Simon Willison releases llm 0.37
Simon Willison announced llm 0.37, a new version of his command-line tool and Python library for accessing large language models. The release adds gpt-6.1-sol and gpt-6.1-terra, introduces an `llm openai endpoint add` command for configuring additional models that use OpenAI-compatible endpoints, changes the default model to gpt-6-luna, and expands embedding support to handle binary content with different content types. Willison said the release represents around two months of accumulated features and fixes.
The update expands model access and adds simpler configuration for OpenAI-compatible endpoints. Its embedding support also accommodates models such as Gemini Embedding 2, which can embed text, audio, images and video.
Release: llm 0.37
Simon Willison’s Weblog
Sponsored by: doubleAI — doubleAI’s Maxwell makes software faster as it runs, no code changes needed. Now in early access
2nd November 2026
Release llm 0.37 — Access large language models from the command-line
#llm#gpt-6.1-sol#gpt-6.1-terra#gpt-6-luna#gpt-5.6-luna#Gemini Embedding 2#Opus 5.5#GPT-6 Astra