Auto-generated comparison

google/gemma-3-4b-it vs google/gemma-4-31B-it

google/gemma-3-4b-it wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.

Side-by-side comparison

Capabilitygoogle/gemma-3-4b-itgoogle/gemma-4-31B-itWinner
Context window
Maximum number of input tokens the model can attend to in a single request.
131KUnknown🏆 google/gemma-3-4b-it
Input price (per 1M)
Cost per million input tokens billed by the provider.
$0.05Custom🏆 google/gemma-3-4b-it
Output price (per 1M)
Cost per million output tokens billed by the provider.
$0.10Custom🏆 google/gemma-3-4b-it
Tool / function calling
First-class support for emitting structured tool calls.
Tie
Vision input
Accepts image inputs alongside text.
Yes🏆 google/gemma-3-4b-it
Reasoning mode
Internal chain-of-thought / extended-thinking support.
Tie

Frequently asked questions

Is google/gemma-3-4b-it better than google/gemma-4-31B-it?

google/gemma-3-4b-it wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.

What's the price difference between google/gemma-3-4b-it and google/gemma-4-31B-it?

Input: $0.05 vs Custom per 1M tokens. Output: $0.10 vs Custom per 1M tokens.

What context windows do google/gemma-3-4b-it and google/gemma-4-31B-it support?

google/gemma-3-4b-it supports up to 131K tokens. google/gemma-4-31B-it supports up to Unknown tokens.

Do both google/gemma-3-4b-it and google/gemma-4-31B-it support tool calling?

google/gemma-3-4b-it: not advertised. google/gemma-4-31B-it: not advertised.

Compare google/gemma-3-4b-it with other models

Compare google/gemma-4-31B-it with other models