I would also assume that in vast majority of cases people don't set temperature to zero even with API calls.

And even if you do set it to zero, you never know what changes to the layers and layers of wrappers and system prompts you will run into on any given day resulting in "on this day we crash for certain input, and on other days we don't": https://www.techdirt.com/2024/12/03/the-curious-case-of-chat...