---
title: "Gemma 3 4B | AI Models | Inference.net"
description: "Run Gemma 3 4B (Google) on Inference.net. 131K context. tool-calling, structured outputs, vision input. Deploy with an OpenAI-compatible API and pay-per-token pricing."
url: "https://inference.net/models/gemma-3-4b-it/"
---

Google Multimodal Model

# Gemma 3 4B

Google's compact open-weight Gemma: the 4B instruction-tuned tier, multimodal (text and image input) with a 128K context. Built for on-device-adjacent workloads — routing, classification, drafting — where unit cost and latency dominate.

[Get Started](https://inference.net/signin/) [Documentation](https://docs.inference.net)

Model details

Developed by Google

Size 4B parameters

Context window 128K tokens

Max output 8K tokens

Model API pricing Per 1M tokens

Input $0.05

Output $0.10

[See all pricing](https://inference.net/pricing/)

```
import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.inference.net/v1",
  apiKey: "<YOUR_API_KEY>",
});

const completion = await openai.chat.completions.create({
  model: "gemma-3-4b-it",
  messages: [
    {
      role: "user",
      content: "What is the meaning of life?"
    }
  ],
  stream: true,
});

for await (const chunk of completion) {
  process.stdout.write(chunk.choices[0]?.delta.content as string);
}
```

## Related models

[See all models](https://inference.net/models/)

Model

[Kimi K3 1024K input context Vision Tools Reasoning $3.00 / $15.00 2 variants](https://inference.net/models/kimi-k3/)

[MiniMax M3.1 Flash 977K input context Vision Tools Reasoning $0.10 / $0.50](https://inference.net/models/minimax-m3.1-flash/)

[Nemotron 3 Super 256K input context Tools $0.102 / $0.48](https://inference.net/models/nemotron-3-super/)

[Schematron V2 Small 125K input context $0.05 / $0.23](https://inference.net/models/schematron-v2-small/)

[Schematron V2 Turbo 125K input context $0.03 / $0.15](https://inference.net/models/schematron-v2-turbo/)

## Start building with Gemma 3 4B today

Serverless, OpenAI-compatible, and billed per token. No commitments.

[Get Started](https://inference.net/signin/) [Read the docs](https://docs.inference.net)