Model Router Policy
A model router policy defines how an application chooses among models based on task type, cost, latency, capability, or safety requirements.
Category
AI Model Routing
These routing concepts help AI applications direct prompts by policy, latency, fallback needs, and safety checks.
How to recognize this theme
Terms for choosing which model handles a request.
In a daily board, this category groups terms by their shared role. Look for four cards that describe the same mechanism, risk area, or workflow rather than four words that merely sound similar.
Educational context
These entries are vocabulary notes for learning. They are not project endorsements, token recommendations, exchange rankings, or trading signals.
Latency Budget
A latency budget is the amount of time an AI system can spend on routing, retrieval, inference, and post-processing before responding.
Fallback Model Path
A fallback model path sends a request to an alternate model when the preferred model is unavailable, too slow, or outside policy.
Prompt Safety Filter
A prompt safety filter checks incoming instructions for policy, security, privacy, or misuse concerns before a model acts on them.