MyCaptionAI
Introducing Gemini Robotics-ER 2GoogleReleased July 30, 2026

Gemini Robotics-ER 2

Cloud embodied foundation model capable of synthesizing novel robotic tool use and executing complex mechanical assemblies.

multimodal-realtimeProprietary APIEnterprise Robotics Cloud 2.0Context: 524.288K (524,288 tokens)
Official Model Card & DocsResearch PaperGitHub Repository

Technical Specifications

Architecture Type
Extended Reasoning (ER) 2.0 Embodied AI
Total Parameters
Frontier Robotics VLA 2.0
Context Window
524.288K (524,288 tokens)
Max Output Tokens
32.768K (32,768 tokens)
Knowledge Cutoff
May 2026
Supported Modalities
vision, text, spatial-3d, actions
License & Access
Google Robotics Cloud License

Benchmark Evaluations

Tool Synthesis Rate
94.2
Autonomous Assembly Pass
96.8

Deep Architectural Overview

Gemini Robotics-ER 2 enables robots to improvise tools when standard equipment is unavailable, adapting to physical constraints and coordinating complex manufacturing assembly lines.

Strengths & Considerations

Core Strengths
  • Autonomous mechanical assembly at 96.8% accuracy
  • Improvisational tool synthesis
  • Multi-robot cooperative planning
Known Limitations
  • Designed for high-end industrial automation setups

Token & API Pricing

Input Tokens (1M)Contact
Output Tokens (1M)Contact
Pricing is verified directly against Google's developer documentation and API rate sheets.

Similar & Alternative Models

Explore other frontier models from Google and comparable reasoning engines.

Browse all models
Google

Introducing Gemini 3.8 Flash

The latest evolution in the Gemini 3 family, delivering state-of-the-art software engineering (73.7% DeepSWE) and agentic enterprise knowledge workflows.

1.049M ctx$0.75 / 1M tok ($1.50 reg)
September 2, 2026Visit
Google

Introducing Gemini Omni Flash

Universal omnimodal generation model that accepts any combination of text, audio, image, and video to generate any combination of outputs.

1.049M ctx$0.60 / 1M tok (Universal Omni)
August 27, 2026Visit