# Why is this amount deducted?

**URL:** <https://community.openai.com/t/why-is-this-amount-deducted/1247176>\
**Category:** API\
**Tags:** gpt-4, api\
**Created:** [April 30, 2025, 8:17am UTC](https://community.openai.com/t/why-is-this-amount-deducted/1247176 "2025-04-30T08:17:56Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![muhammad\_alshelleh](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/muhammad_alshelleh/32/618207_2.png) [@muhammad\_alshelleh](https://community.openai.com/u/muhammad_alshelleh)\
**Post date:** [April 30, 2025, 8:17am UTC](https://community.openai.com/t/why-is-this-amount-deducted/1247176/1 "2025-04-30T08:17:56Z")

</div>

I am running openAi api and this information for tokens  
output\_tokens=230  
input\_tokens=601  
total\_tokens=831  
So, Why are 0.2$ deducted from this?  
Although I see in the documentation that every million tokens is worth two or three dollars

---

<div class="post-metadata">

**Author:** ![aprendendo.next](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/aprendendo.next/32/721758_2.png) [@aprendendo.next](https://community.openai.com/u/aprendendo.next)\
**Post date:** [April 30, 2025, 8:36am UTC](https://community.openai.com/t/why-is-this-amount-deducted/1247176/2 "2025-04-30T08:36:43Z")

</div>

1. Which model did you use?
2. Did you include tools such as web search and file search? They are charged separately.
3. You can detail your billing exporting a csv of your [usage](https://platform.openai.com/settings/organization/usage/legacy).

---

<div class="post-metadata">

**Author:** ![muhammad\_alshelleh](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/muhammad_alshelleh/32/618207_2.png) [@muhammad\_alshelleh](https://community.openai.com/u/muhammad_alshelleh)\
**Post date:** [April 30, 2025, 12:03pm UTC](https://community.openai.com/t/why-is-this-amount-deducted/1247176/3 "2025-04-30T12:03:35Z")

</div>

1. I am using the “GPT-4” model.
2. I’m only using “function calling”, no web search or file search tools.
3. I checked the usage details for today.

- Input tokens: 1,807
- Output tokens: 653
- Total cost: $0.11
- This is for 3 separate requests.

I’m still new to the API and would love to hear any suggestions for managing usage and keeping costs low.

---

<div class="post-metadata">

**Author:** ![aprendendo.next](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/aprendendo.next/32/721758_2.png) [@aprendendo.next](https://community.openai.com/u/aprendendo.next)\
**Post date:** [April 30, 2025, 3:19pm UTC](https://community.openai.com/t/why-is-this-amount-deducted/1247176/4 "2025-04-30T15:19:58Z")

</div>

GPT 4 is $30 per million tokens input $40 output, that’s why you are finding it expensive.

Try using gpt-4.1, it’s cheaper.
