llm 0.37.2 fixes accidental OpenAI API key disclosure
Simon Willison released llm 0.37.2, a command-line tool for accessing large language models. The update fixes issues tracked as GHSA-v9h7-jj4g-f862 and GHSA-r639-rr7r-x72w, which could cause a configured OpenAI API key to be sent to another provider when the named key was not stored or when a responses-enabled model was run with the chat-completions option. It also manages extra-openai-models.yaml through the new `llm openai endpoint add` command introduced in 0.37.
This release closes two paths for accidentally exposing a configured OpenAI API key to an OpenAI-compatible endpoint operated by another provider.
Release: llm 0.37.2
Simon Willison’s Weblog
Sponsored by: Dynatrace — Your coding agent can read your code but can’t see how it runs in production. Read the blog to see how Dynatrace MCP closes that gap.
11th November 2026
Release llm 0.37.2 — Access large language models from the command-line