llm-gemini 0.35

Simon Willison released llm-gemini 0.35, adding support for Google's Gemini 4 Argon model, which became available today via the Gemini API and to subscribers of Google's $100/month plan. Argon launched at $2 per million input tokens and $10 per million output tokens — matching GPT-6 Sol, half the price of Claude Opus 5.5, and one-fifth the price of Claude Fable 5.1 and GPT-6 Astra — but its price is set to double on December 1st. Artificial Analysis measured Argon's total benchmark cost at $2,407, close to GLM-5.3 and cheaper than the latest OpenAI, Anthropic and Meta models.

Release: llm-gemini 0.35 https://github.com/simonw/llm-gemini/releases/tag/0.35 I added support to llm-gemini https://github.com/simonw/llm-gemini for the new Gemini 4 Argon https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-argon/ model, made available today via the Gemini API and for customers of their $100/month subscription plan. Here are the low, medium and high pelicans https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Fd741e4420dea14c460f0108ac22dbc26 . As expected, they are all excellent: Gemini has a track record of producing great SVGs, and are the only lab where I know their staff have invested in SVG specifically https://twitter.com/sunjiao123sun /status/2024555516551372920 and who have boasted about their pelicans https://simonwillison.net/2026/Feb/19/gemini-31-pro/ jeff-dean before. Here's the "high" illustration, which cost me 17.166 cents: The pricing is interesting. At launch, Argon is $2/million input and $10/million output - the same price as GPT-6 Sol, half the price of Claude Opus 5.5 and 1/5th the price of Claude Fable 5.1 and GPT-6 Astra. But on December 1st Argon is set to double in price - so it will be the same price as Opus 5.5. Prices like this aren't really comparable these days since what really matters is how many tokens a model takes to achieve a goal within an agentic harness. One useful clue for that comes from Artificial Analysis, who publish the total cost to run their benchmark https://artificialanalysis.ai/ total-cost-tabs using each model. Argon is looking very good there - costing $2,407 to run the benchmark, putting it close to GLM-5.3 and significantly cheaper than OpenAI, Anthropic, and Meta's latest models. When the price doubles it will still be a little cheaper than GPT-6 Astra. I used ChatGPT to edit that chart https://chatgpt.com/share/6acebe13-5378-83e8-bf2f-9f4d05b206f4 The data is all correct, I checked - I needed to get that Gemini 4 Argon info box to display without overlapping the other numbers. Some bonus examples using Gemini 4 Argon: here's Generate an SVG of an armadillo in fishnet tights jaywalking on Mars https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2F9589ff9e0c977bbf3b012b7a11f5bd71 , here's a Fabergé egg https://tools.simonwillison.net/blender-viewer?url=https%3A%2F%2Fstatic.simonwillison.net%2Fstatic%2Fcors-allow%2F2026%2Fgemini-4-astra-egg.blend it created for me using Blender, and DeepMind staffer @fofrAI shared a video of a pelican riding a bike, using fourier epicycles https://twitter.com/fofrai/status/2110043023954284889 . That's a fun new twist Tags: google https://simonwillison.net/tags/google , ai https://simonwillison.net/tags/ai , generative-ai https://simonwillison.net/tags/generative-ai , llms https://simonwillison.net/tags/llms , llm https://simonwillison.net/tags/llm , gemini https://simonwillison.net/tags/gemini , llm-pricing https://simonwillison.net/tags/llm-pricing , pelican-riding-a-bicycle https://simonwillison.net/tags/pelican-riding-a-bicycle , llm-release https://simonwillison.net/tags/llm-release