Google DeepMind's vision-language-action model for whole-body robot control, dexterous manipulation and multi-robot tasks.
Documentation in progress
The product identity and source are confirmed, but some specifications or interface details do not yet have citable manufacturer evidence. Missing evidence is not treated as a negative claim.
Product information
Information below comes from the product website or public documentation. Pricing and availability may change.
- Category
- Robot Development
- Maturityi
- Beta / limited access
- Deploymenti
- Hybrid
- Buying / access
- Contact the vendor or a partner
- Source
- Official websiteChecked Sep 19, 2026
Reality check
A demo shows what may be possible. These points help judge whether the product fits day-to-day use.
- Simulation, control, perception and repeatable experiments
- Teams that can manage dependencies and hardware interfaces
- Prototyping before committing to a physical deployment
- Supported hardware, GPU requirements and version compatibility
- Documentation, examples and community response
- How simulation results transfer to the real robot
- A guarantee that simulation equals a production cell
- A replacement for safety validation on hardware
- A low-maintenance toolchain without version ownership
About
Gemini Robotics 2 is a vision-language-action model from Google DeepMind that converts vision and language inputs into robot motor control. The official model page demonstrates whole-body humanoid control, dexterous manipulation and multi-robot collaboration. The core VLA model is offered through trusted-tester access rather than general self-service access; Gemini Robotics ER 2 has a separate public developer path.
Tags
Scenes
Product details
- Manufacturer / team
- Google DeepMind
- Product typei
- Component
The cost iceberg
The purchase price is only one part of an automation project.