Gemini Robotics-ER 1.6 Preview

Name: Gemini Robotics-ER 1.6 Preview
Author: Google

Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics

Live

Open / InstallLast updated August 5, 2026

Description

Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics. Supports a context window of 131,072 tokens. Supports extended reasoning. Supports tool calling. Input priced at $1 per million tokens. Weights are not publicly released; access is via the provider API.

Author

Google

Platform

api

Pricing model

paid

Capabilities

Text generation
131,072 token context
Extended reasoning
Tool calling
File attachments
Image input
Audio input

Benchmarks

No benchmark results have been added yet.