Skip to content
Google

Gemma 3 4B

Gemma 3 4B is a large language model made by Google, added to the catalog on 13 Mar 2025. It has a context window of 131,072 tokens and costs $0.04 per 1M input tokens and $0.05 per 1M output tokens. It accepts text and images and produces text. Typical uses: manage multilingual content efficiently, enhance data analysis with advanced reasoning and streamline complex text-image interactions.

Price checked · source: OpenRouter

What Gemma 3 4B is

Meet Google: Gemma 3 4B, launched in March 2025, a versatile AI model designed by Google to handle both text and image inputs, producing text outputs. With a robust context window of up to 96,000 tokens, it's equipped to manage complex queries across over 140 languages. This model enhances tasks with improved math, reasoning, and chat features, including structured outputs and function calling. Whether you're dealing with large datasets or multilingual content, Gemma 3 4B offers a flexible solution with its advanced capabilities.

Key features

  • Handles up to 96,000 tokens
  • Supports text and image inputs
  • Outputs text responses
  • Understands 140+ languages
  • Enhanced math and reasoning
  • Structured outputs and function calling

Typical uses

  • Manage multilingual content efficiently
  • Enhance data analysis with advanced reasoning
  • Streamline complex text-image interactions
  • Improve structured data processing
  • Facilitate detailed multilingual conversations

Gemma 3 4B pricing

US dollars, list price through OpenRouter.

Checked
Gemma 3 4B price list
ItemStandard
Input, per 1M tokens$0.04
Output, per 1M tokens$0.05
Cached input read, per 1M tokens$0.02

The price last changed on 22 Nov 2026. 3 price changes have been recorded since Gemma 3 4B was added.

Gemma 3 4B price history, newest first, in US dollars per 1M tokens
DateInput /1MOutput /1M
$0.04$0.05
$0.05$0.10
$0.04$0.05
$0.05$0.10
What typical tasks cost with Gemma 3 4B
What a task costsCost
Answer a short question500 in / 300 out$0.0000
Summarise a 50-page PDF25,000 in / 800 out$0.0010
Review a 2,000-line source file30,000 in / 2,000 out$0.0013
Read a 300-page contract set150,000 in / 1,500 out$0.0061
Check the provider's pageToken counts are estimates. A maker's direct price and its monthly plans can differ from the per-token price shown here.

Gemma 3 4B specifications

Gemma 3 4B limits and identity
Model idgoogle/gemma-3-4b-it
Versiongemma-3-4b-it
Context window131,072 tokensAbout 98,304 English words
Max output117,964 tokens
Knowledge cutoff2024-08-31
Added to catalog13 Mar 2025
Gemma 3 4B capabilities
Input typestext, image
Output typestext
Tool callingNo
Structured outputsYes
Reasoning effort controlNo
Content moderationNot applied by provider

Sample outputs

The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.

Write a short essay

RUN20 Nov 2026
Prompt

Write 150 words on how AI might positively upend work, leisure and creativity

Output

Okay, here's a 150-word piece on how AI could positively transform work, leisure, and creativity: Artificial intelligence isn’t just about automation; it’s poised to fundamentally reshape our lives for the better. In the workplace, AI will handle repetitive tasks, freeing humans for strategic thinking, complex problem-solving, and genuine collaboration. This shift could lead to more fulfilling and engaging jobs. Leisure will be revolutionized with personalized entertainment, AI-curated travel experiences, and immersive virtual worlds. Creativity itself will be amplified. AI tools will become powerful collaborators, assisting artists, writers, and musicians with brainstorming, generating variations, and overcoming creative blocks. Imagine instantly prototyping designs, composing music, or writing drafts – AI becomes a springboard for human ingenuity. Ultimately, AI promises a future where we spend less time on drudgery and more time pursuing passions and innovation.

Draw with code

RUN20 Nov 2026
Prompt

Generate an SVG of a pelican riding a bicycle.

Output
Gemma 3 4B's drawing for the prompt: Generate an SVG of a pelican riding a bicycle.

Gemma 3 4B questions

How much does Gemma 3 4B cost?

Gemma 3 4B costs $0.04 per 1M input tokens and $0.05 per 1M output tokens through OpenRouter, as checked on 22 Nov 2026. Summarising a 50-page PDF costs about $0.0010.

What is the context window of Gemma 3 4B?

131,072 tokens, or roughly 98,304 English words. It can write up to 117,964 tokens in one response.

Can Gemma 3 4B read images and PDFs?

It accepts text and images as input. It produces text, so it cannot generate images.

How do I try Gemma 3 4B?

Use the "Try Gemma 3 4B" button on this page. It opens the chat with Gemma 3 4B selected; you type the question and press send.

Try Gemma 3 4B on your own question.

It opens in the chat with this model already selected.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.