# HF routed Inference Pricing?

**URL:** <https://discuss.huggingface.co/t/hf-routed-inference-pricing/167789>\
**Category:** Models\
**Created:** [August 26, 2025, 8:00pm UTC](https://discuss.huggingface.co/t/hf-routed-inference-pricing/167789 "2025-08-26T20:00:22Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![andzzz](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/andzzz/32/52949_2.png) [@andzzz](https://discuss.huggingface.co/u/andzzz)\
**Post date:** [August 26, 2025, 8:00pm UTC](https://discuss.huggingface.co/t/hf-routed-inference-pricing/167789/1 "2025-08-26T20:00:22Z")

</div>

I want to Deploy Wan2.2 14B i2v model using fal.ai Routing through HF. Where can i see per hour pricing for H200 and what HF actually bills me?

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [August 27, 2025, 1:15am UTC](https://discuss.huggingface.co/t/hf-routed-inference-pricing/167789/2 "2025-08-27T01:15:01Z")

</div>

The [usage fees for each Inference Provider’s endpoint would apply directly](https://huggingface.co/docs/inference-providers/en/pricing#which-option-should-i-choose).

> Hugging Face charges you the same rates as the provider, with no additional fees. We just pass through the provider costs directly.

For example, for [Wan 2.2-A14B-I2V with Fal.ai, this is probably the case](https://fal.ai/models/fal-ai/wan/v2.2-a14b/image-to-video/turbo).  
To be precise, contacting each Inference Provider directly would be the most reliable way to confirm.