# Using the Log Probabilities Parameter with Open AI's models

**URL:** <https://community.palantir.com/t/using-the-log-probabilities-parameter-with-open-ais-models/1329>\
**Category:** Ask the Community\
**Tags:** build-with-aip\
**Created:** [September 19, 2024, 11:20pm UTC](https://community.palantir.com/t/using-the-log-probabilities-parameter-with-open-ais-models/1329 "2024-09-19T23:20:04Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![blake](https://avatars.discourse-cdn.com/v4/letter/b/a9a28c/32.png) [@blake](https://community.palantir.com/u/blake)\
**Post date:** [September 19, 2024, 11:20pm UTC](https://community.palantir.com/t/using-the-log-probabilities-parameter-with-open-ais-models/1329/1 "2024-09-19T23:20:04Z")

</div>

It would be very helpful to be able to access the Log Probabilities parameter in order to gauge the model’s confidence in it’s output.

Docs: https://cookbook.openai.com/examples/using\_logprobs

---

<div class="post-metadata">

**Author:** ![system](https://yyz1.discourse-cdn.com/palantir/user_avatar/community.palantir.com/system/32/3_2.png) [@system](https://community.palantir.com/u/system)\
**Post date:** [February 22, 2025, 8:28pm UTC](https://community.palantir.com/t/using-the-log-probabilities-parameter-with-open-ais-models/1329/2 "2025-02-22T20:28:26Z")

</div>



---

<div class="post-metadata">

**Author:** ![system](https://yyz1.discourse-cdn.com/palantir/user_avatar/community.palantir.com/system/32/3_2.png) [@system](https://community.palantir.com/u/system)\
**Post date:** [September 22, 2025, 4:00am UTC](https://community.palantir.com/t/using-the-log-probabilities-parameter-with-open-ais-models/1329/3 "2025-09-22T04:00:40Z")

</div>