# $9 Pro for api inference and cost

**URL:** <https://discuss.huggingface.co/t/9-pro-for-api-inference-and-cost/81036>\
**Category:** Beginners\
**Created:** [April 10, 2024, 9:02am UTC](https://discuss.huggingface.co/t/9-pro-for-api-inference-and-cost/81036 "2024-04-10T09:02:36Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![theoracle](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/theoracle/32/25660_2.png) [@theoracle](https://discuss.huggingface.co/u/theoracle)\
**Post date:** [April 10, 2024, 9:02am UTC](https://discuss.huggingface.co/t/9-pro-for-api-inference-and-cost/81036/1 "2024-04-10T09:02:36Z")

</div>

I am subscribed to the $9 Pro plan and I am using for generating a synth dataset, so a bit of heavy usage here.

[https://api-inference.huggingface.co/models/mistralai/Mixtral-8x7B-Instruct-v0.1](https://api-inference.huggingface.co/models/mistralai/Mixtral-8x7B-Instruct-v0.1)

I just wanted to find out for sure that I am not charged anything else than the montly subscription for using it. This is not a dedicated inference api endpoint, but the normally available one.  
There is no indication in the billing section about this usage. I just don’t want surprises.

---

<div class="post-metadata">

**Author:** ![Metin](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/metin/32/26820_2.png) [@Metin](https://discuss.huggingface.co/u/Metin)\
**Post date:** [May 10, 2024, 8:54am UTC](https://discuss.huggingface.co/t/9-pro-for-api-inference-and-cost/81036/2 "2024-05-10T08:54:02Z")

</div>

I’m also interested in this, as I heavily rely on the Inference API (making 1 request per 10 seconds for 24 hours). I searched the documentation but couldn’t find relevant information.

For reference, here’s the code I use to send requests:

```auto
client = AsyncInferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
chat = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hi, can I reach the moon by jumping?"},
]

response = await client.chat_completion(chat, max_tokens=100, temperature=0.1)

```

---

<div class="post-metadata">

**Author:** ![theoracle](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/theoracle/32/25660_2.png) [@theoracle](https://discuss.huggingface.co/u/theoracle)\
**Post date:** [May 10, 2024, 9:10am UTC](https://discuss.huggingface.co/t/9-pro-for-api-inference-and-cost/81036/3 "2024-05-10T09:10:19Z")

</div>

I run quite a bit of inference and I was charged only the $9 a month, so it seems…