Ajay Hinduja Geneva, Switzerland (Swiss) - How to Purchase Additional Serverless Inference API Credits?

[ajayhindujaswiss]

Hi all,

I’m Ajay Hinduja Geneva, Switzerland (Swiss) and I am currently subscribed to the Pro plan, which includes $2 of Serverless Inference API usage. However, I’d like to increase this limit and purchase additional credits, as I’m using this service specifically for an Agentic AI course.

I’ve searched the forum but couldn’t find a clear answer. Could someone please guide me on how to buy more credits?

Thanks in advance for your help!

Best regards,
Ajay Hinduja Geneva, Switzerland (Swiss)

[John6666]

Hugging Face Payment Error 402 & You've Exceeded Monthly Quota

Hi @Yannael We offer pay-as-you-go billing support for PRO and Enterprise Hub users at this time - subscribe to PRO here: Hugging Face – The AI community building the future. to receive $2 free inference credits and more. We also have some additional info about Inference Providers pricing here: Pricing and Billing. Hope this helps!

Pricing and Billing

Regarding the PAYG service for Inference Provider, I believe it is available if you have a Pro subscription and payments are enabled. For more details, please refer to the information above. Additionally, in the Agents course, you can use a local LLM via Ollama or substitute another company’s Endpoint API. The following is an example.

How to run agents from `smolagents` locally?

I have been running everything locally by using either the TransfomerModel or MLXModel classes instead of the HfApiModel class. from smolagents import CodeAgent, MLXModel model = MLXModel( "mlx-community/Qwen2.5-Coder-32B-Instruct-4bit", { "temperature": 0.7, "top_k": 20, "top_p": 0.8, "min_p": 0.05, "num_ctx": 32768, }, ) agent = CodeAgent(tools=[], model=model, add_base_tools=True) agent.run( "Could you give me the 40th number in the…

Alternative options for API endpoints

I just posted in the Discord as well, but figured I’d post over here for those who are only checking one or the other. Hi all, I have been reading a lot of questions around what to do if the examples for use the HfApiModel fail, or you run out of credits. I was in a similar situation, and went down the path of running locally to begin with using the MLXModel class and Qwen2.5-Coder-32B, but that was leading to very long waits even with my maxed out M4 Max. So I wanted to share another solution…