Skip to content
Live
ITHome · AI·· 3 days ago

Anthropic has added a регулирующий effort capability to the Claude API.

Brief overview

Anthropic has added a Beta feature to the Claude API to adjust effort, allowing developers to change the 'level of effort' in model responses during a conversation. Users set the output_config.effort level by inserting an empty system message, affecting resource allocation in aspects such as model thinking and tool calls, enabling adjustments in response adequacy, speed, and cost when switching tasks.

Source: ITHome · AI · ithome.com