It seems weird to me that you'd want a model per API to be trained rather than a model that understands many APIs. There's likely more similarities than differences in that the differences are really your domain model which infects the nouns of the but less so the verbs and structure.
How to make beautiful schemas like those (what tool)<p>(1) <a href="https://github.com/danielgross/LlamaAcademy/raw/main/assets/data_generation.jpg">https://github.com/danielgross/LlamaAcademy/raw/main/assets/...</a>