Gemini Robotics-ER 2 Preview
Summary
Gemini Robotics-ER 2 Preview is a proprietary language model from Google DeepMind, released on 30 Jul 2026. It accepts text, images, PDFs, audio and video and generates text, with a 131K-token context window and up to 66K output tokens per response.
Embodied reasoning model for robotics: spatial understanding, video progress, and multi-robot orchestration
Last verified 21 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Google DeepMind |
|---|---|
| Release date | 30 Jul 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 131K (131,072 tokens) [models.dev] |
| Max output | 66K tokens [models.dev] |
| Input | Text, images, PDFs, audio and video [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
Gemini Robotics-ER 2 Preview API pricing by provider
USD per million tokens. Sorted by input price.
We do not currently track a paid API listing for this model.
Frequently asked questions
What is the context window of Gemini Robotics-ER 2 Preview?
Gemini Robotics-ER 2 Preview has a context window of 131,072 tokens (131K) and can generate up to 65,536 tokens in a single response, according to models.dev.
Is Gemini Robotics-ER 2 Preview open source?
No. Gemini Robotics-ER 2 Preview is a proprietary model; Google DeepMind has not released its weights.
When was Gemini Robotics-ER 2 Preview released?
Google DeepMind released Gemini Robotics-ER 2 Preview on 30 Jul 2026, according to models.dev.
Change history
- Input modalities changed from text, image, pdf, audio to text, image, pdf, audio, video
- Added to the directory