google/gemini-robotics-er-2-preview
Google embodied reasoning preview endpoint for robotics, spatial reasoning, multi-step tool orchestration and video progress understanding. It accepts text, images, video and audio, returns text and supports function calling, code execution and structured outputs.
- Context window
- 131K
- Input
- Audio · Image · Text · Video
- Output
- Text
- Released
- 2026-07-30
- Max output
- 66K
- Capabilities
- Reasoning, Structured, Tool call
IN
$1.00
USD / 1,000,000 token
Google Gemini API paid tier; introductory price through 2026-12-31; future rates from 2027-01-01 are not current prices; standard
OUT
$5.00
USD / 1,000,000 token
Google Gemini API paid tier; introductory price through 2026-12-31; future rates from 2027-01-01 are not current prices; standard; including thinking tokens
Cache read
$0.10
USD / 1,000,000 token
Google Gemini API paid tier; introductory price through 2026-12-31; future rates from 2027-01-01 are not current prices; standard; storage billed separately
Performance
Overall capability
25.0/100
- Coding
- —
- Reasoning
- —
- Professional work
- —
- Knowledge & language
- —
No evaluation results available.
Providers
No providers found
ModelRegistry · Catalog updated 2026-10-20