google

Gemini Robotics-ER 1.6 Preview

gemini

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

ReasoningTool CallingAttachmentsStructured Output

Context Window

131K

Max Output

66K

Temperature

Yes

Open Weights

No

Knowledge Cutoff

2025-01

Released

2026-04-14

Last Updated

2026-04-14

Modalities

Input:TextImageVideoAudio
Output:Text

Available Providers (0)

Tidak ada provider yang terdaftar untuk model ini.