Model Cost Profile

Google: Gemma 2 27B

Developer: google

Pricing updated Mar 11, 2026

Input rank: #217Output rank: #143

Live Pricing

Input: $0.6500

Output: $0.6500

Pricing via OpenRouter API ยท Last synced Mar 11, 2026

Google's Gemma 2 27B model offers a context window of 8192 tokens, making it suitable for applications requiring extensive text analysis, such as document summarization and conversational AI. With a competitive pricing structure of $0.65 per million tokens for both input and output, teams can effectively manage costs while leveraging the model for large-scale projects. This model is particularly beneficial for organizations needing robust language understanding capabilities in areas like customer support automation and content generation.

๐Ÿ“‹ Structured Output

Context Window

8,192

Tokens

Input Price / 1M

$0.6500

Prompt tokens

Output Price / 1M

$0.6500

Completion tokens

Intelligence (MMLU)

Benchmark Pending

Massive Multitask Language Understanding

Price History

Google: Gemma 2 27B Pricing Trend

Input / 1M tokens0.0%Output / 1M tokens0.0%
Mar 7 โ€” Mar 11
$0.6500$0.6500$0.6500Mar 7Mar 8Mar 9Mar 10Mar 11

Current Input / 1M

$0.6500

Current Output / 1M

$0.6500

Cheaper Alternatives to Compare

Quick links for cost-down decisions before production rollout.

FAQ

Common pricing and benchmark questions for Google: Gemma 2 27B.

How much does Google: Gemma 2 27B cost per 1M input tokens?

Google: Gemma 2 27B input pricing is $0.6500 per 1M tokens based on the latest synced provider data.

How much does Google: Gemma 2 27B cost per 1M output tokens?

Google: Gemma 2 27B output pricing is $0.6500 per 1M tokens based on the latest synced provider data.

What context window does Google: Gemma 2 27B support?

Google: Gemma 2 27B supports a context window of 8,192 tokens.

How can I compare Google: Gemma 2 27B with cheaper alternatives?

Use the comparison links on this page to open direct model-vs-model pricing and benchmark pages, then evaluate monthly spend projections for your workload.