Member-only story
Why defaulting to the smartest model might be your most expensive routing mistake. #
If you are using free version of Medium, use link to access this article for free. Please consider following and subscribing , share this article with your friends to support my work. Thank you.
OpenAI wants you to believe Sol is the best model in the GPT-5.6 family, but defaulting to it might be your most expensive engineering mistake. The moment GPT-5.6 stopped being a single endpoint and became three distinct tiers — Sol, Terra, and Luna — model selection turned into a rigorous unit-economics problem. Most teams are about to get the spreadsheet wrong.
The useful question is no longer which tier wins a benchmark. It is: which tier produces an accepted piece of work at the lowest total cost for this specific task? This requires calculating retries, reviewer time, long answers, cache behavior, and the cost of being wrong to build a concrete routing strategy you can deploy today.