Intel / article

llm-anthropic 0.30

Source: simonwillison.net
Date: Published Sep 28, 2026

Context

Version 0.30 of -anthropic, the plugin that lets Simon Willison's llm command-line tool call Anthropic models, adds support for Claude Sonnet 5.5 and two commands, according to his release note.

The first, llm anthropic refresh, updates the list of available models directly from Anthropic's API. Willison says this means he no longer needs to publish a new release just to support a newly launched model. The second, llm anthropic count, uses Anthropic's free counting API to report how many tokens a prompt will use before it is sent, where a token is the unit of text a model reads and bills by.

The note describes changes only and reports no testing or usage results.

Key takeaways · AI-distilled

llm-anthropic 0.30 adds support for Claude Sonnet 5.5.
A new `llm anthropic refresh` command pulls the model list straight from Anthropic's API, so newly released models no longer need a new plugin release.
A new `llm anthropic count` command uses Anthropic's free token counting API to report how many tokens a prompt will use before you send it.

Terms in this piece · Glossary

LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.

Read the source simonwillison.net