Gemini Robotics 2

Google's most advanced vision-language-action model: it turns vision and language into motor control. It drives full humanoids from feet to fingertips as well as bi-arm robots, with whole-body control, dexterous manipulation and multi-robot collaboration.

Отличается от Gemini Robotics ER 2 — та модель воплощённого рассуждения. Закрытое превью, доступ по листу ожидания. Анонс 28.07.2026, карточка модели датирована 30.07.2026.

Understands

text, images

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.