13 OpenRouter endpoints tested: the 7 reporting exactly 205 input tokens mention Claude in 46% of replies
Across 13 OpenRouter endpoints, the 7 reporting exactly 205 input tokens mentioned Claude in 46% of replies versus 0.8% for the other 6; the 205 matches MiniMax's official chat template, mentions hit 90% at temperature 0, and FP4 quantization doesn't explain it, pointing to serving configuration.
MiniMax M3.1 Flash has a weird identity crisis. I tested 13 OpenRouter endpoints. 7 reported exactly 205 input tokens and mentioned Claude in 193/420 replies (46%). The other 6? Just 3/360 (0.8%). That 205-token count exactly matches MiniMax's official open-source chat template. At temperature 0, Claude mentions jumped to 90%. The strangest part is that this doesn't seem to be caused by FP4 quantization. Nebius runs FP4 and almost never mentions Claude. Parasail runs FP8 and does so in 48% of responses. The 205-token group also averages 86% on GPQA vs 88% for the other endpoints. My guess is that the serving configuration plays a major role, but the exact cause is still unclear.