalability of our technology in terms of being able to work across multiple form factors, different price points, different brands and importantly, be productized into a platform that can go across a large existing OEM. This relationship is really important for that. And so that's our focus. But of course, we have relationships with a broad spectrum of other manufacturers. And I've said this in the past, but I deeply believe that over the course of the next several years, every manufacturer has to make the decision as to whether or not to get to a software vehicle or they're going to develop it themselves, secure it from a third source of which we will be the only demonstrated example of having scaled this technology outside of our own products or accept that without the technology, you will lose market share. And so we're quite bullish on the potential for this technology platform, and we see it as really an important part of our portfolio going forward.

Ladies and gentleman, we are having further technical issues, please standby, we will resume the Q&A as soon as possible. Thank you. [Audio Gap].

Our next question comes from Ben Kallo with Baird.

Congrats on all the progress so far. Maybe first, can we talk about just the VW relationship and there was an uptick in revenue from that. And just if you give us a sense of how that progresses and the potential to expand the relationship or how we should think about it growing? And then the second question is just around Georgia, the DOE loan guarantee, how you're looking at that and maybe just liquidity in general as you start working on that.

Thanks, Ben. And I spoke a little bit about this in the previous response, but I understand we've had a few technical difficulties here. So at risk of repeating myself, I'll just say -- cover a few things that I said earlier. The Volkswagen relationship continues to progress. We're now 13 months since the joint venture started. We've -- with that, we've started winter testing on several different Volkswagen Group products. And of course, we're working towards the first launch of those vehicles in 2027.

And the relationship has been very, very strong. We had a great session, in fact, coincidentally last week with a broad set of the Volkswagen Group leadership team. And seeing this be used and deployed across not just vehicles of similar price point to Rivian's vehicles, but across the price point -- across a wide band of price points and across a range of form factors is really important. And it really demonstrates the scalability of the technology. And so ultimately, we're going to continue working towards delivering multiple Volkswagen Group products, but this does, of course, open the door for opportunity with other manufacturers as well.

And then to put some of the financials behind the software and services outlook as a whole, we anticipate seeing that we'll approach about 60% year-over-year growth in our software and services business, and it will be a significant driver of our gross profit outlook as well with margins that we expect to be in the mid-30% area as a whole. Then as your second question, which was on the capital road map, as I mentioned in my prepared remarks, we ended 2025 with $6.1 billion of cash, cash equivalents and short-term investments. We expect that we'll receive another $2 billion from Volkswagen Group throughout the course of 2026. There's still roughly another $0.5 billion payment associated with the original joint venture transaction as well that will happen, we anticipate in 2027.

And then as it pertains to our broader capital road map, we'll continue to remain opportunistic as well on that front. On the DOE loan question, similar to what we've shared in the past, we certainly share the President's desire to bring jobs back to the United States. We're excited to keep up our work on creating new American manufacturing jobs. We'll be adding approximately 2,000 new jobs at our Normal, Illinois plant for the ramp-up of R2, an additional 7,500 jobs at our future Georgia plant as well. And similar to the comments RJ just made, Rivian is working to help drive innovation and technology leadership in the U.S. automotive industry for consumers and also associated with our joint venture with Volkswagen Group, enabling this technology for the industry as a whole.

Our next question comes from George Gianarikas with CG.

As it relates to your guidance for vehicle sales this year, to the extent you see a strong conversion in your backlog for the R2, could you see upside to that? Or are there certain production bottlenecks that you'll have to work through towards the end of the year?

Thanks, George. The process of ramping a vehicle is something we've spent a lot of time talking about in this forum, but certainly internally, we're really putting a lot of effort on making sure we have a very smooth production launch and then associated ramp. And we often think of the plant as being the bottleneck for the ramp. But in fact, we have to remember there's hundreds of other companies that are providing components into Rivian that ultimately really contribute and are a key part of the ramp.

And ramping our supply base is something that we're very focused on and planning around. And you can only ramp as fast as your slowest part, so to speak. So with that said, we've -- as you heard earlier, we're starting with a single shift. We're bringing on a second shift that will be happening near the end of the year. And then in 2027, we'll be adding our third shift. And this has been very methodically laid out to make sure that we're ramping consistently and evenly across the supply chain. And so certainly, and as you alluded to, there's going to be a large demand backlog that we're working through and a tremendous amount of excitement for the R2 vehicle. And as more reviews come out about it and more people get exposure to it, we expect that to continue to expand and grow. It's worth noting some of the preproduction reviews that came out last week, the feedback has been universally super positive. And so we're acutely aware of that, but we are working very carefully to coordinate the ramp and coordinate the growth of output with our supply base.

And maybe as a follow-up, as you sort of crystallized your selling prices and your cost structure for the R2, can you just maybe speak to the guidance you gave at your Analyst Day last year about reaching EBITDA positivity in 2027 and your long-term vision around having 25%-ish gross margins and high teens EBITDA margins?

Thanks, George. As prepared -- as discussed in our prepared remarks, we believe that 2026 is going to be a transition year for the automotive gross profit segment. And our North Star for the normal plant is going to be getting our production and deliveries up to about 4,000 units per week. While there's a lot of execution required, as RJ just walked through from the team in order to achieve that outcome, if we're successful, we believe it would put the company in a strong position to achieve our adjusted EBITDA goals. And as we look at the broader outlook, we certainly see there being 20% gross profit target for our automotive segment. As we think about the overall contribution of software and services, there's many outcomes or licensing deals that [ Rubin ] could do that could allow gross profit to be much higher than the 25% in our end state as well.

Our next question comes from Joseph Spak with UBS.

Just a couple of questions. Claire, I know you said the second shift starts in the back half. Does the guidance contemplate like exiting the year at a full 2-shift rate for the R2? I just want to sort of understand how we should think about a jumping off point for '27.

Sure. As you can imagine, Joe, we'll be in the process of ramping up the second shift. So as you think about the exit rate of 2026, we won't yet be at full production across 2 shifts. We'll be getting there as we continue to progress all of our operational efficiencies and get the team ready to ramp up throughout the course of 2027.

And then I guess, RJ or Claire, just you mentioned more details on March 3. I'm assuming that's also when reservation holders will be invited to configure. But is there any update you could give us on that order book? And then on the pricing side, one of the things we've seen, again, not Rivian specific just to the industry and the world really is the cost side between metals and memory. So curious to sort of wonder how you're thinking about that impacting either your pricing for the vehicle or whether that's contemplated in the EBITDA guidance for the year?

Yes. So on March 12, we'll be providing the full picture around the overall portfolio of products that will exist for R2, and that will include the launch configuration, which, as I've said, is a dual motor performance variant with a premium trim. The different combinations of trim, powertrain performance and battery size are what we'll be describing in detail on the 12th. And then along with that, allowing customers to start configuring their vehicles and allows us to start getting ready to be making deliveries later in Q2.

I think important here, as you think about the overall demand profile for the vehicle, we've put a lot of time into thinking about the different combinations and recognizing what different folks are going to want and having the benefit of having lots of conversations and also the benefit of seeing what are the most popular trims and configurations in R1. And so we're really excited to go through that, but it's something that we do want to go through as -- present it as the full meal as opposed to giving little bits and pieces. So other than talking about the launch configuration, the rest of the configuration is going to be something we talk about in detail in about a month.

And then Joe, our adjusted EBITDA guidance does contemplate some of the increases that we've seen in raw material costs and the current supply chain backdrop as well.

Our next question comes from Mark Delaney with Goldman Sachs.

I was hoping to speak more about automotive COGS. Maybe you can help us better understand what led to the reduction in cost per vehicle, both sequentially as well as year-over-year. And then as you look forward, clearly, you just alluded to some of the supply chain challenges around DRAM and other input costs that are embedded into your guidance. But where do you ultimately think the R2 cost can get to? And is the 50% reduction in the BOM cost compared to R1 still the right level to think about?

Sure. For Q4, we were able to deliver $92,000 of COGS per unit, and that was about a $4,000 per unit improvement relative to the third quarter. One of the key drivers was associated with the mix shift. So we had higher penetration of commercial vans in the fourth quarter relative to the third quarter. And then beyond that, the ongoing operational efficiencies that we continue to execute across our normal operations as well that also contributed to the reduction in our COGS per unit. As we look at the full year-over-year improvement, the biggest driver that we saw was associated with the reduction in our material cost, that was both the transition for us to move fully to Gen 2 vehicles.

We also, in addition, saw a significant step down in terms of a lot of our raw material costs and importantly, a step down in the cost of our lithium prices that was another contributor for us as well as we looked over at the full year-over-year step down in terms of COGS per unit, coupled with the ongoing operational efficiencies that we continue to progress throughout the course of the year. As we look forward to R2, one of the key factors for us with R2 is the opportunity for us to have also over the course of the last year, started to see some meaningful benefit from our joint venture -- joint sourcing opportunities associated with our low-voltage electronics that we're sourcing for the R2 vehicle.

And that's really been a key enabler for us to continue to progress the material cost trajectory of the R2 product as well. And then as we approach the Georgia plant, we'll have further opportunity to drive additional synergies or efficiencies as we start to source future vehicle volumes as well that will share the fundamentals of the midsized platform as a whole. So those are a couple of the puts and takes. The other callout that I would highlight as well is we do anticipate seeing a reduction in terms of our tariffs per unit. So we didn't have the full benefit of the Section 232 offsets for the entirety of the fourth quarter. So we'll see further benefit from a tariff per unit standpoint as we progress forward, and R2 will also benefit from that in the future.

My other question was on EDV, and I understand probably flattish volumes there for 2026 based on your comments earlier on the call, but you did speak to a plan for some additional variants, including one with more range for Amazon. So maybe help us better understand when to expect that new product for the commercial segment and what that might mean for van deliveries and the broader commercial opportunity going forward?

We do expect some growth in our EDV demand in 2026. And as you called out, there's an all-wheel drive version of the van and a larger battery pack variant as well. And both of those are to help unlock specific use cases within the Amazon network. We're working really closely with Amazon in defining the requirements of those and excited to get those launched. And the relationship with Amazon continues to be very positive. And certainly, the EDV continues to perform extremely well.

Our next question comes from Chris Pierce with Needham.

As you talk about adding the second shift, then adding the third shift, can you kind of just walk through setting up hiring for these workers in the normal area? I'm just not sure if we should think about that as a barrier or a burden or just kind of -- is it already in motion? Or do you already have these and you kind of move people from one shift to another? Just kind of any detail around that, please?

Yes. Chris, thank you for your question. Hiring process is in place, is proceeding according to plan. We have enough candidates. At the beginning, it was even spontaneous candidates that wanted to work for us. So we are good from that end. There's part of the team that will populate the R2 line that is coming from the existing flows, but it's an important part as well that is hired from outside.

We have reinforced our training programs. We have even before hiring the people pre-hiring activity, just to let them know what is working in the lines and what they should expect there. And so far, we are very happy with the response of the talent pool and the people pool that we have seen there. So...

Perfect. And then just -- I guess, I just kind of want to understand, you've had the reviews this week. You're kind of flipping over the card as far as first trim and other trims in a month. And then we could see initial deliveries sometime in the second quarter. I guess I'm just kind of curious I'm just thinking about maybe Apple and the iPhone or the iPad, and it's just sort of boom, here it is, you can buy it now. I guess I'd just love to hear about why the spacing? Is there a psychological effect or it just comes down to what you can produce, when you can produce it at the plant, but just the timing of the cadence as you move towards the launch.

Well, thanks, Chris. One of the amazing things about the R2 program is there's an enormous backlog, but that does create a challenge for us with making sure essentially how do we select who receives our vehicles first and having a processor on that. And so opening up the reservation or opening up the configuration process allows us to start taking this demand backlog and organizing around when we make deliveries and who gets the vehicles first. It's not as if you could like press a button and instantly have thousands and thousands of vehicles available.

So we start producing, we are ramping production, but the demand will outpace our ability to produce. And so that process allows us to organize in a thoughtful way and learning a lot from some of the past launches we've had, how do we prioritize and how do we sequence deliveries to our broad base of customers.

Our next question comes from Itay Michaeli with TD Cowen.

I wanted to actually ask on the universal hands-free. Curious how initial feedback has been since December, how we should think about feature improvements and OTA updates this year? And maybe what you're also assuming for paid subscriptions this year?

We're really excited to talk about this. This is a huge effort within the business and autonomy and AI was, of course, focused on all the work that we're doing here. But our Universal Lands Free is really think of it as the first step in a whole series of steps that expand the capability. And so Universal Lands Free expanded the number of miles where you can drive with hands off the wheel, but eyes on the road. It's around 3.5 million miles, essentially any road with marked lanes. And later this year, we'll be unlocking the ability or enabling the ability for the vehicle to drive point to point. So you put your address into the vehicle and the vehicle navigates to that address.

And then the next steps ultimately are driving towards what we think of as personal Level 4. But between point-to-point and personal Level 4, we'll have hands-off eyes off, so you'll be able to take your eyes off the road and do other things starting first on the highway and then expanding from the highway. And then following that, we'll have our first Level 4 applications within a geofence area to start, but ultimately expanding over time.

And our view and really strong conviction is that over the course of the remainder of this decade, we're going to see autonomy go from something that today with hands-off capabilities certainly is a nice feature to have. But as we start to move to hands-off and eyes off and then ultimately to Level 4 where the vehicle can operate itself entirely on its own, including driving empty, it really creates a whole new customer experience, and we think it becomes a critical part of the purchase decision. And this will -- this is going to drive significant change in how we think about the business model. It's going to drive significant change in how consumers think about what vehicles they want to purchase.

That's very helpful. As a quick follow-up on the financials, any sense of how we should think about working capital flows this year, particularly as you go through the initial R2 ramp?

Sure. We will see working capital be an outflow of cash for us over the course of 2026. And that in part is driven by the buildup of our inventory balance associated with the launch of R2.

Our next question comes from Andrew Percoco with Morgan Stanley.

I actually just want to come back, RJ, to what you just said on autonomy really driving the value proposition and driving experience over the next few years. And I guess I'm just curious, like can you share your thoughts around whether or not there will be a retrofit opportunity for existing or new R2 customers that don't have Gen 3 with LiDAR and existing R1 customers? And any thoughts of when you'll introduce LiDAR onto R1 production?

We're not -- in terms of retrofit, this isn't something that's contemplated or planned. Certainly, there will continue to be over their updates for our Gen 2 vehicles, our R1, Gen 2 vehicles and our launch R2 vehicles. But in terms of hardware upgrades, those are not planned. The hardware upgrades that we've talked about in the past, we talked about at our autonomy and AI Day, these are going to be on vehicles in the early part of 2027.

And certainly very, very excited about those. But the capabilities and even the demo that we had at our Autonomy AI Day, which was a point-to-point demo, that's being done. That demo was on a Gen 2 of our R1 vehicles. So that's -- that will be available on any Gen 2 R1 vehicle as well as the R2 vehicles we'll be launching with.

Got it. Okay. And can you get to -- is the plan to get to eyes off point-to-point with Gen 2? Or is that something that's going to require Gen 3?

I think the important thing to keep in mind on our upgraded architecture, which is, as I said, coming in '27, is that has a few really important purposes. One, of course, is it raises the ceiling on what's possible. So it grows the opportunity to add even more capability beyond point-to-point, but it also serves as an even more enhanced part of our data flywheel where we have enhanced cameras, higher level of inference in vehicle, but importantly, we add a LiDAR, as you referenced, which turns essentially every vehicle into part of our ground truth fleet, which is really helpful for training our end-to-end model.

And so the way that the model continues to improve is we're benefiting from the thousands and thousands of drivers that are on the road and the vehicles that are on the road, pulling interesting and unique events back off the vehicles and allowing us to feed that into the overall training loop that we have for what we call our large driving model.

Got it. Okay. And just one quick clarification. When you say Gen 3 will be available early 2027, will that include R1? Or is that just still R2?

This is for R2.

Our next question comes from Edison Yu with Deutsche Bank.

This is Winnie on for Edison. Can you guys hear me?

Yes.

My first question is on the relationship with VW as it matures. I was wondering if the topic of how to best utilize vehicle data come up. And more asking this in the context of VW naturally having a much larger fleet and Rivian being able to potentially benefit from getting access to that data for training. So just curious your thoughts on that topic.

The Volkswagen fleet and what ultimately we're delivering to Volkswagen from a technology platform doesn't include our autonomy platform. So it's our embedded software platform, our topology of ECUs, including our zonal architecture, but it doesn't include our self-driving architecture.

Got it. And then maybe just on the RAP1 chip. Curious to hear your maybe longer-term inspirations for that. Is this something you think that will be limited to Rivian? Or do you envision maybe this being used by some of your partners or other OEMs and whether it could be potentially applied to nonautomotive products like [ humanoid? ]

I guess I'll answer it really broadly. This is -- when we think about our self-driving and autonomy efforts, this is an enormous focus for the business and represents our most significant area of capital investment from an R&D point of view. And so when we look at this through the lens of the next several years, we do believe that as we continue to demonstrate progress and work towards that growing capability set that I talked about before, ultimately culminating in Level 4, this is a platform that certainly beyond Rivian has applications. And so we do envision a world in which this becomes something that we can monetize through a few different ways.

We can monetize it through increased market share and growing number of vehicle sales. We can, of course, do that through new and unique business models and new ways of thinking about consuming transportation, and we can do that through selling and providing the technology to other manufacturers. Now specifically to our RAP1 processor as well as its future variants of that processor, we do see applications for vision-based robotics well beyond the vehicle. Of course, the vehicle is a great near-term vision-based robot. But even within Mind Robotics, which is a new company that we created, that is also an example of a great customer application and a great use case application for our RAP1 processor.

Our next question comes from Tobias Beith with Rothschild & Co. Redburn.

May I ask what Rivian's management's latest thoughts are on captive battery cell manufacturing and assembly are considering the recent development in the price of lithium salts. I know that this activity was contemplated at one point at your forthcoming plant in Stanton Springs.

