Gemini Robotics-ER 1.5

Published

Sep 25, 2025

Gemini Robotics-ER 1.5 is an AI model developed by Google DeepMind (United States), first published in September 2025. It works in the vision, language and speech domain, on tasks such as instruction interpretation, robotic manipulation, image captioning and 5 more.

Epoch AI has no training-compute estimate for this model. Training ran on Google TPU v4,Google TPU v5e,Google TPU v6e Trillium.

Access: API access. Its weights are not openly released.

Full record

Organization: Google DeepMind
Country of organization: United States
Domain: Vision, Language, Speech
Task: Instruction interpretation, Robotic manipulation, Image captioning, Object detection, Search, Language modeling/generation, Question answering, Speech recognition (ASR)
Training hardware: Google TPU v4, Google TPU v5e, Google TPU v6e Trillium
Model accessibility: API access
Open weights: No