Home / Directory / AI SaaS tooling / Prompt / app frameworks / Portkey
Portkey
AI gateway and control plane for routing, fallbacks, guardrails, prompt management, and observability across LLM providers. Palo Alto Networks completed its acquisition of Portkey on May 29, 2026, and now sells the gateway as Prisma AIRS AI Gateway.
Platform teams that need one gateway for multi-model routing, fallbacks, budgets, and request logs in front of many LLM providers.
Teams that only want a prompt CMS without a gateway, or buyers who will not accept a security-vendor-owned control plane after the Palo Alto deal.
Co-founded by Rohit Agarwal.
Verdict
Portkey is a solid AI gateway when the job is reliable routing, fallbacks, caching, guardrails, and logged prompts across providers. Public pricing includes a free Developer tier and Production at $49 per month for 100k recorded logs, with Enterprise quote for VPC and compliance. Engineers like the unified API and cost visibility; documentation gaps and learning curve show up in lighter reviews. Palo Alto Networks completed the acquisition in May 2026, so treat roadmap and contracting as Prisma AIRS-adjacent.
Score Breakdown
How Portkey scores in the categories that matter to its buyers.
Pricing
Portkey publishes Developer, Production, and Enterprise plans on portkey.ai/pricing. Prices below are USD from the public card as of September 2026. LLM provider charges are separate.
| Plan | Price | What stands out |
|---|---|---|
| Developer | $0 | 10k recorded logs/mo; 3-day log retention; gateway features |
| Production | $49 / mo | 100k logs/mo; +$9 per extra 100k (up to ~3M); 30-day logs |
| Enterprise | Sales quote | 10M+ logs, custom retention, SSO, VPC, HIPAA/SOC2 options |
The Field at a Glance
How Portkey compares with other Prompt / app frameworks vendors we reviewed, by Overall Score and relative typical engagement cost.
Portkey scores 7.9 in Prompt / app frameworks, behind LiteLLM (8.0) and ahead of Helicone (7.4) and PromptLayer (6.9). Its relative cost is lower in this subcategory.
Compared with …
- Portkey vs LiteLLM 8.0/7.9
- Portkey vs PromptLayer 7.9/6.9
Use-case matrix
| Use case | Fit | Notes |
|---|---|---|
| Multi-model AI gateway | Strong | The gateway is the core product. |
| Prompt versioning desk | Mixed | Portkey includes prompt versioning, and PromptLayer goes deeper on it. |
| LLM red-teaming / eval suites | Weak | Promptfoo covers this job. |
| Security-vendor gateway roadmap | Mixed | Portkey is now part of Palo Alto Networks and sold as Prisma AIRS AI Gateway. |
Review Excerpts
Excerpts from public reviews and forum discussions of Portkey, plus representative buyer views drawn from public information. Paid reviews and pay-for-play sites were excluded.
“With 30 million policies a month, managing over 25 GenAI use cases became a pain. Portkey helped with prompt management, tracking costs per use case, and ensuring our keys were used correctly.”
“Portkey is a no-brainer for anyone using AI in their GitHub workflows. It has saved us thousands of dollars by caching tests that don't require reruns.”
“We are using Portkey in staging and production, and it works really well for us. With reporting and observability being so bad on OpenAI and Azure, Portkey helps get visibility into how and where we are using AI models.”
“The documentation had gaps, and the routing configuration took us a while to learn.”
Representative buyer view
Where customer reviews couldn't be found, our analysts attempted to give a voice to buyer sentiment, drawing on real information from review sites, forums, and product documentation.
Based on: Portkey’s pricing page and Palo Alto Networks’ acquisition announcement
Key Leadership
Rohit Agarwal
Co-founder and CEO
Methodology
This page is an independent evaluation of Portkey for buyers comparing options in prompt / app frameworks. AI Industry Reviews accepts no sponsorships, advertising, or pay-for-placement fees. Portkey did not pay for this review.
What we scored
The headline number is an Overall Score on a 0-10 scale. Eight criteria fall under it in two groups.
- Buyer outcomes (for prompt / app frameworks)
- Multi-provider gateway / routing
- Logs & cost observability
- Prompt management & guardrails
- Post-acquisition continuity
- Company & commercial
- Innovation & product leadership
- Project management & communication
- Pricing
- Contract fairness
Pricing measures whether the price looks fair for the value delivered, including packaging and renewal friction that show up in real buying cycles.
Score Composition
| Input | Weight | What it covers |
|---|---|---|
| Reviews | 40% | A proprietary read of what practitioners say about likes, complaints, and day-to-day use, including public review sites, forums, and private chat rooms. Paid reviews and pay-for-play sites are out of scope. |
| Product | 35% | Hands-on look at screens and workflows. |
| Pricing | 15% | Whether the price looks fair for what you get. |
| Docs & training | 10% | Docs, tutorials, and training material. |
How we balanced the evidence
The Overall Score is the simple average of the eight criteria. Recommendation language follows that score and the use-case matrix above.
Scope
Portkey is graded here as prompt / app frameworks. Criteria scores can move as more review volume and product checks are added.