Well, thanks, Toby. We've found great working partnerships with our battery cell suppliers and have taken a very active role in securing and sourcing some of the upstream precursor materials. So you called out lithium. That's a really great example of an area that we, from a sourcing point of view, spend a lot of time on. But being able to work with these key battery partners and leverage the investments they've made in production capacity and in their own cell construction and cell design has been really helpful for us in terms of efficiently deploying capital.

Our last question comes from James Picariello with BNP Paribas.

Can you hear me?

Yes, James. We can hear you.

Great. [ Vista ] curious on your thoughts regarding R1's potential to see additional demand from one of your major competitors announcing the end of its 2 high-end models next quarter, right? We're talking about 20,000 annualized units essentially up for grabs in the U.S. It just seems like the R1 can be a natural home for many of those buyers. Just curious your thoughts.

Yes. The Tesla Model X, which, as you said, will stop production, at least what's been said is next quarter. The Model X is a really important product from an electrification point of view, and it was one of the first more at-scale products to show customers how exciting electrification can be. And so as that leaves the market along with the Model X, it does create an opportunity. There's -- I've talked about this a lot in the context of R2, the lack of choice, but this also is true in the case of R1. And R1 as it stands, our R1S is -- I called out in my opening remarks, it's an enormously successful product in this premium price category.

So it's the best-selling premium SUV, electric or nonelectric in the state of California. And then it's the best-selling premium electric SUV in the United States and the best-selling premium electric vehicle, SUV or non-SUV in a number of states across the U.S. And so with even less choice now in that price category, it does represent an opportunity for us. But I'd just say very broadly that the overall lack of choice, and this is really true in the price category of R2, we think is an enormous opportunity for us to capture market share and, of course, provide something really exciting to customers.

Yes, makes a lot of sense. My follow-up, just for the strong gross profit contribution slated for this year, can you help dimension at all what the expected contribution might look like from VW as we think about that 60% year-over-year growth?

Sure. As you think about the Software and Services segment, roughly half of our revenue comes from revenue streams associated with our joint venture with Volkswagen Group, and we expect that to largely remain true as we look ahead to 2026 as well. And it is a more disproportionate share of the overall gross profit dollars that we earn out of the [ Safran ] Services segment as a whole.

This concludes the Q&A section of the call. I would now like to turn the call back to RJ Scaringe for closing remarks.

Well, thanks, everybody, for joining the call, and we apologize for some of the technical difficulties that we had at the start. But -- we are -- hopefully, a takeaway from this is just how excited we are about R2. As I said, I've had a chance to spend a lot of time in the car and in a variety of ways, whether it's taking my kids to sports games or loading up the back with gear, and it is just such an incredible embodiment of the Rivian brand and captures so many -- so much of the essence of what makes R1 a special vehicle, but at a price point that, as we said, starts at $45 and will allow a much larger number of customers to access the vehicle.

And so as we think about the next couple of months, we, as a company, remain incredibly focused on the launch ramp of this vehicle, along with the continued development of the technology we're building, both on the software side, which we talked a bit about, but certainly on -- also on our autonomy side. And so with that, thanks again for joining the call, and we're looking forward to a lot of folks being able to experience the R2 themselves.

Please welcome RJ Scaringe, Founder and Chief Executive Officer of Rivian.

We are incredibly excited to host everybody here today. We are in Palo Alto, which is the hub for Autonomy and our technology development teams. AI is enabling us to create technology and customer experiences at a rate that is completely different from what we've seen in the past.

If we look forward 3 or 4 years into the future, the rate of change is an order of magnitude greater than what we've experienced in the last 3 or 4 years. Directly controlling our network architecture and our software platforms in our vehicles has, of course, created an opportunity for us to deliver amazingly rich software. But perhaps even more importantly, this is the foundation of enabling AI across our vehicles and our business.

I'd like to talk about Autonomy first. The field of autonomy really started about 20 years ago. And about, let's say, up until the early 2020s, the approach was centered on a rules-based environment where a set of perception sensors would identify and classify objects and hand those classified and vector-associated objects to a planner that was built around a human-defined rules-based framework.

A few years ago, it became clear the approach to autonomy needed to shift. With innovations around transformer-based encoding and the design of large parameter models, the approach has moved to building a neural net-like understanding of how to drive instead of following a classical rules-based approach. Recognizing this massive shift in how we approach autonomy, in early 2022, we began the process of a clean sheet design to our platform. This first embodiment of this work was in our Gen 2 R1 vehicles, which we launched in mid-2024.

With this updated platform, our Gen 2 vehicles now have 55 megapixels of cameras, 5 radars and run on an inference platform that was a 10x improvement over our Gen 1 vehicles. This platform was designed around an AI-centric approach. And with the deployment of our Gen 2 R1s, we began the process of building our data flywheel to grow and build our large driving model.

Now because this AI-centric approach represents a model trained end-to-end to the millions and millions of miles driven on our vehicles, enhancing the perception platform or improving the compute is accretive to the capabilities of the model, meaning the model only continues to get better as the perception and as the compute platform improve. So you can sort of think of it like this.

If you learn to drive and you had bad vision and suddenly you're able to put on glasses and see much better and then go even further and supplement that with new perception modalities of radar and LiDAR and then your compute here metaphorically [ brain ] was expanding in capability by an order of magnitude, you wouldn't forget the things you learned, the rules of the road, how to operate a vehicle, but your ability to understand nuance, to respond to complex situations and perceive the world in environments with poor or limited visibility would improve dramatically.

Our approach to building self-driving is really designed around this data flywheel. We're a deployed fleet, has a carefully designed data policy that allows us to identify important and interesting events that we can use to train our large model offline, before distilling the model back down into the vehicle.

Now while our R1 Gen 2 vehicles and the demos some of you are going to be trying today are using our Gen 2 sensor set and of course, the associated compute platform, over the last few years, we've also been developing our Gen 3 substantially enhanced platform, and this will underpin a massive leap forward with R2. Starting in late 2026, our Gen 3 Autonomy platform will include 65 megapixels of cameras, a robust radar array and a front-facing long-range LiDAR. And at the core of this platform, our first in-house Rivian Autonomy Processor.

Now the first iteration of our in-house inference platform includes a neural engine with 800 TOPS. It's optimized to support camera-centric AI in the physical world and enables a dramatic expansion of Rivian's Autonomy capabilities. When integrated into what we call our Gen 3 Autonomy Compute platform, which Vidya will go through later in detail, it will deliver 1,600 TOPs. The effectiveness and efficiency of our in-house processor has been a core focus in its development. Our Gen 3 computer is capable of processing 5 billion pixels per second.

Now you've heard me say this a couple of times. We've designed this entire architecture around an AI-centric approach where the data flywheel of our deployed fleet helps the model get better and better through reinforcement learning. Not only does this sensor set enable a much higher ceiling than what we have in our vehicles today, it also makes the platform much better to serve in building our model. We're going to continue to see improvements on our platform.

Later this month, we'll be issuing an over-the-air update to our R1 Gen 2 customers, and that will dramatically expand the existing hands-free capability, going from less than 150,000 miles of roads to more than 3.5 million miles of roads in North America. And again, this is just a step in a series of steps. Starting in 2026, we'll begin rolling out point-to-point capabilities in which the vehicle can drive address to address. So what that means is you can get into the vehicle at your house, plug in the address to where you're going and the vehicle will completely drive you there.

Now some of you are going to experience this today in our R1 vehicles. And of course, this will be embedded in R2. Now as I described, the Gen 3 hardware architecture launching in 2026 expands the ceiling of what we can achieve. The next major step beyond point-to-point will be eyes off, meaning you can navigate point-to-point with your hands off the wheel, but importantly, your eyes off the road. And this gives you your time back. You can be on your phone or reading a book, no longer needing to be actively involved in the operation of the vehicle.

And following eyes off, the next major step will be personal Level 4. And with this, the vehicle will operate entirely on its own. This means it can drop the kids off at school, it can pick you up from the airport. It allows it to really be integrated into your life in ways that we can't even imagine and haven't seen yet today.

Now while our initial focus will be on personally owned vehicles, which today represent a vast majority of the miles through the United States, this also enables us to pursue opportunities in the rideshare space. Now beyond self-driving, we've also created what we call the Rivian Unified Intelligence. This AI backbone exists across our vehicle and across our entire business. And we've talked for a long time about software-defined vehicles, which are really the foundational building block for an AI-defined vehicle, where every part of the vehicle, the experience and everything that's happening across the vehicle is designed around AI from our Rivian Assistant to enabling our direct-to-consumer sales and service model as well as our future manufacturing infrastructure.

Now as I said at the start, we could not be more excited about what we're building, and we have a lot of details to show you here today. And with that, I'm excited to introduce Vidya to talk about our hardware platform.

Thank you. My name is Vidya Rajagopalan, and I lead the electrical hardware team here at Rivian. My team is responsible for electrical content in the vehicle, ranging from our in-house 5-nanometer silicon that you just heard about that operates at voltages below a volt to the power electronics for electric motors that operate at 400 volts and lots of things in between.

One common thread that runs across all these designs beyond the fact that it involves the transport of electrons is the Rivian ethos of vertical integration. At Rivian, we have chosen to vertically integrate critical pieces of technology that differentiate our -- that allow us to differentiate ourselves over time. We started this journey as a start-up when we consciously chose to build our ECUs in-house. Last year, at Investor Day, we shared how this journey helped us to get to an in-house developed zonal architecture far ahead of other OEMs. Today, I'm here to talk to you about our Autonomy Hardware System, which is similarly very vertically integrated.

As RJ shared earlier today, we will be launching our Gen 3 Autonomy System late next year on the R2 vehicle platform. The hardware enabling it focuses on 3 main areas of leadership, sensors, compute and the overall product integration. Well, let's start with our sensors.

At Rivian, we have a multimodal sensor strategy that provides a rich and diverse set of data for our AI models to operate on. On the screen behind me, you can see the feed from all our sensors on an R2 vehicle. On an R2 platform, much like the R1 before, we have 11 cameras providing a total of 65 megapixels of data. That is 10 megapixels over and above what we had in R1. The cameras provide an extremely rich set of 2-dimensional data and help us see the world around us.

But cameras alone have some shortcomings. They do not perform well under non-ideal lighting conditions. This could be low light, excessive light and fog. And so, much like the R1 platform, again, we still carry 5 radars: one front-facing imaging radar and 4 corner radars. By using radio frequencies, radars are able to see in total darkness while also providing the depth and velocity of objects in their path.

Our corner radars on R2 are further improved. They support a dual mode of operation, short range and long range. In short-range mode, they have very high spatial resolution, which helps us delete the ultrasonic sensors in R2. That's right. We add sensors, but we also delete them when it makes sense. And now for the first time in R2, we're adding a third sensor, the LiDAR.

The LiDAR is an optical sensor, but its strength comes from the fact that unlike the camera, the LiDAR has an active light source, enabling it to see it much better in the dark. Another advantage of the LiDAR is that it can provide a 3-dimensional view of the world unlike cameras, which we know provide a 2-dimensional view, requiring the AI models to infer the depth, which they do, but with a lot less accuracy. So in summary, camera is the main workhorse of our sensor suite, generating the bulk of the data fed to the models, but the radar and LiDAR are critical to addressing the edge cases, which would otherwise create the long tail of problem cases.

So why do we choose to use -- introduce LiDAR now? It turns out that there are 3 main factors that make this the right moment to incorporate LiDAR. They are cost, resolution and size. About 10 years ago, LiDARs used to cost in the tens of thousands of dollars. Today, you can get a very good LiDAR for several hundreds of dollars. The resolution of LiDARs has similarly improved tremendously. The picture on the left here is the data product of a LiDAR from 2016, whereas the picture on the right, it shows the data actually from our R2 LiDAR, the one we use in our vehicle. As you can see, the R2 LiDAR data is much, much richer. Today's automotive LiDARs have point cloud densities of the order of 5 million points per second, which is about 25x better than what we could get 10 years ago.

Finally, today's LiDARs are no longer the large mechanical spinning beasts of the past. The LiDAR of today is more compact and more easily integrated into a vehicle. So let us take a look at the LiDAR integration in an R2.

There you go. This is one of our prototype R2 vehicles. From afar, it looks the same as the R2 many of you have seen and come to love. But if you zoom in closer and look upfront, you can see the LiDAR. What you see is a seamless integration and no signs of the unsightly taxicab-style bump or the TRO structure that is more commonly associated with LiDAR integrations. Our studio and design teams work very closely with the supplier to shape the face of the LiDAR in such a way so that it blends in beautifully with the R2. And now if you zoom out and look at the vehicle from the side, voila!, you'd not even know it had a LiDAR. And by the way, this LiDAR integration is camera safe. It will not burn your phone cameras, so don't worry about it.

So let's move on to compute. Before we get too deep, though, it's important to address why we chose to build in-house silicon. It's a nontrivial development effort. Those who have been involved or observed chip development efforts would know that. It's time-consuming and it requires a world-class team. The reason for doing it, though, ties back to the same reasons for building our own in-house ECUs, which is velocity, performance and cost.

With our in-house silicon development, we're able to start our software development almost a year ahead of what we can do with supplier silicon. We actually had software running on our in-house hardware prototyping platform well ahead of getting first silicon. Our hardware and software teams are actually co-located and they're able to develop at a rapid pace that is just simply not possible with supplier silicon. All of this means we're able to get to market sooner with the most cutting-edge AI product.

Secondly, we understand our application and our vehicle architecture thoroughly and are able to optimize our silicon for our use case. Note, we don't just design for today's use case, but we design with headroom for the models of the future. By building purpose-built silicon, we do not carry the overhead that comes from leveraging a design that was built for some other task and repurposed for autonomous driving. We built the silicon, so we would do a really good job at autonomous driving and physical AI problems. All of this enables us to get the best performance per dollar spent.

Finally, it's all about cost. When we design in-house, we're able to get the best cost point and the best power points. The cost reductions from our design come from the fact that this is optimized for our use case, not just the chip use case, but we look at the whole vehicle use case and as well as the fact that there's a meaningful reduction in supplier margins. Now join me as we go look for the silicon inside the R2 vehicle.

Our Gen 3 autonomy computer is the next step in our vertical integration journey and features our very own Rivian design custom silicon. It is a highly integrated solution. As you can see, there is very little on the board beyond the 2 instances of Rivian silicon, power supply and passives. The hardware and software on this computer are fully designed and developed by Rivian. This computer achieves 4x the peak performance of our Gen 2 computer while improving power efficiency by a factor of 2.5.

So let's go take a look at the chip. The Rivian Autonomy Processor or RAP1, as we call it, is the first in a series of silicon built for physical AI. It is actually much more than one piece of silicon. It's a multichip module or MCM that integrates Rivian silicon and memory die. Our custom Rivian silicon is produced on a leading-edge TSMC 5-nanometer automotive process. The star of the die, of course, is a Rivian design neural engine, which is capable of 800 sparse in 8 TOPS. TOPS stands for 1 trillion operations per second and is a common measure used to assess AI performance.

The chip was also designed with the intent of providing different cost and performance points. We can put multiple RAP processors together in a system, and they can talk to each other via custom high-speed link we call RivLink. So this gets fun. Let's take the lid off RAP1 and look under it. What you see is the RAP1 SoC in the middle, surrounded by 3 memory die spread across 2 sides. This allows for 3 independent LPDDR5 channels, but more importantly, allows for very tight integration between the SoC and memory, enabling a very clean data eye between them, which in turn then enables high memory bandwidth.

With RAP1, we're one of the first to introduce multichip module packaging for high-compute applications in automotive. This is not to be confused with systems in packages or SIPs, which have existed in automotive for a very long time. So it is well known that memory bandwidth is key for AI applications, and this tight coupling enables us to achieve a net bandwidth of 205 gigabytes per second. The MCM design also enables us to significantly simplify the design of the PCB. The PCB that it sits on no longer has to accommodate DRAM chips with critical timing constraints, which means it can be smaller, simpler and implemented with fewer layers, all of which results in a meaningful cost reduction. In summary, using an MCM style package enables us to achieve higher bandwidth and lower cost.

The SoC itself is designed to solve the needs of autonomous driving looking ahead. As mentioned earlier, the star of the show is a Rivian design neural engine capable of 800 intake TOPS. In addition to the neural engine, the SoC has a plethora of other blocks that are required to complete the system. The Application Processor Complex is implemented using 14 power-efficient Arm Cortex-A720AE cores. This allows us to leverage the rich open source software ecosystem that comes along with Arm processors. We will be the first OEM to introduce the Armv9 compute platform for automotive using the Cortex-A720AE in production vehicles.

In addition to an application processor complex, an SoC for autonomous driving applications needs a high availability safety island and compute that is real-time capable. Our SoC implements both a safety island and a real-time processing unit, which are built using 8 Arm Cortex-R52 cores. And finally, we have all the other pieces you would need for sensor processing, including an image signal processor, encoder, GPUs, et cetera.

The Rivian neural engine itself is designed to implement state-of-the-art deep learning models for perception control and planning. It is flexible and supports multiple -- supports mixed precision data formats. The neural engine has native support and hardware for the latest and greatest in AI model technology for inference. An inference chip today must support transformers and support them really well, and that is what we do. We also include support for all types of attention such as multi-headed attention, deformable attention and more. But we don't just implement transformers, the hardware has a host of other capabilities.

Some examples include support for nonlinear functions such as softmax. And of course, we do simple networks such as CNNs. We also have special hooks in the hardware to support LiDAR and radar processing, both of which can be very unstructured unlike transformers and CMMs. Earlier, I talked about designing an MCMM package with a view to optimizing for memory access. Well, we didn't just stop there. We looked at memory very holistically. Our neural engine, for example, supports weight decompression as another way to relieve the pressure on memory bandwidth. And we don't just enable running one model at a time, we can support the concurrent execution up to 4 models at any given time.

All of this would be irrelevant if we didn't have the software and tools to actually exploit the hardware. We made a significant investment in the development of tools and a middleware stack that can exploit the power of RAP1. The entire software stack is fully developed in-house. Our in-house tools include an in-house compiler that can take standard models and generate code targeting a neural engine. We also support profiling tools that can help users optimize their code.

