Add ModelProfile to let model-specific behaviors be configured independent of the model class

[DouweM]

• Fixes Add ModelProfile to let model-specific behaviors be configured independent of the model class #1782

To do:

• Tests
• Docs

[hyperlint-ai]

PR Change Summary

Enhanced OpenAI compatibility by introducing specific provider classes for various models, allowing for more flexible configuration of model behaviors.

• Updated documentation to reflect the use of specific providers like DeepSeekProvider, GrokProvider, PerplexityProvider, FireworksProvider, and TogetherProvider.
• Replaced generic references to OpenAIProvider with model-specific providers in code examples.
• Clarified instructions for using different API keys with their respective providers.

Modified Files

• docs/models/openai.md

---

How can I customize these reviews?

Check out the Hyperlint AI Reviewer docs for more information on how to customize the review.

If you just want to ignore it on this PR, you can add the hyperlint-ignore label to the PR. Future changes won't trigger a Hyperlint review.

Note specifically for link checks, we only check the first 30 links in a file and we cache the results for several hours (for instance, if you just added a page, you might experience this). Our recommendation is to add hyperlint-ignore to the PR to ignore the link check for this PR.

[github-actions]

Docs Preview

commit:	13fef4b
Preview URL:	https://95e98af7-pydantic-ai-previews.pydantic.workers.dev

[Kludex]

Can we include the providers on another PR?

[DouweM]

@Kludex Yep, I wanted to make sure the way I was implementing the feature would allow for proper model profile selection in those cases, but that definitely makes more sense in a follow-up PR.

Edit: Done in #1842

[dmontagu]

I think just the JsonSchemaTransformer thing to have a more specific name, otherwise LGTM

[webcoderz]

This is great and probably fixes a ton of issues I’m running into using OpenAI compatible APIs w/ vLLM