Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics
Specification
gemini listing
Context
131K
Max output
66K
Released
2026-04-14
Knowledge cutoff
2025-01
Retires
2026-08-31
Open weights
no
Input
text, image, video, audio
Output
text
Price
US dollars per million tokens · gemini list price
Input
$1.00
Output
$5.00
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| geminivendor | $1.00 | $5.00 | — | — | 131K | 66K | 2026-08-31 |
| orcarouter | $1.00 | $5.00 | — | — | 131K | 66K | — |
More from Google
most-hosted first