And finally, we have an in-house middleware stack that enables us to write application code that is target agnostic. We use that same middleware stack on our Gen 2 hardware platform, and we will be using it again on our Gen 3 platform. So what makes silicon for physical AI different from general silicon targeting inference is the importance of functional safety. RAP1 was designed from the get-go to factor in functional safety in every block of the design.

We adhere to the ISO 26262 scheme for risk classification, which is also called Automotive Safety and Integrity Levels, which is a mouthful, which is why most people call it ASIL. Every block is designed an appropriate ASIL level based on the scheme and then hardware and software are implemented to ensure that the level is achieved. Even our chip-to-chip interconnect, the RivLink is protected using the scheme.

So in some cases, it means that you actually put an extra redundant hardware in the chip, which is -- does the same function twice and you cross-check the results. In some other cases, it means you put ECC on memories instead of parity, which a lot of other chips will do. So we have really a lot of hardware hooks and bells and whistles to make sure that this chip is really functionally safe.

In addition, we also have software -- it doesn't stop with the hardware, we also have software that runs on the chip when the chip is actually working in the vehicle. We have software that runs at [ KION ] to make sure the chip is still functionally safe and it runs periodically to complete the whole solution. The RAP1 chip is not meant to be just one incantation, it's -- one instantiation, it's really designed to be scalable.

While the first instantiation is a 2-chip solution targeting Autonomy in the R2 vehicle platform, it can be easily extended to solve other physical AI problems such as in robotics. It can scale down to a single chip solution for low cost or scale up to multiple chips for more performance. RivLink was specifically designed to allow multiple RAP chips to talk to each other via a high-bandwidth, low-latency interface. At data rates of up to 128 gigabits per second, RivLink allows sensor data from one SoC to be seamlessly shared with other SoCs. The scalability doesn't just end there. RAP1 was designed to also be flexible in configuration. While the system to be deployed in R2 is liquid cooled, we have demonstrated that this can be configured as an air cooled system.

I'm happy to share that we have successfully demonstrated that our silicon is robust and meeting the performance goals we set out at the start of the project. While peak TOPS are useful to indicate the capability of the hardware, a more useful measure is perhaps the ability of the system to process sensor data. We have shown that our third-gen Autonomy Hardware System is capable of processing 5 billion pixels per second of sensor data.

We are very proud to be at the leading edge of multi-modality sensing and to be continuing our trajectory of vertical integration with our RAP1 chip and Gen 3 autonomy computer. We expect that at launch in late 2026, this will be the most powerful combination of sensors and inference compute in consumer vehicles in North America.

We are now actively testing the silicon in systems and vehicles. For those of you attending this event in person, you'll get a chance to see some of our subsystem test box that test the entire hardware-software configuration. We have also integrated the hardware into our R2 vehicles and are continuing to test it extensively. I will now hand it over to James, who will show you how his team is continuing to improve the Autonomy experience for our customers and how he plans to harness the power of RAP1 to make Autonomy better. Over to James.

Okay. Thanks, Vidya. So Vidya just discussed all the amazing autonomy sensors and compute that we'll have on R2. And now I'll go into detail on some of the software that runs on them and powers the Rivian Autonomy platform. Firstly, our large driving model is trained end-to-end for millions of miles of driving sequences collected across our fleets. That's directly from pixels, radar returns and LiDAR points to trajectories. This large driving model uses state-of-the-art techniques based on transformers, autoaggressive prediction and reinforcement learning that turbocharges our velocity by allowing us to leverage innovation from the world of large language models.

It's also built entirely in-house, and this gives us unprecedented flexibility in being able to change all parts of the stack. So that doesn't -- that means we don't need to coordinate with other Tier 1s and Tier 2s to make changes. Consequently, our features improve with every update.

Finally, and most importantly, the Autonomy platform is built on a data flywheel where growth in vehicle fleets and feature adoption drives improvements in autonomy that compound over time. So let's look under the hood now and discuss the data flywheel in more detail.

We'll start with a multimodal onboard model that runs on every customer's vehicle. And the goal for our onboard sensing stack isn't just human level, it's super human level, and multiple modalities enable that, allowing our vehicle to see way beyond what a person can. By end-to-end training, the sensor data is early fused into a singular world model, a system where the sensors complement each other. They don't fight against each other.

Just like being able to hear can make you a better driver, multiple sensors can make Rivian autonomy better, enabling enhanced precision and more confident predictions. And with more sensors comes richer and better fidelity data. More sensing modalities allows us to achieve the same level of accuracy as a unimodal system, but with much less data or to surpass the unimodal system with the same amount of data. So it's a very efficient approach. Let's see how this works in practice by visualizing the output of early fusion.

So of course, we start with the cameras. Now as Vidya mentioned, our cameras are really good. Some of the highest combined megapixel counts and dynamic ranges of any vehicle on sale today. And what you can see here is that when cameras clearly sense things, the system works very well. In fact, cameras alone can handle most autonomy tasks most of the time. But for full autonomy, most of the time isn't enough. Autonomy needs to work all of the time, on a moonless night, in the snow, and here in the fog. And in those cases, cameras alone don't cut it. If we can't sense something, we can't expect the system to handle it.

And so we add radar to the mix. This is where we are with every Gen 2 R1 vehicle today. You can see that we're now able to detect much more. The system can detect more occluded objects, can assign better depth to objects and is better at estimating object velocities. The confidencies and redundancies are also much greater than with a camera-only system. But to unlock full autonomy, we need to go further. Adding LiDAR creates the ultimate sensing combination. It gives the most comprehensive 3D model of the space the vehicle is traveling through.

And as Vidya showed previously, the combination of all 3 sensors identifies more objects and can detect things more quickly. This trinity of modalities enables Autonomy features that RJ was mentioning, such as eyes-off driving and personal L4 by increasing perception quality, safety and redundancy.

Now our onboard network is designed from the ground up to flexibly and incorporate new modalities and new sensors. And together with our in-house silicon team, we're co-designing this network to run optimally on our chip. So over here, you can see where the sensors and modalities are fed into the model. Each pixel, each radar return, each LiDAR return is encoded, projected and then combined into a geometric feature space shown here in the center. And this is where the fusion happens, optimally and automatically learn through end-to-end training. There's no extra complexity added. There's no handwritten rules that need to adjudicate. The network has figured out the best way to combine this information.

And so what we're visualizing here are the semantic projections of these fused feature maps. And although this space is very abstract, humans were never really designed to see it, you can already see elements here such as other agents and lane lines showing up. So now this whole fuse sensor is fed into our transformer-based decoders to produce the well model. From the same input, the network is trained to generate all of these different outputs for the world around the vehicle.

So that includes other objects and agents shown here on the top left. It also includes dense 3D occupancy to handle short-range maneuvers and narrow negotiation. And here's where we estimate the local map around the vehicle. Note that this is quite different from typical robotaxi efforts where the map is pre-generated offline and then localized online. Those maps are expensive to generate and hard to maintain. But just like a human driver can navigate a road they've never seen before, our local map is produced and accumulated directly from what the vehicle perceives.

And in the bottom right here, finally, we have estimated trajectories. These represent the model's best estimate of how to proceed through the scene. This output will be a key technology enabler for point-to-point driving, and I'll discuss more on this piece later.

So now we're moving on to the next stop in our flywheel, the Autonomy Data Recorder. This is the system that turns real-world driving into data. Essentially, our entire Gen 2 fleet becomes a huge queryable dynamic database of driving scenarios. The data recorder runs trigger code that can far off any set of signals seen by the world model. Jaywalking pedestrians, red light runners, large animals in the road, all of these cases are examples of cases which you can mine with triggers.

We can also run more general triggers such as finding divergences between the human-driven trajectory and our predicted trajectories. These might indicate areas, for example, where the model could be improved. We can even push new triggers live to our fleets outside of the usual OTA cycle. This allows us to capture the data we need on demand with minimal turnaround time, greatly speeding up development. That's a huge driver of developer productivity. As soon as an engineer wants to find more scenarios of an event, they can mine for them immediately. And because ADR is so selective, it's also very efficient. The vast majority of boring driving data is never captured, never uploaded and never trained on.

Now once the trigger fires, all the sensor data before and after the event is captured, tagged, compressed and uploaded. And that data is then immediately available to engineers. These scenarios can be used for model training for evaluation or for replay through our simulator. Here, you can see examples of scenario clusters found automatically by our ADR system. We have examples of environmental conditions such as dusk at night. We have examples of map-based scenarios such as tight turns and mergers and also agent-based situations like animals, bike racks and semi trucks.

And after upload, all of these curative scenarios are immediately available on the Rivian Cloud. So as the feet expands and adoption increases, the size of our knowledge base is growing and compounding. From next year, this growth will be obviously further accelerated with the additional volume of R2. Now all of this data is stored securely, and we don't associate any sequences with your VIN, and if you select it, your home or your place of work. And through ADR, every sequence is already tagged without further processing.

Finally, because we store all sensor modalities, the data is incredibly rich and complete. This allows us to auto label most sequences using large off-line models, which will be too slow to run on board. In fact, the vast majority of our training data today is auto labeled. That's massively more efficient than using human annotators.

So now let's talk about ground truth fleets. You may have seen other autonomy providers, ground truth vehicles. They all typically have multiple nonproduction sensors such as LiDARs and other things strapped to the roofs and sides of the vehicles. And these fleets are incredibly valuable for training perception systems. The LiDAR data is so crisp. It's essentially used as a ground truth that is used to train the other production sensor sets. But because they're prototypes, these fleets are typically small, numbering the 10 to 100s, represented by the dots on this slide. In contrast, for the LiDAR-equipped R2, every vehicle will become a ground truthing vehicle. That's orders of magnitude more data than other OEMs. It's an incredible force multiplier for better and richer training data that massively accelerates our progress.

So let's see how we use all of this data to benefit our customers. This happens in the Large Driving Model. The Large Driving Model or LDM is an end-to-end model from sensors to driving actions. And it's based on many of the same technologies used in large language models. So LDM uses neural net transformers for processing, just like with LLMs. And the large driving model uses tokens for training, also just like LLMs. But instead of thinking about these tokens as words, there are actually small parts of trajectories that are jointly predicted and assembled together. And the large driving model also uses reinforcement learning, just like state-of-the-art large language models.

But here, instead of aligning the output with human values and intentions, we align the large driving model output for safe, performance and smooth driving. Because LDM is such a close cousin to an LLM, we can reap all of the advancements, investments and innovations being made in improving generative AI and can apply them directly to our driving task. This makes the LDM incredibly cost efficient to develop.

So let's do a deep dive into how LDM is trained by reinforcement learning. Over here, you can see the sensor data from a scenario. Here, we're approaching a stop sign. And that sensor data is fed into our transformer base encoders behind me. Then we sample multiple trajectories from this model, token by token and trajectory by trajectory. And the different tokens shape the trajectories in different ways. Once we've sampled all these trajectories, we then need to rank them. Now the one on the left here is actually the most human-like. The vehicle slowed almost to a stop, but then rolled it. A lot of our Rivian data is kind of like that. The one in the middle here, they're clearly stopping too soon. And the one on the right is just right. We're stopping behind the line and correctly following the road rules.

So here, you can see 3 different trajectories that have navigated this stop intersection. Now what we're able to do is apply our road rule rankers that can then say the third here is the optimal trajectory and then we reorder them. And then through back propagation, the model is trained to produce more of these types of trajectories in similar scenarios in the future. Now that's obviously highly simplified and you're just looking at one scenario here. But imagine this process running millions of times a second across millions of scenarios with a whole database of road rule costs and losses. And that's how LDM is trained.

And we can then distill this model into one that we can run on board. All of this work results in new models, continuous enhancements, refinements and new features that we continuously deliver to our customers. But how do we know we can release? We built a cloud-based simulator that runs the whole autonomy stack through millions of miles of real-world scenarios on every release. And that allows us to measure safety, comfort and performance in a statistically significant way without having to manually drive those miles. We also have a capability we call apprentice mode.

And before we release features, we can launch them in the background of a previous release. We can then monitor the performance of that new version compared to the human-driven miles, but also compared to the previous version of autonomy. That allows us to do an even bigger evaluation in the tens of millions of miles. And so through simulation and apprentice mode, we can rapidly build the confidence we need to ship new features and enhancements to customers.

Because the system is developed entirely in-house, we can update any part of the stack from the lowest level camera drivers all the way to the highest level motion planning code. That means that the whole stack is always improving with every release, and we have a feature road map that stretches to the highest levels of autonomy.

Now when we surveyed customers this year on the autonomy capabilities they wanted the most, the answer was resounding. They wanted more road coverage for hands-free highway assist. Now previously, we supported 135,000 miles of divided highways. But as RJ mentioned, our map today is about to grow.

Universal Hands-Free unlocks over 3.5 million miles of hands-free driving on roads across the U.S. and Canada. If there's a painted line and it's clearly marked, you can now drive hands-free. Universal Hands-Free will be part of our paid tier bundled into one simple package, Autonomy+. It's a onetime fee or you can pay month-to-month. And Autonomy+ features will be available to all Gen 2 customers for free until March next year.

And this is just the beginning for Autonomy+. We have many exciting features on the way, such as point-to-point, automatic parking and enabled by the LiDAR in R2 Eyes-Off. As our fleet continues to grow, as our adoption continues to increase, our data flywheel will continue to grow. And we've been thinking about this as a circle, but in fact, the system is better on every orbit. So a better analogy is an upward Helix, continually improving and compounding on itself.

And with that, I'd like to hand over to Wassym to discuss some of the other improvements being made in AI here at Rivian.

Thank you, James. We have made significant progress in our AI-enabled autonomy stack. But as James said, it doesn't stop here. AI runs through the core of everything we do. It's a profound platform shift, which changes our product and everything we do at the company from the way we design, we develop, we manufacture and we service our cars. This is all made possible by the Rivian Unified Intelligence, a common AI foundation that understands our products, our operations as one continuous system and personalizes the experience for our customers. So how does it work?

We revamped our vehicle operating system to be AI ready. We developed an in-house multi-agent, multi-LLM, multimodal intelligence platform. The platform is built on a robust data governance framework with security and privacy as main tenets. We have a suite of specialized agents. Every Rivian system from manufacturing, diagnostics, EVR planning, navigation becomes an intelligent node through MCP. And the beauty here is we can integrate third-party agents. And this is completely redefining how apps in the future will integrate in our cars.

We orchestrate multiple foundation models in real time, choosing the right model for each task. And we support memory and context, allowing us to offer advanced levels of personalized experience. And the architecture is natively multimodal using audio, vision and text through the same unified layer. The beauty of our architecture is the seamless integration between the cloud and the edge.

Edge AI with an embedded small language model allows us to achieve higher levels of performance, lower latency and the best conversational experience. And wait until the R2 comes. R2 will have close to 100 TOPS, Edge AI fully dedicated to in-cabin experience. This will allow us to move most of the intelligence workloads from the cloud to the edge, powering an in-cabin AI experience fully available when the car is offline.

The Rivian Unified Intelligence is the connective tissue that runs through the very heart of Rivian's digital ecosystem. This platform enables targeted agentic solutions that drive value across our entire operation and our entire vehicle life cycle. Let's start with the factory. Our diagnostics agent is the ultimate example of unified intelligence in action. It instantly connects real-time telemetry from vehicles on the assembly line and allows us to validate quality at production, identifying changes needed before the vehicle leaves the factory.

The same unified intelligence is fundamentally helping us redefine service. Because the platform is grounded in real vehicle data, every Rivian technician is now being empowered by AI systems trained on live software data, service manuals, repair histories, electrical diagrams and supply chain logistics. This is accelerating service repair time by hours, helping us to dramatically improve technician efficiency. And it doesn't stop with our technicians, the same platform that will enable in the future our customers to self- troubleshoot and resolve minor issues directly from the Rivian mobile app and from your Rivian car.

Now let me tell you more about the in-vehicle experience. This architecture will fundamentally reshape how we all interact with our Rivians. Today, I'm very excited to announce the Rivian Assistant. As you see from the beautiful wave behind me that our UX team has designed, the Rivian Assistant is fully integrated into the user experience and our in-car operating system. It's designed to understand you, your vehicle and the context you're in. And the Rivian Assistant will be available for all Rivian Gen 2 and Gen 1 customers in early 2026.

Now rather than tell you about all its features, we'll take some risk here, and then we'll do a live demo from the beautiful R1S Borealis, which is over there. So Oscar will be our main driver today. Oscar is the product manager behind the Assistant. Oscar, are we ready?

Yes, I'm ready. Thank you, Wassym. Hello, everyone. Let me show you what the Rivian Assistant can do. To initiate the Rivian Assistant, you can either hold the left steering wheel button or just say, "Hey, Rivian."

The Assistant is not just an integration of a chatbot on top of the vehicle UI. We built an agentic framework, allowing us to integrate into the larger ecosystem and bring your own digital context to the car. We started with Google Calendar. We had a ton of fun collaborating with the Google team on this project. Oscar, can we see that in action?

What's on my calendar today? What's on my calendar today?

You have 2 events today, call with Tim from 2:00 p.m. to 2:30 p.m. and meet up with Wassym from 3:00 p.m. to 4 p.m.

The agentic integration allows us to not only connect with your calendar and we did, but also take actions and manage it. Oscar, can you show us that in action?

Can you move my call with Tim to 5:00 p.m.?

I've moved your call with Tim to 5:00 p.m.

As you see, the same action would have probably taken me multiple taps and clicks and swipes to get to the same result. The Assistant can help you control your calendar in a much safer and easier way. And Google Calendar is just the beginning. The platform will expand to many more applications and many more third-party agents as they become available.

Beyond the agentic integration, our AI platform can blend your personal context into your vehicle context. In this case, the Google calendar agent is connected to other vehicle applications. Oscar, can we see a live example?

Let's go to my meet up with Wassym.

