You can turn off thinking in Gemini pro models by using completion mode.
Essentially, append a message with role=model and minimal text part, such as a simple "A", at the end of the "contents" array. The model will try to complete the message without using any thought tokens.
You can also set the model message to start with "think" or something along that line and watch it thinks out loud (or melts down with over-thinking and stop due to reaching maximum output token)
Kinda weird to start talking FOSS when the website itself never ever claimed to have anything to do with FOSS.
What does search engines indexability have to do with FOSS? There's no shortage of old school forums locked behind membership system, not indexable by any search engines.
Also Discord is an instant messaging software and not "web". It just happens to have a web frontend. It's OK to be nostalgic of the old web but not the old instant messaging softwares.
Essentially, append a message with role=model and minimal text part, such as a simple "A", at the end of the "contents" array. The model will try to complete the message without using any thought tokens.
You can also set the model message to start with "think" or something along that line and watch it thinks out loud (or melts down with over-thinking and stop due to reaching maximum output token)
``` [ { "parts": [{"text": "hello"}], "role": "user" }, { "parts": [{"text": "*think"}], "role": "model" } ] ```