{
  "id": 19919263,
  "title": "Claude Code 2.1.321: Fable 5.2 vs 5.1, 20% Cheaper",
  "url": "https://urgent.news/2026/11/14/claude-code-2-1-321-fable-5-2-vs-5-1-20-cheaper",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-14T04:44:57.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/shaam_ai/claude-code-21321-fable-52-vs-51-20-cheaper-5f4c"
  },
  "original_language": "en",
  "account": null,
  "summary": "Claude Code 2.1.321, released on GitHub on 9 November 2026, introduces Fable 5.2 as the default Fable model, reducing its unit prices to $8 per million input tokens, $40 per million output tokens, and $0.20 per million cache reads, marking a 20% decrease across the board compared to Fable 5.1's prices of $10, $50, and $0.25, respectively. Anthropic claims that Fable 5.2 generates output up to 30% faster than its predecessor, and the upgrade is largely automatic, with only a change in model selection required. While Fable 5.2 outperforms Fable 5.1 in coding benchmarks, Anthropic still recommends Opus 5.5 as the default model for most coding tasks due to its superior performance.",
  "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."
}