Navigating to Ferry Building. You will drive for 55 minutes and arrive around 10:50 a.m.

And the AI integration goes much deeper than navigation. Because this is an AI native operating system, it can connect with all vehicle apps, including our customers' favorites, EVR planner or drive modes. Oscar, can we see that in action?

How much battery will I have when I get to my destination?

You will have 67% battery remaining, which is about 231 miles of range.

Can you switch to a more efficient drive mode?

As you see, Oscar did not have to specify conserve mode. This is the future of vehicle UIs. The assistant allows user to perform use cases without knowing the exact vehicle command, without knowing where they are in the different menus in the UI, making it way easier for every user to interact with your Rivian. Oscar, can we see another example?

Can you make the seats toasty for everyone except me?

As you see, all seats, except the driver's seat are warmed up. Imagine the possibilities that this opens up. The Assistant takes the vehicle experience to the next level. Instead of having multiple UI commands, multiple taps on the touch screen, you can perform the whole task with just one natural language command. And one of the features that our community has requested, and I promise that we will get it, is messaging. But I really wanted to get messaging right. So let me text Oscar. I'm getting a call right now. Lots of text, that people are seeing me on the live feed. Thank you.

Read my last message.

From Wassym. "Hey, I'm nearby. Can you find a good restaurant near the Ferry Building? Let me know." Do you want to reply to Wassym?

So we did not only want to stop at reading your message even with this beautifully integrated UI. The messaging app with this new AI platform is fully integrated into the vehicle operating system and has access to every single application and control.

Oscar, can we see an example?

We're hungry. Can you find some restaurants near my destination?

I found Terrene about 36 miles away in San Francisco. It has a 4.2 star rating. Would you go like to go there or explore other options?

Actually, can you send a text message to Wassym and show him the top 3 options from this list? Ask him which one he wants to meet up at and include my ETA.

Would you like to send message [indiscernible]; two, Eclipse Kitchen & Bar; 5 Embarcadero Center, San Francisco, California; three: Super Duper Burgers, 98 Mission Street, San Francisco, California. My ETA is 10:53 am to Wassym.

Yes, send it.

Received. And Oscar, while I appreciate the invitation, I think I have something else to do right now. You just saw the difference that native integration makes. The Assistant has memory, has context. It remembers the full story, who you're talking to, where you're going and what you just searched for. And then it puts everything into a perfect message.

What you've witnessed today is more than just a new voice assistant. This is a peek into the Rivian Unified Intelligence platform that powers the new foundation of Rivian's digital ecosystem. The gap between software-defined vehicles and traditional architectures is getting exponentially wider with AI. Rivian is uniquely positioned to move from a software-defined vehicle and bring to the world an AI-defined vehicle.

With this, let me welcome RJ back to the stage for some closing comments.

That was so much fun to watch. So much time and effort have gone into building the platforms, designing the architectures; of course, building the teams, growing the teams, organizing the teams, all the work that goes into these really complex systems. And I often describe it as if you're building the plumbing. And if you're building a house, you don't start with the finished house. It takes years of time of planning, you then have to do foundation work, you then have to do wiring and plumbing that go into the house. And then at the very end, it all comes together.

And so when you saw our work that we talked about on our in-house processor, this is something that has been years in the making. And the amount of effort and the amount of time that's gone into it. And by the way, the amount of effort that went into this not leaking, which is amazing, is just so inspiring. And I spent some time last night with the team talking about this right before we're about to show it today. And one of the lead engineers looked at me and said, "Boy, this is -- we've been working on this for years. And I haven't been able to talk about it. It's so cool. Tomorrow, I can start to talk about what I do every day all day long."

But between the work that we put into the processor, the large driving model that you heard us all talk about, how that feeds our data flywheel and this large flywheel approach to building a data set that continues to improve our model. And then as you just heard from Wassym, all the work that went into first building a software-defined architecture, developing and building all the electronics that go into the vehicle and then using that as the foundation for enabling an AI-defined vehicle. This is coming together. You're seeing the house start to form in front of you.

And what customers are going to see on our Gen 2 R1 vehicles starting very soon is a lot of these features. As I said later this month, we're going to be growing the amount of miles you can access with Universal Hands-Free from just under 150,000 to 3.5 million miles, 2026 point-to-point navigation, shortly thereafter that, Hands Off, Eyes Off. So we're very, very excited, and we appreciate all of you being here today.

Now for those that are here, we have demos. I know there's a lot of people here, so not everybody will get through a demo. But for those that are doing demo, you'll get to see the point-to-point navigation, the work that's gone to that. We have a bunch of great displays that show some of the hardware. But for those that aren't here, we appreciate you listening along, and we appreciate your support and enthusiasm for what we're building.

Thanks, everyone. See you later.

Okay. Thanks, folks. As we continue day 1 of the Barclays Global Autos and Mobility Conference. I'm Dan Levy. I lead U.S. autos research coverage at Barclays and very pleased to have with us Rivian, leading EV automaker, leading maker of software-defined vehicles, 1 of the 2 software-defined vehicle makers in the West or leading on this front. Very pleased to have with us Claire McDonough, the company's CFO; as well as Chip Newcom, who's the company -- who's leading IR.

So we're going to go through a series of fireside chat questions. And then at the end, we'll have time for Q&A. Anyone who has questions can also e-mail my colleague, JR Young, [email protected]. You can ask them anonymously. So with that, Claire, welcome. And I would all urge you to look, there's a good Detroit News article about Claire's career trajectory. So from pastry chef to CFO, interesting trajectory.

Thank you.

So I want to actually just first start because you have a big event coming up. You have your AV AI Day on December 11. So just give us a sneak peek of what we can expect.

Sure. Well, first off, thanks so much for having me here. We're going to be live streaming our Autonomy and AI Day event broadly. So everyone has the opportunity to tune into what -- the progression that you'll see from Rivian disclosed as part of the details of the day. And our objective is to both demonstrate the progress that we've made to date at Rivian through first, the transition from our first-generation autonomous programs to today, we're utilizing really a fully in-house camera suite, sensor suite that's feeding all of the data and inputs that goes into the Rivian large driving model that allows us to have an accelerated rate of improvement across our autonomous offering.

So what you'll hear about is both a hardware road map for the future, software trajectory for the future, a lot of the inputs in terms of the data advantages that a vertically integrated player like Rivian that's controlling both the hardware and software has in store. And then I think the piece that sometimes does get missed as you look at our vehicles just sort of point in time from a feature standpoint relative to what else is out there is where is Rivian on the slope of the curve.

And that's one of the areas where we've seen truly rapid acceleration of improvement on our autonomous road map with every single monthly over-the-air update that we provide our vehicles, again, providing over-the-air updates for our software features that feed our autonomous road map. So you'll see and learn a little bit more about what's coming next in terms of the feature development and even some near-term more visible milestones as well.

A lot to look out for.

A lot to see.

Great. Okay. More near term, I want to go back to -- you had your 3Q results recently. And I think what struck us as really maybe the most noteworthy piece of that result was the profit per unit. So it's still negative, but this was the best ever gross profit per unit that you've ever posted. And I know there were some moving pieces in there on EDV versus fixed cost absorption. But maybe you can just talk more broadly right now about the gross profit trends we've seen on the current lineup, R1 and the vans and what the future trajectory is? And does this give us any indication on what R2 can shape up to be?

So for everyone's benefit, we reported roughly $96,000 of cost of goods sold per unit delivered in the third quarter. And as we think about that as a baseline, once the R2 program is launched, we'll have the added advantage point of having significant fixed cost leverage for our existing programs that improves the financial health and profitability of the R1 program and commercial vans, but also importantly, and we have spent a lot of time talking about the underlying unit economics of R2, which has roughly half of the material cost of an R1, but importantly, significantly below that as we think about the non-cost of goods sold or nonmaterial costs that go into our cost of goods sold as well.

Are we seeing right now in the numbers the benefits of that changeover from Gen 1 or Gen 2 to R1? And have you -- I think on our numbers, it looks like you flipped the script on now the vehicles are variable margin positive. Are we seeing that playing out?

The R1 program is variable margin positive. The commercial vans have been variable margin positive for a while now as we made some significant advancements in terms of our battery cell chemistry and drive unit technologies a couple of years ago for the commercial vans. But we're seeing all of the renegotiated costs come into play from the switch to our Generation 2 R1 program, both from a commercial negotiation standpoint, but also importantly, all of the next-generation technologies that are adding to some of the structural cost advantages that we see with R1.

Okay. I want to double-click on a comment you made on R2. And I think this is where there's been a lot of attention. So the BOM costs, right? So BOM being roughly half of R2 of what it is for R1, the non-BOM costs being less than half, but in that ballpark. What is your line of sight on this? And how do we get comfortable that this is going to play out?

So the line of sight that we have on the material costs are driven by the contract terms that we have with our supplier partners, which today, we're -- shortly by the end of this year, we'll be starting our manufacturing build process. So that would be building R2s in our manufacturing facility on our manufacturing lines with production intent parts. And so it just shows you how close we are to getting towards more commercialized serial production in the first half of 2026. So it's a lens into the visibility we have into each of those respective contracts.

The other part of the equation on the non-BOM COGS, so to speak, is driven through the process engineering that we've gone through to understand how many employees in each respective shift does it require for us to produce the part? How do we think about the staffing levels for each location. So there's a very high degree of fidelity as we do a lot of simulation work on our manufacturing lines to simulate the production process and the labor as part of that process.

Walk us through the trajectory to get to positive contribution margin. And then eventually, you targeted exiting 2026 at total gross margin positive. Is the story here -- I mean, maybe you could just walk us through the fixed versus variable costs. If it's fair to assume that the fixed costs aren't increasing all that much and you've got the contribution margin piece figured out, is this then just a function of volume? So walk us through that fixed versus variable dynamic and the path to gross margin positive.

Sure. With any new launch, there is inefficiencies in terms of the overhead staffing levels, you flip the switch on all of a sudden, you now are depreciating new assets into your cost of goods sold as we unlock the first commercial production for R2. And so in the initial quarters of the ramp, you'll see that be a headwind to the business. But very quickly, as we continue to progress the production ramp and have the ability towards the end of the year to add a second shift of operations onto the R2 line, that's where you see the opportunity to very rapidly get to profitability with the R2 program.

R2 also benefits from the fact that we're introducing the product into a running factory as well. And so the same way that R2 benefits R1 and the commercial van, R2 also benefits from their existence and volume as well as we think about this being a lower level of headwind or lack of fixed cost absorption relative to if it was in a fully owned greenfield facility just dedicated to R2 production.

Okay. And you mentioned it briefly, but just the cadence of what we should expect on the ramp. There are going to be some inefficiencies, one line, which implies roughly 50,000 units of annualized capacity. What is the cadence on that ramp? And what's the trajectory over time to get to the full 3 shift production?

Sure. The overall installed capacity across 3 shifts of operation is 155,000 units. And so over the course of 2026, we'll start with one single shift. Part of this is to also ensure that our supplier partners are ready to scale and ramp as quickly as we would want to when we add the second shift of operation on. And we expect to be in a position to add the second shift, as I mentioned, in the second half of 2026, and then that will set us up to continue the progression of ramping up the second shift with the opportunity to add a third shift in '27.

Okay. Great. Just broadly on the economics of R2. The BOM is fixed, right? That's sort of -- that's been in place for a while. But we've seen obviously a lot of changes in the industry that will impact probably the way that you're getting profit in terms of -- and the economics that maybe you've planned out for the vehicle. So be it no EV tax credit, no reg credits or little to no reg credits, there's some tariff costs now. What are the factors that are within your control that you can modify, be it on trim configurations, pricing preferences, I don't know if there are any cost considerations. What is in your control to mitigate maybe some of those regulatory or macro industry factors?

Our philosophy and approach has always been to provide a vehicle that is incredibly compelling from its overall value proposition in the market relative to combustion engine vehicle comparisons, other EVs in market as well. So we think that R2 embodies that in spades, given the R2, I have had the advantage of being able to drive the R2. It is incredibly fun to drive, and we can't wait to get many of you all here behind the wheel in 2026 as well to experience it for yourselves.

But part of the philosophy and approach for more of a mass market price point vehicle is also centered around how do we unlock the largest addressable market possible for the business. And we do that by a focus on how we continuously reduce the cost structure of the vehicle with the material cost being the largest component of our cost of goods sold as well.

So that's a key area of focus for us as we think about the opportunity to unlock our base price variant, which is -- sits well below the average new vehicle price in the U.S., which is centered around $50,000 today, and our base price will be at roughly $45,000. And so even without some of the IRA benefits or credits, our intention is always to give more customers the opportunity to say yes to Rivian.

Can you talk about or unpack the tariff side of it, which on the earnings call, you mentioned had been running at -- it's running right now at a couple of thousand dollars per vehicle, but with the revisions on policy, it gets you down to a couple of hundred dollars. Maybe what are some of the puts and takes? And is there maybe more opportunity if there's further changes on policy to further narrow those pressures?

Sure. One of the biggest changes from a policy standpoint, which is especially beneficial to a vertically integrated player like Rivian was the expansion of the classification of what is a Section 232 automotive part. Because we're very vertically integrated, we buy a lot of direct materials, which are not classified as automotive parts. And so the modification allows us to now capture really the entirety of the parts that we're purchasing as automotive parts outside. And so the areas where we have some exposure today are largely centered around steel and aluminum tariffs and some of the IEPA tariffs that are in place.

And as we look forward, we're always looking for opportunities for us to drive further cost efficiency, whether that may be moving manufacturing locations from our suppliers to a different geography and understanding the inputs that it can have for Rivian from an overall cost perspective.

And I assume that over time from a battery, even though you're sort of insulating that right you have supply on batteries, over time on R2 because that's going to be localized cell supply, that should also be relatively nominal on the tariff front?

Right. So in the longer term there, we have had ample headwind -- or sorry, not headwind, headroom in our -- the fact that we have the opportunity to offset 3.75% of our MSRP on the vehicles with offsets.

Can you help us understand on the reg credits? Is this a temporary air pocket? Or is this something for the next few years, we just shouldn't assume much in the model on reg credit contribution?

Since we don't have a crystal ball on some of the policy dynamics in play, we wanted to ensure that we were being appropriately conservative with an outlook of saying we're not including regulatory credit benefits in our forecast. That doesn't necessarily mean that Rivian won't be able to have some benefit in the future. There also could be additional new state-related programs that provide additional incentives. But given where the landscape sits today, we think it's appropriate to just not factor those into the forecast.

Okay. So adding all of this up, and I'll talk in a bit about the software service side, but you had an Investor Day a little less than 1.5 years ago, and you gave a target of EBITDA breakeven in '27. There's a lot that's changed since then. So we totally understand that. But given those changes, how should we conceptually think about the path to breakeven whenever that may be? Is this purely a volume game? Are there other costs in control? Or -- and we'll get to it in a bit, is all of a sudden the software service revenue piece taking on increased importance.

Right. So relative to -- at the time of our Investor Day, we had just announced, I think, a day before the start of our joint venture with Volkswagen Group, but that was not factored into our economic models. And so while we have had a number of headwinds associated with reductions in regulatory credit revenues or incentives and certainly have more tariffs today than we had in our outlook then. We now have a very profitable software and services side of the business that is rapidly growing as well. And that's a key component for Rivian to achieve EBITDA positive within the future. Now we also need to ensure that we're coupling the strength of software and services with a robust automotive gross profit trajectory. And as we talked a little bit about, R2 is a key enabler as we think about the long-term automotive profitability of Rivian.

Okay. On that topic, I know there's a lot of debate on demand, and you nor no one has a crystal ball here. Maybe we could just talk about -- and we don't know what the EV uptake is going to look, and we'll find out in the coming months. But I want to just start with a question maybe more on brand because I think some of us would argue there is clearly an opportunity on brand awareness. Aside from maybe the coasts, Rivian is probably a far less known brand than some of the legacy names out there or versus Tesla. So as you're ramping on R2, what is the opportunity on brand awareness? And how much of a demand driver do you think that can be?

We see brand awareness as being a key unlock for Rivian. And the best way to drive brand awareness and virality around the brand is to get customers behind the wheel of our product. No words can describe what it feels like to drive one of our vehicles. And a lot of companies talk about the technology, they talk about vertical integration. But when you drive a Rivian, it all makes sense. It all comes together in our form factor as well. And I think we'll surprise people when they experience our product and say, wow, this is so much better than many of the benchmark vehicles at this similar price point that are available in market as well. And so we can't wait to get more and more customers behind the wheel as well.

The other key for Rivian has been the power of the Rivian community. And this is the piece that you can't buy community. But we've had a community of really viral early adopters with R1 that are out there as evangelists for the brand. They're doing their own sort of personalized demo drives for their own communities. And so it's important for us to continue to expand the reach of the brand, get into new markets where we may not have as deep penetration across the United States and provide more accessibility into the product as well that comes from a much lower starting price point with R2.

I think we need to see more gear guard. On this topic of just what R2 is going to comp to, if we do a very, let's call it, traditional comp analysis and we just say, okay, this is going to comp against a typical luxury 2-row crossover, it's -- the TAM is underwhelming. But if we comp this against the broader crossover segment, against Model Y, against the broader brands, all of a sudden, it opens up. So how are we -- how should we think about the comp set or the TAM for R2?

So we see the comp set as being very expansive in nature. And one good analog for this is actually when we started production, one of our top 5 trade-in vehicles for R1S was a Honda Odyssey minivan. That is not the luxury 3-row SUV comp that you might ascribe with the price point of an R1S, for example. But it just shows this was a customer that was really interested in moving their kids gear stuff and the R1S was a new form factor that could address their personal needs. And we expect to see similar opportunities as there are many customers that may be in the RAV4 today or Honda CRV that say, look at what I can achieve with the R2, and I'm willing to make a bigger trade-up in terms of my purchase selection.

What's the demand or competitive outlook right now on the vans? And I thought it was actually interesting because on the third quarter call, you gave us some indication that the van volume outlook actually for next year could be better. Amazon is your anchor customer. But what is the environment on vans right now?

