Everything We Know About the Tesla Semi

By Kevin Armstrong
Tesla's Semi will revolutionize the trucking industry
Tesla's Semi will revolutionize the trucking industry
Tesla

Tesla delivered its first production Semis on December 1, 2022, to its first customer PepsiCo. It was five years in the making; Elon Musk first introduced this idea to the world on December 14, 2017. With deliveries officially taking place, the Tesla Semi is on the right track to change the trucking industry and in the words of Musk: This is going to revolutionize the road, make the world a better place in a meaningful way.

The Semi Beginning

Elon Musk first mused about the Tesla Semi in his Master Plan Part Deux, which appeared on the company website on July 20, 2016. Under the header: Expand to Cover the Major Forms of Terrestrial Transport, the CEO went further than sedans and SUVs. "There are two other types of electric vehicle needed: heavy-duty trucks and high passenger-density urban transport.

Both are in the early stages of development at Tesla and should be ready for unveiling next year (2017)," wrote Musk. He also added, "we believe the Tesla Semi will deliver a substantial reduction in the cost of cargo transport while increasing safety and making it really fun to operate."

However, you could trace the Semi back even further. At the delivery event, Musk reminded everyone of the Tesla mission, “Our actual mission is to accelerate the advent of sustainable energy. So that is why we are making this wide range of cars that don’t really make sense from a brand standpoint traditionally, but makes total sense when you consider what is the mission of the company.”

The company stated there are 15 million passenger vehicles sold in the U.S. every year, but only a couple hundred thousand big rigs. But that small percentage of long haulers makes up 20 percent of U.S. vehicle emissions because they are large vehicles that are always being used. Musk also pointed out that more than one-third of articulate emissions are produced by semi-trucks.

Tri-motors and a 1,000-volt Powertrain

When Musk introduced the Tesla Semi in 2017, he compared it to current semi-trucks on the road today and to a $2 million supercar, the Bugatti Chiron. The first features the CEO talked about were performance, but not just any performance.

Instead, Tesla referred to it as BAMF Performance. I'll let you figure out the acronym. While the appearance alone will make the Semi a standout at truck stops, it's the performance that will change the trucking industry.

The Semi was initially going to have four independent motors; however, when delivered it was down to a tri-motor system, similar to the Model S Plaid. But don’t let that fool you. Senior Manager of Tesla’s Semi Engineering, Dan Priestley, explained why many people refer to the Semi as the beast.

“(It has) three times the power than any diesel truck on the road right now. So, you’ve got all the power you need to get the job done, but the other reason that it’s a beast is because it is efficient, you can go 500 miles on a single charge on one of these things. It’s the mix of those two - this is a game-changer. What’s awesome is both of those are enabled by our 1000-volt powertrain. This is the first vehicle we are doing with that.”

Tri-Motors and a Clutch

The tri-motor power train system has one motor that will carry the load the majority of the time, as it’s mainly for highway driving. That efficiency motor is approximately the size of a football. The other two are for torque and acceleration. Those motors use the system straight out of the Model S Plaid powertrain except the Semi can physically disengage two motors when they're not in use.

Tesla introduced a clutch that will automatically engage or disengage the two performance motors. According to Tesla, the clutch will automatically engage the performance motors when needed and it'll do it completely seamlessly. Instead of having the motors moving freely when not in use like the Model S Plaid, disengaging them results in even better efficiency. Priestly said, “These are clutched automatically, no driver input is needed. It is seamless.”

Semi Performance

Tesla Semi achieves 0 to 60 MPH in 5 seconds (20 seconds under a full load)
Tesla Semi achieves 0 to 60 MPH in 5 seconds (20 seconds under a full load)
Not a Tesla App

Musk commented on the Semi’s performance, “It looks crazy, it looks like an elephant moving like a cheetah.” When it was launched it was promoted as reaching 60 miles per hour in five seconds without a load. It can also reach 60 miles per hour fully loaded with the maximum 80,000 pounds gross vehicle weight in 20 seconds. As for up a hill with the full weight, current diesel trucks achieve 45 miles per hour at a 5% grade; the Tesla Semi will do 65 miles per hour at the same degree.

Semi Range and Efficiency

While the speed and acceleration are undoubtedly impressive and a considerable improvement over the current diesel trucks on the road, the range is the industry's most important factor. Tesla states that its Semis have a 500-mile range at maximum gross vehicle weight and highway speeds. This number is significant because 80% of trucking routes are 250 miles or less. "You can deliver a load out to the middle of nowhere and come back," said Musk.

