What is 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.
Example
A chat config with a 272,000-token threshold bills inputs below the line at the base rate and inputs above it at the long-context rate — crossing mid-session raises costs even though the model name never changes.
What people get wrong
Assuming one flat per-token price. Long sessions can cross the threshold silently, so the meter, not the model name, tells you which rate is active.
Related terms
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.
Model Context Window
How much conversation, code, and history a model can consider at once. Long builds need compaction and stable model selection so decisions survive across sessions.
Session Compaction
Summarizing long build conversations so work continues within context limits without losing decisions. Compaction plus model lock keeps multi-session projects coherent.
Prompt Caching
Reusing priced prefixes of a prompt across requests so repeated system context bills at the reduced cached rate. Long builder sessions benefit most, since stable instructions and history prefixes repeat every turn.
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.