GPT Vision API

The GPT Vision API (GPT-4o, GPT-4V) is a multimodal engine: It processes images, documents, and charts, delivering advanced visual reasoning via the Chat Completions endpoint.

This is your direct path to multimodal AI: The GPT Vision API, powered by models like GPT-4o, integrates image understanding into the familiar Chat Completions API. You send visual inputs (PNG, JPEG, or Base64 data) alongside your text prompt, and the model analyzes them. Use cases are broad: object detection, complex chart and dashboard analysis, OCR for document parsing, and interpreting UI flows. This capability streamlines image-to-text tasks, eliminating the need for separate computer vision pipelines, all within a single, powerful API call.

https://platform.openai.com/docs/guides/vision