More details in email about GPT-3.5 Turbo Updates

GPT-3.5 Turbo This model has been updated with a new version: gpt-3.5-turbo-0613 which is more steerable with the system message and includes a new capability: function calling. By describing functions in your prompts, the model can intelligently output a JSON object containing arguments to call these functions based on user input — perfect for integrating with other tools or APIs. Learn more in our function calling documentation.

Plus enjoy a 25% cost reduction for input tokens on GPT-3.5 Turbo (now $0.0015 per 1K input tokens), effective immediately.

Longer Context We're also introducing gpt-3.5-turbo-16k. This model offers four times the context length of the 4k base model and is priced at $0.003 per 1K input tokens and $0.004 per 1K output tokens.

Model Transitioning You can begin using the new gpt-3.5-turbo-0613 model today. On June 27th, the stable gpt-3.5-turbo will be automatically upgraded to this new version. If you need more time to transition, you can specify gpt-3.5-turbo-0301 to keep using the older version, which will remain available until September 13th as part of our upgrade and deprecation process.

Running the new API now, and it does seem more responsive in both terms of latency and system context.