AI Signal 307
llm-gemini 0.33 adds Gemini 3.7 Flash and LLM 0.32 compatibility
↗
The llm-gemini plugin release 0.33 adds support for Gemini 3.7 Flash and several other Gemini models, plus compatibility with LLM 0.32 that brings reasoning traces and server-side tool invocation to the plugin.
Engineers using the LLM CLI tool can now access Google's latest Gemini 3.7 Flash model alongside its server-side tool execution capabilities such as CodeExecution. The LLM 0.32 compatibility also surfaces reasoning traces, giving visibility into the model's chain-of-thought that was previously unavailable for Gemini models through this plugin.
Written by elseif from the cluster below · every claim links back to a sourceThe three things worth knowing
llm-gemini 0.33 adds support for Gemini 3.7 Flash, gemini-3.6-flash, gemini-3.5-flash-lite, and two embedding models (gemini-embedding-2 and gemini-embedding-001).
Compatibility with LLM 0.32 enables reasoning traces and server-side tools invoked via the -T flag, such as CodeExecution for running Python.
The minimal thinking effort option available in Gemini 3.6 Flash has been removed in 3.7 Flash, leaving low, medium, and high as the remaining effort levels.
THE CLUSTER