TeardexRobots/Boston Dynamics
Boston Dynamics Spot
Quadrupedon sale, price not disclosed
7 sourced facts: 7 confirmed. Last checked 11 Oct 2026.
- Confirmed
- The robot's maker or the part's maker says so.
- Likely
- A good source points to it, but neither maker has said it outright.
- Rumoured
- One unverified report. A lead, not a fact.
Point at any row to see its source.Tap any row to see its source.
Availability
Whether you can get one, and what it costs.
On saleConfirmed
Sold through Boston Dynamics' sales team.
- Applies to
- All versions
- Source
- Boston Dynamics, Spot product pagebostondynamics.com
- Checked
- 11 Oct 2026, saved copy
Not disclosedThe product page gives no price. Buyers are sent to the sales team.
The product page gives no price. Buyers are sent to the sales team.
- We looked at
- Boston Dynamics, Spot product pagebostondynamics.com
- Checked
- 11 Oct 2026, saved copy
Brain layer 1 of 5
AI model
The software that decides what the robot does.
Learned walking controllerConfirmed
A neural network, trained by trial and error, that keeps the robot on its feet. Boston Dynamics says it has built reinforcement learning into Spot's walking control.
- Made by
- In-house
- Applies to
- All versions
- Source
- Boston Dynamics blog, Starting on the Right Foot with Reinforcement Learningbostondynamics.com
- Checked
- 11 Oct 2026, saved copy
Brain layer 2 of 5
Chip
The computer inside the robot that runs it.
Jetson Xavier NXCORE I/O add-onConfirmed
An earlier small AI computer from the same family as the Orin. Inside the CORE I/O, an add-on computer that mounts on Spot's back.
- Made by
- Nvidia
- Applies to
- CORE I/O add-on
- Source
- Boston Dynamics developer docs, CORE I/Odev.bostondynamics.com
- Checked
- 11 Oct 2026, saved copy
Jetson OrinRL Researcher KitConfirmed
A small, powerful computer made for running AI inside machines. A Jetson AGX Orin, in the kit sold to researchers for running their own learned controllers.
- Made by
- Nvidia
- Applies to
- RL Researcher Kit
- Source
- Boston Dynamics blog, Starting on the Right Foot with Reinforcement Learningbostondynamics.com
- Checked
- 11 Oct 2026, saved copy
Not disclosedThe pages checked do not name the computer built into Spot's body.
The pages checked do not name the computer built into Spot's body.
- We looked at
- Boston Dynamics developer docs, About Spotdev.bostondynamics.com
- Checked
- 11 Oct 2026, saved copy
Brain layer 3 of 5
Senses
How the robot sees and hears the world.
Stereo camera pairsConfirmed
Cameras in pairs, like two eyes, so the robot can judge distance. Five pairs, giving black and white images all the way round.
- Made by
- Not named
- Applies to
- All versions
- Source
- Boston Dynamics developer docs, About Spotdev.bostondynamics.com
- Checked
- 11 Oct 2026, saved copy
Brain layer 4 of 5
Training
How the robot was taught.
Isaac LabRL Researcher KitConfirmed
The newer version of Nvidia's robot training simulator. The simulator supplied to researchers for training Spot.
- Made by
- Nvidia
- Applies to
- RL Researcher Kit
- Source
- Boston Dynamics blog, Starting on the Right Foot with Reinforcement Learningbostondynamics.com
- Checked
- 11 Oct 2026, saved copy
Brain layer 5 of 5
Software
The system that ties it together and lets people program it.
Spot SDKConfirmed
Boston Dynamics' toolkit for programming Spot. Includes a Python library for controlling the robot and reading its sensors.
- Made by
- In-house
- Applies to
- All versions
- Source
- Boston Dynamics developer docs, Spot SDKdev.bostondynamics.com
- Checked
- 11 Oct 2026, saved copy
Changes
None since this page was published on 11 Oct 2026. When a fact is corrected, the old version stays listed here.
Spotted a mistake?
Send a link that shows the right answer. Public sources only.