{"slug": "llm-gemini-0-38-1", "title": "llm-gemini 0.38.1", "summary": "Simon Willison released llm-gemini 0.38.1, a dot release of the LLM plugin that fixes missing support for the `xhigh` reasoning level on Gemini 4 Hydrogen and Gemini 4 Neon; Gemini 4 Carbon supports only `low`, `medium` and `high`. Willison's updated comparison grid shows Gemini 4 Hydrogen at `high` used 5,311 output tokens and cost 3.99 cents, while the same model at `xhigh` used 31,477 output tokens, cost 23.61 cents, and produced a pelican competitive with Gemini 4 Neon.", "body_md": "**Release:** [llm-gemini 0.38.1](https://github.com/simonw/llm-gemini/releases/tag/0.38.1)\n\nGemini 4 Carbon only supports `low`, `medium` and `high` reasoning levels - but Gemini 4 Hydrogen and Gemini 4 Neon both have an extra `xhigh` level.\n\nI missed that when I added those models to the `llm-gemini` plugin, which is now fixed in this dot release.\n\nThe `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:\n\nTags: [gemini](https://simonwillison.net/tags/gemini), [llm](https://simonwillison.net/tags/llm), [llm-reasoning](https://simonwillison.net/tags/llm-reasoning), [pelican-riding-a-bicycle](https://simonwillison.net/tags/pelican-riding-a-bicycle), [ai](https://simonwillison.net/tags/ai), [llms](https://simonwillison.net/tags/llms), [google](https://simonwillison.net/tags/google), [generative-ai](https://simonwillison.net/tags/generative-ai)", "url": "https://wpnews.pro/news/llm-gemini-0-38-1", "canonical_source": "https://simonwillison.net/2026/Nov/20/llm-gemini/", "published_at": "2026-11-20 03:01:57+00:00", "updated_at": "2026-11-22 00:44:20.741583+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "generative-ai", "developer-tools"], "entities": ["llm-gemini", "Simon Willison", "Gemini 4 Carbon", "Gemini 4 Hydrogen", "Gemini 4 Neon", "Google"], "also_reported_by": [], "takeaway": "llm-gemini 0.38.1 adds the `xhigh` reasoning level for Gemini 4 Hydrogen and Neon, which on Hydrogen raised output from 5,311 tokens (3.99 cents) to 31,477 tokens (23.61 cents).", "recommendation": null, "alternates": {"html": "https://wpnews.pro/news/llm-gemini-0-38-1", "markdown": "https://wpnews.pro/news/llm-gemini-0-38-1.md", "text": "https://wpnews.pro/news/llm-gemini-0-38-1.txt", "jsonld": "https://wpnews.pro/news/llm-gemini-0-38-1.jsonld"}}