Last updated: 16/04/2025

Google Vertex AIOfficial Docs

Gemma 3 4B

gemma-3-4b-it

active

Gemma 3 4B

Gemma 3 is Google's latest open model, featuring the ability to solve a wide variety of tasks with text and image input, support for over 140 languages, and a long 32K context window.

Supports a 32K token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.

Model Timeline

Launch Date

2/25/2025

Capabilities

Text

Input Pricing

$-/ KTok

Context: 32,768 tokens

Output Pricing

$-/ KTok

Vision Capabilities

Image

Input Pricing

$0.0015 /image

Generation Pricing

$0.02 /image

Video

Input Pricing

$0.000774/second

Embeddings

Embeddings Pricing

$0.0001/1k tokens

Fine-Tuning

Fine-Tuning Pricing

$3.00/MTok training

Flatten your repo for AI in seconds

Flatten repos. Prompt faster. One click → one GPT-ready file

Free Online & Desktop