Gemma 3 4B

Vision

Google's Gemma 3 4B multimodal model. Supports both text and vision inputs with strong instruction following.

Pricing

Input

$0.03/1M

Output

$0.08/1M

Context Length

128K tokens

Max Completion

8K tokens

Capabilities

Chat

Vision

Tool Calling

Technical Details

Model ID

gemma3-4b

Tokenizer

Gemma

HuggingFace

google/gemma-3-4b-it

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llamagate.ai/v1",
    api_key="your-api-key",
)

response = client.chat.completions.create(
    model="gemma3-4b",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response.choices[0].message.content)

Start Using Gemma 3 4B

Create an account and start building with just $5.