Skip to main content
Back to models

Model comparison

Compare model identity and capabilities.

Selected

Gemini Robotics-ER 1.6 Preview

google/gemini-robotics-er-1.6-preview

Google / Gemini

View model

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

Released
2026-04-14
Context window
131K
Max output
66K
Weights
Closed
Modalities
TextInputImageInputVideoInputAudioInputTextOutput
Capabilities
AttachmentsReasoningTool callStructuredTemperature
Providers
Google

Select at least two models to compare.

Compare models
1 models selected
Compare