The Limit Provider AI section in the AI Management Center allows administrators to control usage, performance, and costs by setting specific thresholds for each AI provider.

Key Configuration Parameters:

• Max Instruction: The maximum character or token count allowed for system instructions/prompts.
• Max User Query: The upper limit for the length of a single user question or input.
• Max Response Tokens: Controls how long the AI's answer can be, preventing excessive resource consumption.
• Timeout (seconds): Defines how long the system will wait for a response before terminating the request.

Provider-Specific Examples:

As shown in the dashboard, different providers can have different policies:

• DeepSeek: Currently configured with a 30-second timeout and 2,048 response tokens.
• Gemini: Set with a higher capacity of 8,192 response tokens and a 60-second timeout.

To add a new configuration, click the Add Provider button. You can modify existing policies by clicking the options menu on each provider card.