| name | cheap-swap-guard |
| description | Before swapping any workload to a cheaper model, declare the cases the premium model still dominates and prove they keep routing to premium. Use when the user wants to "just switch" to a cheaper model (text, image, or video), or asks whether a cheap model is good enough to replace an expensive one. |
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
- Name the pair: the cheap model the user wants and the premium model it replaces. This works for any modality: text, image, video, speech.
- 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.
- 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.
- Run the proof below. It fails if any declared dominated case leaks to the cheap model, or if nothing routes cheap at all.
- 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.
