gemma-3-27b-it

completions

On:deepinfraparasail

gemma-3-27b-it

completions

Published by: googleProviders:

deepinfra parasail

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. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)

Provider	Input	Output
deepinfra	$0.09 / 1M tokens	$0.17 / 1M tokens
parasail	$0.1 / 1M tokens	$0.4 / 1M tokens

Released

Mar 12, 2025

Knowledge

Sep 13, 2024

Context

131072

Input

$0.09 / 1M tokens

Output

$0.17 / 1M tokens

Accepts: text, image

Returns: text

Providers	Context	Input Price	Output Price	Input Formats	Output Formats	License
deepinfra	131072 tokens	$0.09 / 1M tokens	$0.17 / 1M tokens	textimage	text	Gemma
parasail	131072 tokens	$0.1 / 1M tokens	$0.4 / 1M tokens	textimage	text	Gemma

Released Mar 12, 2025Knowledge Cutoff: Sep 13, 2024

Access gemma-3-27b-it through LangDB AI Gateway

Recommended

Integrate with google's gemma-3-27b-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

Available from 2 providers

Provider:

Benchmark Results for gemma-3-27b-it

Category Performance Scores:

Academia: Score 32.30 (Top 64% - Rank #221)
Finance: Score 21.35 (Top 74% - Rank #256)
Marketing: Score 30.67 (Top 86% - Rank #297)
Maths: Score 20.70 (Top 69% - Rank #239)
Programming: Score 17.40 (Top 75% - Rank #259)
Science: Score 47.96 (Top 67% - Rank #232)
Writing: Score 31.61 (Top 89% - Rank #308)

Overall Performance: 28.855079365079366 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	25.30	Top 45%	Mathematics
AA Coding Index	17.40	Top 75%	Programming
AAII	22.00	Top 64%	General
AA Math Index	20.70	Top 69%	Mathematics
GPQA	42.60	Top 67%	STEM (Physics, Chemistry, Biology)
HLE	4.70	Top 39%	General Knowledge
HumanEval	87.80	Top 43%	Programming
LiveCodeBench	13.70	Top 84%	Programming
MATH-500	88.30	Top 39%	Mathematics
MMLU-Pro	67.20	Top 63%	General Knowledge
SciCode	21.20	Top 68%	Scientific

HumanEval Score: 87.80 - Coding capability benchmark

GPQA Score: 42.60 - 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

25.3

Mathematics

AA Coding Index

17.4

Programming

AAII

22.0

General

AA Math Index

20.7

Mathematics

GPQA

42.6

STEM (Physics, Chemistry, Biology)

HLE

4.7

General Knowledge

HumanEval

87.8

Programming

LiveCodeBench

13.7

Programming

MATH-500

88.3

Mathematics

MMLU-Pro

67.2

General Knowledge

SciCode

21.2

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	HumanEval	LiveCodeBench	MATH-500	MMLU-Pro	SciCode
Score	25.3	17.4	22.0	20.7	42.6	4.7	87.8	13.7	88.3	67.2	21.2

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for gemma-3-27b-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-3-27b-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-3-27b-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-3-27b-it",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: gemma-3-27b-it

Provider: deepinfra

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

Create API Key

Related Models

Similar models from deepinfra

gemma-3-27b-it

gemma-3-27b-it

Access gemma-3-27b-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-3-27b-it by deepinfra - AI Model Details, Pricing, and Performance Metrics

gemma-3-27b-it

gemma-3-27b-it

Access gemma-3-27b-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