← Ai Gateway / ai-gateway / features / guardrails

Supported model types

AI Gateway's Guardrails detects the type of AI model being used and applies safety checks accordingly:

• Text generation models: Both prompts and responses are evaluated.
• Embedding models: Only the prompt is evaluated, as the response consists of numerical embeddings, which are not meaningful for moderation.
• Unknown models: If AI Gateway cannot determine the model type, it evaluates only the prompt and bypasses Guardrails for the response.