Key Points

The author released llm-openrouter 0.6, an LLM plugin that works with models hosted on OpenRouter.
The update adds an <code>llm openrouter refresh</code> command to reload the available model list on demand instead of waiting for cached data to expire.
The release was motivated by wanting to try OpenRouter’s newly available Kimi 2.6 as soon as it appeared.
The post includes a related Pelican HTML/GitHub gist demonstration and a transcript for an animation-based example tied to Kimi’s UI choice.

Simon Willison’s Weblog

Sponsored by: Honeycomb — AI agents behave unpredictably. Get the context you need to debug what actually happened. Read the blog

20th April 2026

Release llm-openrouter 0.6 — LLM plugin for models hosted by OpenRouter

llm openrouter refresh command for refreshing the list of available models without waiting for the cache to expire.

I added this feature so I could try Kimi 2.6 on OpenRouter as soon as it became available there.

Here's its pelican - this time as an HTML page because Kimi chose to include an HTML and JavaScript UI to control the animation. Transcript here.

The bicycle is about right. The pelican is OK. It is pedaling furiously and flapping its wings a bit. Controls below the animation provide a pause button and sliders for controlling the speed and the wing flap.