# HF Playground Incorrect Billing - **URL:** \ **Category:** Beginners\ **Created:** [May 3, 2025, 12:01pm UTC](https://discuss.huggingface.co/t/hf-playground-incorrect-billing/153328 "2025-05-03T12:01:35Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![KwabsHug](https://avatars.discourse-cdn.com/v4/letter/k/ba8739/32.png) [@KwabsHug](https://discuss.huggingface.co/u/KwabsHug)\ **Post date:** [May 3, 2025, 12:01pm UTC](https://discuss.huggingface.co/t/hf-playground-incorrect-billing/153328/1 "2025-05-03T12:01:35Z")
Hello All, I was testing the HF playground and all my requests were only $0.20, I was testing in the window on the model page now my total is $9.08 (Model is Qwen/Qwen3-235B-A22B) Where can I find the HF Inference pricing and why is it so high? I got at best 10k tokens for price of Millions ---
**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:** [May 3, 2025, 11:07pm UTC](https://discuss.huggingface.co/t/hf-playground-incorrect-billing/153328/2 "2025-05-03T23:07:53Z")
It seems that the criteria have changed. In other words, when using large models, the cost per request becomes expensive. > [@Inference API cost changed for meta-llama-3.3-70b?](https://discuss.huggingface.co/t/inference-api-cost-changed-for-meta-llama-3-3-70b/149074/3): > > In February, Inference billing usage had been a fixed rate while we added pay-as-you-go billing [support](https://huggingface.co/posts/julien-c/158943939527784). Starting in March, usage now takes into account compute time x price of the hardware. We’re really sorry for any confusion! We have more information about Inference Providers here: [Inference Providers](https://huggingface.co/docs/inference-providers/en/index). > Starting in March, usage now takes into account compute time x price of the hardware ---
**Author:** ![Zelgodiz](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/zelgodiz/32/45662_2.png) [@Zelgodiz](https://discuss.huggingface.co/u/Zelgodiz)\ **Post date:** [May 5, 2025, 4:08am UTC](https://discuss.huggingface.co/t/hf-playground-incorrect-billing/153328/3 "2025-05-05T04:08:43Z")
It sounds like the pricing jumped unexpectedly! Hugging Face’s inference costs can vary based on the model’s **size, provider, and token usage**. The **Qwen/Qwen3-235B-A22B** model is a **Mixture-of-Experts (MoE) model** with **235 billion parameters** , which means it can be significantly more expensive than smaller models[43dcd9a7-70db-4a1f-b0ae-981daa162054](https://llm-stats.com/models/qwen3-235b-a22b?citationMarker=43dcd9a7-70db-4a1f-b0ae-981daa162054 "1"). ### **Where to Find Pricing Details** You can check Hugging Face’s official **inference pricing** on their [model page](https://huggingface.co/Qwen/Qwen3-235B-A22B) or explore detailed cost breakdowns on [LLM Stats](https://llm-stats.com/models/qwen3-235b-a22b). ### **Why the Cost Might Be High** 1. **MoE Architecture** – This model activates **22 billion parameters** per request, meaning it consumes more compute resources. 2. **Token Pricing** – Some models charge per **million tokens** , and if the pricing structure isn’t clear, it can lead to unexpected costs. 3. **Inference Provider Differences** – Different providers may have **varying rates** , so switching providers could help reduce costs. 4. **Hidden Overhead** – Some models require **additional processing** beyond just token generation, increasing the total price. ### **Next Steps** - **Check the pricing breakdown** on Hugging Face’s documentation. - **Compare providers** to see if a different one offers lower rates. - **Limit token usage** by adjusting your request length. If you need help optimizing your usage, I can suggest ways to reduce token consumption! 🚀 ---
**Author:** ![KwabsHug](https://avatars.discourse-cdn.com/v4/letter/k/ba8739/32.png) [@KwabsHug](https://discuss.huggingface.co/u/KwabsHug)\ **Post date:** [May 5, 2025, 6:26am UTC](https://discuss.huggingface.co/t/hf-playground-incorrect-billing/153328/4 "2025-05-05T06:26:22Z")
Okay, so we are charged per time on HF inference API which means for now the solution is to use the other providers? Also is there a way to disable providers you dont want to use? Also is there a way to set a spending ceiling for my account? If I used R1 for the same task it wouldnt have cost this much through replicate for example. ![Screenshot 2025-05-03 184046](https://us1.discourse-cdn.com/hellohellohello/original/3X/9/5/9571b8608de9aa5f4df96db66c4c365c1254a517.png) ---
**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:** [May 5, 2025, 7:28am UTC](https://discuss.huggingface.co/t/hf-playground-incorrect-billing/153328/5 "2025-05-05T07:28:40Z")
The payment limit is set to $100 by default. (I think it was already there when I first joined HF.) Changing this should be sufficient for personal use. Detailed limits for the Inference API can apparently be set for Enterprise subscriptions. Well, if multiple people are using it, it’s more convenient to have separate limits for each service. Individual on/off settings for Inference Providers can be configured on the settings page. > [@Inference API budget, billing limit](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/13): > > Hi @John6666, @FilippTrigub, and @im93! This feature now exists for Enterprise Hub organizations for Inference Providers billing! You can check out what setting a limit looks like in the screenshot here: [Pricing and Billing](https://huggingface.co/docs/inference-providers/en/pricing#organization-billing). For more info and to subscribe to Enterprise Hub, head here: [Enterprise Hub - Hugging Face](https://huggingface.co/enterprise). > **[Pricing and Billing](https://huggingface.co/docs/inference-providers/pricing)** > > We’re on a journey to advance and democratize artificial intelligence through open source and open science. Edit: > The payment limit is set to $100 by default Oh… It was wrong… > [@Inference API budget, billing limit](https://discuss.huggingface.co/t/inference-api-budget-billing-limit/13239/14): > > @John6666 The $100 is the threshold limit and please note it doesn’t act as a spending cap. More info here: [Billing](https://huggingface.co/docs/hub/billing#billing-thresholds--invoicing). ---
**Author:** ![system](https://us1.discourse-cdn.com/hellohellohello/original/2X/d/de4155eb4aa4108ecb32a1389d7cc37ae69f88b7.png) [@system](https://discuss.huggingface.co/u/system)\ **Post date:** [May 5, 2025, 7:28pm UTC](https://discuss.huggingface.co/t/hf-playground-incorrect-billing/153328/6 "2025-05-05T19:28:48Z")
This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.