Skip to main content

Gemini

Gemini is an advanced language model (LLM) developed by Google. It has the ability to access Google search results to provide precise and tailored responses to instructions.

The Google Gemini node is designed to interact with the Gemini API, enabling you to perform various tasks such as text generation, image analysis, and more.

Note that you can enable Google Search on this node.

Gemini
System MessageText
ContextText
Prompt*Text (multiline)
File UrlFile upload
ModelSelect
Enable Google Search ToolToggle
ThinkingToggle
Thinking LevelSelect
+ 2 more…
Fields marked * are required. Dots are connection handles.

Inputs

Each input can be typed in directly or connected to another node's output.

InputTypeRequiredDescription
System MessageTextOptionalOverride the default system instructions for the LLM (e.g. 'You are a concise assistant that responds only in bullet points.').
ContextTextOptionalDynamic data for the LLM to process (e.g. email body, document, user input).
PromptText (multiline)RequiredTask instruction for the LLM (e.g. 'Summarize the text').
File UrlFile uploadOptionalProvide files for the LLM to analyze by connecting file URLs to this field.

Settings

SettingTypeDefaultDescriptionAvailable when
ModelSelectGemini 3.1 Pro Preview
Enable Google Search ToolToggleOff
ThinkingToggleModel is “Gemini 2.5 Flash Preview”
Thinking LevelSelectHigh | Deep reasoning (Default)Controls the depth of the model's internal reasoning process. Low minimizes latency and cost, while High maximizes reasoning depth for complex problems. Options: Low | Fast, minimal reasoning · High | Deep reasoning (Default) (default).Model is “Gemini 3.1 Pro Preview”
Budget TokensSlider0Determines how many tokens Gemini can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Range: 0–24576.Model is “Gemini 2.5 Flash Preview” and Thinking is on
Budget TokensSlider128Determines how many tokens Gemini can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Range: 128–32768.Model is “Gemini 2.5 Pro Preview”

Model options

OptionDefault
Gemini 2.5 Flash Preview
Gemini 2.5 Pro Preview
Gemini 3.1 Pro Preview
Gemini 3 Flash Preview

Output

Type: Text (text)