* Improve type annotations and remove some ignored errors.
* Support for new OpenAI models announced June 13th 2023.
* Improved support for model fallbacks. Now if a request has 6k tokens and the model list looks like `['gpt-3.5-turbo', 'gpt-3.5-turbo-16k']`, the 16k model will be used automatically since the default 4k model will not be able to handle the request.