Skip to content
LLM Engineering

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.

Sources

Browse all LLM Engineering terms →