The Pelican comparison grid for Astra is pretty interesting

Simon Willison's comparison grid of AI-generated pelicans shows OpenAI's GPT-6 Astra produces significantly better images than GPT-5.6 Sol, Terra, and Luna across all reasoning levels, with Astra low outperforming any GPT-5.6 Sol model for 9.55 cents. Astra costs about twice as much as Sol ($10/million input, $50/million output vs. $5/$30) but uses fewer tokens, narrowing the price gap. Willison notes Astra and Luna both used 16 input tokens versus 26 for Sol and Terra, suggesting a possible closer relationship between Astra and Luna.

I got access to GPT-6 Astra this afternoon, so naturally I used it to generate SVGs of pelicans riding bicycles https://simonwillison.net/tags/pelican-riding-a-bicycle/ - at low, medium, high, xhigh and max reasoning levels Astra doesn't support reasoning=none . Then I rendered those pelicans in a comparison grid https://static.simonwillison.net/static/2026/gpt-6-and-5.6-pelicans.html with GPT-5.6 Sol, Terra, and Luna, and beyond being fun the result was surprisingly useful. See the grid https://static.simonwillison.net/static/2026/gpt-6-and-5.6-pelicans.html for full quality images. Here's the transcript https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Ff789d2784fc6c5b870cc80f0b7cd9d01 that created the GPT-6 Nova pelicans. There are a few interesting things that stand out from this grid. - The Astra pelicans are much better . The very best GPT-5.6-Sol pelican I liked xhigh better than max is still pretty clearly a bunch of abstract shapes. Every single one of the Astra pelicans, from low to xhigh, looks better than that. The Astra max one is really good. - Astra below max still doesn't reliably get the pelican legs on both sides of the frame. - In terms of cost, Astra may be around twice the price of Sol $10/million input, $50/million output, compared to $5/$30 for Sol , but it uses significantly less tokens at each of the levels, making the prices at the different levels closer than they might otherwise be. - Astra low produces a better pelican than ANY of the GPT-5.6 Sol models at any level, for 9.55 cents. Spending 10 cents on any other model gets a much worse result. - Look at the input token counts: Astra and Luna both used 16 input tokens, Sol and Terra used 26. That's interesting. I wonder if Astra and Luna are more related to each other than OpenAI let on? Tags: ai https://simonwillison.net/tags/ai , openai https://simonwillison.net/tags/openai , generative-ai https://simonwillison.net/tags/generative-ai , llms https://simonwillison.net/tags/llms , pelican-riding-a-bicycle https://simonwillison.net/tags/pelican-riding-a-bicycle , gpt-6-astra https://simonwillison.net/tags/gpt-6-astra