What is Token Metering?
Per-leg usage accounting that turns raw token counts into billable credits using each model price table plus markup. BYOB meters input, output, cached, and thinking tokens separately, with a minimum charge flooring tiny calls.
Example
When a session uses a premium tool model, the meter shows input, output, cached, and thinking legs priced from that model config, so swapping to a cheaper chat model visibly drops the next turn credit cost.
What people get wrong
Reading the credit total as exact provider spend. Credits add platform markup and minimum charges, so they track relative session cost, not the provider invoice.
Frequently asked questions
Why does one long session cost more than several short ones?
Long sessions accumulate output and thinking tokens and can cross long-context price thresholds, while short sessions reset the context each time.
Related terms
Token
The billing and budgeting atom of language models: text is split into subword pieces and every input, cached, thinking, and output token is metered separately. BYOB counts tokens with tiktoken and converts usage into credits per model pricing.
Context Threshold
The input-size line where a provider switches a model to higher long-context pricing. BYOB model configs store the threshold with above-threshold rates, so sessions crossing it pay more per token without changing models.
AI Credits
The metered unit for AI work in BYOB: planning, generation, and agent runs draw down a balance tracked per project. Credits make heavy context work visible instead of hiding it in a flat fee.
Billing Action
The structured paywall signal (insufficient credits, quota exceeded, plan required) with a checkout URL. Generated apps use the same pattern to gate their own premium features.
Temperature
Sampling randomness for generation: low values make output focused and repeatable, high values make it varied and surprising. BYOB chat configs default near 0.5 while tool calls use 0.3 for steadier structured actions.
Thinking Budget
The token allowance reserved for internal model reasoning before answering. Larger budgets suit hard multi-step problems; BYOB prices thinking tokens separately so runaway reasoning shows up in metering.