# Unexpectedly High Token Count When Using Image Inputs with gpt-4o-mini

**URL:** <https://community.openai.com/t/unexpectedly-high-token-count-when-using-image-inputs-with-gpt-4o-mini/1174730>\
**Category:** API\
**Created:** [April 1, 2025, 3:05pm UTC](https://community.openai.com/t/unexpectedly-high-token-count-when-using-image-inputs-with-gpt-4o-mini/1174730 "2025-04-01T15:05:30Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\
**Post date:** [April 1, 2025, 3:19pm UTC](https://community.openai.com/t/unexpectedly-high-token-count-when-using-image-inputs-with-gpt-4o-mini/1174730/2 "2025-04-01T15:19:38Z")

</div>

> [@malle\_friedrich](#):
>
> Is this expected behavior?

You have discovered the way it works.

> [@GPT-4o-mini Vision API: High Prompt Token Usage in Batch Process](https://community.openai.com/t/gpt-4o-mini-vision-api-high-prompt-token-usage-in-batch-process/1149227/2):
>
> Don’t use gpt-4o-mini for images. It costs twice as much per image as gpt-4o - in dollars. Intentionally. This is done by multiplying the bill for image input tokens by 33.33x The bug was a period of not inflating the token bill. :white\_check\_mark:Solved

---

_[View the full topic](https://community.openai.com/t/unexpectedly-high-token-count-when-using-image-inputs-with-gpt-4o-mini/1174730)._