NVIDIA
Open humanoid foundation model
- Version
- n1.7-release
- Cost
- Free and open-source under a commercial license
- Model
- Cosmos Reason
Unitree · #10 most active of 27 in Robotics
Sub-$20k humanoid widely used as a research and RL training platform.
Trust score · Verified
3 data points checked · 2026-11-04
Current version
G1
Entry cost
from $13,500/unit
Changes / 30d
3
The short answers · verified November 8, 2026
Source: Unitree — www.unitree.com · Reusable under CC BY 4.0 — cite Tomorrow
G1
Base model with 23 degrees of freedom
$13500
G1 EDU
Educational version with 23-43 degrees of freedom and secondary development support
$13500
Entry price over time
Orin
Provider undisclosed
UnifoLM
Provider undisclosed
UnifoLM (Unified Robot Large Model)
Unitree
Context window
—
Public API
yes
Multi-model routing
yes
Other tracked products running on the same foundation models — a quick read on how much of the catalog moves when one of these models changes.
green disclosed · amber inferred · grey unattributed. Aliases are folded into one model; provider concentration counts only models with an established vendor.
Reference data. Each figure is whatever the source actually said — weekly users, downloads, revenue run-rate — with its own definition and date. These are not comparable between tools and are never used to rank anything.
No public usage figure on record for this product.
NVIDIA
Open humanoid foundation model
Boston Dynamics
Electric humanoid for industrial work
Open Robotics
The robotics middleware standard
Apptronik
General-purpose humanoid for logistics
Agility Robotics
Warehouse humanoid in production
Sanctuary AI
Teleoperation-trained dexterous humanoid
New capabilities: Continuous OTA Upgrade, Force-Position Hybrid Control, UnifoLM Model Support
79 tracked82 tracked · +Continuous OTA Upgrade, Force-Position Hybrid Control, UnifoLM Model Support
sourceNew capabilities: OTA software upgrade, Dexterous hand
68 tracked70 tracked · +OTA software upgrade, Dexterous hand
sourceNew capabilities: 3D LiDAR + Depth Camera, Secondary Development (EDU), Unified Robot Large Model (UnifoLM)
61 tracked64 tracked · +3D LiDAR + Depth Camera, Secondary Development (EDU), Unified Robot Large Model (UnifoLM)
sourceNew capabilities: Over-the-air (OTA) updates
59 tracked60 tracked · +Over-the-air (OTA) updates
sourceNew capabilities: AI Driven Imitation Learning
57 tracked58 tracked · +AI Driven Imitation Learning
sourceNew capabilities: Imitation & Reinforcement Learning
53 tracked54 tracked · +Imitation & Reinforcement Learning
sourceNew capabilities: 23-43 joint motors, Dexterous hand force control, Secondary Development (EDU model)
48 tracked51 tracked · +23-43 joint motors, Dexterous hand force control, Secondary Development (EDU model)
sourceUnitree G1 added UnifoLM (Unified Robot Large Model) to its model stack
Orin, UnifoLMOrin, UnifoLM, UnifoLM (Unified Robot Large Model)
sourceNew capabilities: Force Control Dexterous Hand, UnifoLM Integration
46 tracked48 tracked · +Force Control Dexterous Hand, UnifoLM Integration
sourceNew capabilities: Imitation Learning, Reinforcement Learning, Dexterous Hand
42 tracked45 tracked · +Imitation Learning, Reinforcement Learning, Dexterous Hand
sourceNew capabilities: Imitation learning, Reinforcement learning
40 tracked42 tracked · +Imitation learning, Reinforcement learning
sourceNew capabilities: UnifoLM (Robot Large Model)
39 tracked40 tracked · +UnifoLM (Robot Large Model)
sourceNew capabilities: Secondary development support
37 tracked38 tracked · +Secondary development support
sourceNew capabilities: 8-core CPU, Dexterous Hand Dex3-1
35 tracked37 tracked · +8-core CPU, Dexterous Hand Dex3-1
sourceStraight head-to-head pages against the busiest products in Robotics.
Free to cite and reuse under CC BY 4.0. Permalink: https://tomorrow.aliensquad.ai/tools/unitree-g1
Tomorrow. (2026). Unitree G1 — version, pricing and model stack [Data set entry]. AlienSquad. Retrieved 2026-11-08, from https://tomorrow.aliensquad.ai/tools/unitree-g1
@misc{tomorrow-tools-unitree-g1,
author = {{Tomorrow}},
title = {Unitree G1 — version, pricing and model stack},
year = {2026},
publisher = {AlienSquad},
howpublished = {\url{https://tomorrow.aliensquad.ai/tools/unitree-g1}},
note = {Accessed: 2026-11-08}
}