{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/route-to-the-cheapest-model-that-still-passes-your-task-eval",
  "id": "MHC-D-RESEARCH-1167",
  "version": "0.1.0",
  "title": "Route to the cheapest model that still passes your task eval",
  "summary": "Do not pay for intelligence the task does not use—but do not guess where the boundary is.",
  "kind": "protocol",
  "body": "Partition requests by observable task features, evaluate candidate models on each slice and route only where the cheaper model continues to meet the required outcome and safety thresholds. Re-test the boundary after model, prompt, tool or traffic changes.",
  "limits": [
    "A cheaper request can still create a more expensive service if retries, failures or human recovery increase."
  ],
  "topics": [
    "union-ai-runtime-verification-2026"
  ],
  "intents": [],
  "source_ids": [
    "RS-AE31C3BE0BBBA1F6"
  ],
  "evidence": [
    {
      "claim": "Model routing can use local task evaluations to identify the least expensive model that still meets the required behavior for a bounded class of requests.",
      "source_id": "RS-AE31C3BE0BBBA1F6",
      "role": "supports",
      "note": "The passing boundary can change with prompts, tools, model versions and request distribution, so routing rules require re-evaluation.",
      "locator": "7:36-12:46, find the least expensive capable model and fit model, harness and task together"
    }
  ],
  "use_when": [
    "A workflow uses a frontier model for every request even though many requests may be easier."
  ],
  "avoid_when": [
    "A cheaper request can still create a more expensive service if retries, failures or human recovery increase."
  ],
  "example": "Use a smaller model for straightforward classification only after local cases show it preserves routing accuracy and escalation behavior; send ambiguous cases to the stronger model.",
  "check": "Every routing rule points to a current local eval slice and a fallback path rather than to model reputation.",
  "steps": [
    "Define task slices that can be identified before inference.",
    "Run the same acceptance eval for candidate models on each slice.",
    "Choose the least expensive model that passes the slice's required thresholds.",
    "Keep a fallback for uncertain or failing cases.",
    "Re-evaluate routing when the system or traffic changes."
  ],
  "sources": [
    {
      "id": "RS-AE31C3BE0BBBA1F6",
      "title": "Improving Agents Is a Data Mining Problem",
      "url": "https://ai.engineer/talks/CvRngaQZQ3Y-improving-agents-is-data-mining-problem"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-1167",
      "to": "MHC-D-RESEARCH-0720",
      "type": "useful_with",
      "url": "/knowledge/own-the-task-eval-before-shopping-for-a-better-model"
    }
  ],
  "collections": [
    {
      "id": "RC-ACD6385FB70207D3",
      "title": "Operate AI agents as systems you can replay, verify and constrain",
      "url": "/collections/operate-ai-agents-as-systems-you-can-replay-verify-and-constrain"
    }
  ]
}