Gemini Robotics-ER 1.6 Preview
Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics
Model facts
- Context window
- 131K tokens
- Maximum output
- 66K tokens
- Cheapest paid input
- $1 per 1M tokens
- Cheapest paid output
- $5 per 1M tokens
- Open weights
- no
- Providers
- 1
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, text, image, audio, video.
Observed price history
- 2026-08-24: $1 input / $5 output per 1M tokens
API providers
- OrcaRouter — model id google/gemini-robotics-er-1.6-preview; $1 input / $5 output per 1M tokens; provider documentation