# Request regarding detailed costs for API use

**URL:** <https://community.perplexity.ai/t/request-regarding-detailed-costs-for-api-use/96>\
**Category:** General\
**Created:** [May 15, 2025, 12:15am UTC](https://community.perplexity.ai/t/request-regarding-detailed-costs-for-api-use/96 "2025-05-15T00:15:46Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![vikvang](https://avatars.discourse-cdn.com/v4/letter/v/67e7ee/32.png) [@vikvang](https://community.perplexity.ai/u/vikvang)\
**Post date:** [May 15, 2025, 12:15am UTC](https://community.perplexity.ai/t/request-regarding-detailed-costs-for-api-use/96/1 "2025-05-15T00:15:46Z")

</div>

Hi to all, doing great job with the API!!!

I now want to clarify the actual exact cost structure, because I want to implement this in my script.

I have seen the following:

| Model | Price per 1000 requests | Price per 1M tokens |
| --- | --- | --- |
| llama-3.1-sonar-small-128k-online | $5 | $0.2 |
| llama-3.1-sonar-large-128k-online | $5 | $1 |
| llama-3.1-sonar-huge-128k-online | $5 | $5 |

But how would a concrete example work?

Lets say one api request and the answer needs 790 token. How is it exactly being calculated?

Many thanks  
Frank

---

<div class="post-metadata">

**Author:** ![jamesliounis](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/jamesliounis/32/897_2.png) [@jamesliounis](https://community.perplexity.ai/u/jamesliounis)\
**Post date:** [May 16, 2025, 9:31pm UTC](https://community.perplexity.ai/t/request-regarding-detailed-costs-for-api-use/96/2 "2025-05-16T21:31:29Z")

</div>

Hi, this refers to an old model that has been deprecated. Thanks!