On Jan 4, OpenAI will retire 33 models, including GPT-3 (text-davinci-003) and various others. This is OpenAI's biggest model deprecation so far. Here's what you need to know:
GPT-3 Model Retirement
The text-davinci-003 model (commonly known as GPT-3) will be unavailable from Jan 4.
→ You must manually transition to the replacement model, gpt-3.5-turbo-instruct.
/fine-tunes Endpoint Retirement
The Ada, Babbage, curie, and DaVinci models on the /fine-tunes endpoint will be retired on Jan 4.
→ You must manually transition to the new endpoint and models on /fine-tuning.
Old Embedding Models Retirement
All models except for text-embedding-ada-002 will be shut down on Jan 4.
→ You must manually transition to the new model text-embedding-ada-002.
No Deprecations for Chat Models
All GPT-4 and gpt-3.5-turbo models remain active. The earliest deprecation is happening on June 13th for gpt-4-0314, gpt-4-0613, gpt-3.5-turbo-0613, and gpt-3.5-turbo-0301. Azure OpenAI will deprecate the -0314 and -0301 models on July 5th. (Azure shutdown for -0613 models is to be announced.)
→ It is recommended to start shifting your gpt-4 and gpt-3.5-turbo workloads to the newer, cheaper -1106 models.
We've put all of these updates in a simple-to-understand OpenAI Model Map. (Click on the image to expand)
For Chat Models
For Text models & /fine-tunes:
Refer to OpenAI's Deprecations guide for more info.