Gemma-2 27B is a high-performance language model designed to handle a diverse range of text generation tasks, including question answering, summarization, and reasoning. It offers significant improvements in efficiency and performance compared to its predecessors, making it suitable for various applications in natural language processing.
The model is intended for software developers and researchers looking to implement advanced language processing capabilities in applications such as chatbots, content creation tools, and automated customer support systems.
Gemma-2 27B supports multiple languages, primarily focusing on English while also accommodating other widely spoken languages.
Gemma-2 27B employs a transformer architecture optimized for both performance and efficiency. It utilizes techniques such as grouped-query attention to enhance inference speed while maintaining high-quality outputs.
The model was trained on a diverse dataset consisting of over 13 trillion tokens sourced from web documents, code repositories, and scientific literature. This extensive training allows the model to generalize effectively across various topics.
Gemma-2-27B-IT has demonstrated impressive performance metrics:
The model is available on the AI/ML API platform as "Gemma 2 (27b)" .
Google emphasizes ethical considerations in AI development by promoting transparency regarding the model's capabilities and limitations. The company encourages responsible usage to prevent misuse or harmful applications of generated content.
Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/termsGemma models are available under a commercially-friendly license that allows both research and commercial usage rights while ensuring compliance with ethical standards.
Get Gemma 2 (27b) API here.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "google/gemma-2-27b-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-2-27b-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-2-27b-it","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| MMLU | 75.2 | Multi-discipline knowledge across 57 school and professional subjects | Source | September 22, 2026 |
| HellaSwag | 86.4 | Commonsense sentence completion with adversarially filtered wrong endings | Source | September 22, 2026 |
| HumanEval | 51.8 | Python function synthesis from a docstring, scored by unit tests (pass@1) | Source | September 22, 2026 |
| GSM8K | 74.0 | Grade-school maths word problems requiring multi-step arithmetic | Source | September 22, 2026 |
| MATH | 42.3 | Competition mathematics problems across five difficulty levels | Source | September 22, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Gemma 2 (27b) This page | Reasoning + agents | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Gemma 2 (27b) has a 8,192 tokens context window and can return up to 2,048 tokens.
Gemma 2 (27b) takes image, text as input and returns text.
Use google/gemma-2-27b-it as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Gemma 2 (27b) is priced at input $0.89401 / 1M tokens, output $0.89401 / 1M tokens.
Yes, Gemma 2 (27b) can stream responses as they are generated.
Yes, Gemma 2 (27b) accepts image input alongside text.
Gemma 2 (27b) was built by Google.
