---
title: "Kong AI Gateway vs Portkey (2026): Compared - API7.ai"
description: "Kong AI Gateway vs Portkey after the acquisition: compare the Portkey OSS gateway, GA Prisma AIRS, routing, caching, deployment, and buying paths."
url: "https://api7.ai/kong-ai-gateway-vs-portkey"
---

# Kong AI Gateway vs Portkey: Which AI Gateway in 2026?

By API7.ai Team

Last updated: August 2026

Kong AI Gateway and Portkey put governed APIs in front of LLM providers, but the vendor context changed in 2026. Palo Alto Networks completed its acquisition of Portkey, and the commercial Portkey offering is now the generally available Prisma AIRS AI Gateway. This guide compares Kong with both the Portkey OSS gateway and that commercial path.

TL;DR

Kong adds AI plugins to a general-purpose gateway with self-hosted, hybrid, and Konnect options. Portkey still provides an MIT-licensed gateway, while its commercial offering is now the GA Prisma AIRS AI Gateway. Compare Kong edition boundaries with both the Portkey OSS scope and the current Prisma AIRS contract; do not treat those two Portkey paths as one product.

- Teams standardizing on a general-purpose API gateway: Kong AI Gateway
- Teams evaluating OSS AI gateway and broader AI security paths: Portkey / Prisma AIRS

<!---->

- [At a glance](#at-a-glance)
- [What is Kong AI Gateway?](#what-is-kong)
- [What is Portkey?](#what-is-portkey)
- [Feature comparison](#feature-comparison)
- [Pricing](#pricing)
- [When to use each](#choose)
- [Bottom line](#bottom-line)
- [FAQ](#faq)

## Kong AI Gateway vs Portkey at a glance

Kong layers AI plugins onto a general-purpose API gateway. Portkey provides an MIT gateway, while the commercial Portkey offering is now the GA Prisma AIRS AI Gateway.

| Dimension           | Kong                                         | Portkey                                                             |
| ------------------- | -------------------------------------------- | ------------------------------------------------------------------- |
| Best for            | AI plugins on a general-purpose API gateway  | OSS AI gateway or Prisma AIRS evaluation                            |
| Core & runtime      | Lua on OpenResty; AI plugins on Kong Gateway | MIT TypeScript gateway; commercial path now tied to Prisma AIRS     |
| Open-source license | Apache-2.0 core; advanced AI Enterprise      | MIT gateway; commercial capabilities separate                       |
| Provider coverage   | Multiple documented providers                | Multiple documented providers                                       |
| Semantic routing    | ✓ Enterprise (AI Proxy Advanced)             | OSS: conditional; Prisma AIRS: semantic routing                     |
| Ensemble / fusion   | — Not documented                             | — Not documented                                                    |
| Caching             | Semantic cache (edition-dependent)           | Simple + semantic; verify current tier                              |
| MCP gateway         | AI MCP Proxy (Enterprise)                    | ✓ Documented                                                        |
| Self-host / VPC     | Docker/K8s, hybrid, Konnect SaaS             | OSS self-host; managed/private options require current offer review |
| SSO / SCIM          | Enterprise/Konnect                           | Commercial offering; verify current tier                            |

## What is Kong AI Gateway?

Kong AI Gateway is a set of AI plugins on Kong Gateway, a mature general-purpose API gateway (Apache-2.0 core, Lua/OpenResty), running self-hosted, hybrid, or via the managed Konnect SaaS.

Kong AI Gateway is a set of AI plugins layered on Kong Gateway, a mature general-purpose API gateway (Apache-2.0 core, Lua on OpenResty). It routes to 15+ LLM providers and can run self-hosted, hybrid, or through the managed Konnect SaaS control plane.

Language

Lua (OpenResty)

License

Apache-2.0 core + Enterprise AI plugins

Form factor

API gateway + AI plugins; Konnect SaaS

Best for

AI plugins on a general-purpose gateway

### Pros

- AI plugins on a mature, general-purpose API-gateway platform
- Self-host, hybrid, or managed Konnect SaaS control plane
- Semantic routing, semantic cache, and MCP proxy (Enterprise)
- 15+ LLM providers behind one API

### Cons

- Free AI surface is thin: OSS AI Proxy handles a single provider/model
- Multi-model LB, semantic routing/cache, token/cost limits are Enterprise
- Semantic/PII guardrails, MCP, LLM-as-judge, SSO/RBAC are Enterprise

## What is Portkey?

Portkey provides an MIT-licensed TypeScript AI gateway. After Palo Alto Networks completed the acquisition in May 2026, the commercial Portkey offering became the generally available Prisma AIRS AI Gateway.

