GPT-4 0125 Preview

A preview version of GPT-4 released in January 2025, with expanded capabilities including text, image, video, audio, transcription, and text-to-speech support, as well as the ability to generate structured outputs and integrate with external tools.

Supports a 128,000 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications. Supports tool use for advanced automation. Capable of generating structured output formats.