Amazon has been very forward-looking as they think about the technology suite and the productivity that the van can unlock for their overall operations. I would say beyond Amazon, the broader market has been slower to adopt electrification and EVs. And Amazon is now at a point where they've deployed a lot of EV-related infrastructure across their DSPs nationally, and that allows them to increase volumes as well because of the forward investments that they've already made. In the longevity of time, I think more commercial operators will certainly get there. I think in autonomy will be another enabler for EV adoption in the commercial space in the longer term as well.

Maybe just one last one on R2 because we know that R1 benefited heavily from the EV leasing credit. How does the approach on R2 change now that leasing is, I would venture to guess, going to get relatively deemphasized versus where it was previously?

We expect leasing to be more normalized relative to what you would see in a typical sort of traditional price point of the product in the combustion engine world. So it won't disproportionately have share from a Rivian standpoint, but we still will have a very meaningful healthy leasing business over the longer term.

Okay. I want to jump back to the software service side because you said that was incremental versus what you discussed at your Investor Day. So -- how do we -- and the numbers have been good year-to-date, I think, probably better than what most of us expected. What is the trajectory of that software service revenue and margin going forward? And what exactly is driving that right now with the core business with VW plus you have some other ancillary businesses that are in that revenue stream?

So overall, we expect there to be considerable ongoing growth of the software and services, and that's both driven by JV-related growth through both background IP revenue recognition that will continue to increase as we achieve ongoing development milestones as part of the joint venture. It will also increase because we're investing in the build-out of our team in the JV. So there'll be additional development services revenue that Rivian will also earn as part of that growth. And beyond that, we've had the mantra of getting every single element of our business to profitability as well from a gross profit standpoint. And so we've also continued to see significant contribution as well from our broad-based software and services.

So whether that's software subscriptions like our FleetOS offering for Amazon, where every single commercial van has a subscription to our software offering, whether that's our Connect+ offering for R1 vehicles, we also have ongoing maintenance and repair. We have used -- robust used business, so both reselling Rivian to customers, which also helps us address and expand the addressable market over the future.

Your collaboration with Volkswagen right now, I think, is just limited to that core network architecture JV. But you talked about some opportunities to improve your procurement economics on joint sourcing. So how much opportunity is there? Maybe what's some of the lower-hanging fruit to change the procurement so you're getting better economics on your sourcing -- part sourcing?

Sure. So the joint sourcing opportunity for Rivian stems from areas of shared collaboration between the businesses. So you can think about that first directly on the ECUs that go into the vehicles on a go-forward basis. So those being a part of a joint sourcing opportunity. You can think about software and sort of external software subscriptions or things that also embed within the technology development opportunity and then adjacent systems. So as you think about the efficiency of the JV working with a handful of braking or steering other component players as well, there's efficiency and collaboration in some of those areas over the longer term as well. So it's not just the direct materials that go into the electrical architecture. You can also think about it a little bit more expansively of some of the adjacencies that those ECUs will touch.

And how long does it take to work that self into the BOM?

So it depends. We've already gone through the process of jointly sourcing the ECU. So that will be projected within the R2 material costs, for example. But as we think about additional areas of sourcing, those would be more future areas of collaboration.

Can you talk about the consideration to license this technology out to other automakers? And I know there's a media article, I think Wassym has talked publicly, who's heading -- your CTO. He talked about the opportunity to license this to other automakers. So what are the considerations? What's the time line? What does this look like?

For us, the priority one is getting the Volkswagen Group programs launched efficiently and effectively in market. Part of what makes Volkswagen Group such an attractive partner is you can solve for all of the applications from the very most premium vehicles in their portfolio to their entry price vehicles, you can address really any other OEM's lineup of product as well. And so the philosophy and approach is building an architecture that's very extensible in nature. And you see that through the fact that we -- last week, we celebrated our 1-year anniversary of the joint venture. And as part of the 1-year celebration, Volkswagen Group talked about some of their upcoming winter testing milestones, which requires us to have brand-new electrical architectures running in there in their vehicles with our software stack.

So it's a very accelerated time line from a development standpoint. And that, again, demonstrates the extensibility of the technology that we built and the foundations that they're working off of by leveraging many of the advancements that are already going into R2 program, which will be the first program out of the joint venture.

Can you license out what you're doing on AV to other automakers?

On AV, yes, we can definitely license that to other players. And I think one of the areas that Rivian is focused on is being a technology provider to the industry, and you see that with our joint venture with Volkswagen Group, but there's other technologies that certainly could be part of future licensing deals as well.

Okay. Let's just wrap with a couple of cash balance sheet questions. Maybe one of the questions that's on folks' mind is you have -- you're ramping on R2 next year. Historically, we've seen is when there's a big launch, that can be a working capital drag. Should we expect a significant working capital drag related to this?

So we will see working capital be a drag for us next year. And it's been a significant tailwind for us this year, but we will certainly see that flip as we ramp up both raw material and finished goods inventory as part of the R2 ramp.

Okay. And then between the VW funding, there's still more to come. You have the DOE loan related to Georgia. Do you think -- or do you feel like you have sufficient resources to comfortably get through the R2 ramp at both normal and Georgia?

So we ended Q3 with $7.1 billion of cash and equivalents. We expect to receive another $2 billion from -- as part of the initial proceeds from the joint venture with Volkswagen Group in 2026, and then another $0.5 billion that will come between '27 and January of '28 from them. And then as you mentioned, the way that the DOE loan is constructed, it's up to $6.6 billion of capital. We would use that capital to offset the capital investments that we're making as we build out the Georgia facility and plant. But we'll always be opportunistic as we think about ensuring we are always maintaining a robust balance sheet position as we look at the future and additional vectors and avenues for growth and investment.

Okay. Folks, any questions in the room?

Can you talk a little bit about the international opportunity for the R2 and how long that will take? I mean, obviously, there's a lot of debate around electric vehicle demand in the U.S. in Europe. Obviously, things are still progressing in the right direction for you.

We designed the R2 for global markets. And so we intend to have the opportunity to export R2 to Europe and internationally. And one of the policy changes that has happened that is a net benefit to Rivian is actually the reduction in the tariffs of vehicles exported from the U.S. to Europe that previously had a 10% tariff. Now that's gone down to 0. So it makes it an even more attractive proposition for us to continue to grow and export abroad. We'll start focused on the ramp here in North America, but certainly have the opportunity to go international.

And how would you look at the distribution of that? Is that also an aspect where you can work together with Volkswagen?

From a distribution standpoint, we want to make sure we're owning the customer relationship, but certainly can look and explore different avenues or approaches for the advancement of our products in new geographies. We've been selling vans to Amazon in Germany, for example. So we do have some physical infrastructure in Germany right now and would continue to expand that as well.

That was my question as well, but I have a follow-up on that. Now that you're looking abroad with the R2, can you just give us your quick assessment on the competitive landscape when we think about the build of materials coming out of China, the technology coming out of China, the attempts, your software-defined vehicle, I -- put you in a leadership position, but there's some Chinese players catching up very quickly. And they seem to be looking at Europe as like their high-price region as they all continue to put in a lot of new capacity. So walk me through how you are going to differentiate in, say, Europe in terms of that competitive dynamic. And maybe you disagree a little bit about that threat, but curious what you think.

We see there being still significant opportunity for Rivian in the continent of Europe, given the brand positioning, given the advanced technologies, the software-defined vehicle attributes and the autonomy runway that we have as well ahead of us. And so I think we're also continuing to invest in innovation for Europe through our joint venture, where we're developing some of the Volkswagen Group products that are designed for the continent of Europe.

And so one of the areas that we thought was really exciting with the joint venture was actually the opportunity to build more globalization into our frameworks, into our software stack earlier on in our process relative to what we would have potentially been able to do completely on our own. So we think that, that can be a key differentiator for us as well.

Great. Panels? Okay. We'll leave it there. Claire, Chip, thank you so much. Looking forward to the AV Day on the 11th. Thank you.

Thanks, Dan. Appreciate it.

Good afternoon, and thank you for joining us for Rivian's Third Quarter 2025 Earnings Call. Today, I'm joined by RJ Scaringe, our CEO and Founder; Claire McDonough, our Chief Financial Officer; and Javier Varela, our Chief Operations Officer.

Before we begin, matters discussed on this call, including comments and responses to questions reflect management's views as of today. We will also be making statements related to our business, operations and financial performance, that may be considered forward-looking statements under federal securities law. Such statements involve risks and uncertainties that could cause actual results to differ materially. These risks and uncertainties are described in our SEC filings and the shareholder letter we have filed with the SEC.

During this call, we will discuss both GAAP and non-GAAP financial measures. A reconciliation of historical non-GAAP to GAAP financial measures is provided in our shareholder letter. Just before the earnings call, we published and filed our shareholder letter, which includes an overview of our progress over the recent months. I encourage you to read it for additional details around some of the items we will cover on today's call. Following our prepared remarks, we will be taking questions from sell-side analysts. In the interest of keeping the call to 1 hour, we would ask these analysts to limit any follow-on questions to one.

With that, I'll turn the call over to RJ.

Thanks, Chip. Good afternoon, everyone, and thanks for joining us for today's call. We continue to make progress against our key strategic priorities, including preparation for the launch of our 2 and development of our technology road map, including autonomy and our vertically integrated hardware and software. As we've stated before, over the long term, we expect the industry to be fully electric, autonomous and software-defined. I've never been more confident in the opportunity ahead for Rivian than I am today. I firmly believe Rivian's technology, along with our direct-to-consumer ownership experience, position our company to build a category-defining brand with a strong product portfolio for the U.S. and European markets.

One of the key drivers for attracting customers to electric vehicles and to Rivian's products more specifically is consumer choice and price point. The average new vehicle purchase price in the United States is now just over $50,000, and the most popular configuration is a 5-seat SUV or crossover. Given the attractiveness of this addressable market, I believe R2 is addressing the largest market opportunity with the right product. We leveraged the performance, utility and personality of R1 and refactored into a smaller SUV at a lower cost.

From an R&D perspective, our teams are executing well to ensure the development of R2 remains on track with our plans. We continue to increase the quality and maturity of our design validation builds, positioning us to begin manufacturing validation builds at year-end following the full commissioning of production equipment. We recently completed the construction of our 1.1 million square foot R2 Body Shop and General Assembly Building and our 1.2 million square foot Supplier Park and Logistics Center. All shops have started equipment bring up, and we are in the process of commissioning the robots in the R2 body shop.

In addition, we have completed updates to our paint shop that will allow us to increase our total annual plant capacity to 215,000 units. I've been driving an R2 for a while now, and it is incredible. From a performance perspective, it delivers on the adventure spirit. Customers expect from Rivian, while also being a great daily driver that will fit so many different use cases for our customers. Looking longer term, we expect to add an additional 400,000 annual units of capacity for R2, R3 and associated variants with our next U.S. manufacturing facility in Georgia.

In September, we are honored to be joined by state and local officials for groundbreaking ceremony. Our significant investment in the state of Georgia is expected to create 7,500 jobs as well as billions of dollars of economic benefits to the local community as we expand our U.S. manufacturing and technology footprint.

In parallel to the progress we've made in developing R2, we've also continued to invest in our technology, including our hardware, our software and our autonomy platform. I'm excited to share the progress we're making at our upcoming autonomy and AI Day on December 11. Over the longer term, we believe what will differentiate Rivian's autonomous capabilities will be our end-to-end AI-centric approach. With the launch of our 2, our growing fleet of customer vehicles will collect real-world driving data, which will complement the data already collected by our second-generation R1 vehicles. That data can be used to train our large driving model which we believe will allow a rapid rollout of updating driving inference models with growing capabilities.

In closing, as we look towards 2026, I'm excited about the opportunity ahead for Rivian, I believe our technology and our products will position even as a market share leader over the long term. I want to thank our employees, customers, partners, suppliers, communities and shareholders for their continued support.

With that, I'll pass the call over to Claire.

Thanks, RJ, and good afternoon, everyone. As RJ mentioned, we continue to make progress on our priorities, and I want to thank our team for their continued focus as we drive execution throughout the business. While we face near-term uncertainty from trade, tariff and regulatory policy, we remain focused on long-term growth and value creation. It's great to see the continued progress in R2 validation and testing. We're also excited to share more about our hardware and software road map and vision in December at our autonomy and AI Day.

Turning to the results for the third quarter. Our consolidated revenues were approximately $1.6 billion, and consolidated gross profit was $24 million. Gross profit included $125 million of depreciation and $24 million of stock-based compensation expense. Adjusted EBITDA losses for the third quarter were $602 million. As expected, we saw a quarter-over-quarter step-up in overall operating expenses. This was driven by elevated R&D investments related to prototyping as we prepare for the launch of R2 and training costs for our Autonomy platform.

SG&A stepped up primarily related to the growth of our sales and service infrastructure and team as well as operating expenses, we don't anticipate will be part of our ongoing cost structure. Now looking at our Automotive segment. During the third quarter, we produced 10,720 vehicles and delivered 13,201 vehicles from our manufacturing facility. As we've said previously, we expect Q3 will be our highest delivery quarter for the year, which was the primary driver of the $1.1 billion of automotive revenue.

Automotive gross profit in the third quarter was negative $130 million and was negatively impacted by low fixed cost absorption associated with planned shutdown to prepare the normal plant R2. Despite this headwind, we saw strong progress in our unit economics with one of the best quarters ever in automotive cost of goods sold per unit delivered driven by improved material costs. Our Software & Services segment reported another strong quarter with $416 million of revenue and $154 million of gross profit. About half of the revenue within Software and Services was a result of the software and electrical hardware joint venture we created with Volkswagen Group.

We also experienced strong growth in gross profit contribution from remarketing and vehicle repair and maintenance. Looking at our balance sheet, we ended the quarter with approximately $7.1 billion of cash, cash equivalents and short-term investments. We continue to see improvements in our working capital, primarily driven by our focus on reducing our raw material, work in progress and finished goods inventory levels. We continue to expect to receive additional capital of up to $2.5 billion associated with our Volkswagen Group joint venture transaction, $2 billion of which we expect to receive in 2026. Additionally, we continue to partner with the Department of Energy for an up to $6.6 billion loan at a favorable cost of capital. We will update the market as we progress on this important project for the company.

Finally, for our guidance. We are reaffirming our 2025 delivery guidance range of 41,500 to 43,500 units. We are reaffirming our 2025 adjusted EBITDA loss guidance range of $2 billion to $2.25 billion and 2025 capital expenditures guidance of $1.8 billion to $1.9 billion. We continue to expect our gross profit for the full year of 2025 to be roughly breakeven.

Thank you again to the team for delivering a great quarter. As we near the end of the year, we look forward to 2026 and remain steadfast in our belief that R2 and our technology road map will be truly transformative for our growth and profitability.

I'd like to turn the call back over to the operator to open the line for Q&A.

[Operator Instructions] Our first question comes from Emmanuel Rosner, Wolfe Research.

My first one is on -- curious if you could characterize the demand environment in the U.S. that you're experiencing on the back of the removal of the consumer tax credit. Obviously, a big portion of industry reports monthly sales and did so yesterday. And for those that are involved in the EV business. There were quite a bit of a drop September into October. So just curious what you've seen and then sort of like level of comfort around the demand levels on a go-forward basis.

Thanks, Emmanuel, for the question. We certainly expected to see a pull forward of demand from October into September with the end of the IRA program, and we saw that in September. And that pull forward, of course, results in somewhat of a softer demand environment as we look at October. And I think that's as you referenced. I think that's true just across the full space across the industry across multiple different manufacturers. I think it's important that we look out from a longer-term horizon point of view and recognize that ultimately, customers are going to be making decisions around what's the best product for them. And we spend a lot of time, I think, often overly focused on electric vehicle sales relative to others. And the way we think about this, in particular with regards to R2 is we need to build the best vehicles and give customers great choices. And so in the case of R1, we have the best-selling premium SUV sold in the United States, and that's for EVs, premium SUVs, electric or nonelectric in the state of California. And with R2, we're really hoping to capture the magic of what is in R1 in terms of performance features, capabilities in a much more cost-effective or affordable package that allows us to have this vehicle be cross shop with so many different types of vehicles, and it's hitting the most popular segment with midsized SUV 5 [indiscernible] with a price point that starts at 45, the average price of new vehicles sold in the United States is around [indiscernible]. So we're really bullish, really confident on R2 and what that represents for us as a business.

Okay. Great. And then as a quick follow-up. What are you expecting in terms of demand for regulatory credits? I don't believe you're assuming any additional sales this year, but any directional view into 2026?

Thanks, Manuel. We don't expect to have meaningful revenues from the sale of regulatory credits, and we've taken those out of our forecast. Just given some of the uncertainty on potential policy changes, we wanted to make sure that our forecast was conservative on this front.

Our next question comes from Mark Delaney with Goldman Sachs.

Meaningfully, I think it came down to about $96,000 per vehicle, even with the downtime the company take to get the normal site ready for R2. I think, Claire, you mentioned material cost is one of the key drivers of that. But I was hoping you could speak a bit more on what you're seeing in terms of cost per vehicle. I guess, ultimately, any change in where you think costs can get to, especially as you look out to R2.

Thanks for the question, Mark. As you noted, we had about [indiscernible] of cost of goods sold per unit delivered in Q3. And that was despite the fact that we had several weeks of downtime. So there was an impact from fixed cost absorption included within these results. As we look forward, the big driver of performance improvement in terms of our cost of goods sold, in 2026, we'll be the volumes that we'll receive from R2 ramp and scaling efforts. So we'll see benefit not just with R2's path to positive gross profit and positive unit economics, which we expect to achieve by the end of 2026, but also the volume impacts that will benefit both R1 as well as our commercial vans as volumes scale throughout the normal facility as a whole.

My other question was on mine and robotics. You mentioned doing work with [indiscernible] antibiotics, but also bringing in external financing. So maybe just talk a bit more about what mine robotics does and what kind of opportunity you see for the entity going forward.

