gemma-3-4b-it

completions

bydeepinfra

gemma-3-4b-it

completions

Published by: googleProvider:

deepinfra

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.

Released

Mar 12, 2025

Knowledge

Aug 1, 2024

License

Gemma

Context

131072

Input

$0.02 / 1M tokens

Output

$0.04 / 1M tokens

Accepts: text, image

Returns: text

Released Mar 12, 2025Knowledge Cutoff: Aug 1, 2024License: Gemma

Context: 131072 Input: $0.02 / 1M tokensOutput: $0.04 / 1M tokensAccepts: text, imageReturns: text

Access gemma-3-4b-it through LangDB AI Gateway

Recommended

Integrate with google's gemma-3-4b-it and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Benchmark Results for gemma-3-4b-it

Category Performance Scores:

Academia: Score 22.32 (Top 83% - Rank #287)
Finance: Score 13.70 (Top 93% - Rank #321)
Marketing: Score 23.83 (Top 95% - Rank #328)
Maths: Score 12.70 (Top 83% - Rank #287)
Programming: Score 9.30 (Top 90% - Rank #311)
Science: Score 32.14 (Top 92% - Rank #318)
Writing: Score 24.17 (Top 96% - Rank #332)

Overall Performance: 19.7384126984127 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	6.30	Top 72%	Mathematics
AA Coding Index	9.30	Top 90%	Programming
AAII	14.70	Top 76%	General
AA Math Index	12.70	Top 83%	Mathematics
GPQA	29.95	Top 93%	STEM (Physics, Chemistry, Biology)
HLE	5.20	Top 30%	General Knowledge
HumanEval	71.30	Top 89%	Programming
LiveCodeBench	11.20	Top 89%	Programming
MATH-500	76.60	Top 56%	Mathematics
MMLU-Pro	42.65	Top 92%	General Knowledge
SciCode	7.30	Top 93%	Scientific

HumanEval Score: 71.30 - Coding capability benchmark

GPQA Score: 29.95 - Graduate-level reasoning benchmark

Model Comparison:

Provider: deepinfra

Model Type: completions

Context Size: 131072 tokens

Comparing against 345 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

6.3

Mathematics

AA Coding Index

9.3

Programming

AAII

14.7

General

AA Math Index

12.7

Mathematics

GPQA

29.9

STEM (Physics, Chemistry, Biology)

HLE

5.2

General Knowledge

HumanEval

71.3

Programming

LiveCodeBench

11.2

Programming

MATH-500

76.6

Mathematics

MMLU-Pro

42.6

General Knowledge

SciCode

7.3

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	HumanEval	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	6.3	9.3	14.7	12.7	29.9	5.2	71.3	11.2	76.6	42.6	7.3

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for gemma-3-4b-it

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="gemma-3-4b-it",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "gemma-3-4b-it",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-3-4b-it",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: gemma-3-4b-it

Provider: deepinfra

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from deepinfra

gemma-3-4b-it

gemma-3-4b-it

Access gemma-3-4b-it through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

deepseek-r1-0528

DeepSeek-R1-Distill-Llama-70B

gemma-3-4b-it by deepinfra - AI Model Details, Pricing, and Performance Metrics

gemma-3-4b-it

gemma-3-4b-it

Access gemma-3-4b-it through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

deepseek-r1-0528

DeepSeek-R1-Distill-Llama-70B