# Google DeepMind — Gemini Robotics ER 2 in public preview

- Company: Google DeepMind (deepmind.google)
- Announced: 2026-07-30
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://ai.google.dev/gemini-api/docs/changelog#07-30-2026
- Record: https://forck.live/items/24009-gemini-robotics-er-2-in-public-preview
- Subject: Gemini API
- Models affected: gemini-robotics-er-2-preview, gemini-robotics-er-2-streaming-preview

Google DeepMind released two new embodied reasoning model endpoints for robotics, gemini-robotics-er-2-preview and gemini-robotics-er-2-streaming-preview, adding spatial reasoning and multi-robot coordination capabilities. The preview endpoint supports agentic code execution, multi-step tool orchestration, video moment finding, and progress classification for complex robot tasks. The streaming variant is optimized for real-time text streaming via the Live API, enabling low-latency robot agents with bidirectional audio and video input. Both endpoints accept text, image, video, and audio inputs and support function calling with blocking behavior for physical robot actions.

## Evidence

Verbatim from https://ai.google.dev/gemini-api/docs/changelog#07-30-2026:

> gemini-robotics-er-2-preview: Advanced spatial reasoning, agentic code execution, multi-step tool orchestration, video moment finding, progress classification, and multi-robot coordination.

---

Record: https://forck.live/items/24009-gemini-robotics-er-2-in-public-preview
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md