Generalist AIUnited States2026

GEN-1

An AI model: a vision-language-action model (VLA) takes camera images and an instruction and turns them into movements for a robot. This page describes the software, not a robot.

Robotsnot stated

Key figures as stated by the developer

3 of 6 stated · 3 gaps

Model type not stated
Controls ⁠A arms and hands
Inputs not stated
Access ⁠A partners-early access only
Parameters not stated
Base model ⁠A no

How to read the figures

14kgA30.9lbA: The letter in the grey square after a figure points to the source the figure came from. Robots with several sources carry several letters.
74.5lb: Imperial figures are our own conversion unless the manufacturer states an imperial figure itself. The source letter always belongs to the metric figure — a conversion has no source of its own.

The four states

Versions and notes in the key figures (4)

Model type

Note Generalist's wording: "It is a large multimodal model that emits actions in real-time."

Controls

The model emits actions: "It is a large multimodal model that emits actions in real-time." Recovery behaviour: the robot can "decide to use its other hand to enable bimanual in-hand regrasping".

Access

Developer wording: "Early access partners will have access to GEN-1 starting today."

Base model

Note Generalist's wording: GEN-1 "is trained from scratch on our dataset". It also writes that GEN-1 comes "through further scaling of GEN-0’s foundation".

Full specifications

4 of 12 fields stated

The letter points to the source at the foot of the page. Fields without a figure are dashed: the developer does not state them — that is not the same as zero, and not the same as no.
Field	Value	Source and caveats
Input and output
Model type	not stated	Note Generalist's wording: "It is a large multimodal model that emits actions in real-time." ⁠A
Inputs	not stated
Controls	`arms and hands`	A The model emits actions: "It is a large multimodal model that emits actions in real-time." Recovery behaviour: the robot can "decide to use its other hand to enable bimanual in-hand regrasping".
Degrees of freedom controlled	not stated
Size and speed
Parameters	not stated
Control rate	not stated
Where it runs and what it is built on
Runs where	not stated
Base model	no	Note Generalist's wording: GEN-1 "is trained from scratch on our dataset". It also writes that GEN-1 comes "through further scaling of GEN-0’s foundation". ⁠A
Openness
Access	partners-early access only	A Developer wording: "Early access partners will have access to GEN-1 starting today."
License	not stated
The developer’s own claims
Learns new tasks	needs retraining	A Developer claim: "when GEN-1 adapts to a new task, it is simultaneously adapting to that robot embodiment and to that task for the first time". Generalist also mentions "task-specific data and fine tuning steps".
Works across robots	not stated	Note Generalist's wording on embodiments: "when GEN-1 adapts to a new task, it is simultaneously adapting to that robot embodiment and to that task for the first time". ⁠A Yes only if the developer itself says the model runs on different robot models, for example robots from two manufacturers or two of one manufacturer’s models. Several units of the same robot do not count.

Notes

Generalist describes GEN-1 as a large multimodal model that emits actions in real-time.
Generalist adds that it is even more accurate to call GEN-1 a system than a model.

Sources

A Manufacturer product page. generalistai.com/blog/gen-1 · Retrieved 2026-10-14

One line per source, not per figure: a source has one retrieval date. The letter beside a figure points to the line it came from.