Profile-Specific Custom API Keys and Model Grouping

Hi,

Currently, TypingMind allows profile-specific API keys for providers like OpenAI, Anthropic, and Gemini. Could we extend this functionality to custom models as well? Specifically:

• Enable profile-specific keys for custom models, if any configuration exists under the global model settings.

• Introduce grouping and tagging options for custom models, so we don’t have to re-enter the same key multiple times.

This would greatly improve usability and streamline model management across profiles.