Gemini Robotics-ER 1.6 Preview
google/gemini-robotics-er-1.6-preview
Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics
Capabilities
ReasoningYes
Tool callingYes
Structured outputYes
TemperatureSupported
AttachmentYes
Open weightsNo
Limits
Context131,072 tokens
Max inputN/A
Max output65,536 tokens
Details
Familygemini
Knowledge cutoff2025-01
Release date2026-04-14
Last updated2026-04-14
Modalities
Inputtext, image, video, audio
Outputtext
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A