Anthropic documents Claude effort defaults and guidance for choosing models

1. 4:03 PM
   ClaudeDevs@ClaudeDevsOfficial

   Anthropic publishes a guide to choosing among Claude models

   AIAnthropic publishes a guide on which Claude model to build with, covering Fable 5.2, Opus 5.5, Sonnet, and Haiku. The guide also explains when to adjust effort instead of switching models and how to lower costs by running subagents on smaller models.

2. 2:04 PM
   ClaudeDevs@ClaudeDevsOfficial

   Anthropic explains Claude effort defaults and when to use higher settings

   AIAnthropic says effort defaults to high in the Claude Platform and medium in Claude apps. It recommends xhigh only for the hardest long-running agentic work with measurable gains, and says Max is for finding the ceiling rather than everyday use.

   

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.