Model Cost Profile

Google: Gemma 3 27B

Developer: google

Pricing updated Mar 11, 2026

Input rank: #36Output rank: #45

Live Pricing

Input: $0.0300

Output: $0.1100

Pricing via OpenRouter API ยท Last synced Mar 11, 2026

Google's Gemma 3 27B model features an extensive context window of 128,000 tokens, making it suitable for applications that require processing large volumes of text, such as document summarization and complex conversational AI. With an input price of $0.04 per million tokens and an output price of $0.15 per million tokens, teams must consider their usage patterns to optimize costs effectively while leveraging the model's capabilities. This pricing structure allows for scalable integration in various projects, from customer support automation to content generation, catering to diverse business needs.

๐Ÿ‘ Vision๐Ÿ”ง Tool Calling๐Ÿ“‹ Structured Output

Context Window

128,000

Tokens

Input Price / 1M

$0.0300

Prompt tokens

Output Price / 1M

$0.1100

Completion tokens

Intelligence (MMLU)

Benchmark Pending

Massive Multitask Language Understanding

Price History

Google: Gemma 3 27B Pricing Trend

Input / 1M tokens-25.0%Output / 1M tokens-26.7%
Mar 7 โ€” Mar 11
$0.0300$0.0900$0.1500Mar 7Mar 8Mar 9Mar 10Mar 11

Current Input / 1M

$0.0300

Current Output / 1M

$0.1100

Cheaper Alternatives to Compare

Quick links for cost-down decisions before production rollout.

FAQ

Common pricing and benchmark questions for Google: Gemma 3 27B.

How much does Google: Gemma 3 27B cost per 1M input tokens?

Google: Gemma 3 27B input pricing is $0.0300 per 1M tokens based on the latest synced provider data.

How much does Google: Gemma 3 27B cost per 1M output tokens?

Google: Gemma 3 27B output pricing is $0.1100 per 1M tokens based on the latest synced provider data.

What context window does Google: Gemma 3 27B support?

Google: Gemma 3 27B supports a context window of 128,000 tokens.

How can I compare Google: Gemma 3 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.