Gemma 4 31B IT
gemma4-31b
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
Specification
most-agreed values
Context
100K
Max output
100K
Released
2026-04-02
Knowledge cutoff
2025-01
Retires
—
Open weights
yes
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.46
Output
$2.42
Cache read
$0.40
Available from 5 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| qvac | free | free | — | — | 262K | 33K | — |
| nano-gpt · tee | $0.40 | $1.00 | $0.40 | — | 262K | 131K | — |
| nano-gpt · thinking | $0.40 | $1.00 | $0.40 | — | 262K | 131K | — |
| tinfoil | $0.40 | $1.00 | — | — | 262K | 33K | — |
| regolo-ai | $0.46 | $2.42 | — | — | 100K | 100K | — |
Other listings of this model
this page is one of them
The corpus files Gemma 4 31B IT under several keys. This page is the gemma4-31b listing. The full record — every host, every price and every benchmark score — is on the main Gemma 4 31B IT page.