# Structured Outputs - un-minified **URL:** \ **Category:** Bugs\ **Created:** [March 14, 2026, 11:36pm UTC](https://community.openai.com/t/structured-outputs-un-minified/1376747 "2026-03-14T23:36:18Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![peter.adelman](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/peter.adelman/32/149286_2.png) [@peter.adelman](https://community.openai.com/u/peter.adelman)\ **Post date:** [March 14, 2026, 11:36pm UTC](https://community.openai.com/t/structured-outputs-un-minified/1376747/1 "2026-03-14T23:36:18Z")
I reported this shortly after structured outputs were released, but had 0~90% problems and didn’t come back to it until now. I 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. I’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. Anyone 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. ---
**Author:** ![peter.adelman](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/peter.adelman/32/149286_2.png) [@peter.adelman](https://community.openai.com/u/peter.adelman)\ **Post date:** [April 14, 2026, 2:21pm UTC](https://community.openai.com/t/structured-outputs-un-minified/1376747/2 "2026-04-14T14:21:47Z")
This design flaw is the only one I haven’t been able to work around. Right now retries don’t work because I keep the temperature low, so all subsequent retries fail with the same error. Because it’s server-side behavior, the only thing I can think of is to bump up the temperature or use a synonymous prompt when I get stuck like this. ---
**Author:** ![OpenAI\_Support](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/openai_support/32/561845_2.png) [@OpenAI\_Support](https://community.openai.com/u/OpenAI_Support)\ **Post date:** [September 7, 2026, 7:29pm UTC](https://community.openai.com/t/structured-outputs-un-minified/1376747/3 "2026-09-07T19:29:05Z")
Sorry for the slow reply. Thanks for explaining the whitespace loop — we’ll pass the minification feedback to the relevant team, with no timeline to share. The guide covers detecting incomplete outputs, though that doesn’t resolve the reported loop: [https://developers.openai.com/api/docs/guides/structured-outputs](https://developers.openai.com/api/docs/guides/structured-outputs) ---
**Author:** ![Mark\_G](https://avatars.discourse-cdn.com/v4/letter/m/e8c25b/32.png) [@Mark\_G](https://community.openai.com/u/Mark_G)\ **Post date:** [September 10, 2026, 7:49pm UTC](https://community.openai.com/t/structured-outputs-un-minified/1376747/4 "2026-09-10T19:49:45Z")