Update model token mappings/cost to include 0613 models

[eoriont]

Add gpt-3.5-turbo-16k to model token mappings, as per the following new OpenAI blog post: https://openai.com/blog/function-calling-and-other-api-updates

Fixes #6118

Before submitting

Each example using gpt-3.5-turbo should already work, and I think shouldn't be updated as the new 16k token model costs more per token to use.

If there are tests I should add, please let me know.

Who can review?

Tag maintainers/contributors who might be interested:

@hwchase17

[mheguy-stingray]

@eoriont Could you also add the tokens for the 0613 models? That would be: gpt-4-32k-0613, gpt-4-0613, gpt-3.5-turbo-0613, and gpt-3.5-turbo-16k-0613

[eoriont]

This also fixes #6150. Any thoughts @hwchase17 @agola11?

[vercel[bot]]

@hwchase17 is attempting to deploy a commit to the LangChain Team on Vercel.

A member of the Team first needs to authorize it.

[vercel[bot]]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
langchain	🛑 Canceled (Inspect)			Jun 21, 2023 8:33am

[dev2049]

thanks @eoriont!