# Stop Defaulting to Sol: How to Route GPT-5.6 by Cost and Quality > Source: > Published: 2026-07-29 09:38:40+00:00 Member-only story # GPT-5.6 Sol, Terra, and Luna: A Practical Tier-Selection Guide ## 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.