Name: Google: Gemma 3 4B
Author: google

Question 1

What is Gemma 3 4B?

Accepted Answer

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.

Question 2

How much does Gemma 3 4B cost?

Accepted Answer

Gemma 3 4B costs $0.05/M input tokens and $0.10/M output tokens.

Question 3

What is the context length of Gemma 3 4B?

Accepted Answer

Gemma 3 4B has a 131,072 token context window. It supports up to 16,384 completion tokens.

Question 4

Does Gemma 3 4B support tool calling and structured outputs?

Accepted Answer

The Gemma 3 4B endpoint shown on this page does not accept tools, so function calling is unavailable there. It also supports structured outputs via a JSON schema in response_format.

Question 5

What inputs and outputs does Gemma 3 4B support?

Accepted Answer

Gemma 3 4B accepts text and images as input and returns text.

Question 6

What other text models does Google have?

Accepted Answer

Gemini 3.7 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash Lite and 25 more are other text models from Google.

Question 7

When was Gemma 3 4B released?

Accepted Answer

Gemma 3 4B was released on 2025-03-13. Its knowledge cutoff is 2024-08-31.

Google: Gemma 3 4B

google/gemma-3-4b-it

Google: Gemma 3 4B

google/gemma-3-4b-it

Frequently asked questions

Frequently asked questions