Hacker News · AI· 882542F3884314B·· 2 hours agoSelectedAI score71
Which Claude Model Should You Choose for Your App? A Selection Guide for Fable, Opus, Sonnet, and Haiku
Which Claude model should you build with? Fable, Opus, Sonnet, or Haiku
AI guide
Anthropic has released a Claude model selection guide, recommending Opus 5.5 with medium effort as the default starting point for most coding and knowledge work. Developers can step down to Sonnet 5.5 for well-scoped routine bug fixes or feature iterations, choose Haiku 5.5 for high-concurrency, low-cost extraction and classification, and upgrade to Fable 5.2 for the most complex technical challenges and long-horizon tasks.
Why it matters
The article provides a trade-off framework across capabilities, costs, and reasoning effort for the four models, offering readers direct guidance on task-specific model selection and sub-agent delegation strategies.
Source:Hacker News · AI · claude.dev