{"slug": "llm-0-37", "title": "llm 0.37", "summary": "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.", "body_md": "**Release:** [llm 0.37](https://github.com/simonw/llm/releases/tag/0.37)\n\nThere'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.\n\nI 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.\n\nI 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`.\n\nLLM'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.\n\nA 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!\n\nThis 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.\n\nSo 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!\n\nTags: [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)", "url": "https://wpnews.pro/news/llm-0-37", "canonical_source": "https://simonwillison.net/2026/Nov/2/llm/", "published_at": "2026-11-02 23:49:30+00:00", "updated_at": "2026-11-03 00:21:48.430596+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "large-language-models", "generative-ai"], "entities": ["Simon Willison", "LLM", "gpt-6.1-sol", "gpt-6.1-terra", "gpt-6-luna", "gpt-5.6-luna", "Gemini Embedding 2", "Opus 5.5"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/llm-0-37", "markdown": "https://wpnews.pro/news/llm-0-37.md", "text": "https://wpnews.pro/news/llm-0-37.txt", "jsonld": "https://wpnews.pro/news/llm-0-37.jsonld"}}