davinci-002

The davinci-002 model is a powerful language model that serves as a replacement for the GPT-3 curie and davinci base models. It offers a 4000 token context window and supports a wide range of capabilities, including text, image, video, audio, transcription, and text-to-speech.

Supports a 4000 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.