modelgrep
G

Google: Gemma 2 27B

google/gemma-2-27b-it

JSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
39
208th fastest
Latency
853ms
first token
Input price
$0.650
180th cheapest
Context
8K
2K max out

How it compares

Faster than32%
of all ranked models
Cheaper than40%
of all ranked models

Overview

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...

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
NextBitint4$0.650$0.650100%

Specifications

Context window8K
Max output2K
Knowledge cutoffJun 2024
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Gemma 2 27B FAQ

How much does Gemma 2 27B cost?

Gemma 2 27B costs $0.650 per million input tokens and $0.650 per million output tokens via OpenRouter, making it 180th cheapest of 298 paid models.

How fast is Gemma 2 27B?

Gemma 2 27B generates around 39 tokens per second with 853ms time-to-first-token (p50), the 208th fastest tracked model.

What is Gemma 2 27B's context window?

Gemma 2 27B supports a 8K-token context window and can output up to 2K tokens. It accepts text input.

Compare head-to-head