Gemini Robotics ER 2

Preview

This feature is a Generative AI Preview offering, subject to the "Pre-GA Offerings Terms" of the Service Specific Terms and the Additional Terms for Generative AI Preview Products. Pre-GA features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

For this Generative AI Preview offering, Customers may elect to use it for production or commercial purposes, or disclose Generated Output to third-parties, and may process personal data as outlined in the Cloud Data Processing Addendum, subject to the obligations and restrictions described in the agreement under which you access Google Cloud.

Gemini Robotics ER 2 (gemini-robotics-er-2-preview) is a vision-language model (VLM) available on Gemini Enterprise Agent Platform that delivers precise reasoning about a robot's physical environment. Built on Gemini 3.5 Flash, it specializes in embodied reasoning capabilities such as spatial reasoning, pointing, instrument reading, robot video understanding (including moment finding and progress classification), and multi-step robot and tool orchestration.

For setup instructions, code samples, and capability guides, see the Gemini Robotics ER 2 overview.

Try in Agent Studio View in Model Garden Deploy example app Developer guide Pricing

Note: "Deploy example app" requires a Google Cloud project with billing and Agent Platform API enabled.

Model ID	gemini-robotics-er-2-preview
Modalities	description Text Input and output photo Image Input only mic Audio Input only videocam Video Input only
Token limits	Input token limit	131,072
	Output token limit	65,536
Capabilities	Thinking Supported System instructions Supported Structured output Supported Context caching Implicit context caching, explicit context caching Supported RAG Engine Not supported Tuning Not supported Agentic video understanding Not supported
Tools	Grounding Google Search, Google Maps Supported Code execution Supported Function calling Supported URL context Supported Computer use Preview feature Supported
APIs	GenerateContent API Supported Interactions API Preview feature Not supported Gemini Live API Not supported Count Tokens API Supported Chat Completions API Not supported
Consumption options	Provisioned Throughput Not supported Batch inference Not supported Pay-as-you-go Standard PayGo Supported Fixed quota Not supported
Supported regions	Model availability	Global: global
	Standard PayGo	Global: global
Quota limits	250 requests per minute (RPM) default per project (200 to 300 RPM depending on project quota tier)
Versions	gemini-robotics-er-2-preview Launch stage: Preview Release date: October 27, 2026