Open Gemma instruction model for efficient chat and self-hosted deployments
Specification
most-agreed values
Context
128K
Max output
128K
Released
2025-09-23
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.351
Output
$0.555
Rate limits
Requests per minute
300
Available from 4 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| publicai | free | free | — | — | 8K | 4K | — |
| cloudflare | $0.351 | $0.555 | — | — | 128K | 128K | — |
| cloudflare-workers-ai · cf | $0.351 | $0.555 | — | — | 128K | 128K | — |
| edenai | $0.351 | $0.555 | — | — | 128K | 128K | — |
More from Google
most-hosted first