For each model reasoning was enabled, and the reasoning effort is set to high. I included GPT 5.2 because it could be argued that it can reason better than mini. However, I couldn't test GPT 5.2 as much as the other models because it was too costly. Gemini 3 Pro was costly as well, but it didn't spend as much time as GPT 5.2 during reasoning which made it more affordable in my experience.
When adapting to a ReadableStream, a bit more work is required since the alternative approach yields batches of chunks, but the adaptation layer is as easily straightforward:
，更多细节参见51吃瓜
Мерц резко сменил риторику во время встречи в Китае09:25
Мощный удар Израиля по Ирану попал на видео09:41
据微信派昨日消息，在最新版微信里：