> Image inputs via the gpt-4o, gpt-4o-mini, chatgpt-4o-latest, or gpt-4-turbo models (or previously gpt-4-vision-preview) are not eligible for zero retention."
It's still not used for training, though, and the retention period is 30 days. It's... a livable compromise for some(many) use cases.
I kind of get the abuse policy reason for image inputs. It makes sense for multi-turn conversations to require a 1h audio retention, too. I'm just incredibly puzzled why schemas for structured outputs aren't eligible for zero-retention.
It takes >50 seconds to generate these schemas for some pretty simple use-cases with large enums, for example.
Imagine that latency added to each request...
It's still not used for training, though, and the retention period is 30 days. It's... a livable compromise for some(many) use cases.
I kind of get the abuse policy reason for image inputs. It makes sense for multi-turn conversations to require a 1h audio retention, too. I'm just incredibly puzzled why schemas for structured outputs aren't eligible for zero-retention.