google

Google: Gemma 3 4B

Gemma 3 4B from Google is designed for handling text and image inputs with a context length of up to 131,072 tokens. However, it does not support reasoning or structured output, nor can it interface directly with tools. This model stands out for its capability in processing both textual and visual data but lacks advanced analytical features. Given its blended benchmark score of 14.5 across three independent benchmarks, Gemma 3 4B is a solid choice for applications that require text and image processing without the need for complex reasoning or structured outputs. Its price point of $0.05 per million input tokens and $0.1 per million output tokens makes it competitive for projects with moderate computational demands; however, users should consider its performance across fewer benchmark tests before committing.

Quality Score
81/100
price + capability + benchmarks
Input Price
$0.05
per 1M tokens
Output Price
$0.10
per 1M tokens
Context Window
131,072
tokens

Benchmark results

Independent, published benchmarks. Blended score 14.5 across 3 benchmarks, last refreshed 2026-07-21. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 1.8
AI Index Coding software engineering tasks 4.4
EQ-Bench emotional understanding in dialogue 42.4
Model ID
google/gemma-3-4b-it
Vendor
google
Released
March 2025
Tokenizer
Gemini
Input Modalities
text, image
Output Modalities
text
Max Output
16,384 tokens
Tool Calling
not supported
Structured Output
✓ supported
Reasoning Mode
not supported
Vision
✓ accepts images
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.05/M input and $0.10/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.03
A month of a busy support chatbot 5M in / 2M out $0.45

Similar models

Quick answers

How much does Google: Gemma 3 4B cost?
$0.05 per million input tokens and $0.10 per million output tokens.
What is Google: Gemma 3 4B's context window?
131,072 tokens, roughly 196 pages of text in a single request.
Does Google: Gemma 3 4B support tool calling?
It supports structured output.
Can Google: Gemma 3 4B process images?
Yes, it accepts image input.