llm 0.37

Simon Willison released version 0.37 of his LLM CLI tool and Python library, adding the gpt-6.1-sol and gpt-6.1-terra models, a new `llm openai endpoint add` command for configuring OpenAI-compatible endpoints, and a default model switch to gpt-6-luna at half the price of the previous default, gpt-5.6-luna. The release also extends embeddings support to accept different content-types for binary content, needed for models such as Gemini Embedding 2 that embed text, audio, images and video. Willison said the release includes fixes from 12 authors, almost all AI-assisted, and that reviewing them was less burdensome than expected because he used Opus 5.5 or GPT-6 Astra to help triage.

Release: llm 0.37 https://github.com/simonw/llm/releases/tag/0.37 There's a lot of stuff in this new release of my LLM CLI tool and Python library, representing around two months of accumulated features and fixes. I added gpt-6.1-sol and gpt-6.1-terra , plus a new llm openai endpoint add https://llm.datasette.io/en/stable/other-models.html configure-an-openai-compatible-model command to make it easier to configure additional models that use OpenAI-compatible endpoints. I switched the default model if you have not set your own default to gpt-6-luna - half the price of the previous default, gpt-5.6-luna . LLM's support for embeddings now accepts that different binary content may have different content-type - necessary for models like Gemini Embedding 2 https://deepmind.google/models/gemini/embedding/ , which can embed text, audio, images, and video. A lot of open source maintainers complain about a flood of AI-assisted PRs. LLM is my project that has been most affected by this and, to be honest, I'm not finding it to be a problem. That's mainly because I have Opus 5.5 or GPT-6 Astra help me with triage to spot the most useful fixes This release includes fixes from 12 authors - almost all AI-assisted - and the burden of reviewing them wasn't nearly as great as I expected. I really see them as bug reports with attached examples - sometimes I land them, sometimes I implement my own fix. So thanks to 0d00ciallo0721 https://github.com/0d00ciallo0721 , ac1982 https://github.com/ac1982 , Allen Flux https://github.com/allenflux , Bian Yuhan https://github.com/bianyh , Bishop Kammeraad https://github.com/porkedchop , Chen Yufeiyang https://github.com/feiiiiii5 , Christopher Krah https://github.com/chrikrah , Ethan Stoner https://github.com/ethanstoner , Jiachen Xie https://github.com/er-s-an , Olamide Faniyan https://github.com/Pajimo , Sharat Chandra Sai Boddu https://github.com/sharatchandrasai999-sketch , nosmile99 https://github.com/nosmile99 for helping out with or spending tokens on this release Tags: open-source https://simonwillison.net/tags/open-source , projects https://simonwillison.net/tags/projects , ai https://simonwillison.net/tags/ai , annotated-release-notes https://simonwillison.net/tags/annotated-release-notes , generative-ai https://simonwillison.net/tags/generative-ai , llms https://simonwillison.net/tags/llms , embeddings https://simonwillison.net/tags/embeddings , llm https://simonwillison.net/tags/llm