Portkey vs Vercel AI Gateway
Both are llm gateways tools. Here is how they actually differ on price, billing model and deployment.
Portkey
An open-source LLM gateway that routes to 1,600+ models with fallbacks, caching, budgets and guardrails. The gateway self-hosts free under Apache 2.0 - but real logging, traces and analytics require the managed paid tier.
Vercel AI Gateway
No markup on tokens and $5 of free credits a month per team. The details worth knowing are that BYOK is paid-tier only, and zero data retention is a metered add-on at $0.10 per 1,000 requests.
| Portkey | Vercel AI Gateway | |
|---|---|---|
| Category | LLM Gateways | LLM Gateways |
| Our rating | 4/5 | 4/5 |
| Starting price | $49/mo | $0 plus provider list price |
| Billing meter | No usage metering | No usage metering |
| Free plan | Yes | Yes |
| Free self-hosting | Yes, free | No or paid tier only |
| Best for | Teams that want one gateway to route, cache, budget and guardrail across many LLM providers, and are fine paying for the managed tier once they need real observability | Teams already deploying on Vercel who want provider-agnostic model access at list price with no markup, and who do not need governance features that carry a per-request charge. |
Our verdict on Portkey
Portkey is the strongest LLM gateway in this set, and the open-source core is a genuinely good, free, self-hostable proxy for routing, fallbacks and guardrails. The catch is where the value migrates. Self-host gives you routing for free, but the logs, traces and analytics that most teams actually adopt an observability tool for live on the managed tier. Know that split before you plan a self-hosted deployment, or you'll stand up the gateway and then discover the dashboard you wanted is a paid feature.
Full Portkey review →Our verdict on Vercel AI Gateway
Vercel AI Gateway takes no markup on tokens, which puts it in the right half of this category immediately. You pay provider list price from prepaid credits, every team gets $5 a month in credits that refresh every 30 days, and platform seats are free on Hobby - so a solo developer pays nothing for the gateway itself. Against OpenRouter's 5.5% with no volume discounts, that difference compounds indefinitely. Three details deserve attention before you commit. BYOK is paid-tier only, so using your own provider keys requires the $20 per seat plan. Failed BYOK requests fall back to system credentials and are charged against your balance, which is the kind of thing you discover on an invoice rather than in documentation. And zero data retention is not a default - it is a team-wide add-on metered at $0.10 per 1,000 successful requests, with provider allowlists priced the same way. Charging per request for privacy and for basic governance is an unusual choice and worth modelling if either matters to you.
Full Vercel AI Gateway review →Frequently Asked Questions
What is the main difference between Portkey and Vercel AI Gateway?
Portkey: Teams that want one gateway to route, cache, budget and guardrail across many LLM providers, and are fine paying for the managed tier once they need real observability Vercel AI Gateway: Teams already deploying on Vercel who want provider-agnostic model access at list price with no markup, and who do not need governance features that carry a per-request charge. Both sit in LLM Gateways, so the decision usually comes down to billing model and deployment rather than raw capability.
Which is cheaper, Portkey or Vercel AI Gateway?
It depends entirely on your workload shape, because they meter differently - Portkey bills on no usage metering and Vercel AI Gateway bills on no usage metering. Published starting prices are $49/mo and $0 plus provider list price respectively, but those numbers are not comparable until you apply them to the same traffic. Use our cost calculator to model both against your own request volume and span count.
Can I self-host Portkey or Vercel AI Gateway?
Portkey: Yes, free. Vercel AI Gateway: No or paid tier only. Free self-hosting means no licence fee, not no cost - you still own the infrastructure, upgrades and on-call.