Google: Gemma 3n 4B

Google: Gemma 3n 4B

google · Released May 20, 2025 Legacy
Intelligence #390 / 576
29.6 Our Score
Speed
— Not reported
Input #165 / 579
$0.060 per 1M tokens
Output #154 / 579
$0.120 per 1M tokens
Context #395 / 579
32,768 tokens

Analysis Summary

Gemma 3n 4B is the paid variant of Google's compact Gemma 3n model, priced at $0.06 input / $0.12 output per million tokens with a 32K context window. It has no benchmark data published under this specific variant, though the free version benchmarks suggest limited capability.

For businesses, the very low pricing makes it accessible for high-volume, low-complexity tasks, but the small context and absence of tool use or vision support restrict its utility. It is not suited to coding, agentic, or multimodal workflows.

Teams should treat this as an entry-level option for simple text tasks where cost is the dominant factor. The free variant with published benchmarks is a better starting point for evaluation.

Assessed June 6, 2026

Editorial notes

Gemma 3n 4B (paid) is a small Google model with no published benchmarks under this variant, a 32K context, and very low pricing suited only to lightweight experimentation.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence0Technical0Value7.8Content3
Intelligence 0/10
Technical 0/10
Content 3/10
Value 7.8/10

How Google: Gemma 3n 4B compares

Its 33K-token context window is larger than 32% of the models we list. At $0.06 per million input tokens it is cheaper than 72% of comparable models.

About Google: Gemma 3n 4B

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks..

4B Parameters

How does Google: Gemma 3n 4B stack up?

Compare side-by-side with other legacy models.

Compare Models

Model Information

OpenRouter ID google/gemma-3n-e4b-it
Providergoogle
Release Date May 20, 2025
Context Length32,768 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.06 $0.000060
Output $0.12 $0.000120

Live Performance

Live endpoint metrics, refreshed every 30 minutes.

100%
Avg Uptime
393ms
Best Latency (TTFT)
46 tok/s
Best Throughput
1/1
Active Endpoints
Available via: Together

Frequently asked questions about Google: Gemma 3n 4B

How much does Google: Gemma 3n 4B cost?

Google: Gemma 3n 4B costs $0.06 per million input tokens and $0.12 per million output tokens.

What is the context window of Google: Gemma 3n 4B?

Google: Gemma 3n 4B has a context window of 32,768 tokens (33K).

Who created Google: Gemma 3n 4B?

Google: Gemma 3n 4B is developed by Google and was released on May 20, 2025.