Gemma 2 27B

Google Gemma 2 Generally Available Jun 2024

Google's 27B open-weight model from the Gemma 2 family. Competitive with Llama 3 70B on many benchmarks at a fraction of the size, using a novel interleaved attention architecture.

Context

tokens

Input

$0.65

per MTok

Output

$0.65

per MTok

Model Page API Docs

About

Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...

Modalities

Input

Text Code

Output

Text Code

Code Examples

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-2-27b",
    "messages": [
      { "role": "user", "content": "Explain quantum entanglement in one sentence." }
    ]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key=os.environ["OPENROUTER_API_KEY"],
)
response = client.chat.completions.create(
    model="google/gemma-2-27b",
    messages=[
        {"role": "user", "content": "Explain quantum entanglement in one sentence."},
    ],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: process.env.OPENROUTER_API_KEY,
});

const response = await client.chat.completions.create({
  model: "google/gemma-2-27b",
  messages: [
    { role: "user", content: "Explain quantum entanglement in one sentence." },
  ],
});
console.log(response.choices[0].message.content);

API Parameters

Name	Type	Default	Description
`frequency_penalty`	number	0	Penalize tokens by their frequency so far. Positive values reduce repetition.
`max_tokens` deprecated	integer	—	Deprecated. Use max_completion_tokens.
`presence_penalty`	number	0	Penalize tokens that have appeared at all so far. Positive values encourage new topics.
`repetition_penalty`	number	1	Penalize repeated tokens (>1.0 reduces repetition, <1.0 encourages it).
`response_format`	one of	—	Constrain output to a JSON schema or an enum (structured outputs).
`seed`	integer	—	Deterministic seed for sampling. Same seed + same prompt produces identical output.
`stop`	array	—	Up to 4 sequences where the API will stop generating tokens.
`structured_outputs`	boolean	—	Enable JSON-schema-constrained output.
`temperature`	number	1	Sampling temperature; higher values produce more random output. 0 is deterministic.
`top_p`	number	1	Nucleus sampling: consider only tokens whose cumulative probability ≥ top_p.

Standard OpenAI-compatible parameters. Consult the provider docs for model-specific behaviour.

Benchmark Scores

Benchmark	Score	Methodology
MMLU	75.2%	5-shot
HumanEval	51.8%	0-shot
MATH	42.3%	4-shot
GSM8K	74%	8-shot

Performance

tok / sec

output speed

Source: Gemma 2 technical paper + Artificial Analysis, April 2026

Strengths & Limitations

Best For

Compact 27B for strong benchmark scores

Gemma licence allows broad use

Interleaved local/global attention

Good for on-device or limited-GPU deployments

Limitations

8K context window only

No vision, audio, or tool use in base model

Superseded by Gemma 3 for new deployments