Gemma 3 4B

google

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.

Try Now

Capabilities

Image Input

Example Use Cases

Lightweight multimodal task

Fast affordable vision-language task

On-device or edge deployment

Technical Specifications

Context Window

131,072 tokens

Max Output

131,072 tokens

Cache Miss Cost

$0.04 per 1M tokens

Non-Reasoning Cost

$0.08 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.5 Plus