I also believe some providers fallback to another model entirely. I was recently using Kimi K3 and saw that some requests had no reasoning trace whatsoever. Unsurprisingly, those requests were routed to the less reputable providers (Sail Research).
I had quite a few Kimi K3 requests served by Sail. Most of these were fine and had the reasoning traces (I like reading them), however I noticed that some requests were being generated unusually quick and had no reasoning trace, which led me to believe another fallback model was being used, since Kimi K3 always emits reasoning tokens.