AI Gateway Data Governance

Visualize LLM metrics in Konnect.

Expose and visualize LLM metrics.

Learn about AI Gateway logging capabilities.

Per-request OpenTelemetry span attributes for AI traffic.

Aggregated OpenTelemetry metrics for AI, MCP, and A2A traffic.

Check llm/v1/chat or llm/v1/completions requests against a list of allowed or denied expressions

Use Azure AI Content Safety to check and audit AI Proxy plugin messages before proxying them to an upstream LLM

Use AWS Guardrails to validate requests and/or responses in the AI Proxy plugin before forwarding them between clients and upstream LLMs.

Audit and validate LLM prompts with Google Cloud Model Armor before forwarding them to an upstream LLM.

Semantically and intelligently create allow and deny lists of topics that can be requested across every LLM.

Permit or block prompts based on semantic similarity to known LLM responses, preventing misuse of llm/v1/chat or llm/v1/completions requests

Inspect and enforce Lakera Guard safety policies on LLM requests and responses before they reach upstream models.

Use a third-party guardrails service to validate requests and/or responses in the AI Proxy plugin before forwarding them between clients and upstream LLMs

Include your Amazon Bedrock guardrails configuration in AI Proxy requests

Protect sensitive information in client request or response bodies before they reach upstream services or clients

Create RAG pipelines by automatically injecting content from a vector database