llm-gemini 0.32 adds gemini-3.5-flash
simon willison released llm-gemini 0.32, adding support for the new gemini-3.5-flash model.
developer simon willison announced the release of llm-gemini 0.32, an update to his python plugin for accessing large language models. the primary feature of this release is integration with gemini-3.5-flash, a new model iteration which willison notes is more expensive but is central to google's future roadmap. this tool enables developers to evaluate and utilize the model via a cli interface. the announcement references recent developments from may 2026, including partnerships between xai and anthropic and google's strategic shift towards the 3.5 flash model.