Translate with Google Gemini

Translate with Google Gemini

Google Gemini models offer fast, cost-effective translations backed by Google’s language expertise. Gemini is a strong choice for high-volume translation jobs, especially with its generous free tier for lower-traffic usage.

Prerequisites

Connect Google Gemini to ButterKit

Open Settings

In ButterKit, go to Settings > Models.

Add a new model

Click the + button to add a new cloud model.

Enter your model details

Fill in the following fields:

FieldValue
DescriptionGoogle Gemini (or any label you prefer)
URLhttps://generativelanguage.googleapis.com
API KeyYour Google AI API key
Modelgemini-2.5-flash (recommended)
API Key HeaderLeave blank (auto-detected)
Temperature0.35

Temperature controls randomness: lower values (0.0-0.3) produce more literal translations, while higher values (0.4-0.7) allow light paraphrasing. We recommend 0.35 as a good starting point. Some endpoints may clamp or ignore this value.

Security: Your API key is stored securely in the macOS Keychain. It is never sent to ButterKit servers or any third party other than the provider you configure.

ButterKit Settings showing a cloud model configuration for Google Gemini

Connecting a cloud translation model in ButterKit Settings

Test the connection

Click Test Connection to verify that ButterKit can reach Google Gemini with your key. You should see a success confirmation.

Start translating

Toggle Use as default if you want Gemini for all translations, or select it from the Translate with dropdown when adding a localization.

Available Models

ModelBest forRelative cost
gemini-2.5-flashRecommended default; best price-performance for high-volume translationLow
gemini-2.5-proHighest quality for complex or nuanced textMedium
gemini-2.5-flash-liteFastest and cheapest; ideal for simple, bulk translationsVery low

Recommended Settings

gemini-2.5-flash is the recommended default. It is optimized for speed and efficiency, making it ideal for translating many screenshots at once.

For translations requiring deeper reasoning or handling complex phrasing, gemini-2.5-pro offers the highest quality. For maximum throughput at the lowest cost, gemini-2.5-flash-lite is an excellent budget option.

Billing

You are billed directly by Google based on token usage. Google AI Studio includes a free tier that covers moderate usage. Monitor your usage and billing at aistudio.google.com.

Quick Help