Portkey provides an MIT-licensed TypeScript AI gateway. Palo Alto Networks completed its acquisition of Portkey in May 2026, and the commercial Portkey offering is now the generally available Prisma AIRS AI Gateway. Buyers should map OSS and commercial responsibilities separately.

Language

TypeScript (Node.js)

License

MIT gateway; commercial offer separate

Form factor

OSS gateway + GA Prisma AIRS offering

Best for

Teams evaluating OSS and commercial paths

### Pros

- MIT-licensed gateway with documented self-hosting
- Provider routing, fallback, caching, and observability features
- Documented MCP and guardrail integrations
- Commercial security portfolio through Prisma AIRS

### Cons

- OSS docs confirm conditional routing, not semantic-intent routing
- OSS, hosted Portkey, and Prisma AIRS boundaries require mapping
- Pricing, identity, retention, and private deployment are contract-dependent

See Palo Alto Networks' [acquisition announcement](https://www.paloaltonetworks.com/company/press/2026/palo-alto-networks-completes-acquisition-of-portkey-to-secure-ai-agents) and the current [Prisma AIRS overview](https://www.paloaltonetworks.com/ai-security/prisma-airs) and its [general-availability announcement](https://www.paloaltonetworks.com/blog/2026/07/announcing-general-availability-of-prisma-airs-ai-gateway/) before making a commercial comparison.

## Kong AI Gateway vs Portkey: feature comparison

Both expose open-source gateway code and separate commercial capabilities, but Portkey's acquisition means the OSS gateway and Prisma AIRS commercial portfolio must be evaluated as distinct scopes.

| Feature             | Kong                                                                                                                                                                               | Portkey                                                                                                                |
| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- |
| Core & runtime      | AI plugins on Kong Gateway (Apache-2.0 core, Lua/OpenResty)                                                                                                                        | MIT TypeScript gateway; hosted and commercial capabilities now need Prisma AIRS/Portkey offer mapping                  |
| Provider coverage   | 15+ providers (OpenAI, Azure OpenAI, Bedrock, Anthropic, Gemini, Vertex, Cohere, Mistral, and more)                                                                                | Provider and model catalog documented by Portkey; verify live catalog and Prisma AIRS coverage                         |
| Routing             | AI Proxy (single provider/model) in OSS; multi-model load balancing, semantic routing & failover via AI Proxy Advanced (Enterprise)                                                | Portkey OSS documents load balancing, fallback, retry, and conditional routing; Prisma AIRS documents semantic routing |
| Semantic routing    | ✓ Enterprise (AI Proxy Advanced)                                                                                                                                                   | Not established in OSS docs; documented for Prisma AIRS GA                                                             |
| Ensemble / fusion   | — Not documented                                                                                                                                                                   | — Not documented                                                                                                       |
| Caching             | AI Semantic Cache (Enterprise)                                                                                                                                                     | Simple and semantic caching are documented; verify current product, edition, and data-isolation controls               |
| Guardrails          | AI Prompt Guard (regex) in OSS; AI Semantic Prompt Guard, AI PII Sanitizer, and provider guardrails (Azure Content Safety, AWS Guardrails, GCP Model Armor, Lakera) are Enterprise | Portkey and Prisma AIRS document guardrail capabilities; validate execution point, data path, and purchased tier       |
| Rate limiting       | Request-based in OSS; token- and cost-based via AI Rate Limiting Advanced (Enterprise)                                                                                             | Gateway rate and budget controls are documented; verify counter scope, failure behavior, and current tier              |
| Observability       | Kong analytics and logging plugins; deeper analytics via Konnect                                                                                                                   | Logging, tracing, and analytics are documented; retention and commercial ownership require current offer review        |
| MCP gateway         | AI MCP Proxy (Enterprise)                                                                                                                                                          | ✓ Documented (auth + access control for remote MCP)                                                                    |
| LLM-as-judge        | AI LLM-as-Judge (Enterprise)                                                                                                                                                       | — Not documented                                                                                                       |
| Self-host / VPC     | Self-host Docker/K8s (KIC), hybrid (data plane in your network), or Konnect SaaS                                                                                                   | OSS gateway self-hosts; verify private, managed, and Prisma AIRS deployment options                                    |
| Enterprise identity | SSO (OIDC/SAML) + RBAC via Enterprise/Konnect; SCIM for Konnect not documented                                                                                                     | Commercial identity features are edition-dependent; confirm current Portkey/Prisma AIRS contract                       |

## Pricing comparison

Open-source licenses do not define hosted, support, security, or enterprise pricing. Compare current quotes and published usage dimensions for the exact deployment.

