Anthropic's official guide: when to use Fable 5.2, Opus 5.5, Sonnet or Haiku
ClaudeDevs · x · 2026-11-10
Anthropic (claude.dev, by Addy Osmani) published an official model-selection guide covering its four GA models: Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.2, plus Claude Mythos 5.2 for cybersecurity/life-sciences research via verification programs.
- Start most work on Opus 5.5 at medium effort — the Claude Code default, costing half of Fable 5.2 per token.
- Drop to Sonnet 5.5 for well-scoped everyday work (bug fixes, spec-driven features), but migrations and performance optimizations can still warrant Opus or Fable.
- Use Haiku 5.5 for simple high-volume tasks (classification, routing, extraction) and for subagents handling a larger model's side tasks — the main cost-saving lever.
- Reserve Fable 5.2 for the hardest technical projects.
The guide's key tactics: adjust effort before switching models, and put subagents on smaller models to cut costs.
More from coding & agent
- Anthropic's S-1: 'agent' appears 177 times, 'SaaS' zero — the AWS playbook — brucemacv · 2026-11-10
- CoreWeave Launches Claude Code Skill to Build GPU Clusters and Serve Models from the CLI — altryne · 2026-11-10
- Designer ships portfolio built entirely with Claude Code, declaring the Design Engineer era — evilrabbit_ · 2026-11-10
- Stripe's claimable sandboxes: frictionless test accounts for AI agents, 50k+ provisioned daily — dl_weekly · 2026-11-10
- Simon Willison Hides AI-Generated PR Descriptions Behind Collapsed details Tags — tdhopper · 2026-11-10
- Ex-film composer vibe codes his dream ambient DAW in a week with Claude Fable 5.2 — yawnxyz · 2026-11-10