⚡
Brief IA
›

llm-gemini 0.33 Supports Gemini 3.7 Flash

💻 Code & Dev·Tom Levy·

llm-gemini 0.33 Supports Gemini 3.7 Flash

llm-gemini 0.33 Supports Gemini 3.7 Flash
⚡
Key Takeaways
1llm-gemini 0.33 supports Gemini 3.7 Flash, 3.6 Flash, 3.5 Flash Lite, and two embedding models
2The plugin becomes compatible with LLM 0.32 with reasoning traces and server-side tools
3The author notes that in Firefox/Chrome, the bike displays but the pelican is missing (SVG)
💡Why it matters — LLM 0.32 compatibility allows for displaying reasoning traces and activating server-side tools with this model.
⚡Le brief IA que lisent les pros

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.

Choisis ton rythme

Gratuit · Pas de spam · Désabonnement en 1 clic

📄
Full Analysis

Version 0.33 of the llm-gemini plugin introduces support for Gemini 3.7 Flash, other variants, and two embedding models, while becoming compatible with LLM 0.32 to display reasoning traces and enable server-side tools. The author also reports an SVG rendering discrepancy between browsers and notes that the minimal effort option present in 3.6 Flash has disappeared in 3.7.

Firefox and Chrome display the bike but not the pelican

The author indicates that the image of the pelican shown was rendered with Safari. According to him, Safari handles empty SVG <filter> elements better than Firefox and Chrome, resulting in different outcomes across browsers. In Firefox and Chrome, the bike appears, but the pelican does not. He also points out that in Gemini 3.7 Flash, the minimal effort option, which was available in 3.6 Flash, is no longer present.

Version 0.33 adds 3.7 Flash and becomes compatible with LLM 0.32

The llm-gemini plugin has been updated to version 0.33, described as the first update in a while. This version adds support for Gemini 3.7 Flash, gemini-3.6-flash, gemini-3.5-flash-lite, as well as the embedding models gemini-embedding-2 and gemini-embedding-001. It is compatible with LLM 0.32, allowing for reasoning traces to be displayed and server-side tools to be activated with this model.

A command line example illustrates usage

A command line example demonstrates the use of the gemini-3.7-flash model with the -T CodeExecution option and the prompt "use python to calculate (factorial of 13) * 3." The author specifies that Gemini 3.7 Flash was released today. The publication was posted online on August 13, 2026, at 7:37 PM.

⚡

Brief IA — L'actualité IA en français

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