Explains the billing process for exceeding the 50 million token allocation in Vultr Serverless Inference subscriptions, detailing the overage rate of $0.0002 per 1,000 tokens.
If your usage exceeds the 50 million tokens included in your Vultr Serverless Inference subscription, any additional tokens are billed at the standard overage rate of $0.0002 per 1,000 tokens. Your inference workloads will continue to run without interruption, and the overage charges are automatically applied to your monthly invoice.
You can monitor your token consumption and track potential overage in real time through the Usage tab in the Vultr Customer Portal, which provides detailed breakdowns of both included and consumed tokens. This helps you manage usage efficiently and anticipate any additional costs before the end of the billing cycle.