Fable 5.1 review: Anthropic's best coding model uses half the tokens of Opus 5

every · x · 2026-10-03

Every.to's day-zero Vibe Check on Anthropic's Fable 5.1 finds it stronger than Fable 5, running for days on coding challenges that stumped its predecessor, while being fast and natural to talk to.

Key findings: token usage is about half of Opus 5 for similar tasks, putting Fable-level capability at an Opus budget; a zero-data-retention option removes the main enterprise adoption barrier; and it's the first model non-programmers can truly delegate to, like assigning a slide deck and walking away. The post also describes using it to build a Pokémon-style Generative Agents village simulation in an hour, hinting at future A/B testing of message diffusion by policymakers.

Related event: Every's hands-on: Anthropic Fable 5.1 is the strongest coding model, using half the tokens(3 posts)→

Original post →

More from Models

Models channel →