Claude 3.7 support has been released for both JavaScript (via @langchain/anthropic package) and Python versions of LangChain.

This lets LangChain users to access Anthropic's latest, most capable model, Claude 3.7 Sonnet. 3.7 Sonnet includes a new "extended thinking mode," which allows the model to spend time thinking about the user's question before producing an answer. This change allows users to access the model's thought process, and correctly handles chains of thought that have been redacted for safety reasons.

Learn more about Claude 3.7 Sonnet at https://www.anthropic.com/news/claude-3-7-sonnet