Portkey vs Kong AI Gateway
The question that decides it: Is this a new AI product to adopt, or one more route on the API gateway your platform team already operates?
Our verdict
If Kong already sits in front of your services, the AI Gateway is a plugin on infrastructure your platform team already knows, and that institutional advantage usually outweighs everything else on this page. If it does not, Portkey is the AI-native choice, with published pricing, deeper AI-specific features and far fewer surprises about what tier you need.
Why
Both are open core, both can be self-hosted or bought as a service, and both do the routing, guardrails, semantic caching and prompt management you would expect. The difference is lineage. Kong AI Gateway is an AI capability added to a mature API gateway with 44,100 GitHub stars, and it inherits that platform's operational model, its config-as-code, and its performance: 8,200 requests per second and 12ms of measured overhead, the fastest figures in this catalogue. Portkey was built for LLM traffic from the start and is deeper on the things only LLM traffic needs.
Pricing transparency separates them sharply, and not in Kong's favour. Portkey publishes its numbers: free Developer plan with 10,000 recorded logs a month, $49 a month for Production with 100,000 logs and 30-day retention, $9 per additional 100,000 requests. Kong publishes a 30-day Konnect trial and a Plus plan billed per gateway per month with the amount not published, and pushes fully self-hosted gateways, audit logs and SSO into a custom-priced annual Enterprise contract. If you need a number before you can get approval, only one of these gives you one.
There is a specific trap in Kong's Plus tier worth knowing before you plan around it: it caps the AI Gateway at five unique LLM models, with more available only on Enterprise. That is a small number for anything doing model comparison, gradual migration or per-task routing, and it is the kind of limit that is discovered after the architecture is committed rather than before.
On the AI-specific columns Portkey is ahead where it matters for most teams: it publishes evals, a HIPAA BAA and zero data retention, none of which Kong publishes. Kong leads on raw throughput and on provider-independent operational maturity, and its guardrails and prompt management are real. Coverage is thin on both sides and neither publishes a model total — Portkey lists 40 to 48 providers, Kong 17.
Which one, concretely
Choose Portkey if
- You need evals, a HIPAA BAA or documented zero data retention
- You want published pricing you can put in a budget request today
- You want the deepest AI-specific feature set — prompt management, semantic cache, guardrails, evals in one place
- You are not already running Kong and do not want to adopt an API gateway to get an AI one
Choose Kong AI Gateway if
- Kong is already in front of your services and your platform team runs it
- Throughput and latency overhead are the binding constraints — 8,200 rps at 12ms is the best measured here
- You want AI traffic governed by the same policies, config and pipelines as the rest of your API estate
- You want an Apache-2.0 core you can self-host at infrastructure cost only
What catches people out
- Kong's Plus plan caps the AI Gateway at five unique LLM models; going beyond that means Enterprise
- Kong's Plus and Enterprise prices are not published — expect a sales conversation before you get a number
- Kong's self-hosted gateways, audit logs and SSO are Enterprise-only, annually billed
- Portkey's model figures range from 250 to 2,300 across its own pages, so treat its catalogue size as unsettled
Side by side
2 of 10 fields differ, marked with a dot. Every figure links to the vendor page it came from. Blank values read Not published rather than No — silence from a vendor is not a negative answer.
| Field | Portkey | Kong AI Gateway |
|---|---|---|
| Ease of leaving Derived score, higher is easier | 100/100 Easy to leave | 100/100 Easy to leave |
| How long they keep it Default content retention (days) | 90 days | 30 days |
| GitHub stars GitHub stars | 12,848 | 44,100 |
| Quality testing Evals | Yes | Not published |
| Will sign a HIPAA agreement HIPAA BAA | Yes | Not published |
| Does not retain your data Zero data retention | Yes | Not published |
| Similar-question caching Semantic cache | Yes | Yes |
| Content guardrails Content guardrails | Yes | Yes |
| Prompt versioning Prompt management | Yes | Yes |
| Delay it adds Proxy overhead | Not published | 12 ms |
| Requests per second ceiling Throughput | Not published | 8,200 rps |
Verified 3 days ago for Portkey and Verified 3 days ago for Kong AI Gateway. Want more fields, or a third option in the mix? Open these two in the full comparison tool.
Common questions
How much does Kong AI Gateway cost?
Kong does not publish the price. There is a 30-day Konnect free trial with enterprise functionality, a Plus plan billed per gateway per month at an unpublished rate, and a custom-priced annual Enterprise contract required for fully self-hosted gateways, audit logs and SSO. The Kong Gateway core is Apache-2.0 and free to self-host at infrastructure cost.
Is there a limit on how many models Kong AI Gateway can route to?
On the Konnect Plus plan the AI Gateway is capped at five unique LLM models. More requires Enterprise. Portkey publishes no equivalent cap.
Which is faster?
Kong, on the figures either vendor publishes: 8,200 requests per second at 12ms of gateway overhead, the strongest measured numbers in this catalogue. Portkey publishes no comparable latency or throughput figures.
Can both be self-hosted?
Yes. Portkey's gateway core is MIT licensed and Kong's is Apache-2.0, and both offer managed options. The difference is that Kong puts fully self-hosted gateways behind its Enterprise tier.