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.
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.
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.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "google/gemma-3-27b-it", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = 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": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST 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":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 4.9 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 22, 2026 |
| Coding | 10.1 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 22, 2026 |
| Math | 20.7 | Composite score across standardised mathematics evaluations, measured independently by Artificial Analysis | Source | September 22, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Gemma 3 (27B) This page | Chat + assistants | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Gemma 3 (27B) has a 128,000 tokens context window and can return up to 131,072 tokens.
Gemma 3 (27B) takes image, text as input and returns text.
Use google/gemma-3-27b-it as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Gemma 3 (27B) became available on September 9, 2025.
Gemma 3 (27B) is priced at input $0.20631 / 1M tokens, output $0.632684 / 1M tokens, cached input $0.103155 / 1M tokens.
Yes, Gemma 3 (27B) can stream responses as they are generated.
Yes, Gemma 3 (27B) accepts image input alongside text.
Gemma 3 (27B) was built by Google.
