Using Cerebras Inference Provider with Custom API Key

Just signed up with HF and had some questions for the general community to help us get started:

We plan to use the Cerebras Inference Provider using direct calls rather than routing through HF itself.

  1. Can we use the same API key obtained from Cerebras as the Custom API key for HF?

  2. With a Pro subscription, are there any limits to token usage or queuing constraints when using a custom API key and direct calls? The free tier on Cerebras did have such constraints.

  3. Anyone here use the meta-llama/Llama-3.3-70B-Instruct model with Cerebras as the Inference Provider that can share feedback in terms of performance/deterministic behavior etc?

Thanks in advance

1 Like