The max tokens parameter can be manually set when using any OpenAI API call.
You can find the settings in API logins > OpenAI etc
Set max completion tokens to -1 to disable the setting.
SCM sends both max_tokens and max_completion_tokens to keep up to date with the new API changes from reasoning models.
Refer to here:
https://platform.openai.com/docs/api-reference/chat/create
The same parameters are also in open ai alt #1/#2
