Hugging Face cost tracking
Inference Endpoints, Spaces and enterprise seats.
How does Camaze work with Hugging Face?
Camaze connects to Hugging Face with read-only credentials and pulls spend and usage into the same view as every other place you pay for AI.
What Camaze pulls from Hugging Face
Camaze connects to Hugging Face with read-only credentials and pulls spend and usage into the same view as every other place you pay for AI.
- Compute spend, split out of the wider cloud or platform bill
- Which models and endpoints that compute is serving
- Utilization, so an idle dedicated endpoint is visible as an opportunity
- Cost per million tokens served, comparable to hosted providers
See your Hugging Face spend in context.
Book a walkthrough and we will show you Hugging Face costs next to everything else you pay for AI.
Keep reading
Every integration
The full list of providers, tools, self-hosted sources and destinations Camaze connects to.
Read moreSpend visibility
How Hugging Face spend joins every other source on one cost basis, in one number.
Read moreCost optimization
The standing list of what to cut, including findings specific to Hugging Face usage.
Read moreQuestions people ask
What access does Camaze need for Hugging Face?
Read-only billing and usage credentials. Nothing that can spend money, change a deployment, or read your prompts and completions. Details are on the security page.
Does it backfill historical Hugging Face spend?
Yes. Camaze pulls the available history on connection, typically the last twelve months, so you start with a trend rather than an empty chart.
Can we split Hugging Face spend by team or project?
Yes. Map keys, projects, workspaces or tags to your own org structure once, and every Hugging Face charge is attributed from then on. See cost allocation.
Do we have to use Hugging Face exclusively?
No. Camaze is built for the opposite case. Hugging Face sits alongside every other provider, tool and self-hosted model in the same view, on the same cost basis. It is equally useful if Hugging Face is the only thing you run: see single-provider visibility.