Gemini Robotics
Google DeepMind's family of vision-language-action and embodied-reasoning models for robotics.
Core record
Status: Research / limited access
Access: Research / trusted tester access
API status: Limited / research access
Openness: Closed
Modalities: Vision, language and robot actions
Best suited for
Embodied reasoning, robot control, dexterity and physical-world planning.
Limitations
General public access is limited; hardware support and capabilities depend on the specific Robotics model and partner environment.
API / auth
Interface: Limited / research access
Base URL: Pending
Authentication: Pending field audit
Compatibility: Pending field audit
Rate limits: Pending field audit
Deployment
Models / versions
| Model | Context | Max output | Modalities | License | Status |
|---|---|---|---|---|---|
| Pending dedicated model/version audit. | |||||
Pricing snapshots
| SKU / model | Unit | Input | Output | Flat | Notes |
|---|---|---|---|---|---|
| Pending dedicated pricing audit. Artificial Index does not infer current prices. | |||||
Integrations
Regions
Pending field audit
Governance / privacy
Pending field audit
Benchmarks
Pending methodology-aware benchmark audit unless separately documented. Vendor and independent benchmark results are kept distinct.