Can someone lead me to any information on limits of files and image inputs that can be sent in a single message. Files are sent using the Files API.
https://platform.openai.com/docs/guides/text#planning-for-the-context-window
Planning for the context window
Models can only handle so much data within the context they consider during a generation request. This memory limit is called a context window, which is defined in terms of tokens (chunks of data you pass in, from text to images).
Models have different context window sizes from the low 100k range up to one million tokens for newer GPT-4.1 models. Refer to the model docs for specific context window sizes per model.