It seems that this claim was the most in dispute. Bill Gates openly doubted the range in a blog post dated August 24, 2020. The Gates Notes stated: Even with big breakthroughs in battery technology, electric vehicles will probably never be a practical solution for things like 18-wheelers, cargo ships, and passenger jets. Electricity works when you need to cover short distances, but we need a different solution for heavy, long-haul vehicles.

Tesla set out to prove him wrong. They recorded an entire, unedited video of the Tesla Semi traveling 500 miles on a single charge. Luckily, they speed up the eight-hour video to a few seconds for the presentation, but it did show a long haul, with 82,000 pounds, going from Fremont to San Diego.

There are several advanced technologies at work to make this happen. The Semi's current efficiency is about 1.7kWh per mile, but Musk sees a way to make it even more efficient.

"We designed the Tesla truck to be like a bullet, whereas normal diesel trucks are designed more like a barn wall; this is a bullet," said the Tesla CEO. The Semi can generate the performance and the range due to the design. The drag coefficient or wind resistance of the regular diesel trucks is a .65 to .70. The Tesla Semi scores a 0.36, cutting the regular diesel truck drag in half and even beating the Bugatti Chiron score of .38.

The sleek nose and flat bottom are accompanied by side flaps that adjust to the trailer. These features help cut the drag and increase the range.

Charging the Semi

The Semi will be capable of charging much faster than ordinary EVs
The Semi will be capable of charging much faster than ordinary EVs
Tesla

Tesla nearly upstaged the Semi delivery by announcing what will be charging it. The new V4 Superchargers are capable of producing 1 MW DC. Musk explained, “to charge a truck like this quickly you need a high-powered charger. It’s our next-generation immersive cooling. It’s liquid-cooled, so you don’t need like a gigantic elephant truck of a cable, you can actually have a small cable, and that cable delivers a megawatt… We’ve 3x-ed the current density.”

Priestley, went further into detail, “This is pretty cool stuff. You’re actually immersing the conductor in the coolant. This water-based coolant that we have, we are doing some really neat isolation monitoring on the back end to ensure that it is safe and delivering what it needs to. But it means that we can really shove a lot of current in a very, very small place. So, for those who have charged their cars at a V3 Supercharger and the cable’s nice and maneuverable, it’s the same thing here, but now we’re just shoving a megawatt through it instead.”

Tesla wants the Semi to go from empty to 70 percent in 30 minutes. That time is vital to note because, in most jurisdictions, drivers must stop every six hours for a 30-minute break. The company says that the Semi will have added 400 miles in half an hour, which can last another six hours. Additionally, these chargers will be at destinations that would allow owners to charge the Semi while it is being loaded or unloaded.

Tesla Semi Unveiling

Displays and Software

The Semi's interior is most similar to the Model 3 or Model Y.

The Semi lacks an instrument cluster but features two horizontal displays, one to either side of the driver.

The right display appears to contain the traditional launcher we have in today's Teslas with access to music, phone, cabin temperature and more, while the left display contains truck-specific features at the bottom, such as tire PSI, trailer air supply and parking brake functions.

Although the software can be changed at any point, the best way to describe the vehicle's current software is to compare it to a Model 3/Y.

The Semi essentially takes the display of the Model 3 or Model Y, and splits it down the middle then puts those items on two separate displays.

The left display contains the speedometer, gear selector, battery indicators and the vehicle's visualization.

The Semi's interior features two horizontal displays
The Semi's interior features two horizontal displays
Tesla

The right portion of the display on a Model 3 which includes information such as maps and apps is displayed on the Semi's right display.

However, Tesla isn't taking up the entire display with these features. About one-third of each display appears to be reserved for always-on blind spot camera monitors.

Battery

Although Tesla hasn't released the exact size of the batteries in the Tesla Semi, they have released enough information for us to accurately assess its size.

Tesla has said that the Semi will achieve an efficiency of less than 2 kWh per mile (1.24 kWh per km). Tesla has also said that the Semi will have a range of approximately 300 or 500 miles.

With these two bits of information, we can speculate that the Semi will be available in two versions. A "Long Range" model that will have approximately a 1,000 kWh, or 1 MWh battery, and a "Standard" version with about a 600 kWh battery.

For comparison, a 2022 Model S contains a 100 kWh battery, so the Tesla Semi will have a significantly larger battery at 6x to 10x the size of its smaller cousin.

