Gemma 3 (4B) API

Gemma 3 4B is a lightweight open language model from Google, suitable for on-device deployment and efficient inference.

Modalities: Text, ImageText
In / Out price: $0.0529/$0.1058per 1M
Context window: 131K tokens
Released: Sep 9, 2025

Gemma 3 (4B) overview

Gemma 3 (4B) by Google

Gemma 3 (4B) is Google's latest open AI model, designed for seamless text and visual content processing across over 140 languages.

Gemma 3 (4B) specs

Model ID: google/gemma-3-4b-it
Developer: Google
Context window: 131,000 tokens
Max output: 32,768 tokens
Input: Text, Image
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Gemma 3 (4B) Description

Gemma 3 (4B) represents an advanced multimodal AI system that expertly combines capabilities in both text and visual comprehension. Equipped with a substantial 131,000-token context window, it is designed to handle extensive information processing and incorporates function calling to efficiently execute sophisticated tasks. Built for flexible deployment, Gemma 3 delivers a strong mix of high performance and resource efficiency, operating effectively across various platforms ranging from smartphones to high-end workstations.

Technical Specifications

Modality Support: Text and image processing
Language Coverage: Supports over 140 languages

Key Features

Multimodal Understanding: Combines visual and textual inputs to generate coherent, context-aware responses.
Extended Context Handling: Maintains coherence across very long documents and interaction sessions.
Multilingual Processing: Enables seamless communication and translation across diverse languages.‍
Deployment Optimization: Efficient operation on hardware-limited environments including single-GPU systems

Ethical Guidelines

Google prioritizes ethical AI development, emphasizing transparency about Gemma 3’s capabilities and limitations. Responsible usage is strongly encouraged to mitigate risks of misuse or harmful applications related to generated outputs.

Licensing

Gemma 3 is distributed under the Gemma Terms of Use with a commercially-friendly license model. This license supports both research and commercial applications while ensuring adherence to established ethical standards.

Use cases

AI assistants and chatbots with multimodal inputs
Multilingual content creation and summarization
Visual content analysis and captioning
Interactive educational and tutoring applications
Research and development with extended context capability
Intelligent automation and agentic workflows

Capabilities

Streaming

Gemma 3 (4B) benchmarks by Artificial Analysis

See how Gemma 3 (4B) scores on independent evaluations. Data retrieved Nov 3, 2026.

Humanity's Last Exam#309 / 4585.3%Score GPQA Diamond#410 / 43929.1%Score AA-LCR#328 / 3916.7%Score IFBench#279 / 32528.3%Score

Benchmark results

Compare 13 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Gemma 3 (4B) API pricing

Gemma 3 (4B) pricing in US dollars
Usage	Price	Unit
Input	$0.0529	1M tokens
Output	$0.1058	1M tokens
Cached input	$0.0423	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Gemma 3 (4B) vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Gemma 3 (4B)	$0.0529	$0.1058
Gemini 3.5 Flash Lite	$0.3	$2.5
Gemini 3.8 Flash	$0.75	$3.75
Gemini 3.7 Flash	$0.75	$3.75
Gemini 4 Argon	$2	$10

How to use the Gemma 3 (4B) API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "google/gemma-3-4b-it",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "google/gemma-3-4b-it",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemma-3-4b-it",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Gemma 3 (4B) FAQ

What is the context window of Gemma 3 (4B)?

Gemma 3 (4B) has a 131,000 tokens context window and can return up to 32,768 tokens.

What inputs and outputs does Gemma 3 (4B) support?

Gemma 3 (4B) takes image, text as input and returns text.

What is the model ID for Gemma 3 (4B)?

Use google/gemma-3-4b-it as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was Gemma 3 (4B) released?

Gemma 3 (4B) became available on September 9, 2025.

How much does Gemma 3 (4B) cost?

Gemma 3 (4B) costs $0.0529 input and $0.1058 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Gemma 3 (4B) support streaming?

Yes, Gemma 3 (4B) can stream responses as they are generated.

Can Gemma 3 (4B) read images?

Yes, Gemma 3 (4B) accepts image input alongside text.

Who created Gemma 3 (4B)?

Gemma 3 (4B) was built by Google.

Can Gemma 3 4B be deployed on local or on-device hardware?

Yes, it is designed for on-device deployment and efficient inference.

Start building with Gemma 3 (4B)

Get API key

Gemma 3 (4B) API

google/gemma-3-4b-it

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "google/gemma-3-4b-it",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "google/gemma-3-4b-it",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemma-3-4b-it",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Gemma 3 (4B) API

Gemma 3 (4B) overview

Gemma 3 (4B) by Google

Gemma 3 (4B) specs

Gemma 3 (4B) Description

Technical Specifications

Key Features

Ethical Guidelines

Licensing

Use cases

Capabilities

Gemma 3 (4B) benchmarks by Artificial Analysis

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

Gemma 3 (4B) API pricing

Gemma 3 (4B) vs other models: token prices

How to use the Gemma 3 (4B) API

Build with your agent

1Get your API key

2Make your first request

Related articles

Gemma 3 (4B) FAQ

Start building with Gemma 3 (4B)

Gemma 3 (4B) API

Build with your agent

1Get your API key

2Make your first request

Gemma 3 (4B) API

Gemma 3 (4B) overview

Gemma 3 (4B) by Google

Gemma 3 (4B) specs

Gemma 3 (4B) Description

Technical Specifications

Key Features

Ethical Guidelines

Licensing

Use cases

Capabilities

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

Gemma 3 (4B) API pricing

Gemma 3 (4B) vs other models: token prices

How to use the Gemma 3 (4B) API

Build with your agent

1Get your API key

2Make your first request

Models similar to Gemma 3 (4B)

Gemini 4 Argon

Gemini 3.8 Flash

Gemini 3.7 Flash

Schematron V2 Small

Nemotron 3 Nano 30B A3B

Small 3

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Gemma 3 (4B) FAQ

Start building with Gemma 3 (4B)