In my experience, you can only use Gemini structured outputs for the most trivial of schemas. No integer literals, no discriminated unions and many more paper cuts. So at least for me, it was completely unusable for what I do at work.
Fixed some of the things, indeed. But don't let this blog post fool you. When using discriminated unions, Pydantic exports JSON schema with `oneOf` while the google-genai expects `anyOf` so that does not work out of the box. Also it still does not support basic stuff like when you have this in you Pydantic model: `foo: Literal[1, 3, 5]`
It's still far from what I'd expect should be supported.
Can you elaborate what you mean - OAI structured outputs means JSON schema doesn't it? So are you just saying they both support JSON schema but Anthropic has a limitation?
OpenAI, in addition to JSON schema, supports "context-free grammar"[0], i.e. regex and lark. Anthropic also supports JSON schema since a few weeks ago, but they don't support specifying the length of JSON array, so you still have to worry about the model producing invalid output.
One thing that pisses me off is this widespread misunderstanding that you can just fall back to function calling (Anthropic's function calling accepts JSON schema for arguments), and that it's the same as structured outputs. It is not. They just dump the JSON schema into the context without doing the actual structured outputs. Vercel's AI SDK does that and it pisses me off because doing that only confuses the model and prefilling works much better.
