{
  "id": 9274356,
  "title": "Opus 5.5 Made Cache Reads 60% Cheaper. I Redid the Math on My Text-to-SQL Architecture",
  "url": "https://urgent.news/2026/09/23/opus-5-5-made-cache-reads-60-cheaper-i-redid-the-math-on-my-text-to",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-09-23T04:55:42.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/rakno/opus-55-made-cache-reads-60-cheaper-i-redid-the-math-on-my-text-to-sql-architecture-4jjb"
  },
  "original_language": "en",
  "account": "Yesterday, Claude Opus 5.5 release brought cache reads at $0.20 per million tokens, 60% cheaper than Opus 5. Cost comparison for a text-to-SQL CRM assistant revealed a smaller gap between retrieving only relevant schema and sending the whole schema every time. The choice shifted from cost to accuracy. The migration guide introduced two breaking changes affecting text-to-SQL setups. Opus 5.5's pricing eliminated the need for a full semantic layer, changing the cost equation. However, the decision still hinged on accuracy. The recommended approach involves a hybrid solution - a static cached schema alongside retrieved examples.",
  "summary": "TL;DR: Claude Opus 5.5 came out yesterday with cache reads at $0.20 per million tokens, 60% cheaper than Opus 5. I redid the cost math for my text-to-SQL CRM assistant. For one design choice, the cost gap between \"retrieve only the relevant schema\" and \"send the whole schema every time, cached\" shrank from 2.1x to 1.2x . At that point the choice stops being about cost and becomes about accuracy.…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}