Gemini Robotics 2
Robotics model
Price not published
Gemini Robotics ER 2
The hosted, publicly callable half of the Gemini Robotics 2 stack: a high-level planner that points at objects, plans multi-step tasks and calls a robot’s own VLA/skills as tools.
Model idgemini-robotics-er-2-preview
Price$1 in, $5 out per 1M tokens
Checked29 September 2026
Where it stands
6newer robotics models since its release
- Praxis-130 Sep 2026
- Helix 2.517 Sep 2026
- UnifoLM-WLA-1.010 Sep 2026
- Skild S1 (Skild Brain)25 Aug 2026
- Generalist GEN-1.519 Aug 2026
The 5 newest are listed. All robotics models
- Before it from Google
- Gemini Robotics-ER 1.5 / 1.625 Sep 2025
- Weights
- Closed weights; access is hosted only.
How to call it
5 ways to use Gemini Robotics ER 2, with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Gemini API | gemini-robotics-er-2-preview |
https://generativelanguage.googleapis.com/v1beta/models/gemini-robotics-er-2-preview:generateContent |
ai.google.dev |
| Gemini API (Live API, streaming) | gemini-robotics-er-2-streaming-preview |
ai.google.dev | |
| Google AI Studio | aistudio.google.com | ||
| Gemini Enterprise Agent Platform (Google Cloud, private preview) | docs.cloud.google.com | ||
| Sample code (GitHub) | github.com |
Pricing
| Input | $1 per 1M tokens |
|---|---|
| Output | $5 per 1M tokens |
As published: “per 1M tokens (text/image/video/audio input); introductory rate through 2026-12-31, rising to $2.00 in / $10.00 out from 2027-01-01; Batch API half price”.
Source: ai.google.dev, checked 29 September 2026.
Specs
- Input
- Text, images, video and audio
- Output
- Text
- Context window
- 131,072 tokens
- Max output
- 65,536 tokens
- Open weights
- No
- Licence
- Proprietary
- Released
- 30 July 2026
- Status
- Preview
- Type
- Robotics model
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Embodied reasoning “robot brain” in a public API
Spatial reasoning (points, boxes, trajectories), multi-step task planning, tool/function calling and code execution to orchestrate a robot’s VLA or controller; publicly callable, unlike the VLA models.
Continuous video monitoring and task-progress tracking
Watches video feeds to track progress and adapt; Google reports 91.3% moment-finding accuracy (0.96 s mean absolute distance) at ~4x the speed of the previous generation and 57.4% progress classification.
Low-latency streaming via Live API
Separate gemini-robotics-er-2-streaming-preview id supports bidirectional audio/video streaming with function calling and thinking (no caching, code execution or structured output).
Multi-robot collaboration
Coordinates heterogeneous robots (e.g. wheeled rovers and humanoids, Boston Dynamics Spot demo) to communicate and hand off tasks.
Notes
Vision-language model for robotics (outputs text/JSON, not motor commands). 131,072 input / 65,536 output tokens. Standard id supports caching, code execution, computer use, file search, function calling, Search and Maps grounding, structured outputs and thinking. Replaces gemini-robotics-er-1.6-preview (shut down 2026-08-31). No GA id yet. Knowledge cutoff not stated.
Sources: model page, pricing, Google blog, model card.