Google routes gemini-3.7-flash calls to gemini-3.8-flash and gemini-3.5-flash calls to gemini-3.6-flash, so the model name in your logs no longer tells you which model answered.
The minimal thinking level is not supported on Gemini 3.8 Flash and returns an error, so any call that set it needs the low level instead.
Gemini 3.8 Flash and 3.6 Flash prices double on January 1, 2027, from $0.75 and $3.75 to $1.50 and $7.50 per million input and output tokens.