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.
# Release: llm-gemini 0.33
Source: [https://simonwillison.net/2026/Aug/13/llm-gemini/](https://simonwillison.net/2026/Aug/13/llm-gemini/)
It's been a while since the last`llm\-gemini`release\. This version of the plugin adds support for today's[Gemini 3\.7 Flash](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/)release, plus`gemini\-3\.6\-flash`,`gemini\-3\.5\-flash\-lite`and two embedding models`gemini\-embedding\-2`and`gemini\-embedding\-001`\.
The plugin is also upgraded for compatibility with LLM 0\.32, which means you can now see reasoning traces and you can also enable server\-side tools using this pattern:
```
llm -m gemini-3.7-flash -T CodeExecution \
'use python to calculate (factorial of 13) * 3'
```
I had Gemini 3\.7 Flash[draw me some pelicans riding bicycles](https://tools.simonwillison.net/markdown-svg-renderer.html#url=https%3A%2F%2Fgist.github.com%2Fsimonw%2F6779a22d5e7bb6bdf29936f1600a5259)at high, medium, and low thinking efforts \(minimal, which was an option in 3\.6 Flash, has been removed in 3\.7\.\) Here's the high level one, which is pretty great:

One catch though: the pelican I showed here was rendered with Safari\. Both Firefox and Chrome render it differently, due to Safari being more tolerant of empty SVG`<filter\>`elements than those other two browsers\.
They still display the bicycle, but the pelican is missing entirely\!

A user tested Gemini-3.5-flash-lite on grading classwork and found it performed worse than its predecessor Gemini-2.5-flash-lite, suggesting newer models are not always better.
Gemini 3.7 Flash is highlighted as an upgrade over Gemini 3.6, scoring 67% on a browser use dataset compared to 83% SOTA, while Luna offers a cost-effective alternative with a 5x price reduction.