llm-gemini 0.36 Google made Gemini 4 Carbon available to all users on November 10, 2026, two weeks after announcing it for "a subset of cyber defenders," and Simon Willison shipped llm-gemini 0.36 to support it. The model launched at $2 per million input tokens and $10 per million output tokens — matching GPT-6.1 Sol and Claude Sonnet 5.5 pricing — with prices scheduled to double to $4/$20 on December 1st, the same as Opus 5.5. Willison tested Gemini 4 Carbon's low, medium and high thinking efforts with pelican prompts and used Google's Antigravity IDE to generate a Three.js animation of Yonkers as a mech stomping through Manhattan, Queens and Brooklyn from OpenStreetMap data. Release: llm-gemini 0.36 https://github.com/simonw/llm-gemini/releases/tag/0.36 Gemini 4 Carbon was announced two weeks ago https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-carbon/ for "a subset of cyber defenders", but today it's available to everyone else https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-carbon-now-available/ . This is Google's best ever Gemini, priced at $2/million input and $10/million output at launch that's GPT-6.1 Sol / Claude Sonnet 5.5 prices but scheduled to double in price to $4/$20 on December 1st same as Opus 5.5 . Here are three pelicans https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Fe5bf860633fc12e8f926f305c4c3190c for the low, medium and high thinking efforts it defaults to medium . This is the pelican I got for high: Gemini pelicans have all been great for a while now, so I also tested it out using Google's Antigravity IDE with a prompt I first tried with Claude Fable 5.2 yesterday https://simonwillison.net/2026/Nov/10/yonkers-rises/ : Make a three js animation where yonkers stands up as a big mech cool stand up motion and stomps around manhattan and queens and Brooklyn, use openstreetmap mapping data Here's the HTML result https://static.simonwillison.net/static/2026/yonkers-mech-standalone.html I had to prompt "build that into a standalone HTML file" to get a version with no external dependencies . I then screen-captured that as a video: Tags: llm-release https://simonwillison.net/tags/llm-release , gemini https://simonwillison.net/tags/gemini , llm https://simonwillison.net/tags/llm , google https://simonwillison.net/tags/google , generative-ai https://simonwillison.net/tags/generative-ai , ai https://simonwillison.net/tags/ai , llms https://simonwillison.net/tags/llms