The Interactions API is now generally available. We recommend using this API for access to all the latest features and models.

Gemini Robotics ER 2 Preview

Gemini Robotics ER 2 is a vision-language model (VLM) for robotics that accepts text, image, video, and audio input. It supports spatial reasoning, video understanding, agentic code execution, multi-step tool orchestration, and multi-robot coordination.

Try in Google AI Studio

Documentation

Visit the Robotics page for full coverage of features and capabilities.

gemini-robotics-er-2-preview

Gemini Robotics ER 2 Preview

Property	Description
Model code	`gemini-robotics-er-2-preview`
Supported data types	Inputs Text, images, video, audio Output Text
Token limits^[*]	Input token limit 131,072 Output token limit 65,536
Capabilities	Audio generation Not supported Caching Supported Code execution Supported Computer use Supported File search Supported Function calling Supported Grounding with Google Maps Supported Image generation Not supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Supported URL context Supported
Consumption options	Batch API Supported Flex inference Not supported Priority inference Not supported
Versions	Read the model version patterns for more details. Preview: `gemini-robotics-er-2-preview`
Latest update	July 2026
Model card	Model card

Gemini Robotics ER 2 Streaming Preview

Property	Description
Model code	`gemini-robotics-er-2-streaming-preview`
Supported data types	Inputs Text, images, video, audio Output Text
Token limits^[*]	Input token limit 131,072 Output token limit 65,536
Capabilities	Audio generation Not supported Caching Not supported Code execution Not supported Computer use Not supported File search Not supported Function calling Supported Grounding with Google Maps Not supported Image generation Not supported Live API Supported Search grounding Supported Structured outputs Not supported Thinking Supported URL context Not supported
Consumption options	Batch API Not supported Flex inference Not supported Priority inference Not supported
Versions	Read the model version patterns for more details. Preview: `gemini-robotics-er-2-streaming-preview`
Latest update	July 2026
Model card	Model card

Gemini Robotics ER 1.6 Preview

Property	Description
Model code	`gemini-robotics-er-1.6-preview`
Supported data types	Inputs Text, images, video, audio Output Text
Token limits^[*]	Input token limit 131,072 Output token limit 65,536
Capabilities	Audio generation Not supported Caching Supported Code execution Supported Computer use Supported File search Supported Function calling Supported Grounding with Google Maps Supported Image generation Not supported Live API Not supported Search grounding Supported Structured outputs Supported Thinking Supported URL context Supported
Consumption options	Batch API Supported Flex inference Not supported Priority inference Not supported
Versions	Read the model version patterns for more details. Preview: `gemini-robotics-er-1.6-preview`
Latest update	December 2025
Knowledge cutoff	January 2025