What happened to Portkey?
+
Palo Alto Networks announced its intent to acquire Portkey on April 30, 2026 and completed the acquisition on May 29, 2026. Portkey's technology now forms the foundation of the Prisma AIRS AI Gateway, which became generally available on July 16, 2026. The standalone portkey.ai product and pricing page remain live, and the long-term roadmap for the standalone offering is not stated.
Is Portkey an AI gateway?
+
Yes. Portkey is an AI gateway with an OpenAI-compatible API across a vendor-stated 1,600+ models, with observability, guardrails and prompt management, run over your own provider keys. Since the acquisition it is the core of Palo Alto Networks' Prisma AIRS AI Gateway.
How much does Portkey cost?
+
Portkey's standalone pricing page lists a free tier with 10k recorded logs a month at 3-day retention, Production at $49 a month with 100k logs and 30-day retention, and Enterprise beyond. Because you bring your own keys, each model provider bills you on top. Opper bills every model at provider prices with no markup and 3% on credit purchases (5.5% with Control Plane).
Is Portkey free?
+
Partly. There is a free tier with 10k recorded logs a month and 3-day log retention, and the open-source gateway core is free to self-host. You still pay each model provider directly.
What is the difference between Opper and Portkey (Prisma AIRS AI Gateway)?
+
Both are AI gateways with OpenAI-compatible APIs, tracing and guardrails. Portkey is a control panel over your own provider keys that records requests and responses as its core product, now aimed at enterprise security buyers as part of Prisma AIRS. Opper is a gateway where models, billing and the EU API come with the account: 700+ models through one key, with no prompts stored by default.
Is Opper a drop-in replacement for Portkey?
+
For the gateway path, yes. Both expose OpenAI-compatible endpoints, so you swap base_url and API key on the OpenAI SDK and keep your prompts, tool calls and streaming code. The difference is setup: on Opper there are no provider keys to wire up because models are billed through your Opper account, and bringing your own keys stays optional.
Does Opper store my prompts the way Portkey records logs?
+
No. Portkey's observability records requests and responses by default, with log retention windows of 3 to 30 days below the enterprise tier; a request can opt out with Portkey's debug header. Opper stores metadata only by default, per-call cost, latency and token counts, and stores prompts only when you turn tracing on in the Control Plane. Zero data retention routes keep the provider from storing them too.
Does Opper offer EU data residency without an enterprise contract?
+
Yes. Opper's API runs in Stockholm on every plan, and calling an EU route keeps inference in Europe too, for Claude, GPT, Gemini and Mistral models on AWS Bedrock, Azure, Google Cloud or Berget AI, with no plan upgrade. Portkey's public documentation describes no self-serve EU region for its managed service; residency is addressed through enterprise hybrid or private-cloud deployment, and where the models run is a separate question you settle with each provider.
