Gemma 3 (27B) API

Gemma 3 27B is Google's largest Gemma open model, delivering strong reasoning and text generation capabilities.

Modalities: Text, ImageText
In / Out price: $0.1587/$0.4867per 1M
Context window: 125K tokens
Released: Sep 9, 2025

Gemma 3 (27B) overview

Gemma 3 (27B) by Google

Its large context window allows for in-depth processing of extensive content, ideal for tasks requiring long-term contextual awareness.

Gemma 3 (27B) specs

Model ID: google/gemma-3-27b-it
Developer: Google
Context window: 128,000 tokens
Max output: 117,964 tokens
Input: Text, Image
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Gemma 3 (27B) Description

Gemma 3 (27B) is an advanced multimodal AI model integrating both text and vision processing capabilities. With a 96,000-token context window, it excels at handling large volumes of information and supports function calling for complex, multi-step tasks. Engineered for broad deployment, Gemma 3 balances powerful performance with efficiency, running effectively on devices from mobile phones to high-end workstations.

Technical Specifications

Multimodal Inputs: Text and visual data processing
Language Support: Over 140 languages
Deployment: Optimized for single-GPU systems and hardware-constrained environments

Key Features

Multimodal Understanding: Combines text and images to generate coherent and contextually relevant outputs.
Extensive Context Handling: Processes up to 96K tokens to maintain deep content coherence.
Multilingual Proficiency: Supports communication and translation across more than 140 languages.
Efficient Deployment: Designed to perform well even on limited hardware, including mobile devices and single-GPU setups.

Ethical Guidelines

Google underscores responsible AI development by promoting transparency around Gemma 3’s functions and limitations. The company advocates for ethical usage to minimize risks of misuse or generating harmful content.

Licensing

Gemma 3 is distributed under the Gemma Terms of Use, providing a commercially-friendly license that permits both research and commercial applications, contingent on adherence to established ethical standards.

Use cases

AI assistants with image and text modalities
Multilingual content generation, summarization, and translation
Visual data analysis including captioning and Q&A
Research and academic tasks requiring extended context understanding
Code generation and technical assistance

Capabilities

Streaming
Structured outputs

Gemma 3 (27B) benchmarks by Artificial Analysis

See how Gemma 3 (27B) scores on independent evaluations. Data retrieved Nov 3, 2026.

Humanity's Last Exam#369 / 4584.4%Score GPQA Diamond#341 / 43942.8%Score Terminal-Bench 4.0#88 / 1540%Score AA-LCR#324 / 3917.3%Score

Benchmark results

Compare 6 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Gemma 3 (27B) API pricing

Gemma 3 (27B) pricing in US dollars
Usage	Price	Unit
Input	$0.1587	1M tokens
Output	$0.4867	1M tokens
Cached input	$0.0794	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Gemma 3 (27B) vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Gemma 3 (27B)	$0.1587	$0.4867
Gemini 3.5 Flash Lite	$0.3	$2.5
Gemini 3.8 Flash	$0.75	$3.75
Gemini 3.7 Flash	$0.75	$3.75
Gemini 4 Argon	$2	$10

How to use the Gemma 3 (27B) API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "google/gemma-3-27b-it",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "google/gemma-3-27b-it",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemma-3-27b-it",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Gemma 3 (27B) FAQ

What is the context window of Gemma 3 (27B)?

Gemma 3 (27B) has a 128,000 tokens context window and can return up to 131,072 tokens.

What inputs and outputs does Gemma 3 (27B) support?

Gemma 3 (27B) takes image, text as input and returns text.

What is the model ID for Gemma 3 (27B)?

Use google/gemma-3-27b-it as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was Gemma 3 (27B) released?

Gemma 3 (27B) became available on September 9, 2025.

How much does Gemma 3 (27B) cost?

Gemma 3 (27B) costs $0.1587 input and $0.4867 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Gemma 3 (27B) support streaming?

Yes, Gemma 3 (27B) can stream responses as they are generated.

Can Gemma 3 (27B) read images?

Yes, Gemma 3 (27B) accepts image input alongside text.

Who created Gemma 3 (27B)?

Gemma 3 (27B) was built by Google.

Start building with Gemma 3 (27B)

Get API key

Gemma 3 (27B) API

google/gemma-3-27b-it

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "google/gemma-3-27b-it",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "google/gemma-3-27b-it",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemma-3-27b-it",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Gemma 3 (27B) API

Gemma 3 (27B) overview

Gemma 3 (27B) by Google

Gemma 3 (27B) specs

Gemma 3 (27B) Description

Technical Specifications

Key Features

Ethical Guidelines

Licensing

Use cases

Capabilities

Gemma 3 (27B) benchmarks by Artificial Analysis

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Gemma 3 (27B) API pricing

Gemma 3 (27B) vs other models: token prices

How to use the Gemma 3 (27B) API

Build with your agent

1Get your API key

2Make your first request

Related articles

Gemma 3 (27B) FAQ

Start building with Gemma 3 (27B)

Gemma 3 (27B) API

Build with your agent

1Get your API key

2Make your first request

Gemma 3 (27B) API

Gemma 3 (27B) overview

Gemma 3 (27B) by Google

Gemma 3 (27B) specs

Gemma 3 (27B) Description

Technical Specifications

Key Features

Ethical Guidelines

Licensing

Use cases

Capabilities

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Gemma 3 (27B) API pricing

Gemma 3 (27B) vs other models: token prices

How to use the Gemma 3 (27B) API

Build with your agent

1Get your API key

2Make your first request

Models similar to Gemma 3 (27B)

Gemini 4 Argon

Gemini 3.8 Flash

Gemini 3.7 Flash

Mk1.5

Mk1

Mistral Nemo

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Gemma 3 (27B) FAQ

Start building with Gemma 3 (27B)