Mark, this is an area we've spent a lot of time on as a company thinking around and thinking about, I should say, what does our manufacturing infrastructure and manufacturing platforms look like long term. And as we thought through that, it led us to the view that we need to develop products and robotic solutions that allow us to run and operate our manufacturing plants more efficiently. And the design of these robotic solutions, capturing the data that we have within our existing facilities to train the robotic platforms on manufacturing and to train on some of these high dexterity operations. And so we've ultimately raised $110 million in a seed round to launch this as an effort outside of Rivian, but obviously with Rivian still as a close partner and as a shareholder in this entity. But the applications will include Rivian applications but also much wider ranging. So thinking about essentially a wide spectrum of industrial applications where we see the benefit of AI-enabled robotics.

Our next question comes from George Gianarikas with Canaccord Genuity.

Maybe you could just update us a little bit on the Volkswagen relationship just because there are lots of headlines as to what's going on there internally. Any update there would be very much appreciated.

The Volkswagen relationship is coming up in terms of the joint venture on the 1-year anniversary. And it's -- a lot has happened in the last year. We continue to make great progress. We have an incredibly productive and strong relationship with Volkswagen Group. I was just in Munich a few months ago for a number of different product reveals, one of which was the Volkswagen ID 1, which is a roughly $22,000 EV that's being developed by Volkswagen and of course, leveraging our technology platform. And it's just an awesome vehicle. I'm really excited for that to be one of the launch vehicles that comes out of our collaboration and joint venture with Volkswagen. But it's the first of what will be many programs that come out of this joint effort. And so the relationship remains very strong, very positive, and there are lots of things to come in front of us in terms of products and other ways we can work together.

And maybe as a follow-up. I don't mean to front run the Autonomy Day in December, but what role do you see Rivian playing in the robotaxi market? There are some of your peers also developing electric vehicles that have teamed up with some of the rideshare companies. Any sort of anything you could share on that front?

A lot of emphasis has gone on the robotaxi side. I think independent of whether the application is in a personally owned vehicle than a robotaxi I think really important is recognition that the technology is going to become really a key part of our automotive ecosystem. And so in our view, as we look towards the end of this decade, it will start to become really an important driver for consumer purchase decisions around whether or not a vehicle is capable of driving itself with both hands off the wheel and eyes off the road.

But importantly, doing that across a very wide spectrum of roads. So essentially, any drivable road should be something that can be driven by a vehicle without a lot of involvement from the driver. And as it stands today, more than 95% of the miles driven in the United States are in personally owned vehicles, the remainder being a mix between taxi, ride share and rental. We think that that's likely to stay mostly the same, maybe a rideshare grows by some percent. But we think in terms of large-scale adoption autonomy, it's going to be solving this for personally owned vehicles that's going to drive the biggest step change for us.

Now saying that, the opportunity for us to participate in robotaxis, it's, of course, there. It's something that if we chose to partner with some of the big rideshare operators, there's lots of market opportunities there. But our focus today is really on the technology. And that's what we'll spend, as you said, George, we'll spend our Autonomy Day really talking about the technology road map, how we've developed it. That's both the hardware, the software, our data flywheel -- of course, we'll demonstrate what all those different elements come together to enable in terms of what the vehicle can do. And I think through that event, you'll see there's lots of different ways that can be applied in terms of go-to-market, whether that's personally owned or whether that's through robo taxi partnerships as you stated.

Our next question comes from Joseph Spak with UBS.

The CEO of Scout Motors was recently reportedly said that 80% of their preorders are for their ERA variant. And you have BYD has both a BEV portfolio and [indiscernible] portfolio. And even if you look at China overall, in recent years, ERA has been growing arguably faster. So there's clearly demand for that type of product. And I think there's probably some benefits to that type of powertrain for the vehicles you want to sell, meaning trucks. So maybe you disagree, I'd be curious to hear that. But I know you talked about this all-electric future you envisioned. But the question is, would you actually consider offering an ERV for the US market or globally? And if so, how easy is it to adjust the platform?

Thanks, Joe. We're not planning to offer an ERA or effectively a serious hybrid, which would involve putting an engine into the vehicle. So that's not in our product road map or something that were at all contemplating. But I do think it's important to note that part of the journey of electrification is providing customers with choice, -- and so different manufacturers are going to make different decisions on this. Some will decide to take more of a hybrid approach or an EV approach. Others are going to take a pure EV approach. And in the end, aseptically this is all going to be driving towards in our view, as I said in my opening remarks, we believe everything will be electric, everything will be software defined and everything will have very high levels of autonomous capabilities.

And so we're very focused on continuing to lead with electrification. We think particularly for the midsized segment SUV, which is going to make up the vast majority of our volume with the launch of R2 and then it's follow-on product with R3. That that segment really works beautifully with an electric -- fully electric architecture, where we're able to deliver great performance, outstanding range and at a price point that's very comparable to ice or hybrid alternatives.

Okay. And as a second question, I know you spoke briefly on mind. I guess I just want to -- one, there's no spend or has there been spend already going on for that to -- how should we think about that spend going forward? Or is it all ring-fenced in the sort of external company of which you're just an owner. Maybe just if you could clarify that for us, that would be helpful.

So mind Robotics is a separate company from Rivian. Rivian is a shareholder in this. The $110 million that I referenced before is the seed financing for its capital from outside of Rivian, -- and we're -- I mean, we're incredibly excited about it. I think the -- as much as we've seen AI shift how we operate and run our businesses through the wide-ranging applications for LLMs. The potential for AI to really shift how we think about operating in the physical world is, in some ways, unimaginably large. And so that influences how we think about designing logistics inside of a plant, it influences how we think about designing even plant layouts. And so the [indiscernible] company is ultimately the culmination of us coming to the view that we wanted to have direct control and direct influence over the design and development of advanced AI robotics that would be very focused on industrial applications. And so these are robotic solutions, we will be creating through this entity through mind robotics that are designed and optimized around manufacturing and industrial environments. .

Our next question comes from Dan Levy with Barclays.

I would like to ask if you could possibly give us the latest update on tariffs within the results? I know you had stockpiled batteries. So I don't know if there's any impact there, but we have seen some changes in tariff policy. And then maybe just broadly on tariffs, given IRA is no longer really a consideration, how does that change the battery sourcing strategy for R2? Can you rely perhaps on some of the cheaper LFP batteries from overseas?

Thanks for the question, Dan. As you mentioned, the administration announced the lengthening of the 3.75% offset for Section 232 automotive tariffs to 2030 last week. It also included the ability to designate parts in the 232 automotive classification that expands the pool of eligible parts, which is particularly important for a company like Rivian, which is heavily vertically integrated. So today, we source a lot of raw material inputs that we're building subassemblies of internally that aren't necessarily -- weren't previously necessarily designated under a Section 232 classification. And we're really appreciative of the administration for -- at these new changes that were announced most recently. So as you think about the impacts on the quarter itself, based off of what we -- the product that we sold, we were just under the couple of thousand dollars per vehicle of impact in Q3. And on a go-forward basis, we expect the impact to be a few hundred dollars per unit for new builds once these policies are fully in place. We'll see a trend down in terms of the tariff exposure in Q4 since we'll certainly be selling some vehicles that may have higher levels of tariff sitting in inventory or parts that we're building towards in inventory today. But that's the general applied path and trajectory there. And then maybe I'll pass the second part of your question on the R2 battery cell sourcing back over to RJ.

Yes. So the R2 program, we've talked about this in the past, is launching with $46.95 sungical cell, and that cell starting in the late 2026 time frame will be produced in the United States and Arizona. And so we, of course, sourced that quite some time ago and have been developing in close partnership with the supplier of that cell, which is LG for some time. As you point out, there are opportunities to look at other sources of battery cells, both in terms of chemistry, but also in terms of supplier, but as it relates to the production that's coming out of our normal facility, that's planned to be the LG cell produced in Arizona.

Okay. Great. Second question is somewhat related. And I know that the regulatory picture still has to sort of emerge a bit more. But it is a bit more clear now. And so -- can you tell us to what extent now that you have maybe a better sense on tariffs, you have a better sense on red credits. Those have moved against maybe some of the initial assumptions you had when you were planning the R2 BOM and knowing that, that BOM is sticky, what mitigants do you have to ensure that you're going to get the appropriate unit economics? I know you've talked about plans to get the BOM cut in half versus R1 and exiting '26 with a positive gross margin. But how do you mitigate against some of these given the BOM is sticky?

Well, there's -- yes, there's a lot in that question, but to unpack. I think first and foremost, the building materials is -- it's contractual. And so as we negotiated the build materials and also made decisions strategically as to where the content that ultimately makes up the bill materials in the vehicle is coming from. We made decisions around prioritizing domestic or USMCA compliant sourcing. So having the parts come out of USMCA compliant locations. And that was because those decisions were made where we already had line of sight to the likely shift in some of the policies that we've seen recently.

I think importantly, these contractual agreements that we have on the bond itself help really give us confidence in us achieving the BOM and us ultimately getting to the exit rate positive unit economics on R2 -- R2 positive unit economics at the exit of 2026. I think another element that's changing is the expansion of the 232 framework and the allowance for that -- the 3.75% to carry out longer is very helpful for us. And we previously have guided to say the effect of tariffs have been a couple of thousand dollars and what we would now guide to say is that it's a few hundred dollars of tariff cost per vehicle. So it's a pretty significant shift for us.

Now I think above and beyond that, just in terms of the overall COGS framework, Javier, you and the team have been very focused on making sure we're already at the plant. Of course, your team is also responsible for the building materials and supplier sourcing. But just comment on the confidence we have in our cost structure.

Yes. When it comes to the BOM, RJ, you have explained it, and I want to insist that we have sourced on a landed basis. So by contract, we have 100% of the car source. We understand what is the cost that we are incurring. And the tariff situation is much more favorable, as Claire explained. The rest of the content of the COGS -- we are working, obviously, in the conversional cost, logistics and all the transformation costs in the plant. We have -- we are doing already in normal huge lean transformation, improving our performance in our daily operations, and all these learnings, we will translate them to R2 operations, ramp, the design of our process is more compact in R2, lesser space, less costs in terms of maintenance and overhead consumption. So we are really confident and we can see and confirm with our internal numbers that we are sticking to our target of reducing by half the cost.

Our next question comes from Edison Yu with Deutsche Bank.

This is [indiscernible] for Edison. I wanted to ask about the OpEx trajectory on a going quarter basis. You mentioned in the shareholder letter that there is some inclusion that for economy training. So on a go-forward basis, how should we think about that [indiscernible]?

Sure. Our philosophy and approach has always been to drive efficiencies into the business to help self-fund strategic areas of differentiation, such as our autonomous driving training. And as we look at our future road map of investment, that remains intact from a philosophy and approach. We're always looking for and committed to finding efficiencies and opportunities to reduce within the organization so that we can also scale the business for the increased volume that we expect to come with the introduction of R2 next year as well. So as you think about the R&D spend, we'll see elevated levels of R&D spend in the lead up to the launch of R2 and that's primarily driven by a lot of the work that we do to build development prototypes. So today, design validation builds. We talked a little bit in our prepared remarks about starting to have manufacturing validation builds in our normal plant at the end of this year. And then you'll see some of that external spend, some drop down when we launched the R2 product. So you'll see over the course of '26 more normalizing levels despite the fact that we're going to be continuing to ramp up our autonomous training over the longer term as well.

Got it. That's very helpful. My second question is on the R2 launch for next year. I was wondering if you can comment maybe on the production cadence as you see order flow coming through? Like how should we anticipate that to sort of look like first half versus second half, et cetera, for next year?

Sure. For R2, as we mentioned, we plan to start saleable builds and deliveries in the first half of '26, but we would steer folks to there being limited volumes in the first half of the year. And then the second half of the year will build up our ramp and see increasing production volumes throughout the second half of the year and then into 2027, where we'll first be in a position to have fully optimized the 215,000 sort of run rate units of capacity that we have established within the normal facility.

Our next question comes from Federico Merendi from Bank of America.

I wanted to touch upon the capacity that you're building up. Normal facility, you're going to have 215,000 units of production available in Georgia from what I understand, $400,000 additional. But given what you -- what Emmanuel said about the underlying demand and that you're not going to integrate your production with hybrid vehicles or rented vehicles. How should we think about the separation of those 2 plans that you are building up?

The normal facility, as you said, will have 215,000 units of capacity, and that will be split between R1, our commercial van and R2. And our 2 of that will have 155,000 units of capacity. The Georgia facility built across 2 phases will ultimately have 400,000 units capacity, and that will support R2, R3 and variants of each of those products. And we -- again, I said this before, but I think it's a very important point to make that the understanding the demand profile from customers for electric vehicles, it requires us to look deeper than just EV sales in aggregate, but rather to look at the strength of a vehicle offering relative to what else is on offer. And ultimately, the way customers are going to be making decisions is the price of the vehicle, the value it provides, which is performance capability, features and so we're very, very bullish on what we're building with R2.

The way we think about it as a team is we're building the best car you can buy in this category and in this price point. And we want that to be like abundantly clear and something that is so self-evident when you use the vehicle. We were just talking about how exciting it will be for people to compare the vehicle to other things in this price category. And so we're very bullish on or 2. We've also seen that the rate of adoption of EVs really does tie heavily to the number of highly compelling offerings. And to date, at this mass market price points, so call it in the $45,000 to $50,000 range, there's really been a single dominant brand with really 2 products. It's, of course, Tesla with the Model 3 and the Model Y. And with them taking up roughly half the market, 50% market share, it's not a reflection of a healthy market. It's a reflection of a very underserved market in terms of choice and options. And so what we're building with R2 is very different than a Model Y. It's similar size, similar price but very, very different in terms of it's the way it's executed. And so it's going to attract we think a very wide range of customers that's including people that may be considering EV but also importantly, folks that are not necessarily considering EV, but just looking for a great vehicle for $45,000, $50,000.

And so with all that said, what we've shown to date in terms of product sets, our product portfolios, R2, the R3 and the R3X, importantly, there's other variants which, of course, we haven't shown yet, but that will be built off the R2 and R3 platforms that will support the overall volume in Georgia as well.

And I would assume that to basically ramp all the volume you will export vehicles to other regions or countries. When should we assume that you will enter into other markets?

Yes, the R2 and R3 vehicles are absolutely architected from the very beginning and designed from the very beginning, contemplating Europe and planning for Europe. And we think they both fit the European market extremely well. We haven't announced European timing yet. But -- it is really a core part of the program and it was also a key element of the decision that we made to set up the plant in Georgia, given it's ease of export for vehicles going to Europe.

Our next question comes from James Picariello from BNP Paribas.

So just on free cash flow, how are you thinking about working capital in the fourth quarter relative to the strong source of cash contributions in the second and third quarters. And I know it was previously indicated that we should expect CapEx to run higher next year. Is there any dimensioning you can share in that increase.

Sure. As we look at the fourth quarter as implied by our guidance, we do expect to see a step-up in our capital expenditures [indiscernible] and then as you rightfully called out, we've seen strong favorability in working capital trends throughout the first 3 quarters of this year, we'll see that reverse a little bit, in the fourth quarter and where we expect working capital to consume cash in the fourth quarter. And then as we look at the working capital outlook for 2026, as we build up inventory for R2, we expect working capital overall for 2026 to be a use of cash. And we'll see that normalize as we ramp and get to our run rate levels overall.

And as Javier mentioned, very focused on making sure that we have very lean operations in normal as we look at the broad-based inventory outlook for the business in the longer term. We'll provide more details on the 2026 CapEx outlook on our Q4 earnings call. So we'll circle back with more details there. But as RJ mentioned, that would be additional capital to start vertical construction for the Georgia facility that would be reflected in our 2026 CapEx spend.

Understood. That makes sense. So -- my follow-up, with respect to the mix tranche of BW investment, the $1 billion in equity, this is tied to 2 scopes of successful winter testing, I believe. Do you expect the testing to take place this winter or late next year? Just curious on the time there.

We don't plan to comment on exact timing. But as you heard me talk about in my prepared remarks, we're confident in our ability to achieve the $1 billion of equity investment from Volkswagen Group in 2026. .

Our next question comes from Ben Kallo with Baird.

So maybe 2 parts with R2 coming. I know, RJ, you've talked about $45,000. Can you just talk about your philosophy around pricing [indiscernible] and other Tesla models, they would release the highest trim if we want to call it that, first and then kind of scale down from there as the market expands. But can you think about -- can you talk to us about pricing and how you set that versus cutting it in the future, considering the -- for now, at least at normal, it seems like supply could be limited. And then how that ties into the Georgia plant and R2 because it seems like you have a lot going on in bed pricing kind of differentiating the 2 in a short amount of time.

In the early part of next year, we're going to have an R2 event where we'll go through the full portfolio of R2 products, which would include the different pricing levels across trim and powertrain configuration -- and so of course, as you called out, when we're starting a production line of a new vehicle, we're going to limit the number of variants that we're building and so we have a launch addition for the R2 and -- this is a classic challenge because there's the thousands and thousands of people that are excited for R2. Some will want the most base version, the lowest priced version. Others are going to want the highest end versions, some will want something in the middle. And so we spent a lot of time really thinking around what's the right version to launch with.

And so we've -- well, I'm not going to provide the pricing, what that is here, I'll say that it's a dual motor variant, and that's well appointed, but it's not -- it's not intended to be our most expensive version, but it is intended to be a very nicely set up vehicle, which we think will make the most people the most happy, which is really the goal we had in selecting our launch configuration -- but as implied, following the initial ramp-up with that launch configuration will then add in the other trims and other configurations, which at that event, I referenced earlier, we'll go through that in the early part of 2026 and talk about when those different trims are going to be available.

And my follow-up is along the same lines. Just in terms of marketing versus advertising, versus cutting price to figure out the market size. How do you guys think about where advertising fits in because a lot of the questions are focused about on other OEMs retrenching not going down the path of EVs or doing hybrid electric. And so is there something that you guys can do through advertising or marketing to distinguish that not all EVs are built alike.

