Navigation

Mobile Docs

Google Gemini

Access Google Gemini AI for multimodal generation

Integrate with Google Gemini AI to generate text, analyze images, create code, and access multimodal AI capabilities. Use Gemini Pro for advanced reasoning and Gemini Flash for fast responses with live web data integration.

Toolsgemini

Usage

01Add the block to your workflow and connect it to the upstream step.
02Connect the required credentials or OAuth provider before running.
03Fill in required inputs and optional parameters for the run.
04Run a test execution, inspect outputs, and iterate before deploying.
05Deploy the gemini block with monitoring enabled in production.

Inputs (UI)

Google Account

oauth-input

Placeholder: Select Google account

Layout: full

Provider: google

Model

dropdown

Layout: full

Options: Gemini 2.0 Flash (Experimental), Gemini 1.5 Pro, Gemini 1.5 Flash, Gemini Pro

Operation

dropdown

Layout: full

Options: Generate Text, Analyze Image, Generate Code, Chat Completion

Prompt

long-input

Placeholder: Enter your prompt here

Layout: full

Condition: operation = ["generate_text","generate_code","chat"]

Image URL

short-input

Placeholder: https://example.com/image.jpg

Layout: full

Condition: operation = "analyze_image"

Image Analysis Prompt

long-input

Placeholder: Describe this image in detail

Layout: full

Condition: operation = "analyze_image"

Temperature

short-input

Placeholder: 0.7

Layout: half

Condition: operation = ["generate_text","generate_code","chat"]

Max Tokens

short-input

Placeholder: 2048

Layout: half

Condition: operation = ["generate_text","generate_code","chat"]

Inputs (API)

credential

string

Required

model

string

Required

operation

string

Required

prompt

string

Optional

imageUrl

string

Optional

imagePrompt

string

Optional

temperature

string

Optional

maxTokens

string

Optional

Outputs

Primary response type:

{
  "data": "json"
}

Tool Access

gemini_api