# Enforcing JSON Outputs in Commercial LLMs

**URL:** <https://discuss.dvc.org/t/enforcing-json-outputs-in-commercial-llms/2264>\
**Category:** Blog Comments\
**Created:** [October 18, 2024, 4:23pm UTC](https://discuss.dvc.org/t/enforcing-json-outputs-in-commercial-llms/2264 "2024-10-18T16:23:20Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![jendefig](https://avatars.discourse-cdn.com/v4/letter/j/e9a140/32.png) [@jendefig](https://discuss.dvc.org/u/jendefig)\
**Post date:** [October 18, 2024, 4:23pm UTC](https://discuss.dvc.org/t/enforcing-json-outputs-in-commercial-llms/2264/1 "2024-10-18T16:23:20Z")

</div>

🙏 Please leave your feedback/comments here for this blog post!

> **[Enforcing JSON Outputs in Commercial LLMs](https://datachain.ai/blog/enforcing-json-outputs-in-commercial-llms)**
>
> The results of our tests on the structured outputs of Google Gemini Pro, Anthropic Claude, and OpenAI GPT. DataChain used for evaluation.