Yes. It's an awesome question. And so I mean, ultimately, the question is getting at this point of awareness, awareness of what R2 is and awareness of Rivian as a brand. And some of that will naturally come just from the presence of R2 on the roads and having more people have access to it, the brand becoming much more accessible because of a much lower price point and some of the same word of mouth that's benefited the brand to date with R1. But beyond just the existence of the product, the presence of it on the roads and the positive dynamics associated with word of mouth, we are putting a lot of thought into exactly how we'll launch different campaigns of the vehicle that's putting in unique places making sure that it's -- whether those are physical activations that are temporary in nature, physical activations that are through partnerships with other entities is which -- is it going to show up at a ski resort? Is it going to show up at a restaurant, these types of decisions to the more digitally focused marketing spend that allows people to see and experience the vehicle.

And we've historically not really relied heavily on paid marketing, and that's certainly -- it's been a decision, but it's also, I think there's an opportunity there for us to be thoughtful and highly measured but thoughtful in how we deploy dollars into driving awareness. So folks know about this really incredible product that we developed.

Our next question comes from Philippe Houchois with Jefferies.

Yes. My question was on -- so it's clear on tariff and thanks for the clarification that it's a negative still, but lesser negative than you would have been 6 months ago. What has become a net positive, though, compared to the past of $50 is weaker and import duties into Europe are going to go from 10 to 0, and I'm just wondering to what extent it has kind of shifted your thinking on Europe. I know you talked about Europe and R2, R3 are well suited for the market, I would agree. And does it make sense to think about a faster rollout into Europe and potentially also a bigger scale? And if you think about the potential of the market, is it still appropriate to try to do a direct selling from the U.S. exports? Or does it make sense to try to use local distribution and dealers in Europe as a separate business model? .

Yes, the impact of a 0% export tariff is certainly something we've been quite enthusiastic about, and we're pleased to see. And it has -- as you pointed out, it hasn't had as much attention as we think it deserves. And -- and so while -- as I said before, we haven't announced the timing for when we're going to be exporting to Europe. It's certainly part of our own calculus on deciding when we add that layer of complexity to the business. recognizing that we have a lot of demand here in the United States, and we want to make sure we achieve critical mass for this large pool of demand that we have here in the U.S. But at the same time, as you said, without a tariff to now bring our vehicles from the United States to Europe, there is a real opportunity to get into Europe sooner. And so these are the types of things we're thinking about, but we haven't yet said exactly when we'll be in Europe.

Right. And if I can do a follow-up. I think you've been quite efficient in delivering the R2 development on time, and that congratulations for that. Can you remind us what kind of time lag we might expect between R2 hitting the road and then R3? Is it 12, 18 months, 24 months? What's the time frame there? .

We haven't announced R3 yet in terms of timing. But what we have said is that R3 will be produced only in our Georgia facility. We're not planning to produce that in our [indiscernible] facility. And the Georgia facility, we have said is launching in late 2028. And so it would be no sooner than the launch of that facility in Georgia. .

Our next question comes from Andres Sheppard with Cantor Fitzgerald.

Wonderful. Congrats on all the progress. R.J., I think most of my questions have been asked. I do want to maybe go back to a subject which I believe you're quite passionate about, which is autonomy I guess with the rapid acceleration and deployment of self-driving vehicles, both in passenger vehicles and commercial vehicles, I'm curious if maybe you can give us perhaps a little bit more into your vision for Rivian's approach. And I realize we probably get a lot of these answers in the AI day coming up. But curious if you see a scenario where Rivian might pursue -- is more likely to pursue perhaps a robotaxi partnership with a vendor or perhaps pursue autonomy in commercial vehicles, maybe even with the EDVs. Any thoughts there?

Yes. Well, first, thanks for the plug for our Autonomy Day on December 11. We're incredibly excited about that. We're going to be going into a lot of detail there and talking about a number of things that we've not yet talked about publicly and unveiling a lot of the technology behind what we're building and what we've been focused on over the last several years to enable this. But I guess, first at the highest level, this is an area of the business, and this is a technology drive within our business that we think is going to be among the most important for transportation. And so it represents one of the largest investment areas for us as a company. It represents one of the most focused R&D efforts for us as a company. And as you already said, it captures a tremendous amount of excitement from us as a business and certainly for me. As I said earlier though, in terms of the applications for autonomy, it is very wide-ranging. We think it's going to become a very powerful driver of sales -- and when you think about the products we're launching, particularly with R2 and R3, the form factor of those vehicles is so universally useful.

So it's universally useful for a personally owned vehicle, it's universally useful for a vehicle that's going to -- that might participate in any form of ridesharing services. It's university applicable in the United States and in Europe. And so layering on top of that already very interesting vehicle in terms of form factor, package, pricing, very high levels of autonomy, where we start to look at well beyond hands-off wheelies on road, but into hands-off wheel. eyes off-road, point-to-point navigation, so address to address. We look at that as a really significant driver of demand and what will unlock a lot of folks that may not have you been considering Rivian or an EV, but to say, "Wow, I really like this car, but I also really like the fact that it can do -- it can give me my time back. It can drive places with me sitting in the car on my phone, getting my time back. And so that is our north star. It's not that we will be able to start immediately there. But what we'll talk about on December 11 will be what that road map looks like.

First, expansion of the number of roads that we have hands free on, then overlaying that with point-to-point address to address navigation and then following that, adding in for select specific environments, hands off and eyes off, which is an important one and then over time, growing the number of locations and broadening the operational design domain for where the vehicle can operate with eyes off. And so that's -- that is like the core focus for us as a business and doing that well will unlock up, as you already alluded to, many different types of businesses that will support what we already build on our commercial business, which we're quite excited about. It opens up opportunities for robotaxi, but importantly, by far away, the largest revenue opportunity. is consumer-owned vehicles or vehicles owned by household that represents well in excess of 95% of the miles driven in the United States. And that's largely true for Europe as well. And so that's our core focus to start. But to be very, very clear, the technology can be applied in many, many different places.

Wonderful. That's super helpful. I really appreciate all that color. Maybe just as a quick follow-up, one for Claire, I don't believe this has been asked about yet. But just on the DOE loan -- can you maybe just remind us or refreshes kind of your expectations from 4 withdrawals for next year or and beyond?

Sure. The DOE loan, if you recall, it's a project-based finance loan, which means that we would need to be underway with vertical construction of our site in Georgia and have also met at that point in time for first advance a number of different conditions, precedents ahead of initial draw. As RJ alluded to, we plan to begin vertical construction in 2026 and see the first vehicles coming off of the line by the end of 2028.

Our final question for today will come from Colin Langan with Wells Fargo.

If I look at the midpoint of guidance, it implies adjusted EBITDA is actually improving into Q4. But the midpoint on delivery guidance will be down. So what would drive better Q4 EBITDA and lower volumes?

Sure, Colin. As you think about the trajectory for the fourth quarter overall, -- we anticipate seeing consistent level of EDV volume as a whole as you look to Q4, our results. And the EDV has historically had a lower cost basis associated with it as well. So that's 1 factor. And then the other factor is, as we look ahead to the future, is we'll continue to earn increasing levels of background revenue associated with our background IP for the Volkswagen Group joint venture as we continue to show progress against key milestones in the JV as similar to what you've seen throughout the course of Q3 relative to Q2, there could be incremental improvement in terms of the gross profit benefit from software and services as well. And then in my prepared remarks, I had mentioned on the SG&A side, we do expect to see a slight reduction in our SG&A spend in the fourth quarter. .

Got it. you talked about regulatory credits, you don't expect any for the rest of the year. Are there any -- as we think about '26, is there any coming in sometimes the contracts or multiyear? Or should we kind of assume things is also doesn't have [indiscernible]?

Yes. As I mentioned before, we've taken regulatory credits out of our forecast, just given some of the uncertainty in the broader policy environment.

This concludes the Q&A section of the call. I would now like to turn the call back to RJ for closing remarks.

Thanks, everyone, for joining today's call. Hopefully, you can hear in our voices, just the level of excitement that we have for R2. And importantly, the technology platforms that we're building certainly, our autonomy platform being chief among them. We've got a lot of work to do in front of us as we get ready for the launch of our 2. But as I said, I've been spending a lot of time in our vehicles, and they are just absolutely incredible, both the vehicle the technology, the autonomous capabilities of the vehicles. And so we're incredibly excited to spend more time in December 11, talking around our autonomy technology and overall AI within the business and within the vehicles. And then certainly in the early part of next year, starting to get folks in R2 products and that has -- that is what we're heads down on focus. We spent a lot of time talking about the vehicle itself. But the rest of the business is also being prepared. That's all of our go-to-market functions, our service functions. Of course, as you heard from Javier getting our plant and our operations seems ready. And so we are focused on that and feeling very excited for the launch of the vehicle and for the launch of all this technology that we've talked about today. Thank you, everyone, for joining today's call.

This concludes today's call. Thank you for joining us. You may now disconnect.

All right. Get started. RJ, thanks for being here.

Yes. Love to be here.

I am -- I've had more than a handful of people who come up to me and say, "did you see the R2? Do you see the R2?" I'm like, "yes, it's RJ's truck, but like we can't drive it," like, "I know it's awesome." There are other vehicles out there, by the way, that you can, including Rivian vehicles R1 that are awesome to drive. But just visually in the packaging, and it seems to be getting a lot of attention.

Yes. It's funny when you photograph something, it's hard to get a sense of scale, but when you have them sitting here next to other cars, next to R1s. It's -- I think people like it. I've been driving it to pick up my kids from the school. And it's funny because I can see the parents who either own Rivian or like Rivian and sometimes like, "yes, yes."

And then my middle son, the rear window drops and he loves to put it backpack in through the back with the window drop. So it's a good school pickup car.

That's cool. You're a cool dad. I do my best, but I don't have the keys to that kind of technology. But thanks for joining us. Just any kind of key messages at the top, but you wanted to kind of convey to the audience and then we'll get into it.

I mean it's great that he referenced or two. For us, it's such an important program. We're really excited to get it to market. the vehicles benefits from so many learnings that we've had as a company in terms of manufacturability, cost optimization. It embeds the next-generation technology for both the embedded platforms, but importantly, for our autonomy platform, both on the compute side and the perception side. And so it's a huge program for us. So we're really 100% focused as a business on getting us ready to launch and the scale it brings is going to be a big inflection point for us as a business.

Yes. And it really does mark, I mean, at the time of the IPO and leading up to it, you had to R1 made obviously a crazy reengineering of the vehicle pretty soon after the launch, right, you learned a lot. You learn a lot about suppliers, architecture or technologies, levels of vertical integration and everything else. So yes, this is, share your view that this is almost your first right.

Now we've all the lessons we've learned. And then importantly, the post-GenAI moment, and on the autonomy part, which is really, now we've got the shot, this is the socket for the physical AI.

Completely. And we have our timing and AI data we're planning at the end of this year. And we're going to show a lot of the detail around the hardware that's in that vehicle and what's gone into it. So everything from a compute point of view to a perception to our data flywheel, how we've structured that We, of course, have some demos that show it operating and what it can do in terms of the autonomous platform. But R2 is really the full embodiment of all those different things we're working on that come together into, we think, just an incredible package and something that really has broad appeal. It's a 5-passenger SUV. It fits so many different use cases. It's priced from $45,000. So it's -- I couldn't be more excited.

RJ, You're a robotics company, right? You just is car-shape robots, adventure robots.

Yes.

I just want to ask since we began on this topic because I recently spent I did about 1,400 miles with FSD in a Model Y. And I estimate that the FSD probably drove 90 -- well over 99% of the miles. There were, it was like a giant downpour where I had to kind of basically is like watch the road. Otherwise, I took my shoes off and just hit drove, right? And you've experienced these kinds of things in your technology and competitor technology. So a lot of would-be buyers for R2, for example, maybe coming from Tesla, for a variety of reasons or coming from a competing technology, where they're used to this really good ADAS. You have to ADAS. You have advanced ADAS. But what is that path to at kind of more end-to-end turn by turn. That would be something no compromise differential from a Tesla. And when could you see the vehicles getting there?

Yes, that's a great question. So we've -- I guess this is a little bit of context. We launched in late 2021 with our first product and Gen 1 architecture used what I call like an 81.0 solution. So it was a rules-based environment. It had a collection of different cameras, some of which were ours, importantly, the front-facing camera was not ours was a Mobileye camera, and then with our Gen 2 vehicle, which we launched about a year ago now. We started working on that and the technology went into that, really in like early -- late 2021, early 2022. But we brought all of our perception stack in-house, we brought the compute platform in-house. We built a data flywheel around it and really redesigned everything. Not a single line of code, not a single piece of hardware we shared between Gen 1 and Gen 2, but designed it around as you put it, this end-to-end AI-centric approach where we're training on this -- the data flywheel that's built with the vehicles driven by our customers. And so here we are a year later, and that's now starting to deliver the features that are enabled by this approach.

And so currently, we have a hands-free highway self-driving feature. That's soon going to be expanded to hands-free everywhere, which is really important. And so that's a big -- it's something like 50x increase in the number of roads that the vehicle is not going to be able to drive on driving itself. And then we go from hands-free everywhere to hands-free and some unique situations where eyes off the hands-free eyes off. And then we layer in with that turn by turn. So address to address.

And then following that, then it's just further and further removing the need of the driver to do any driving. And so you expand the operating design domain to include every type of road, every environment. As you said, that some of them are more challenging things like rain, but we're going to talk a lot about that at our [indiscernible], we're actually going to demonstrate what's to come. But for us, a lot of those features around expanding the ability for it to drive everywhere with hands-free and then going eyes off. That's something we're really focused on for next year. These are really key developments. So we think not yet today, but certainly by '27 and '28, this starts to become a really important consideration for purchase. And if done well can completely unlock massive pools of demand relative to the competitive set.

I agree. I just from experience -- people who have an experience that kind of technology.

Once you have it, it's hard to imagine having it.

And then when you see as the robotaxis just kind of propagate and you show the general public want this technology completely and they want to have some of that as an ownership.

Yes. So this is by far our biggest focus here from an investment point of view and from a technology development. We've built a really robust network architecture, topologies ease of use, our own operating system at the vehicle level. And that's not built. It's scaled. We've licensed it as part of a large deal, $5.8 billion deal with the Volkswagen Group, but the big next frontier for us is driving into autonomy.

All right. Let's take it back to the core business and the path to profitability, a lot of moving pieces over the past 12 months between the tariffs and the regulatory credits running off, which not only affect the purchase price decision at the end of this month, and we'll talk about that and maybe some things that you might be able to do to give a little more -- get some more [indiscernible] to the door. And then also just the regulatory credits around selling GHG credits and ZEV credit is also changing. So kind of how are you navigating that so far? And what are the ways that you can kind of offset that to maintain margins, maintain the very significant improvement in margins that you've had over the last couple of years?

Yes. There's, I mean, there's been a lot of changes. I think first the thing about the categories, there's changes to trade, which impacts us both in terms of cost of smaller components. And uniquely, in Q2, there was an export control out of China, which impacted a lot of things, but importantly for us, it impacted heavy rare earth metals, which for us, we -- 100% of our vehicles per states, all of those vehicles are, of course, electric, all those vehicles require heavy rare earth metals. That was very painful for us in Q2. That's since been lifted. And I think a tremendous amount of work is happening across many companies and in collaboration in conjunction with the U.S. government to create new supplies for some of these very China-specific materials.

Putting that aside, I'd say the 2 big shifts we see here, this removal of the greenhouse gas emissions, zero mission vehicle requirements and what that's driving in terms of the credit sales. So for us, it used to be a large source of revenue. We're the second largest seller of this. Of course, Tesla being the largest. So that goes away and then the consumer-facing tax credit, the 7,500 goes away. Certainly, those are immediate short-term headwinds. But I think a part of this that we should recognize is those incentives also have been creating a bunch of unnatural things in the market. And most specifically, they've created a dynamic where a number of manufacturers in order to earn credits, have products that maybe aren't selling that well on their own, but they've incentivized them to such a degree that you have very artificial pricing on vehicles. So you can lease, you can go out, you can go lease an EV for $50 to $100 a month. And that's actually very unhealthy for the landscape because you have this artificially low pricing, which creates downward pressure on everyone else. And that's going to go away after September 30. And you're going to see a lot less pressure from most of the existing incumbent legacy manufacturers to try to use incentives as a way to drive volume and use that volume to earn their own credits. That's sort of going to disappear. And so you're going to see a less competitive environment from both a pricing point of view, and you're going to see a less competitive environment with folks stepping back from electrification and focusing more on other hybrid or their existing combustion business.

And so as I look at R2 into '26 and '27, I think it's really going to be important in terms of driving overall electric vehicle adoption in the United States. To date, we've really had 1 set of really good choices with the Model 3 and the Model Y. I think for the first time, we'll have a choice that's also really compelling, but a different form factor, different brand presentation, different attributes and features that are embedded into the vehicle that are going to give consumers a real choice.

And the fact that Tesla has been able to maintain such significant market share with a great set of products, but nonetheless, with the set of products that have not changed a huge amount in the last few years is reflective of just a market that does not have a lot of great choice. It's reflective of a market with, I think, consumers looking for something out there and just not finding it.

So yes, you can compete more on your strengths now on design, engineering and technology. So kind of expressing that with the R2 kind of going back to that. How much of the design and the hardware and software, let's say, build materials and work is done already? How much of it's cooked or how much is still potentially in play? And remind us kind of your milestones for start of production you think about or anything about [indiscernible].

I mean, from like a bill materials point of view, the vehicle's block. So it's the vehicle, the BOM is sourced, vehicle drove here drove today is well north of 99% of the parts on a production tool. So it's -- that means both from a supplier cost point of view and from a supplier readiness point of view, the risks are being really well managed, and we have a tremendous amount of visibility into the health of all those different components. And importantly, the suppliers to our suppliers and this is what has, we felt some pain on this in the past where...

A year ago, there was some..

