Google's Gemini 4 model for everyday coding and agentic workflows, with four thinking levels and a 1M-token context window
Specification
most-agreed values
Context
1M
Max output
66K
Released
2026-11-12
Knowledge cutoff
2026-03
Retires
—
Open weights
no
Input
text, image, video, audio, pdf
Output
text
Price
US dollars per million tokens · most-agreed
Input
$1.65
Output
$8.25
Cache read
$0.0825
Cache write
$0.0917
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| edenai | $1.65 | $8.25 | $0.0825 | $0.0917 | 1M | 66K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-11-13 | edenai | Cache read | $0.075 |
| 2026-11-14 | edenai | Cache read | $0.0825 |
| 2026-11-13 | edenai | Cache write | $0.0833 |
| 2026-11-14 | edenai | Cache write | $0.0917 |
| 2026-11-13 | edenai | Input | $1.50 |
| 2026-11-14 | edenai | Input | $1.65 |
| 2026-11-13 | edenai | Output | $7.50 |
| 2026-11-14 | edenai | Output | $8.25 |
More from Google
most-hosted first