Loading...
Loading...
Simon Willison released two updates to the open-source llm-gemini plugin that streamline developer access to Google’s latest Gemini models. Version 0.32 adds explicit support for the higher-performance gemini-3.5-flash model and includes a demo showing the upgraded capabilities. The subsequent 0.32a0 alpha release expands compatibility with the llm framework (llm>=0.32a0) and introduces streaming of reasoning tokens, improving responsiveness and observability for applications. Together these releases signal active ecosystem development around model integrations and offer an easy path for developers and tools to experiment with and deploy Gemini models within existing llm-based workflows.
These updates make it easier for developers to access higher-performance Gemini models and integrate them into llm-based tooling. Streaming reasoning tokens improves responsiveness and debugging for applications using Gemini models.
Dossier last updated: 2026-05-21 09:16:45
Simon Willison announced llm-gemini 0.32a0, a new plugin that integrates Google’s Gemini family of models into the llm framework, released 19 May 2026. The plugin requires llm>=0.32a0 alpha and introduces the ability to stream reasoning tokens, enabling finer-grained output as models generate chain-of-thought or intermediate steps. This matters for developers and researchers building applications that need real-time token-level reasoning or observability from Gemini models, and reflects ongoing ecosystem work to support major LLM providers within open ML tooling. The post links this release to other recent LLM developments and targets practitioners using the llm library and Google’s Gemini models.
Simon Willison released llm-gemini 0.32, an update to his LLM plugin that adds support for Google’s new gemini-3.5-flash model. The short post points readers to Willison’s separate notes on Gemini 3.5 Flash and mentions a pelican image generated using the updated plugin, highlighting practical experimentation. This matters for developers and researchers who use third-party integrators to access Gemini models, as plugin updates streamline adoption of new model variants and features. The release continues to track rapid LLM iteration and ecosystem tooling that connect open tooling to major model providers, affecting developer workflows and integration choices.
Simon Willison announced llm-gemini 0.32a0, a new plugin release that enables access to Google’s Gemini family of models and supports streaming of reasoning tokens. The release is compatible with llm>=0.32a0 (alpha), positioning the plugin as an integration point for developers using the llm framework to connect to Gemini models. This matters because it simplifies developer access to Google’s latest LLMs and adds streaming reasoning capability, which can improve responsiveness and observability in applications. The post appears on Willison’s weblog on 19 May 2026 alongside other LLM-focused updates, signaling active ecosystem development around model integrations and developer tooling.
Simon Willison announced llm-gemini 0.32, an updated plugin that adds support for Google’s new gemini-3.5-flash model. The short post links to Willison’s broader notes about Gemini 3.5 Flash and includes a demo (a pelican image) generated using the upgraded plugin. The release matters for developers and tools that integrate LLMs because it enables access to Google’s latest, higher-performance model via an existing open-source plugin, simplifying experimentation and deployment for applications that rely on Gemini family models.