Gemma 4
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
Context
131,072
Max output
131,072
Input / 1M
$2.00
Output / 1M
$5.00
Providers
1
01Profile
Profile
Released
2026-04-02
Last updated
2026-04-02
Knowledge cutoff
—
Weights
Open
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 1 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
5+ recent events since 2026-04-02
2026-08-16Price cutllmtrinput / 1M$5.00→ $2.00
2026-08-16Price cutllmtroutput / 1M$10.00→ $5.00
2026-08-16ContextllmtrContext window32,768→ 131,072
2026-08-16ContextllmtrMax output8,192→ 131,072
2026-06-08Addedllmtroffering→ new