Skip to main content

What costs what

ActivityHow it’s billed
Inference calls (API)Per token, varies by model
Eval judge callsPer token (these are full LLM inferences)
Training computePer GPU-hour (1616–24/hr, minimum 8 GPUs)
Deployment GPU hoursPer hour while the deployment is online

Credits

Your account has a credit balance. All platform activity draws from this balance. Make sure you have sufficient credits before launching training runs or deploying models — both will fail if credits run out.

Checking your usage

View your current balance and usage breakdown in the Catalyst dashboard.