>are cheap and strong enough to make this practical.

It all depends on the scale you need them, with the API it's easy to generate millions of tokens without thinking.

You don't need full reasoning to get accurate results, so even with GPT5 it's still pretty cheap for a one-time job and easy to reason about costs. It's certainly cheaper if you have data where reliability is key and classical OCR will undoubtedly require some manual data cleaning...

I can recommend the Mistral OCR API [1] if you have large jobs and don't want to think about it too much.

[1] https://mistral.ai/solutions/document-ai

In that case you should run a model locally, this one for example: https://huggingface.co/ds4sd/docling-models