Swap cheap, but guard the cases the cheap model loses

Every "the cheap model is 95% as good" claim hides a distribution: on most inputs the gap is invisible, and on a few specific cases the premium model isn't a few percent better, it's a different class. The canonical example (image generation, as of 2026-06): a cheap model like Wan runs ~7-8x cheaper per image than GPT-Image-2 and a normal viewer barely notices, except on text inside the frame, charts, dense layouts, and typography, where GPT-Image-2 leads its leaderboard by the largest margin recorded. A blind swap saves money and quietly ships garbled slides. Your job is to make the swap conditional and write the conditions down.

Steps

1. Name the pair: the cheap model the user wants and the premium model it replaces. This works for any modality: text, image, video, speech.
2. List the dominated cases: the input types where the premium model is known to win by a class, not a margin. Get these from a current leaderboard's category breakdown or the user's own failure examples, not from the headline average. If the user claims there are none, make them say it explicitly; that claim is the riskiest line in the config.
3. Build the route table: every dominated case routes to premium; everything else routes to cheap. Then check the saving is real: if nothing routes to cheap after honest accounting, the swap was a fantasy and the user just learned that for free.
4. Run the proof below. It fails if any declared dominated case leaks to the cheap model, or if nothing routes cheap at all.
5. At request time, tag each input by case before dispatch (for images: does the prompt ask for words in the frame?). The same pattern covers video: cheap for iterations, premium for the physics-heavy hero shot.

Prove it