MyCaptionAI
Introducing Gemini Robotics 1.5GoogleReleased September 25, 2025

Gemini Robotics 1.5

Cloud-scale spatial reasoning model providing high-level semantic navigation and multi-step plan generation for robotics fleets.

multimodal-realtimeProprietary APIEnterprise Robotics CloudContext: 131.072K (131,072 tokens)
Official Model Card & DocsResearch PaperGitHub Repository

Technical Specifications

Architecture Type
Cloud-Scale Embodied AI Transformer
Total Parameters
Frontier VLA
Context Window
131.072K (131,072 tokens)
Max Output Tokens
8.192K (8,192 tokens)
Knowledge Cutoff
May 2025
Supported Modalities
vision, text, spatial-3d, actions
License & Access
Google Robotics Cloud License

Benchmark Evaluations

Task Completion Rate
91.5
Multi Room Navigation
94.1

Deep Architectural Overview

Gemini Robotics 1.5 bridges cloud foundational reasoning with physical execution, allowing fleets of humanoid and industrial mobile robots to plan long-horizon tasks across complex indoor and outdoor spaces.

Strengths & Considerations

Core Strengths
  • 3D spatial reasoning across multiple camera feeds
  • Long-horizon task decomposition
  • Fleet coordination support
Known Limitations
  • Requires cloud connection for high-level planning

Token & API Pricing

Input Tokens (1M)Contact
Output Tokens (1M)Contact
Pricing is verified directly against Google's developer documentation and API rate sheets.

Similar & Alternative Models

Explore other frontier models from Google and comparable reasoning engines.

Browse all models
Google

Introducing Gemini 3.8 Flash

The latest evolution in the Gemini 3 family, delivering state-of-the-art software engineering (73.7% DeepSWE) and agentic enterprise knowledge workflows.

1.049M ctx$0.75 / 1M tok ($1.50 reg)
September 2, 2026Visit
Google

Introducing Gemini Omni Flash

Universal omnimodal generation model that accepts any combination of text, audio, image, and video to generate any combination of outputs.

1.049M ctx$0.60 / 1M tok (Universal Omni)
August 27, 2026Visit