Prisma AIRS AI Gateway (formerly Portkey)
AI InfrastructureFreemiumVisit Site
An AI gateway that adds routing, caching, observability, and guardrails to LLM traffic through a single control plane.
Overview
Portkey is a managed or self-hostable AI gateway: route requests across providers, fail over automatically, cache responses, enforce guardrails, and get observability and cost analytics on every call. It overlaps with LiteLLM but leans more toward a polished, batteries-included product with built-in dashboards and guardrails. For an enterprise standardizing how dozens of teams call models, a gateway like this is the layer where reliability, cost control, and policy actually get enforced — rather than living in scattered application code. Palo Alto Networks completed its acquisition of Portkey on 2026-05-29, and portkey.ai now carries the banner "Portkey is now PRISMA AIRS AI Gateway"; the MIT-licensed gateway remains open source, but confirm whether the free developer tier survives under the new owner.
Pros & Cons
Pros
- Routing, failover, and caching out of the box
- Built-in observability and cost analytics
- Guardrails enforced at the gateway
- Managed or self-hosted
Cons
- Another vendor in the critical request path
- Overlaps with observability tools you may already run
- Full governance features need a paid plan
Workflows that use Prisma AIRS AI Gateway (formerly Portkey)
Get a new AI workflow each week — many feature Prisma AIRS AI Gateway (formerly Portkey) and other tools in this category.