Brief IA
›

llm-gemini 0.38.1 fixes Gemini's reasoning levels

Code & Dev·Tom Levy·

llm-gemini 0.38.1 fixes Gemini's reasoning levels

llm-gemini 0.38.1 fixes Gemini's reasoning levels
Key Takeaways
1llm-gemini 0.38.1 corrects an omission regarding reasoning levels.
2Carbon does not offer xhigh, unlike Hydrogen and Neon.
3The comparison reports a cost of 23.61 cents for Hydrogen in xhigh.
Why it matters : the correction specifies which settings are available for each model.

llm-gemini 0.38.1 corrects an omission regarding the reasoning levels available for the Gemini models. This plugin for LLM provides access to Google's range.

Hydrogen reaches 23.61 cents in xhigh

The individual who integrated the models into the plugin has updated their Gemini 4 comparison: they report for Hydrogen, set to high, a consumption of 5,311 tokens in output, charged at 3.99 cents. With xhigh, they note 31,477 tokens for a cost of 23.61 cents. They consider the pelican obtained to be competitive compared to that of Gemini 4 Neon.

La lettre du soirGratuit · 19 h

Le brief IA que les pros lisent chaque soir

Les 7 actus IA du jour, décryptées en 5 min. Gratuit.

Inclus dès l'inscription : notre sélection des meilleurs guides & comparatifs IA.

Choisissez votre rythme

Gratuit · Pas de spam · Désabonnement en 1 clic

Carbon remains limited to three settings

For Gemini 4 Carbon, the only reasoning options are low, medium, and high. Hydrogen and Neon additionally offer xhigh. The person who added these models to llm-gemini indicates they initially forgot to specify this distinction.

Brief IA — L'actualité IA en français

L'essentiel de l'actualité de l'intelligence artificielle, décrypté et expliqué chaque jour.