{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreigcs3efnl6ropy4d7g6l4cthrdwh4wxjrbuf7n44xa2vwoyb6tnne",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mh2m77ue2je2"
},
"path": "/t/structured-outputs-un-minified/1376747#post_1",
"publishedAt": "2026-03-14T23:36:18.000Z",
"site": "https://community.openai.com",
"textContent": "I reported this shortly after structured outputs were released, but had 0~90% problems and didn’t come back to it until now.\n\nI use structured outputs, which constrains the LLM to only produce tokens that would make valid JSON that matches a provided schema. However, it is still possible to get an unparseable response because JSON is whitespace insensitive. The LLM can and does choose to do something like reply with repeating ` \\n` tokens (as I’m seeing in a few responses tonight) until it fills up the output context window, and then parsing the resulting (~max cost) response will fail.\n\nI’ve tried putting Minified in the JSON Schema name, noting it should be minified, etc. Those things may help a little, but they haven’t been a silver bullet.\n\nAnyone have a solution, or would OpenAI possibly consider making their structured outputs respond with minified JSON? It feels like it should be a relatively trivial adjustment.",
"title": "Structured Outputs - un-minified"
}