KO

Kong AI Gateway

AI plugins on a mature API gateway platform

Enterprise AI gatewayResearch complete

Company overview

Kong AI Gateway extends Kong Gateway with AI-specific plugins covering prompt guards, response handling, PII sanitisation, semantic caching, routing and rate limiting, deployable wherever Kong runs.

Ideal customer: API platform and infrastructure teams with an existing Kong or Kubernetes footprint

  • Applying prompt and response guards as gateway plugins
  • Semantic caching and rate limiting for LLM traffic
  • Routing across multiple model providers from one proxy

GateYourAI verdict

Kong's advantage is that AI controls are plugins on a data plane many organisations already operate, with self-hosted and Kubernetes deployment as first-class options. Per-plugin verification against Kong's developer documentation is queued before we mark individual controls as available.

Best for: Platform teams already running Kong that want AI policy in the same data plane. Read how we assess platforms.

Security capabilities

A capability is marked available only when an official page or documentation says so. “Not publicly documented” means we could not find it — not that the vendor lacks it.

Security capabilities for Kong AI Gateway
CapabilityStatusVerificationSource
Prompt-injection detectionIdentifies attempts to override system instructions in prompts or tool output.Provided by the AI Prompt Guard plugin.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Prompt-injection blockingBlocks the request before it reaches the model, rather than only logging it.Prompt Guard rejects matching requests at the gateway.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Jailbreak detectionDetects known jailbreak and guardrail-evasion patterns.Verification pendingVerification pending. Verification pending.Verification pending
PII detectionIdentifies personal information in prompts or responses.AI Sanitizer / PII plugin.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
PII redactionMasks or removes personal information before it leaves the gateway.Sensitive values can be redacted before the request is forwarded.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Secret & credential scanningDetects API keys, tokens and credentials in prompts or output.Verification pendingVerification pending. Verification pending.Verification pending
Input inspectionInspects outbound requests before they reach the model.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Output inspectionInspects inbound model responses before they reach the application.Response guarding is available as a plugin.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Content moderationClassifies harmful or policy-violating content. Not equivalent to injection defense.Content-safety plugin integration.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Policy enforcementConfigurable rules applied per route, team, key or environment.Capabilities are configured as per-route plugins.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Agent & tool controlsConstrains tool calls, autonomous actions and agent permissions.Verification pendingVerification pending. Verification pending.Verification pending
MCP securityControls or inspects Model Context Protocol server traffic.MCP traffic can be proxied and governed.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Audit logsDurable, reviewable record of requests and policy decisions.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Access controlsRoles, teams, keys and scoped permissions.Consumers, keys and RBAC from Kong Gateway.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation

Cost-optimization capabilities

Token reduction, avoided calls, cheaper-model routing, budgets and reporting are tracked separately because they are not interchangeable.

Cost-optimization capabilities for Kong AI Gateway
CapabilityStatusVerificationSource
Prompt compressionReduces the number of tokens actually sent to the model.Not publicly documentedNot publicly documented. Not publicly documented.Not publicly documented
Exact cachingReturns a stored response for a byte-identical request.AI Proxy caching.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Semantic cachingReturns a stored response for a semantically similar request using embeddings.AI Semantic Cache plugin.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Intelligent model routingChooses a model per request based on task, cost or performance.AI Proxy Advanced routes across providers and models.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Automatic fallbackRetries against an alternate model or provider on failure.Provider fallback on failure.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Load balancingDistributes traffic across keys, regions or providers.Load balancing across model targets.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Token budgetsHard or soft limits expressed in tokens.Token-based rate limiting acts as a token budget.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Dollar budgetsSpending limits expressed in currency.Verification pendingVerification pending. Verification pending.Verification pending
Rate limitsRequest throttling. Throttling is not the same as token reduction.AI Rate Limiting Advanced plugin, including token-based limits.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Cost attributionAttributes spend to teams, keys, users or features.Usage is reported per consumer and route; dedicated cost attribution not stated.LimitedLimited. Partially documented.Partially documentedKong AI Gateway developer documentation
Cost analyticsDashboards and reporting on token and dollar usage.AI analytics and observability.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Savings reportingReports the spend avoided by compression, caching or routing.Verification pendingVerification pending. Verification pending.Verification pending

Supported models and deployment options

Self-hosted, Kubernetes and managed options associated with Kong Gateway. Verification pending.

Models, infrastructure and deployment for Kong AI Gateway
CapabilityStatusVerificationSource
OpenAISupports OpenAI models.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
AnthropicSupports Anthropic models.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Google GeminiSupports Google Gemini models.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
AWS BedrockSupports AWS Bedrock as a provider.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Azure OpenAISupports Azure OpenAI deployments.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Open-source modelsSupports open-weight models or self-hosted inference endpoints.Ollama, Hugging Face and self-hosted endpoints.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
SaaS deploymentVendor-hosted managed service.Konnect managed control plane.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
VPC / private cloudDeployable inside a customer cloud account.Kubernetes and cloud deployment.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
On-premiseDeployable in a customer data centre.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Self-hostedCustomer runs and operates the gateway themselves.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
Open-source optionSource code published under an open-source licence.Kong Gateway is open source; some AI plugins are enterprise-only.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
APIProgrammatic API for configuration or traffic.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation
SDKOfficial client libraries.AvailableAvailable. Verified from official documentation.Verified from official documentationKong AI Gateway developer documentation

Pricing status

Verification pending. Kong publishes plan tiers; AI Gateway specifics not yet verified.

Commercial information for Kong AI Gateway
CapabilityStatusVerificationSource
Public pricingList pricing published on the vendor website.Verification pendingVerification pending. Verification pending.Verification pending
Free tierA permanently free usage tier.Verification pendingVerification pending. Verification pending.Verification pending
Free trialA time-limited or credit-limited trial.Verification pendingVerification pending. Verification pending.Verification pending
Enterprise planA named enterprise tier.Verification pendingVerification pending. Verification pending.Verification pending
Contact sales requiredPricing requires contacting the vendor.Verification pendingVerification pending. Verification pending.Verification pending

Strengths

  • Runs in the same data plane as existing API traffic
  • Self-hosted and Kubernetes deployment are core to the platform

Limitations

  • AI capabilities are spread across plugins that must be configured individually
  • Some capabilities are enterprise-tier only and need contract-level confirmation

Alternatives to Kong AI Gateway

You can also compare Kong AI Gateway against up to three other platforms, or read the AI Gate pillar page.

Sources

  1. Kong AI Gateway product page Kong Inc. · Official product page · Accessed 2026-07-30Queued for detailed capability extraction.
  2. Kong AI Gateway developer documentation Kong Inc. · Official documentation · Accessed 2026-07-30Primary source of truth for per-plugin capability marks.

Last reviewed: 2026-07-30

Newsletter

The AI Gateway Brief

A weekly briefing on AI security threats, gateway technology, token economics, model routing, and the infrastructure controlling enterprise AI.

No vendor sponsorship in the brief. Unsubscribe at any time.