Gemini

Use Google's Gemini models. Input a natural language text prompt and image files, and output the text result to the output.txt file in the working folder.

Parameters

API KEY - API key for using the Gemini model. Supports the %FILENAME% variable, or use the prepaid dedicated key %credit-key%.

MODEL - Defaults to the gemini-2.5-flash model. Can be replaced when new models are released in the future.

IMAGE - Optionally select an image file for the model to analyze.

OUTPUT - Output can be plain text or JSON format.

TEMPERATURE(0~1.0) - Randomness of the response. 0 is the lowest and most stable; 1.0 is the most random.

MAX TOKENS - Limits the maximum number of response tokens. Higher values generally require more time to generate a response.

SYSTEM PROMPT - Specifies the role or output guidelines for the model. Supports the %FILENAME% template.

USER PROMPT - User prompt and input. Supports the %FILENAME% template.

Model Limits and Pricing

For features, capabilities, limits, and pricing of each Gemini model, refer to the Gemini website.