Yes, we had some supplier challenges were supplier bankruptcies, and this actually wasn't our Tier 1. This is in the lower tiers, so we're very, very focused on making sure the supply base inclusive of the Tier 2s, Tier 3s, Tier 4s are ready to support this significant step-up in volume. And in many ways, the challenges we've encountered with R1 have been good training for processes and tools, ramping in the middle of COVID and then ramping in the 2022, 2023 supply chain crisis was good for some of these learnings.

So what about milestones then in terms of the production ramp in normal and then also what you're thinking about R2 GA and the Georgia plant.

Yes. So we've got, we're launching our 2 out of our facility in Normal, Illinois. We made the decision it allows us to have all of our production still in 1 campus we're able to reuse a number of parts of our existing plants, our paint shop or stamping operation. But we added a new general assembly plant, and we added a new body shop and in total added about 2.1 million square feet, to the existing facility. That's now built that's finished. The vast majority of the equipment has been installed. And later on this year, we're going to be building what we call manufacturing validation builds, and so there's several hundred vehicles we'll build to validate everything from suppliers to logistics to the plant itself.

By the end of this year.

Yes. And those get built to support the ramp-up of then as we shift to saleable units. And the interesting thing is as you go from what we call MVP builds to the sale units, there's essentially like we draw a line in the sand. And once we hit enough of the criteria around things running smoothly. We then turn on the full plant. We start running across a full shift. And we started in a single shift and then very quickly, we pulled in a second shift. And the constraint for us in ramping as we look at '26 is going to be a few of our suppliers that are being asked to jump up pretty quickly in volume. And so we're very cognizant. We know exactly which suppliers are going to throttle production '26, and then those same suppliers are important for us to continue to ramp into '27.

And so the amount of planning that we have on looking at the plan for every part, the plan for the parts that go into every part has been really robust just Based upon a lot of the scars on our back and the learnings that we've accumulated since first launching.

Okay. If we were in Georgia right now during the land, the projects, what will we see?

We actually have a say there next week with an official groundbreaking with the governor, but it's -- I mean it's an amazing site. It's a 2,000 acre site. We've built in partnership with the state. The state is funded a full highway that goes right into the site. We have rail that comes into the site, where the plant is going to sit. All the grading work is done. We've got a water tower. So all the infrastructure is there so that when we start to build the site, it will go up pretty quickly. And we've done a lot of work to optimize how we laid out the plant and the logistics in and out of the plant and have the advantage of it, of course, as being a greenfield site.

And so in addition to that, we also have the benefit of having, launching our 21st in our normal facility. We've found opportunities at the vehicle level to further improve it for Georgia site, further optimization.

In terms of manufacturing optimization.

Really in terms of the vehicle design then in conjunction with that, optimize the manufacturing design in Georgia. so those are all things that are underway right now.

Okay. So from that groundbreaking to production, we're talking about 2 years about that.

We haven't provided a precise time about that.

Okay. In terms of business model, a lot of investors, particularly after leading up to the Volkswagen investment in cooperation and after see a good opportunity for Rivian to get into different businesses, maybe potentially some more capital-light businesses or licensing model, seeing you potentially like a stood up kind of Tier 1 advanced robotics and AI-embodied enabler or a technology supplier and partner, how is that kind of -- is it something you've acknowledged before in calls, how has that evolved? And I asked that question now because your biggest, let's say, your biggest peer, Tesla, Elon's making some pretty deliberate and decisive actions to diversify away from the steering wheel having car business. So when I see a lot of car companies, including you, but also a lot of your others, pure plays and legacy peers, they say, we're going to make to see if you're going to make the CV, like why are you doubling down a business? Or what is it that you -- why do you think you could be profitable in this business when Tesla even at 1.8 million units is not and the Chinese haven't even come here yet?

Yes. So the question is how do we think about technology? So yes, I guess the deal we did with Volkswagen is that it's really important in that it is the second largest car company in the world, Volkswagen Group. And it's not a large car company but it has a whole host of brands. So Porsche, VW, Audi, Škoda, CUPRA, Bentley. There's just a wide spectrum of brands across price points, form factors, markets. And in many ways, it's the perfect first customer for us as a technology provider because that complexity allows us to demonstrate almost as an existence proof.

You pick The Double Black Diamond with Wolfsburg.

Yes. As a way to put it, but it allows us to really demonstrate the scalability of the technology. And so it's now been stated publicly, but one of the first products that come out of this effort is what's called the VW ID 1. And so it's their smallest vehicles, you can Google it, you can see pictures of it. It's a $20,000 vehicle.

Your answer to China.

Yes, exactly. It's the answer to China. And when that car launches, as is the case of any car that's pushing tech boundaries. Every car company role will buy it, BYD will buy it. Xiaomi will buy it and XPeng will buy it. We'll take it apart, and everyone is going to be impressed with how elegant the network architecture is, the ECU layout and importantly, the associated wiring and electrical systems to support that. It's really a massive step forward relative to anything that's been done before and the size of the vehicle and the price point of the vehicle forced it. But that's part of our technology platform. And so that same platform is going to equally be used obviously, with a lot more I/O and maybe a few more ECUs, zonal used to support bigger cars, but flagship vehicles in the Porsche, Audi brand. And so to cover flagship within Porsche, Audi down to the lowest priced EV available in Europe on the same technology backbone demonstrates really capability that we think is scalable to many other manufacturers. And so we're absolutely thinking about that. We do think it's an interesting part of the business.

We also think that every manufacturer is going to have to make this transition to a software-defined architecture just as a foundational element to even really be serious about integrating any form of AI or autonomy into the vehicle. And so we see this as a really exciting opportunity.

It's been over a year. It's been like 15 months or so, I think, since you announced the deal. It was like a spring early summer 2024.

Yes, about a year.

How is it going so far? I mean it sounds like based on what you said, you're getting product into vehicles.

Yes. Yes, I was just -- I was in unique this week for IAA. And it's serial. So I grew up a car enthusiast. And specifically, as a Porsche.

You're still a car enthusiast.

I'm still a car enthusiast, very much so but as a Porsche fan and a Volkswagen fan. And when I was a kid, I would like wait for the European car shows to come, and I read about Frankfurt, read about what's happening, the car is being released and like wait for the magazines to come out and read them. And it was surreal to be there at this time, and to be part of that and see a carbon presented it and realize that car is all of our tech. And so within Volkswagen, very large display that they had, it was beautiful layout where they had a bunch of different brands, a bunch of different cars. The only brand that was on the wall in their display and that wasn't one of their own brands was Rivian. And I said, Rivian and had a whole description is a beautiful animated thing with a car that described by our technology. And then I said, a partnership to change the world, big letters. And so I was reflecting on exactly what you said. It's been about a year since we signed the deal. And so I was thinking, boy, in the last year, we've now announced these programs. We built deep relationship with the Volkswagen Group. And they're very happy with it. So happy that they're willing to put it on the wall and very publicly broadcast how closely we're working together. And I think a lot of that has come out of our working teams really like the technology they see it as a big advancement relative to what else is out there. And then my relationship with the CEO of Volkswagen Group with Ali is outstanding, the person who's running the joint venture, who is our Head of Software. He's an outstanding leader and he's built great partnerships. But as I said, it really demonstrates our ability to work with large companies. And this is now the second large company that we do business with. The other being Amazon, which we partner with to build commercial bands. So we've -- we continue to show that we're capable of working with large businesses and applying our technology and our capabilities to support those businesses.

And the partnership does not yet include ADAS at this point, but it could. And then, of course, you, so you could deepen and expand the scope within a big complex partner. You could also diversify among the partners as well, but when I think about the autonomy, we touched on earlier, just to go back to that, I remember, it was also around, a little over a year ago, you mentioned when we were talking about ADAS and you were getting the Mobileye camera off the wind screen you said an OEM either needs to kind of outsource everything to a partner or do everything or almost everything in-house. It's a hybrid model of doing some things and outsourcing where things kind of go wrong.

Just for this audience to kind of understand like everything that you continue to learn, especially as the technology gets on the AI flywheel, why is that? Why have you taken the approach to go internal? Do you have any -- are you -- tell us why that was the right decision, and where do you go from here?

Yes. That's a really important question. So when we think of self-driving, I think we often look at it and we think of it as a space that's sort of been around for maybe 15 years. And while that's true, there's 2 very different chapters of self-driving. There's the chapter from, call it, early 2010s to maybe 2021, 2022. In that chapter, it consisted of platforms that had a perception stack that saw the world and in this seen the world, whether it's cameras or cameras plus radar plus LiDAR, whatever the perception stack is to identify objects would classify those objects, and then it would associate vectors to those objects.

And that is by drawing a circle around the object.

Yes, and you have annotations and you have a bunch of, actually often humans that would try to write the programs for, is that a tree? Is that a person? But those of them we get handed to a planner and the planner would be operating around a set of rules that were written by humans. So it's a program set of rules. And that rules-based environment would then prescribed to the vehicle, how it should behave based upon all that object detection in that environment. And so as a result, these systems were very specific to the market that they were tuned for, meaning you couldn't take a self-driving vehicle that was developed and tuned for California and put it in Tokyo and expect it to work.

Similarly, they were very specific to the vehicle and the sensor set that was on that vehicle. So if you had increased cameras or different cameras. It required a very heavy lift to reprogram the vehicle to work in that environment.

And then early 2020s, along came this big technical innovation of transformers and using transformers to do things like encoding. And suddenly, the whole model started to shift where we went from a rules-based environment of how a self-driving vehicle would work to one of which you're building a very large foundation model or [ neural net ] that prescribes how the world works, how you drive in the world. And to train that model, you need raw data, meaning you can't take a bunch of outputs from third parties that you can't take outputs from let's say a Mobileye camera that's saying, hey, that's a car moving at this philosophy. You need the raw information that you're going to feed into building a large multidimensional model, and you're going to train that model with the benefit of all the data coming off of your deployed car park.

And so to do this well, you need control of the sensor set. All the sensors need pride there all signals in. You need a really robust and thoughtfully designed triggering systems. So how you select which piece of information you want to take, and so there's obvious ones, like does the card disengage when it's being driven on its own. That's obvious.

But less obvious, like, for example, if you running the model in parallel to them driver. Anytime the model predicts something different than the human driver, that's interesting, and that's a chance to learn. And so if you build this framework to trigger and select data, and then you need to take that data and move it off the vehicle. So you need a really robust data management platform, you need to be WiFi connected, and then that data has to go somewhere, it needs to go to a large training environment. This is thousands of GPUs that are running and building this model. And that needs to happen all the time every day on every car that's deployed.

And so to do what I've just described, it just simply doesn't work, does not apply in an AI-centric world, if you have Tier 1 supplier doing these cameras, another Tier 1 slower doing these cameras. You just don't have an ability to build this data flywheel.

And so what I said to Adam, which I still strongly believe is that you have to give it all to 1 person to 1 entity, that's going to have the ability to create that data flywheel or the inverse of that, which is you have to own it all yourself. And so we, of course, took the decision, this is, a as I said, a few years ago now, late '21, early '22 to build this in-house. We built a large team. We built a perception stack. We built a compute platform. We built this data flywheel. We launched the vehicles middle of '24, and we've been building this data set since then and rapidly training. And given the size of our car park is much smaller than Teslas, which is also using this approach of a really data-heavy end-to-end trained AI-based approach, we've also gone in. We have a really robust camera set. We supplement that with a robust radar platform so have a 3D imaging radar in the front and then corners. And we're using the stronger perception stack to allow for accelerated learning, particularly in tough environments. So I think being able to drive in the rain or being able to drive in the fog is really how you can teach the model, teach the model and the camera is much better if you have things that can see through the rain or the fog like radars.

And so that's where we are. It's -- and we're starting to see the progress of it really manifest in features. We're going to see big steps forward. In some ways, a nonlinear acceleration to the content, as we look at the next 12 months with the next one being the ability to, as I described it, go hands-free, just about any road. But we're going to provide some demos at this economy day at the end of the year that's going to...

We know where this is going to be. Is it [indiscernible].

In the Bay Area, we haven't announced yet, but I just did. So there we go.

We've got 5 minutes left. Any questions from the audience for RJ? Just speak up. Project.

Given what's going on with your largest competitor and maybe turning off the customer base, which is alliances and politics, how does this open the opportunity for R2 to really maybe have -- help quantify just a bigger market opportunity? I don't know if you've quantified this at all internally. But how do you think about that?

Yes. I mean it's hard to quantify, I think.

Are you getting into politics any time soon?

No.

Okay. All right. I just want to make sure.

I think the way we look at it is the customers ultimately are going to need choice. And in the United States, we've had electrification somewhat stabilized at around 8% penetration. And a lot of talk goes on to what's causing that. And I actually really believe we often miss the true causality of it, which is just a true lack of choice -- a true lack of choice of highly compelling options. And if you're going to go buy a vehicle today. The number of great choices is well under the number of fingers on my hand. It's -- I'd say, Model 3 model, why great vehicles in terms of if you want a vehicle under $50,000, they're strong, but there's not a lot of others. And so you contrast with the IC space, we have 300-plus different choices. It's really created a glass ceiling on how much demand is going to be. And so we look at our two and I think certainly, there's going to be some cross shop and maybe some movement of customers from Tesla to Rivian, we'll see that. But I think the bigger point is that there's 92% of customers that haven't yet found a product that was compelling enough to get them to move out of the right vehicle.

And I mean I'm highly biased, but when I drive an R2, I just can't imagine someone choosing to be in a similarly priced 5-passenger crossover SUV in the ICE world. The technology, the smoothness of pride, the acceleration, the range the cost of operating the vehicle. It's just so advantaged. And the form factor is really interesting, and there's a bunch of other unique features we've developed in the vehicle.

So the part I'm most excited about is just I really -- I drive a Rivian almost every day, but we want to travel a lot of times, I'll be in a rental car just because I want to get experience in sort of be in these non-EVs. and every time I'm in on, I'm sort of blown away that people are still buying them. And then I think, why are they doing that? Well, they need a different form factor than what's available or they need a different -- they want a different brand or look. They want a different set of attributes. But the delta in terms of capability features is really significant. So we're -- I've never been more bullish than I am today on what we're building and what's to come with R2.

All right. Quick one here. Yes. Okay.

You mentioned earlier that heavy rare earths are kind of a pinch point. Do you see OEMs like yourself investing up the supply chain directly into mines, like similar to what GM did with MP Materials maybe couple of years ago now?

Yes. It's a great question. It's a really hard question in that. The reality -- the harsh reality is, when we look at ever earth metals, there's not processing that exists at scale here in the United States. There's some efforts, as you know and as referenced, but they're not yet at scale. And until they're at scale to support production, in our case, lots of magnets for motors. We do have a real dependency on the China supply chain. And so we and many other industries as well felt this in the second quarter when there was the export control out of China that it halted production. And so I think that was a wake-up call to many that we need to build supply chains outside of that. There's roles that we play in -- there's a role that we play in that. There's a role that I think collaborations play in this, and there's certainly a role that the U.S. government plays in helping to create the right environment for those to thrive here either in the United States or in friendly places. So I think that's a real risk not just of electric vehicles, but to a wide range of things that need heavier rare earth metals.

Question here?

Thanks, RJ. When it comes to the upcoming expiry of the credit, I guess there's this dynamic of some demand pull forward this quarter and maybe it's probably going to pull some from this year or next year, I guess, presents some challenge with your sales and delivery team and fulfilling those orders. Could you maybe talk to how the team is handling that?

Yes. I mean the teams are working hard. I think that we have the ability to absorb those types of spikes and we've built, we've built a process that allows it to move pretty quickly. I think a related question is what does Q4 look like or Q1 look like? And in our case, because our products today with R1, the price -- the average selling price in R1 is around $90,000. And that's the average, that means people buying a tri-motor or a quad-motor is spending quite a bit more than that. And so what we're finding is that a number -- a lot of our customer base is much more pricing sensitive and the tax credit isn't a huge motivator. It doesn't really change perspective of whether they're going to buy the vehicle or not. For the more entry side of our business where we have like our standard pack, there is more sensitivity. And so we're spending a lot of time thinking about how to -- as we get into Q4, what demand was pulled forward into Q3 from that, that we're going to see a fall off in Q4. We are projecting there's going to be some impact in Q4, but we're watching really closely to try to project what that's going to look like.

Okay. We were at, sorry -- Got one. Go for it.

Very quick. You're going smaller in size of a lot of vehicles, but I'm somebody that has a large family and true 7-passenger Yukon kind of sized vehicle. Is that something that's conducive to an electric vehicle because I don't see too many of those today. I know GM and Ford, I mean, are trying, but it seems like that's something that you do very well in.

Yes, we have like our current 7 passenger is not quite as big as like the big Denali. But it's, I mean I ask that in the third road, comfortable you can hit back there.

We're not planning to build anything larger than that. It's a very unique U.S. market vehicle. You end up with -- it's a pretty small niche, and the bigger market by far is actually the mid-sized SUV, which is [indiscernible] are playing.

RJ, we're on time, just a quick one as we head out. I'm going to let buy, sell, hold, a rapid fire. I'm going to list to say a word or two, and you tell me buy, sell, hold, okay?

Okay. I don't know where this is going to go.

That's good. That's why I'm doing it, okay? I hope you come back again some time.

All right. LiDAR.

We think it's important.

Buy, sell or hold?

Buy.

Okay. Simulation?

Important. Buy.

Okay? Rare earth magnets?

Super important.

Okay. Humanoids.

I think many form factors in robotics, yes.

Micromobility?

Absolutely. Yes.

Okay. Selling cars into Europe from the U.S.

Very important. Yes. And easier now with the tariff structure changing.

Robotaxis.

We think important.

Do you experience them on the regular -- do you use?

I mean I split my time in the Bayer, so yes.

Coldest place you've ever driven a Rivian?

Probably Utah. Utah and Milan.

Okay. all right, 2 more. Favorite vegan dish.

[indiscernible]

Okay? And how does the vegan get buy in Wolfsburg, Germany.

With energy bars.

Okay. Thanks, RJ. that was awesome.

Absolutely.