Gemma 2 27B Instruct

Name: Gemma 2 27B Instruct
Author: Google DeepMind

Newer version available: Gemma 3 27B

Released

2024-06-27

Last refreshed

2026-10-17

Status

Researched 9d ago

Open weightsCommercial use: restrictedClassificationJSON / Tool use

Google DeepMind releases · 53 in the last 12 monthsChangelog →

Specifications

Family: Gemma 2
Released: 2024-06-27
Context: 8K
Parameters: 27B
Architecture: Decoder Only
Specialization: general
Openness: Open weights
License: GemmaRestricted
Weights: Unknown
Code: Unknown
Training: Fine-tuned

Created by

Google DeepMind

Pioneering artificial intelligence research.

London, United Kingdom

Founded 2014

Website

Pricing

Output / 1M

$0.400

Input / 1M

$0.400

Cheapest of 6 routes · Replicate API

Providers(6)

OpenRouter Fireworks AI Arcee AI Replicate API NextBit Featherless

View 6 provider routes

About

Gemma 2 27B Instruct is a cutting-edge large language model from Google, excelling in text generation, question answering, summarization, and reasoning tasks. It features a decoder-only transformer architecture, utilizing 27 billion parameters, and supports context length processing of up to 8,192 tokens. The model incorporates innovative mechanisms like Grouped Query Attention and Sliding Window Attention to enhance efficiency and effectiveness in handling long texts. Its instruction-tuned variants are designed for improved interaction in conversational tasks, and it benefits from knowledge distillation techniques for enhanced performance. Additionally, Gemma 2 27B Instruct is openly accessible, promoting wider innovation in AI applications.

Providers(6)

Compare all 6

Compare API pricing across 6 tracked provider routes for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Route
Replicate API	$0.400	$0.400	Serverless
Featherless	$0.650	$0.650	Serverless
NextBit	$0.650	$0.650	Serverless
OpenRouter	$0.650	$0.650	Serverless
Arcee AI	$0.250	$0.750	Serverless
Fireworks AI	$0.900	$0.900	Serverless

Deprecated provider routes(1)

Provider	Status	Catalog ID
NVIDIA NIM	DeprecatedRetired April 15, 2026	—

Available via routers & gateways(2)

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughFireworks AI

NVIDIA LLM Router Blueprint

Router

NVIDIA's open-source AI blueprint for LLM routing that selects the optimal model per prompt via intent classification or neural auto-routing; being deprecated 2026-06-20.

Free OSSNVIDIA NIM

Capabilities

Structured Outputs

Benchmark peer barsfor Classification

Massive Multitask Language UnderstandingRank 33 of 100

Gemini 3.1 Pro Preview

98.0

Clef-omni

92.7

GPT-5.5

92.4

Clef-flash

91.8

Gemma 2 27B Instructcurrent

82.3

Benchmark scores(1)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.