Add GPT-5 in Analyze Image Operation in OpenAI Node

Feature Requests
1

OpenAI Node

The idea is:

Add support for “Analyze Image” operation in the OpenAI Node for n8n specifically for GPT-5, allowing workflows to directly process and analyze images (object detection, text extraction, classification, description, etc.) within n8n automations.

My use case:

I’ve built an Whatsapp → Google Sheets Receipt Processor in n8n that turns receipt management into a simple “take a photo” process.
Right now, my workflow:
Listens for uploads via Whatsapp, uses ChatGPT 4o to read receipt details → saves to Google Drive → updates Google Sheets
However, GPT-4o’s OCR capabilities are not good enough for me at the moment and I need an option for GPT-5.

I think it would be beneficial to add this because:

  • Increases Workflow Speed because for some reason a HTTP Request to GPT-5 Takes 1.5-2 minutes for a response
  • It makes the OpenAI Node more complete by supporting multimodal GPT-5 features.
  • Reduces the need for custom HTTP Request nodes or external scripts to handle image analysis.
  • Enables more powerful automation use cases (e.g., classifying incoming images, extracting text, summarizing diagrams, visual QA, etc.).
  • Keeps workflows cleaner and more accessible for non-developers.

Thanks!