Having a larger battery will allow the Semi to charge faster than Tesla's current models since the current can be spread across more batteries.

The first Tesla Semi trucks will use the 2170 battery cell; the same one that is used in the Tesla Model 3 and the Model Y. However, it's expected the Tesla will eventually switch over to use their 4680 batteries once production improves.

Safety

The Semi comes with the same safety features as Tesla's existing vehicles, the same kind of standards that have earned Tesla countless accolades. The Semi has Enhanced Autopilot, Automatic Emergency Braking, Automatic Lane Keeping and Forward Collision Warning.

The company also believes that moving the driver seat to the middle of the vehicle makes the Semi safer if it is involved in a crash. It has a low center of gravity due to the battery pack's location at the bottom and middle of the vehicle. That is the same as current Teslas, reducing the vehicle's chance of rolling over. "Jackknifing is impossible," declared Musk. He said that due to the independent motors, the Semi would detect a jackknifing situation and adjust the torque to the wheels needed to keep the vehicle from skidding out of control. "Your worst nightmare is gone with this truck. Gone. You never have to worry about it."

Driver Experience

When it comes to the experience of driving a Tesla Semi, Musk summed it up best, "it's like driving a Model S or X or 3. It's just big." Today, big trucks on the roads can have anywhere from 10 to 18 gears . That's a lot of shifting. Operators of the Tesla Semi need to simply shift into drive. It's a lot less fatiguing and lets truckers focus more on the road.

The driver's seat is in the center of the expansive cockpit that is also tall enough that someone can stand in it. The videos and pictures have failed to show the sleeper cab portion of the vehicle. However, there is a significant amount of room behind the cockpit to house a sleeping area.

Reliability

At the unveiling, Musk made a shocking promise; he guaranteed that the Semi will not break down for a million miles. He was confident in that number because of the independent drivetrains. If one motor stops working, the others can pick up the slack. Musk said if just two of the motors were active, the Semi would still beat a diesel truck in performance.

Trucks put brakes to the test because they haul so much weight. But, again, like other Teslas, the brakes will be used as generators and put back energy into the battery. "Brake pads literally last forever," said Musk. Removing the internal combustion engine also means no transmission to maintain, emissions scrubber or differentials.

The Semi has thermonuclear explosion glass. Musk quipped, "it survives a nuclear explosion, or you get a full refund." He pointed out that, on average, semi-trucks' windshields crack at least once a year. Trucks are not legally allowed to drive with a cracked windshield in several areas worldwide. That means a single crack could park a trucker for an undetermined amount of time waiting to get fixed. The Tesla armored glass takes away that risk.

Just like other Teslas, the app will be available for the Semi. That feature includes remote diagnostics, predictive maintenance, location tracking, and connection to Tesla Mobile Service.

Cost of Ownership

The Semi can be charged while the vehicle is loaded or unloaded
The Semi can be charged while the vehicle is loaded or unloaded
Tesla

Trucking is a unique business. The costs are difficult to predict mainly due to the fluctuations in the cost of diesel and maintenance. When the Semi was unveiled in 2017, the diesel fuel price per gallon was $2.50; Five years later, it has more than doubled.

Tesla estimates that operators will save approximately $200,000 over three years because electricity is 2.5 times cheaper per mile. There will also be considerable savings by not having to leave the truck in the shop for routine maintenance and less time off the road for cracked windshields.

Aerodynamics and Drag Coefficient

The Tesla Semi has a drastically lower drag coefficient compared to other trucks
The Tesla Semi has a drastically lower drag coefficient compared to other trucks
Tesla

The Semi's aerodynamics produce even bigger cost savings if they operate in convoy. It's estimated a three-truck convoy averaging 60 miles per hour would cost $0.85 per mile. That price not only beats diesel trucks but also trains.

The Tesla Semi has a drag coefficient of just 0.36. This helps reduce wind noise and improve efficiency. A traditional diesel semi truck has a drag coefficient range between 0.65 and 0.70, while a Buggatti Chiron has a coefficient of 0.38. For comparison the Tesla Model 3, one of the most aerodynamics vehicles ever created, has a coefficient of 0.23.

Buyers

Big name companies were some of the first to put down a deposit. Walmart ordered 130 Semis, UPS purchased 125, Pepsi is waiting for 100, Anheuser Busch asked for 40, and FedEx has reserved 20.

Other names reported to have bought the Semi include Sysco, DHL, Ryder and Loblaws. It's believed that several independent truckers have also secured the Semi. Obviously, Tesla is using its Semi. The attention-grabbing technological breakthrough has been spotted delivering Tesla products to dealerships in California.

A Megacharger has been installed at the Pepsi facility in California as well. Expect more companies to jump on board as these impressive beasts start to be spotted on highways worldwide.

While Tesla has closed reservations, buyers in the United States may be lining up to get in once Tesla starts retaking orders. The Inflation Reduction Act announced in July could net Tesla Semi buyers upwards of $40,000 in incentives.

Ordering a New Tesla?

Consider using our referral code (karan29050) to get up to $2,000 off your new Tesla and get 3 Months of FSD for free.

Tesla Included FSD V12.6.1 and V13.2.4 in the Same Update: What Caused This and What It Means

By Karan Singh
Not a Tesla App

Tesla launched two FSD updates simultaneously on Saturday night, and what’s most interesting is that they arrived on the same software version. We’ll dig into that a little later, but for now, there’s good news for everyone. For Hardware 3 owners, FSD V12.6.1 is launching to all vehicles, including the Model 3 and Model Y. For AI4 owners, FSD V13.2.4 is launching, starting with the Cybertruck.

FSD V13.2.4

A new V13 build is now rolling out to the Cybertruck and is expected to arrive for the rest of the AI4 fleet soon. However, this build seems to be focused on bug fixes. There are no changes to the release notes for the Cybertruck with this release, and it’s unlikely to feature any changes when it arrives on other vehicles.

While this update focuses on bug fixes, Tesla’s already working on bigger features for FSD V13.3, which we have already confirmed to include improvements to highway following and speed control.

FSD V12.6.1

FSD V12.6.1 builds upon V12.6, which is the latest FSD version for HW3 vehicles. While FSD V12.6 was only released for the redesigned Model S and Model X with HW3, FSD V12.6.1 is adding support for the Model 3 and Model Y.

While this is only a bug-fix release for users coming from FSD V12.6, it includes massive improvements for anyone coming from an older FSD version. Two of the biggest changes are the new end-to-end highway stack that now utilizes FSD V12 for highway driving and a redesigned controller that allows FSD to drive “V13” smooth.

It also adds speed profiles, earlier lane changes, and more. You can read our in-depth look at all the changes in FSD V12.6.

Same Update, Multiple FSD Builds

What’s interesting about this software version is that it “includes" two FSD updates, V12.6.1 for HW3 and V13.2.4 for HW4 vehicles. While this is interesting, it’s less special when you understand what’s happening under the hood.

The vehicle’s firmware and Autopilot firmware are actually completely separate. While a vehicle downloading a firmware update may look like a singular process, it’s actually performing several functions during this period. First, it downloads the vehicle’s firmware. Upon unpacking the update, it’s instructed which Autopilot/FSD firmware should be downloaded.

While the FSD firmware is separate, the vehicle can’t download any FSD update. The FSD version is hard-coded in the vehicle’s firmware that was just downloaded. This helps Tesla keep the infotainment and Autopilot firmware tightly coupled, leading to fewer issues.

What we’re seeing here is that HW3 vehicles are being told to download one FSD version, while HW4 vehicles are being told to download a different version.

While this is the first time Tesla has had two FSD versions tied to the same vehicle software version, the process hasn’t actually changed, and what we’re seeing won’t lead to faster FSD updates or the ability to download FSD separately. What we’re seeing is the direct result of the divergence of HW3 and HW4.

While HW3/4 remained basically on the same FSD version until recently, it is now necessary to deploy different versions for the two platforms. We expect this to be the norm going forward, where HW3 will be on a much different version of FSD than HW4. While each update may not include two different FSD versions going forward, we may see it occasionally, depending on which features Autopilot is dependent on.

Thanks to Greentheonly for helping us understand what happened with this release and for the insight into Tesla’s processes.

Nvidia’s Cosmos Offers Synthetic Training Data; Following Tesla’s Lead

By Karan Singh
Not a Tesla App

At the 2025 Consumer Electronics Show, Nvidia showed off its new consumer graphics cards, home-scale compute machines, and commercial AI offerings. One of these offerings included the new Nvidia Cosmos training system.

Nvidia is a close partner of Tesla - in fact, they produce and supply the GPUs that Tesla uses to train FSD - the H100s and soon-to-be H200s, located at the new Cortex Supercomputing Cluster at Giga Texas. Nvidia will also challenge Tesla’s lead in developing and deploying synthetic training data for an autonomous driving system - something Tesla is already doing.

