Routeway Logo
Back to Models
Google

Gemma 3n 2B

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

Description

Gemma 3n E2B IT is a multimodal, instruction-tuned model developed by Google DeepMind, designed to operate efficiently at an effective parameter size of 2B while leveraging a 6B architecture. Based on the MatFormer architecture, it supports nested submodels and modular composition via the Mix-and-Match framework. Gemma 3n models are optimized for low-resource deployment, offering 32K context length and strong multilingual and reasoning performance across common benchmarks. This variant is trained on a diverse corpus including code, math, web, and multimodal data.

At a Glance

Key pricing and model details available for this model.

Input price

$0.03$0.03

per 1M tokens

Output price

$0.02$0.02

per 1M tokens

Context window

8K

tokens

Hallucination rate

92.6%

Token Pricing

Token pricing normalized to per-million-token rates.

Input / 1M tokens

$0.03$0.03

Output / 1M tokens

$0.02$0.02

Cache Read / 1M tokens

Free

Token Pricing Details

Rates are shown per 1M tokens for easier comparison.

Input / 1M tokens$0.03
Input unit1M tokens
Output / 1M tokens$0.02
Output unit1M tokens
Cache Read / 1M tokensFree
Cache Read unit1M tokens

Feature Availability

Capabilities explicitly listed in the current payload.

LLM

Available

Yes

Vision

Not listed

No

Function calling

Available

Yes

Reasoning

Not listed

No

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

7.7

Coding Index

0

Math Index

2.3

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.

7.7

Reported score

Coding Index

index

How well the model handles real programming tasks.

0

Reported score

Math Index

index

Composite score measuring mathematical reasoning and problem-solving.

2.3

Reported score

MMLU-Pro

reasoning

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

5.5%

Reported score

GPQA

reasoning

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

22.4%

Reported score

HLE

reasoning

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

4.2%

Reported score

LiveCodeBench

code

Fresh programming tasks meant to test current coding ability.

0.3%

Reported score

SciCode

code

Coding tasks drawn from real scientific workflows.

0%

Reported score

MATH-500

math

A set of difficult competition-style math problems.

69.1%

Reported score

AIME

math

Advanced math competition questions.

9%

Reported score

AIME 2025

math

The 2025 AIME benchmark used to reduce data leakage concerns.

2.3%

Reported score

IFBench

accuracy

Measures how precisely the model follows detailed instructions.

12.1%

Reported score

LCR

accuracy

Tests long-context reasoning over large documents and conversations.

0%

Reported score

TerminalBench Hard

code

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

0%

Reported score

Tau2

accuracy

Evaluates realistic agent behavior in tool-using support workflows.

9.1%

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-e2b-it",
    messages: [
      {
        role: "user",
        content: "Explain quantum computing in simple terms"
      }
    ]
  });

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

main();