Kong Gateway's core is free (Apache-2.0) and several AI plugins are free, while advanced AI and identity capabilities are edition-dependent. Konnect and Enterprise costs depend on the current plan and usage. The Portkey gateway is MIT-licensed, but hosted or private deployment, identity, retention, support, and Prisma AIRS capabilities are commercial questions. Review the current [Portkey pricing page](https://portkey.ai/pricing) for its current plans. Palo Alto Networks documents Prisma AIRS AI Gateway metering by LLM, MCP, and A2A token consumption through Software NGFW credits for its SaaS and Hybrid offerings; review the [current licensing guidance](https://docs.paloaltonetworks.com/ai-runtime-security/activation-and-onboarding/activate-your-ai-runtime-security-license) and request an estimate for the intended deployment. Build a total-cost model that also includes provider tokens, gateway traffic, data transfer, storage, observability, support, infrastructure, and migration.

## When to use Kong AI Gateway vs Portkey

Choose Kong when its general-purpose gateway and edition model fit. Evaluate Portkey OSS for self-hosting, and evaluate Prisma AIRS separately when commercial AI security and support are required.

### Choose Kong AI Gateway if you…

- Already run (or want) a general-purpose API gateway like Kong
- Want AI plugins alongside your existing API traffic
- Are prepared to buy Enterprise for advanced AI and identity

### Choose Portkey / Prisma AIRS if you…

- Want to self-host the MIT Portkey gateway and validate its current scope
- Want to evaluate Prisma AIRS for a broader commercial AI security program
- Can map data flow, identity, retention, support, and migration across the current offerings

## Bottom line

The decision is now three-way: Kong's gateway and editions, the MIT Portkey gateway, and the generally available Prisma AIRS AI Gateway.

If you already operate Kong, test the required AI plugins and edition boundaries on your traffic. If you want the Portkey OSS gateway, validate the repository, release, provider adapters, and operational ownership you will support. If you need a commercial Portkey path, treat Prisma AIRS as a separate procurement and data flow review. Also compare other candidates with the same source-backed checklist; see [all AI gateway comparisons](https://api7.ai/ai-gateway-comparison).

## Frequently asked questions

### Is Kong AI Gateway or Portkey better?

It depends on the operating and buying model. Kong adds AI plugins to a general-purpose gateway that can run self-hosted, hybrid, or through Konnect. The MIT-licensed Portkey gateway remains available, while the commercial Portkey offering is now the generally available Prisma AIRS AI Gateway. Evaluate the OSS gateway separately from the current Prisma AIRS SKU and contract.

### Is Kong AI Gateway open source?

Partly. Kong Gateway's core is open source (Apache-2.0, written in Lua on OpenResty), and several AI plugins are free — AI Proxy (single upstream provider/model), AI Prompt Guard, AI Prompt Decorator, AI Prompt Template, and AI Request/Response Transformer. The advanced AI plugins are Enterprise-only.

### Is Portkey open source?

The Portkey AI Gateway repository is available under the MIT license and is written in TypeScript. That does not make every hosted, governance, security, or support capability open source. Following Palo Alto Networks' acquisition, confirm which commercial capabilities are sold through Portkey or Prisma AIRS and which remain in the OSS gateway.

### Do Kong AI Gateway or Portkey support semantic routing?

Kong documents semantic routing through AI Proxy Advanced. Public Portkey OSS documentation confirms conditional routing by request context but does not establish semantic-intent routing in the OSS gateway. Palo Alto Networks documents semantic routing for Prisma AIRS AI Gateway; verify the current GA SKU, version, and contract.

### Can I self-host both Kong AI Gateway and Portkey?

Kong Gateway and the MIT-licensed Portkey gateway both provide self-hosting paths. Kong also offers Konnect and hybrid modes. For Portkey's managed, private, or Prisma AIRS deployment options, verify the current Palo Alto Networks offering, support boundary, and data path before procurement.

### What are some alternatives to Kong AI Gateway and Portkey?

Alternatives include LiteLLM, OpenRouter, AISIX, and other API or AI gateway products. Compare the exact release and edition for provider adapters, routing, caching, identity, guardrails, observability, deployment, and support. Do not treat an open-source data plane and a hosted commercial platform as the same procurement option.

## Related comparisons

[Portkey vs LiteLLM](https://api7.ai/portkey-vs-litellm) · [AISIX vs LiteLLM](https://api7.ai/aisix-vs-litellm) · [All AI gateway comparisons](https://api7.ai/ai-gateway-comparison)

## Ready to get started?

For more information about full API lifecycle management, please contact us to Meet with our API Experts.

[Contact Us](https://api7.ai/contact)
