Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

llm-gemini 0.38.1 fixes Gemini 4 xhigh reasoning support

AI summary

llm-gemini 0.38.1 is a dot release that fixes handling of the extra xhigh reasoning level for Gemini 4 Hydrogen and Gemini 4 Neon. Simon Willison notes that Gemini 4 Carbon supports only low, medium and high reasoning levels. In his comparison, Hydrogen at high used 5,311 output tokens and cost $0.0399, while xhigh used 31,477 output tokens and cost $0.2361.

In-depth insight

The patch restores access to the additional reasoning option for Gemini 4 Hydrogen and Neon, while the reported token and cost comparison illustrates the practical trade-off between high and xhigh.

Release: llm-gemini 0.38.1

Simon Willison’s Weblog

Newsletter

Sponsored by: WorkOS — Auth.md: signup built for agents. See how it works

20th November 2026

Release llm-gemini 0.38.1 — LLM plugin to access Google's Gemini family of models

#llm-gemini 0.38.1#Gemini 4 Hydrogen#Gemini 4 Neon#Gemini 4 Carbon#Google

Original · 1 min readRead the original
Group chat

No comments yet. Start the conversation.