As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/gemini-robotics-on-device-2/

# Gemini Robotics On-Device 2

Google DeepMind, Gemini Robotics family. Status: preview. Type: robotics model. Released: 2026-07-30.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Gemini Robotics trusted tester / early-access program (application form) |  |  | https://deepmind.google/models/gemini-robotics/ https://docs.google.com/forms/d/1sM5GqcVMWv-KmKY3TOMpVtQ-lDFeAftQ-d9xQn92jCE/viewform |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: text, image, video
- Output: action
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer robotics models in the registry since its release: 6. The 5 newest:
  - Praxis-1 (2026-09-30) https://postcutoff.com/m/praxis-1/
  - Helix 2.5 (2026-09-17) https://postcutoff.com/m/figure-helix-2-5/
  - UnifoLM-WLA-1.0 (2026-09-10) https://postcutoff.com/m/unifolm-wla-1-0/
  - Skild S1 (Skild Brain) (2026-08-25) https://postcutoff.com/m/skild-s1/
  - Generalist GEN-1.5 (2026-08-19) https://postcutoff.com/m/generalist-gen-1-5/
- Before it from Google: Gemini Robotics-ER 1.5 / 1.6 (2025-09-25) https://postcutoff.com/m/gemini-robotics-er-1/
- Closed weights.

## What stands out

- Local VLA inference on robot hardware: Lightweight version of the Gemini Robotics VLA optimized to run locally without a network connection. Source: https://deepmind.google/models/gemini-robotics/
- Fast adaptation to new embodiments: Adapts to completely new robot bodies with a few hours of data; typically fewer than 200 examples for a new bi-arm robot (uses motion transfer from Gemini Robotics 1.5). Source: https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/

## Notes

Successor to Gemini Robotics On-Device (June 2025). Trusted-tester / partner access only; parameter count and hardware requirements not published.

On-robot VLA for low-latency or offline deployments.

Sources: [DeepMind blog](https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/).

Model page: https://postcutoff.com/m/gemini-robotics-on-device-2/