Is Gemma 3 4B IT or Gemma 4 26B A4B IT cheaper?

Gemma 3 4B IT is cheaper on output tokens ($0.10 vs $0.34 per 1M).

Which has the larger context window, Gemma 3 4B IT or Gemma 4 26B A4B IT?

Gemma 4 26B A4B IT has the larger context window (262K tokens).

Gemma 3 4B IT vs Gemma 4 26B A4B IT

Gemma 3 4B IT is cheaper on output tokens, while Gemma 4 26B A4B IT offers a larger context window. Choose Gemma 3 4B IT or Gemma 4 26B A4B IT based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Gemma 3 4B IT	Gemma 4 26B A4B IT
Provider	Deep Infra	Deep Infra
Input / 1M tokens	$0.05	$0.07
Output / 1M tokens	$0.10	$0.34
Context window	131K	262K
Parameters	—	—
Open weights	Yes	Yes
Released	Mar 2025	Apr 2026

Gemma 3 4B IT details →Gemma 4 26B A4B IT details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.