Google
The latest voice foundation model from Google DeepMind, integrating extended chain-of-thought reasoning directly into live spoken dialogues.
262.144K ctx$0.0035 / min (Live Extended Thinking)
Introducing Gemini Robotics On-Device 2GoogleReleased July 30, 2026
Gemini Robotics On-Device 2
Second-generation on-device physical AI foundation model incorporating tactile sensor feedback for delicate robotic manipulation.
multimodal-realtimeProprietary APIOn-Device Edge Embedded 2.0Context: 32.768K (32,768 tokens)
Technical Specifications
Architecture Type
Second-Gen Edge Vision-Tactile-Action VLA
Total Parameters
Edge VLA 2.0
Context Window
32.768K (32,768 tokens)
Max Output Tokens
4.096K (4,096 tokens)
Knowledge Cutoff
May 2026
Supported Modalities
vision, text, actions, tactile
License & Access
Google Robotics Research License
Benchmark Evaluations
Grasp Adaptation Rate
97.4
Tactile Feedback Latency Ms
25
Deep Architectural Overview
Gemini Robotics On-Device 2 integrates real-time tactile sensor arrays with visual inputs, enabling robotic hands to handle fragile objects like eggs, glassware, and flexible electronics with sub-25ms closed-loop feedback.
Strengths & Considerations
Core Strengths
- 25ms tactile-visual closed-loop reflex
- Handles fragile and non-rigid objects safely
- Zero cloud latency requirement
Known Limitations
- Requires tactile-equipped robotic end-effectors
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.
Google
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)
Google
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)
Google
Universal multilingual speech engine supporting live simultaneous translation and speaker diarization across 100+ languages.
262.144K ctx$0.0025 / min audio (Translate & Live)