However, this is far more important for other manufacturers. We’re going to take a look at what Nvidia is offering and how it compares to what Tesla is already doing. We’ve done a few deep dives into how Tesla’s FSD works, how Tesla streamlines FSD, and, more recently, how they optimize FSD. If you want to get familiar with a bit of the lingo and the background knowledge, we recommend reading those articles before continuing, but we’ll do our best to explain how all this synthetic data works.

Nvidia Cosmos

Nvidia’s Cosmos is a generative AI model created to accelerate the development of physical AI systems, including robots and autonomous vehicles. Remember - Tesla’s FSD is also the same software that powers their humanoid robot, Optimus. Nvidia is aiming to tackle physical, real-world deployments of AI anywhere from your home, your street, or your workplace, just like Tesla.

Cosmos is a physics-aware engine that learns from real-world video and builds simulated video inputs. It tokenizes data to help AI systems learn quicker, all based on the video that is input into the system. Sound familiar? That’s exactly how FSD learns as well.

Cosmos also has the capability to do sensor-fused simulations. That means it can take multiple input sources - video, LiDAR, audio, or whatever else the user intends, and fuse them together into a single-world simulation for your AI model to learn from. This helps train, test, and validate autonomous vehicle behavior in a safe, synthetic format while also providing a massive breadth of data.

Data Scaling

Of course, Cosmos itself still requires video input - the more video you feed it, the more simulations it can generate and run. Data scaling is a necessity for AI applications, as you’ll need to feed it an infinite amount of data to build an infinite amount of scenarios for it to train itself on.

Synthetic data also has a problem - is it real? Can it predict real-world situations? In early 2024, Elon Musk commented on this problem, noting that data scales infinitely both in the real world and in simulated data. A better way to gather testing data is through real-world data. After all, no AI can predict the real world just yet - in fact, that’s an excellent quantum computing problem that the brightest minds are working on.

Yun-Ta Tsai, an engineer at Tesla’s AI team, also mentioned that writing code or generating scenarios doesn’t cover what even the wildest AI hallucinations might come up with. There are lots of optical phenomena and real-world situations that don’t necessarily make sense in the rigid training sets that AI would develop, so real-world data is absolutely essential to build a system that can actually train a useful real-world AI.

Tesla has billions of miles of real-world video that can be used for training, according to Tesla’s Social Media Team Lead Viv. This much data is essential because even today, FSD encounters “edge cases” that can confuse it, slow it down, or render it incapable of continuing, throwing up the dreaded red hands telling the user to take over.

Cosmos was trained on approximately 20 million hours of footage, including human activities like walking and manipulating objects. On the other hand, Tesla’s fleet gathers approximately 2,380 recorded minutes of real-world video per minute. Every 140 hours - just shy of 6 days - Tesla’s fleet gathers 20 million hours of footage. That was a little bit of back-of-the-napkin math, calculated at 60 mph as the average speed.

Generative Worlds

Both Tesla’s FSD and Nvidia’s Cosmos can generate highly realistic, physics-based worlds. These worlds are life-like environments and simulate the movement of people and traffic and the real-life position of obstacles and objects, including curbs, fences, buildings, and other objects.

Tesla uses a combination of real-world data and synthetic data, but the combination of data is heavily weighted to real-world data. Meanwhile, companies who use Cosmos will be weighting their data heavily towards synthetically created situations, drastically limiting what kind of cases they may see in their training datasets.

As such, while generative worlds may be useful to validate an AI quickly, we would argue that these worlds aren’t as useful as real-world data to do the training of an AI.

Overall, Cosmos is an exciting step - others are clearly following in Tesla’s footsteps, but they’re extremely far behind in real-world data. Tesla has built a massive first-mover advantage in AI and autonomy, and others are now playing catch-up.

We’re excited to see how Tesla’s future deployment of its Dojo Supercomputer for Data Labelling adds to its pre-existing lead, and how Cortex will be able to expand, as well as what competitors are going to be bringing to the table. After all, competition breeds innovation - and that’s how Tesla innovated in the EV space to begin with.

Latest Tesla Update

Confirmed by Elon

Take a look at features that Elon Musk has said will be coming soon.

More Tesla News

Tesla Videos

Latest Tesla Update

Confirmed by Elon

Take a look at features that Elon Musk has said will be coming soon.

Subscribe

Subscribe to our weekly newsletter