A look at Claude 3.7 Sonnet's extended thinking mode and its 128K token output limit; long thinking runs are impressive but can take several minutes to complete news simonwillison.net

Simon Willison / Simon Willison's Weblog: A look at Claude 3.7 Sonnet's extended thinking mode and its 128K token output limit; long thinking runs are impressive but can take several minutes to complete  —  Claude 3.7 Sonnet (previously) is a very interesting new model.  I released llm-anthropic 0.14 last night adding support for the new model's features to LLM.