---
title: "Traps — named pricing failure modes · Undominated.ai"
canonical: https://undominated.ai/traps/
---

# Traps — named pricing failure modes · Undominated.ai

# Traps

Named ways a headline price stops being the price. Each page is a definition, a computation, and the offender table — or an explicit we cannot say. We will not invent a ninth trap without a computation, and we will not print a tokenizer-tax percent.

As of 2026-09-19, 60 publishable models raise the input rate past a prompt-length threshold — a context cliff, with every rung kept. Other traps on this index are computed the same way or marked we cannot say. The tokenizer-tax page refuses a percent until a public corpus exists.

 - Context cliff computed · 60 Every published context-tier step function. Ladders keep every rung.
- Reasoning meter computed · 29 Separately billed reasoning tokens. The headline input/output pair is incomplete.
- Cache-write penalty we cannot say The lean catalogue carries cached-input rates, not a cache-write tariff, so a break-even cannot be computed here.
- Credit cliff we cannot say Included-pool exhaustion is a plan fact. This page will not guess a mid-month revert to API without a measured pool in the catalogue projection.
- Silent truncation we cannot say No catalogue field records a hidden context cap (the ChatGPT Free Instant 27K claim is not in this payload). We will not guess.
- Alias drift computed · 18 *-latest is a moving SKU. The pointer is recorded; we do not freeze a vendor alias as a model.
- Precision bait computed · 84 Distinct sellers, not rows. A cheaper lower-quant endpoint is a trade, not a saving. See /spreads/.
- Tokenizer tax refused The cross-vendor tokenizer-inflation figure is unverified in this repo. This page exists to refuse a percent until a public corpus exists. We will not print one.

## See also

 - [Context cliffs](/cliffs/)
- [Spreads](/spreads/)
- [Reasoning effort](/effort/)
- [Methodology](/methodology/)