How much does Gemma 3n 4B API cost on Routeway?

Gemma 3n 4B costs $0.05/1M input tokens on Routeway, offering competitive pricing compared to google's direct rates.

Is Gemma 3n 4B compatible with OpenAI's API format?

Yes, Gemma 3n 4B on Routeway uses the same API format as OpenAI, making it easy to switch with zero code changes. Simply update your API endpoint and key.

What is the context window for Gemma 3n 4B?

Gemma 3n 4B supports a context window of 8,192 tokens, allowing for extensive conversations and document processing.

How do I get started with Gemma 3n 4B on Routeway?

Getting started is easy: 1) Create a Routeway account, 2) Generate your API key, 3) Use our OpenAI-compatible endpoint with Gemma 3n 4B as the model parameter.

Back to Models

Gemma 3n 4B

Available

5% off— A 5% discount applies to input and output token pricing only.

Description

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 such as text generation, speech recognition, translation, and image analysis. Leveraging innovations like Per-Layer Embedding (PLE) caching and the MatFormer architecture, Gemma 3n dynamically manages memory usage and computational load by selectively activating model parameters, significantly reducing runtime resource requirements. This model supports a wide linguistic range (trained in over 140 languages) and features a flexible 32K token context window. Gemma 3n can selectively load parameters, optimizing memory and computational efficiency based on the task or device capabilities, making it well-suited for privacy-focused, offline-capable applications and on-device AI solutions. [Read more in the blog post](https://developers.googleblog.com/en/introducing-gemma-3n/)

At a Glance

Key pricing and model details available for this model.

Input price

$0.05$0.05

per 1M tokens

Output price

$0.04$0.04

per 1M tokens

Context window

tokens

Hallucination rate

96.6%

Token Pricing

Token pricing normalized to per-million-token rates.

Input / 1M tokens

$0.05$0.05

Output / 1M tokens

$0.04$0.04

Cache Read / 1M tokens

Free

Token Pricing Details

Rates are shown per 1M tokens for easier comparison.

Input / 1M tokens	$0.05
Input unit	1M tokens
Output / 1M tokens	$0.04
Output unit	1M tokens
Cache Read / 1M tokens	Free
Cache Read unit	1M tokens

Feature Availability

Capabilities explicitly listed in the current payload.

LLM

Available

Yes

Vision

Not listed

Function calling

Available

Yes

Reasoning

Not listed

Supported Parameters

frequency_penalty

logit_bias

max_completion_tokens

presence_penalty

reasoning_effort

response_format

stop

temperature

tool_choice

tools

top_p

Artificial Analysis

Index scores currently reported for this model.

Intelligence Index

6.4

Coding Index

4.2

Math Index

14.3

Category Radar

Aggregated from the benchmark values present for reasoning, code, math, and accuracy.

Benchmark Breakdown

Detailed benchmark results drawn from the current payload.

Intelligence Index

index

Overall 'how smart' score for an AI, combining reasoning, math, coding, and knowledge.

6.4

Reported score

Coding Index

index

How well the model handles real programming tasks.

4.2

Reported score

Math Index

index

Composite score measuring mathematical reasoning and problem-solving.

14.3

Reported score

MMLU-Pro

reasoning

A broad and difficult knowledge-and-reasoning benchmark across many subjects.

48.8%

Reported score

GPQA

reasoning

Graduate-level science questions designed to be difficult to shortcut.

29.6%

Reported score

HLE

reasoning

A very hard expert-level exam across a wide range of subjects.

4.4%

Reported score

LiveCodeBench

code

Fresh programming tasks meant to test current coding ability.

14.6%

Reported score

SciCode

code

Coding tasks drawn from real scientific workflows.

8.1%

Reported score

MATH-500

math

A set of difficult competition-style math problems.

77.1%

Reported score

AIME

math

Advanced math competition questions.

13.7%

Reported score

AIME 2025

math

The 2025 AIME benchmark used to reduce data leakage concerns.

14.3%

Reported score

IFBench

accuracy

Measures how precisely the model follows detailed instructions.

27.9%

Reported score

LCR

accuracy

Tests long-context reasoning over large documents and conversations.

Reported score

TerminalBench Hard

code

A harder coding-agent benchmark for complex multi-step terminal tasks.

2.3%

Reported score

Tau2

accuracy

Evaluates realistic agent behavior in tool-using support workflows.

Reported score

Code Samples

Quick start with the Routeway API

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: "https://api.routeway.ai/v1",
  apiKey: "<YOUR_API_KEY>",
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "gemma-3n-e4b-it",
    messages: [
      {
        role: "user",
        content: "Explain quantum computing in simple terms"
      }
    ]
  });

  console.log(completion.choices[0].message);
}

main();