Google: Gemma 3 4B
google/gemma-3-4b-it
Cheaper than 95% of paidJSONVision
Intelligence
—
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.050
18th cheapest
Context
131K
16K max out
How it compares
Cheaper than95%
of all ranked models
Overview
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,...
Providers & pricing (1)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfrabf16 | $0.050 | $0.100 | 131K | 100% |
Specifications
Context window131K
Max output16K
Knowledge cutoffAug 2024
Input modalitiestext, image
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsgoogle/gemma-3-4b-it ↗
Gemma 3 4B FAQ
How much does Gemma 3 4B cost?
Gemma 3 4B costs $0.050 per million input tokens and $0.100 per million output tokens via OpenRouter, making it 18th cheapest of 332 paid models.
What is Gemma 3 4B's context window?
Gemma 3 4B supports a 131K-token context window and can output up to 16K tokens. It accepts text, image input.
More from google
All Gemma 3 4B alternatives →Compare head-to-head
Google: Gemma 3 4B vs Google: Gemini 3.6 FlashGoogle: Gemma 3 4B vs Google: Gemini 3.6 Flash (batch)Google: Gemma 3 4B vs Google: Gemini 3.5 Flash LiteGoogle: Gemma 3 4B vs Google: Gemini 3.5 Flash Lite (batch)Google: Gemma 3 4B vs Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google: Gemma 3 4B vs Google: Nano Banana 2 (Gemini 3.1 Flash Image)