Google DeepMindSpecialist modelRolling out to robotics partners
Gemini Robotics 2.5
Summary
Google DeepMind introduced Gemini Robotics 2.5 on November 10, 2026, as a vision-language-action model. It converts visual input and language into motor control. The model family separates this action control from the spatial understanding and multi-step planning handled by Gemini Robotics ER.
Google DeepMind is rolling Gemini Robotics 2.5 out to robotics partners. Its official model information does not list a general API, public model ID, or downloadable weights, so the directory records it as partner-access only.
Similar models
More models of the same kind as Gemini Robotics 2.5, chosen by model line, developer, size, price and release date.
- EmbeddingGemma 2Google DeepMind · same developer
- AlphaGenome 2Google DeepMind · same developer
- Gemini 3.8 Flash CyberGoogle DeepMind · same developer
- Unlimited OCR 2Baidu · released around the same time
- Kumo-TabularNVIDIA · released around the same time
- Qwen-Drive-1.0-4BQwen · released around the same time
- Hy-SimulMT-30B-A3BTencent Hunyuan · released around the same time
- TeleOCRTeleAI · released around the same time
All specifications
Architecture
- Model class
- Vision-language-action (VLA) model that converts visual and language input into motor control for robots. It handles action control; Gemini Robotics ER is the separate model for spatial understanding and multi-step planning.
- Source: Model class
Input and output
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
- Access
- Google DeepMind is rolling the model out to robotics partners. The cited official sources do not list a general API, public model ID, or downloadable weights.
- Source: Access
- Shutdown
- None announced
- no source