Low-latency Gemini model for high-volume multimodal and agent workloads
Specification
most-agreed values
Context
1M
Max output
66K
Released
2026-05-07
Knowledge cutoff
2025-01
Retires
—
Open weights
no
Input
text, image, video, audio, pdf
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.275
Output
$1.65
Cache read
$0.0275
Cache write
$0.0917
Available from 2 hosts
More from Google
most-hosted first