Still tuning gpt-6-sol? Switch to gpt-6.1-sol: same input and output prices, cache reads cut from 10% to 5%—a 3-step migration
Author’s note: gpt-6-sol and gpt-6.1-sol have the same input and output prices, but their cached-read rates differ by half. This article explains how to lower cache costs for long conversations by changing only the model field in your request. Many developers already use 6.1 Sol, 6.1 Terra, and 6 Luna in their day-to-day work. But…