Gemma 3 4B

Google

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.

Try Now

Capabilities

Image Input

Technical Specifications

Context Window

131,072 tokens

Max Output

131,072 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.04

Non-Reasoning Output

$0.08

Legacy

Made legacy on

Reason

Superseded by Gemma 4 26B A4B with thinking; 4B too small for reliable chat

Recommended Replacement

Gemma 4 26B A4B