Anthropic publishes Claude model selection guide
What happened
On November 9, the claude.dev developer blog published a guide to choosing among Claude models: Fable, Opus, Sonnet and Haiku. Anthropic recommends starting most coding and knowledge work with Claude Opus 5.5 at medium thinking effort, then picking Sonnet 5.5, Haiku 5.5 or Fable 5.2 based on task difficulty. The guide says to choose by the cost of completing the task: set up automated acceptance checks first, then adjust thinking effort or move up a model, and hand easily checked side tasks to smaller models. When switching models, teams should also check prompt caching, thinking block retention and API parameter compatibility, and compare quality and spend on real tasks.
Written by AI from the coverage · updated 2 days ago
Coverage
Follow the reports to see the story from different sides.
- claude.dev BlogPickAnthropic's Claude model guide: choosing between Fable, Opus, Sonnet and Haiku
Anthropic's selection guide says most coding and knowledge work should start with Claude Opus 5.5 at medium thinking effort, moving to Sonnet 5.5, Haiku 5.5 or Fable 5.2 as task difficulty changes. It frames model choice around the cost of finishing a task: set up automated acceptance checks first, then adjust thinking effort or step up a model, and hand easy-to-verify side tasks to smaller models.
Heat over time
Heat now 3·Comparable peak 8（Nov 10 05:00）·Comparable change over 24 hours -49%
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.