Anthropic adds in-conversation effort adjustment to Claude API
AIAnthropic adds a beta feature to the Claude API that lets developers change the effort setting partway through a conversation. Developers set the target level through a new output_config.effort parameter, inserting an empty system message without changing top-level configuration or prompt caching.
Source details
IThome · AI · ithome.comPublished · added here
Original title: Claude API 新增调节 effort 能力：让 AI 按任务使劲，从闲聊转复杂分析可中途“换挡”