# Uncertainty score

The API returns a confidence score of the cutout through the HTTP header `x-uncertainty-score`.

The uncertainty score is a number between `0` and `1`:

* `0` means the model is very confident that the cutout is accurate
* `1` means the model is unsure.

For instance, shoes on a shoe box might give a higher uncertainty score as the model is unsure what to segment (shoes, box or both):

<table data-header-hidden data-full-width="false"><thead><tr><th align="center"></th><th align="center"></th></tr></thead><tbody><tr><td align="center"><img src="https://2855892273-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1SYxn7dWbQYsNtUdJE3f%2Fuploads%2FJeLReY3dpn15d6hZAjKb%2Fnoah-boisclair-REFw0jTEJOk-unsplash%20Large.jpeg?alt=media&#x26;token=faba7dd6-4b2b-417b-baa2-a7955d426e50" alt=""></td><td align="center"><img src="https://2855892273-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1SYxn7dWbQYsNtUdJE3f%2Fuploads%2F6eeegP0ext9B86EUnPY4%2Frevolt-164_6wVEHfI-unsplash%20Large.jpeg?alt=media&#x26;token=e4b47ab7-708c-4ac2-85a8-c9f47a9f6458" alt=""></td></tr><tr><td align="center">High uncertainty score: between 0.6 and 1</td><td align="center">Low uncertainty score: between 0 and 0.3</td></tr></tbody></table>

{% hint style="warning" %}
Please note that the uncertainty score is not guaranteed to be stable over time: the same image might yield a different uncertainty score in the future.
{% endhint %}

In some cases, we might not be able to able to return an uncertainty score (e.g. if an image contains humans), in that case the value `-1` will be returned.
