llm-gemini 0.36 tests latest Gemini model at discounted launch pricing
Simon Willison released version 0.36 of his llm-gemini plugin on November 10 and tested Google's latest Gemini model with three reasoning effort levels.
By GennnAi··1 min read
The test covers all three thinking effort levels: low, medium and high, with medium as the default setting. Willison illustrates each level with a pelican drawing. At launch, the model is first priced at $2 per million input tokens and $10 per million output tokens. Those rates will then double on December 1, reaching $4 per million input tokens and $20 per million output tokens.
Source: Simon Willison's Weblog, published on November 10, 2026.