Multimodal Support Program
geminicli2api supports simultaneous processing of text and image inputs, providing solutions for content creation, education, and more:
Implementation steps
- API Call Methods::
- OpenAI-compatible interface: via
filesField to submit image path (supports local files/URLs) - Native Gemini interface: in
partsThe array containsfileDataboyfriend
- OpenAI-compatible interface: via
- file formatSupport JPEG/PNG/GIF and other common formats, single file is recommended to be less than 4MB.
- mixing instruction: Include both text instructions and image references in the message (e.g., "Describe the main object in this picture").
Application Cases
- Education: Upload photos of math problems to get step-by-step answers
- E-commerce scenario: analyzing product images to generate marketing copy
- Medical Assisting: Interpreting Abnormal Features in Medical Imaging
This answer comes from the articlegeminicli2api: Proxy tool to convert Gemini CLI to OpenAI-compatible APIsThe
May not be reproduced without permission:AI productivity tools " How to achieve multimodal content generation for text and images?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil