Added gpt-3.5-turbo 0613 16k and 16k-0613 pricing

[matias-biatoz]

@agola11

Issue
#6193

I added the new pricing for the new models.

Also, now gpt-3.5-turbo got split into "input" and "output" pricing. It currently does not support that.

[vercel]

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

Name	Status	Preview	Comments	Updated (UTC)
langchain	❌ Failed (Inspect)			Jun 16, 2023 1:55pm

[hinthornw]

We should update the logic in this line to split the turbo pricing by prompt and completion tokens as well

elif is_completion and model_name.startswith("gpt-4"):
        return model_name + "-completion"

to check for gpt-3.5-turbo prefixes as well

[wqj97]

I'm depending on ths MR too~

[vercel]

@dev2049 is attempting to deploy a commit to the LangChain Team on Vercel.

A member of the Team first needs to authorize it.

[dev2049]

i don't think function-calling models cost anymore than their regular counterparts but maybe im missing something. cc @hinthornw @hwchase17?