← Models

Gemini Robotics-ER 1.6

Google · Gemini Robotics

Google DeepMind's robotics-tuned Gemini for embodied reasoning, spatial planning, and physical agent tasks.

Type
multimodal
Context
131K tokens
Max Output
66K tokens
Status
preview
Input
$1/1M tok
Output
$5/1M tok
API Access
Yes
License
proprietary
robotics embodied-reasoning vision spatial-reasoning tool-use preview
Released April 2026 · Updated June 8, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on June 8, 2026.

Gemini Robotics-ER 1.6 is Google’s robotics-tuned Gemini variant, published as gemini-robotics-er-1.6-preview. It is built as a vision-language model for advanced reasoning in the physical world: interpreting complex visual data, performing spatial reasoning, and planning actions from natural-language commands.

This is a specialized model. For typical chat or coding workflows, the standard Gemini 3.1 Pro line is the right reference. Robotics-ER 1.6 is the entry to consult when the question is “how does Google approach embodied reasoning for physical agents?”

Capabilities

Google’s current model and pricing docs highlight a specific capability profile:

  • Embodied reasoning for robots and physical-world agents.
  • Text, image, video, and audio inputs with text output.
  • Spatial and physical reasoning for interpreting visual scenes and planning actions.
  • Tool-oriented capabilities including function calling, code execution, file search, URL context, search grounding, Google Maps grounding, Computer Use, structured outputs, thinking, caching, batch, flex, and priority inference.
  • No image generation, audio generation, or Live API support on the current model page.

Technical Details

Public anchors at this snapshot:

  • Model ID: gemini-robotics-er-1.6-preview
  • Input token limit: 131,072
  • Output token limit: 65,536
  • Inputs: text, images, video, and audio
  • Output: text
  • Designed as a planner and reasoning model for physical-world workflows, not as a generic chat model.
  • Available through the Gemini API and Google AI Studio at this snapshot.
  • Marked as a preview release; DeepMind may adjust capabilities and access before GA.

Google’s deprecation table lists no shutdown date for gemini-robotics-er-1.6-preview at this snapshot.

Pricing & Access

Google’s current pricing page lists a separate Robotics-ER 1.6 Preview tier:

  • Input: $1.00 per 1M text, image, or video tokens
  • Input: $2.00 per 1M audio tokens
  • Output: $5.00 per 1M tokens
  • Batch: 0.50text/image/videoinput,0.50 text/image/video input, 1.00 audio input, and $2.50 output per 1M tokens

Access options:

  • Gemini API for developers
  • Google AI Studio for prototyping
  • Vertex AI / Gemini deployment paths where this preview model is enabled

Best Use Cases

Choose Gemini Robotics-ER 1.6 for:

  • Industrial inspection workflows where reading analog gauges and instruments matters.
  • Robotics planners that delegate motor control to VLA models while keeping high-level reasoning in a frontier model.
  • Embodied agents that need spatial reasoning, multi-view understanding, and tool-call orchestration in one surface.
  • Research and prototyping work around robotics planning, physical-scene interpretation, and tool-using embodied agents.

This is not the right model for general assistant work, chat, or non-physical agentic coding; the standard Gemini 3.1 Pro and Flash lines are better defaults there.

Comparisons

  • Gemini Robotics-ER 1.5 (Google): Direct predecessor; 1.6 is the current documented Robotics-ER preview route.
  • Gemini 3.5 Flash (Google): General-purpose fast Gemini model; Robotics-ER 1.6 is the robotics-specialized counterpart with embodied-reasoning positioning.
  • Other embodied-AI research models: Typically narrower research demos; Robotics-ER 1.6 differentiates through Gemini API access, physical-world reasoning, and broad tool support.