Home / Kong AI Gateway
Report

Kong AI Gateway Policies Hub

Extend Kong AI Gateway with powerful policies and easy integrations

AI

AI AWS Guardrails

Use AWS Guardrails to validate requests and/or responses before forwarding them between clients and upstream LLMs.

AI Azure Content Safety

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

AI Custom Guardrail

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

AI GCP Model Armor

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

AI LLM as Judge

Score prompt-response pairs with a dedicated LLM to evaluate the accuracy and quality of model responses.

AI Lakera Guard

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

AI PII Sanitizer

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

AI Prompt Compressor

Compress prompts with LLMLingua 2 before they reach the upstream LLM to stay within context limits, cut token costs, and reduce latency.

AI Prompt Decorator

Prepend or append an array of messages to a user’s chat history.

AI Prompt Guard

Check text completion requests against a list of allowed or denied expressions

AI Prompt Template

Provide fill-in-the-blank AI prompts to users

AI RAG Injector

Create RAG pipelines by automatically injecting content from a vector database

AI Rate Limiting Advanced

Provides rate limiting for the AI plugins.

AI Request Transformer

Use an LLM service to transform a client request body prior to proxying the request to the upstream server

AI Response Transformer

Use an LLM service to transform the upstream HTTP(S) prior to forwarding it to the client

AI Semantic Cache

Cache LLM responses based on semantic similarity between requests to reduce latency and cost.

AI Semantic Prompt Guard

Permit or block LLM prompts based on semantic similarity to predefined allow and deny rules.

AI Semantic Response Guard

Permit or block LLM responses based on semantic similarity to predefined rules for chat, completions, and embeddings requests

Traffic Control

ACL

Control which Consumers can access Services and Routes

Canary Release

Slowly roll out software changes to a subset of users

Confluent Consume

Consume messages from Confluent Cloud Kafka topics and make them available through HTTP endpoints

Premium Partner

Forward Proxy Advanced

Allows Kong AI Gateway to connect to intermediary transparent HTTP

GraphQL Proxy Caching Advanced

Cache and serve commonly requested responses in Kong AI Gateway

GraphQL Rate Limiting Advanced

Provides rate limiting for GraphQL queries

Kafka Consume

Consume messages from Kafka topics and make them available through HTTP endpoints.

Mocking

Provide mock endpoints to test your APIs against your Services

OAS Validation

Validate HTTP requests and responses based on an OpenAPI 3.0 or Swagger API Specification

Proxy Cache

Cache and serve commonly requested responses in Kong

Proxy Caching Advanced

Cache and serve commonly requested responses in Kong, in-memory or using Redis

Rate Limiting

Limit how many HTTP requests can be made in a given period of seconds, minutes, hours, days, months, or years.

Rate Limiting Advanced

Enhanced rate limiting capabilities such as sliding window support, Redis Sentinel support, and increased performance.

Redirect

Redirect incoming requests to a new URL

Request Size Limiting

Block requests with bodies greater than a specified size.

Request Termination

Terminates all requests with a specific response

Request Validator

Validates requests before they reach the upstream service

Response Rate Limiting

Rate limit based on a custom response header value.

Route By Header

Route requests based on specified request headers

Service Protection

Prevent abuse and protect services with absolute limits on the number of requests reaching the service

Solace Consume

Consume messages from Solace topics and make them available through HTTP endpoints

Premium Partner

Standard Webhooks

Validate that incoming webhooks adhere to the Standard Webhooks specification

Upstream Timeout

Set custom timeouts on connections to upstream services to override Gateway Service-level timeouts.

WebSocket Size Limit

Block incoming WebSocket messages greater than a specified size

WebSocket Validator

Validate WebSocket messages before they are proxied

XML Threat Protection

Apply structural and size checks on XML payloads

Something wrong?
Report an Issue
View all Kong documentation

Help us make these docs great!

Kong Developer docs are open source. If you find these useful and want to make them better, contribute today!
Contribute

Still need help?

Ask in our Slack Community
Contact Support