There are a few libs that already abstract this away, for example:

- https://github.com/BerriAI/litellm

- https://jxnl.github.io/instructor/

- langchain

It's not hard for me to imagine a future where there is something like the CNCF for AI models, tools, and infra.

Langchain.

But it's too bleeding edge, you are asking a lot.

Just do the work and don't be spoiled senseless

Langchain, for all its popularity, is some of the worst, most brittle Python code I’ve ever seen or tried to use, so I’d prefer to have things sorted out for me at the API level.

I switched to using Instructor/Marvin which works really nicely with native pydantic models and gets out the way for everything else.

Imo it's unfortunate that python is the dominant tech of this domain. Typescript is better suited for the inference side of things (I know there a ts version of most things, most most companies are looking for python dev)

Python is fine. The problem is all the folk writing Python as if they were doing Java cosplay and without any tests or type annotations.

It looks very similar if not identical to OpenAI?

OpenRouter is a great step in that direction: https://openrouter.ai/

check out LiteLLM... been using in (lite) production and they make it easy to switch between models with a standardized API.