Ninety-Nine Cents: Price-Ending Bias in Language Models Is Learned, Not Perceived

Language models respond systematically to price endings: they are much more likely to buy a product at USD 4.99 than at USD 5.00, echoing the left-digit bias documented in human consumers. We measure this effect with a within-price placebo design that compares the 4.99 to 5.00 change with nine otherwise identical one-cent price increases that do not cross a dollar boundary. The nine placebo steps establish a baseline, isolating the additional effect at the dollar boundary. Across 683,559 cells spanning 21 models, the corrected left-digit effect is $-3.25$ percentage points $[-5.64,-0.99]$, while a matched design that removes the roundness confound by construction gives $-6.14$ $[-8.36,-3.86]$. Several experiments then probe whether the bias is perceptual (arising from digit-level processing akin to humans), or semantic (reflecting learned associations with conventional endings). Purchase probability responds to price endings with a graded pattern that favours round endings rather than dropping discretely at the dollar boundary, and the ending profile correlates with corpus frequency. Stating a fictional pricing convention in a single sentence shifts the preferred ending by $36.02$ percentage points, roughly ten times the native 99-cent effect. The same design applied to non-price quantities produces domain-specific patterns instead of a uniform digit effect. Rendering prices as images with progressively smaller cent digits produces a perceptual gradient reaching $-18.76$ points, but this is entirely driven by one of 3 vision models tested. These results suggest that price-ending effects in language models resemble human left-digit bias in their functional form, but reflect learned semantic associations that can be substantially revised by in-context information.