llm-gemini 0.34 Adds Gemini 3.8 Flash With Three Thinking Levels
llm-gemini 0.34 adds support for Google's new gemini-3.8-flash model with low, medium, and high thinking levels to Simon Willison's LLM command-line tool.
What it is
llm-gemini 0.34 is the latest release of the Gemini plugin for Simon Willison's llm command-line and Python tool for talking to language models.
What it does
It adds the new gemini-3.8-flash model with configurable low, medium, and high thinking levels, and fixes a bug where async responses failed to record the model version that actually handled the request.
Why it matters
Same-day plugin support means anyone already using llm as their model-agnostic CLI can try Google's new Flash model without waiting on a separate SDK or rewriting scripts.
How to use it
Run llm install -U llm-gemini then call llm -m gemini-3.8-flash, optionally setting a thinking level via the model's options.
llm 0.35 Adds Support for OpenAI's GPT-6 Astra Model
llm 0.35 adds support for OpenAI's gpt-6-astra model to Simon Willison's command-line and Python tool for talking to language models.
Reasoning Traces, Responses API, New SQLite Logs: LLM 0.32 Lands
LLM 0.32 is Simon Willison's command-line and Python tool for talking to language models, updated with visible reasoning traces, server-side provider tools, redesigned content-addressable SQLite logs, and support for the OpenAI Responses API.
llm-mcp-client Lets Simon's llm CLI Talk to Any MCP Server
llm-mcp-client is a new alpha-stage plugin that lets Simon Willison's llm command-line tool connect to and call tools from Model Context Protocol servers.