I wanted to verify this for myself, so I set up a small test harness on my production server. It ran 360 chat completions across a range of models, cancelling each request immediately after the first token was received. Below are the resulting first-token latency measurements:
Авиакомпания Emirates начала перебронировать билеты россиян, застрявших в ОАЭ на фоне обострения конфликта на Ближнем Востоке. Об этом сообщает Ассоциация туроператоров России (АТОР).，推荐阅读体育直播获取更多信息
“高铁+新春+红色”，延安文旅准备充分。。体育直播对此有专业解读
This is easy to incrementalize, as changing a few letters in the input
It was shown off for the first time at the Central Library tram stop in Centenary Square - with the tram given a new name, Steven Knight, in recognition of his work promoting the city and the wider region through the franchise.