gemini-robotics-er-2-preview

proprietary

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

Context
131K
Max output
66K

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Batch Processing

Details

Provider Google Vertex AI
Creator Google AI
Familygemini-2
Licenseproprietary
Statusactive
Typechat
Input modalitiestext, image, video, audio
Output modalitiestext, image, audio
Open weightNo
Parameters—
Architecture—
Context window131K tokens
Max input—
Max output66K tokens
Reasoning tokens—
Knowledge cutoff
Release date—
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Generate ContentPOST
Generate text from multimodal inputhttps://us-central1-aiplatform.googleapis.com/v1beta/models/{model}:generateContent
Stream ContentPOST
Stream text generation responseshttps://us-central1-aiplatform.googleapis.com/v1beta/models/{model}:streamGenerateContent

Family Comparison: gemini-2

ModelContextMax out
gemini-robotics-er-2-preview131K66K
gemini-robotics-er-2-streaming-preview131K66K

API

GET/v1/models/vertex/gemini-robotics-er-2-preview