llm-gemini 0.38.1

Simon Willison's Blog Tools

Summary

llm-gemini 0.38.1 adds the missing `xhigh` reasoning level for Gemini 4 Hydrogen and Neon models, with Simon Willison showing that xhigh significantly boosts output quality at higher token cost.

No content available
Original Article
View Cached Full Text

Cached at: 11/21/26, 07:11 PM

# Release: llm-gemini 0.38.1 Source: [https://simonwillison.net/2026/Nov/20/llm-gemini/](https://simonwillison.net/2026/Nov/20/llm-gemini/) Gemini 4 Carbon only supports`low`,`medium`and`high`reasoning levels \- but Gemini 4 Hydrogen and Gemini 4 Neon both have an extra`xhigh`level\. I missed that when I added those models to the`llm\-gemini`plugin, which is now fixed in this dot release\. The`xhigh`setting for Hydrogen makes a*significant*difference\. I updated my[Gemini 4 comparison grid](https://static.simonwillison.net/static/2026/gemini-4-carbon-neon-hydrogen-with-xhigh.html)\- note how Hydrogen at high used 5,311 output tokens and cost 3\.99 cents, but the same model at xhigh used 31,477 output tokens, cost 23\.61 cents, and produced a pelican that's competitive with Gemini 4 Neon: ![Screenshot of a comparison table of illustrations of a pelican riding a bicycle, generated by three models at two thinking levels. Column headers: Thinking, gemini-4-carbon, gemini-4-neon, gemini-4-hydrogen. Row XHIGH: gemini-4-carbon cell is empty and reads "Unsupported". gemini-4-neon shows a detailed white pelican with a large orange beak riding a red cruiser bicycle along a beachside road, a fish in the wicker basket on the handlebars, with sea, a sailboat, clouds and sun behind, captioned "40 input tokens, 26,546 output = 39.83 cents · 3m 47s". gemini-4-hydrogen shows a similar pelican on a teal bicycle on a sandy beach with a blue fish in the basket, captioned "40 input tokens, 31,477 output = 23.61 cents · 2m 36s". Row HIGH: gemini-4-carbon shows a pelican wearing a sailor hat riding a red cruiser bicycle with a fish in the basket beside the sea, captioned "40 input tokens, 20,305 output = 20.31 cents · 4m 11s". gemini-4-neon shows a pelican on a simpler red bicycle on a dark asphalt road with yellow dashed lines and the sea behind, captioned "40 input tokens, 9,691 output = 14.55 cents · 1m 11s". gemini-4-hydrogen shows a plainer, flatter pelican on a red bicycle over a green strip of ground with no basket or sea, captioned "40 input tokens, 5,311 output = 3.99 cents · 19s".](https://static.simonwillison.net/static/2026/gemini-4-xhigh-pelicans.webp)

Similar Articles

llm-gemini 0.38

Simon Willison's Blog

Simon Willison releases llm-gemini 0.38, updating his Gemini model comparison tools alongside Google's confusing Gemini 4 lineup announcement, which now includes the new Gemini 4 Neon model alongside Carbon and Hydrogen.

llm-gemini 0.33

Simon Willison's Blog

llm-gemini 0.33 adds support for Gemini 3.7 Flash and several new models, plus compatibility with LLM 0.32 including reasoning traces and server-side tools.

llm-gemini 0.34

Simon Willison's Blog

Simon Willison announces the release of llm-gemini 0.34, a tool for interacting with Gemini AI models.

llm-gemini 0.31

Simon Willison's Blog

llm-gemini 0.31 is a new release of the plugin for using Google's Gemini models with the LLM command-line tool.

llm-gemini 0.37

Simon Willison's Blog

Simon Willison 发布 llm-gemini 0.37 插件更新,同时介绍 Google 新推出的 Gemini 4 Hydrogen 模型及其令人困惑的 Gemini 4 家族定价方案,并附上三代模型在不同思考等级下的生成对比。