Gemini Robotics ER 1.6

Previous embodied reasoning model: text, images, video and audio in, text out. It interprets visual scenes, reasons about space and plans actions from natural language. Knowledge cutoff January 2025.

Legacy-превью: вендор до сих пор даёт выбрать её в Gemini API рядом с ER 2.

Understands

text, images, audio, video

Produces

text

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.