---
type: "post"
id: "simon-willison-s-llm-gemini-package-is-available-5eb0ee"
slug: "simon-willison-s-llm-gemini-package-is-available-5eb0ee"
title: "Simon Willison’s llm-gemini package is available on PyPI as version 0.35"
description: "Simon Willison’s `llm-gemini` package is available on PyPI as version 0.35."
retrieval_nugget: "Simon Willison’s `llm-gemini` package is available on PyPI as version 0.35."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["gemini","google"]
entities: ["llm-gemini","LLM","Gemini","Gemini 4 Argon","Simon Willison","Google"]
related_patterns: []
novelty_label: "same_event"
what_changed: "Same event as llm-gemini 0.35"
prior_refs: ["memory:c0cba699-b52f-8ff8-ab74-1cbc73078c4d"]
source_url: "https://pypi.org/project/llm-gemini/0.35"
source_urls: ["https://pypi.org/project/llm-gemini/0.35"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:simon-willison-s-llm-gemini-package-is-available-5eb0ee"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/simon-willison-s-llm-gemini-package-is-available-5eb0ee/","markdown":"https://newruntime.com/posts/simon-willison-s-llm-gemini-package-is-available-5eb0ee.md","json":"https://newruntime.com/posts/simon-willison-s-llm-gemini-package-is-available-5eb0ee.json"}
---

# Simon Willison’s llm-gemini package is available on PyPI as version 0.35

## Retrieval answer

Simon Willison’s `llm-gemini` package is available on PyPI as version 0.35.

Simon Willison’s `llm-gemini` package is available on PyPI as version 0.35. It is a plugin for the LLM command-line tool that provides access to Google’s Gemini model family.

The package requires Python 3.10 or later and LLM 0.32 or later, and is distributed under the Apache-2.0 license. Installation is via `llm install llm-gemini`; users can provide a Gemini API key through `llm keys set gemini` or the `LLM_GEMINI_KEY` environment variable.

The version page lists model aliases including Gemini 4 Argon, which can be invoked as `gemini-4-argon`. Its documented thinking-level options are low, medium, and high. The page also documents multimodal file inputs and optional server-side tools such as code execution and Google Search.

The PyPI page does not include release notes or a changelog describing what changed specifically in version 0.35, nor does it establish model availability, pricing, quotas, or API access terms.

Source: https://pypi.org/project/llm-gemini/0.35

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Gemini](https://newruntime.com/topics/gemini.md): Explore the gemini topic hub.
- topic hub: [Google](https://newruntime.com/topics/google.md): Explore the google topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)